mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
Merge remote-tracking branch 'origin/master' into worktree/pr348-retarget-latest-master
This commit is contained in:
Tianyi Cui
@@ -21,7 +21,9 @@ Long-running tools are producers. `dsh-tool-bash` adapts a `BashProcess` into in
|
||||
|
||||
## Runtime contract
|
||||
|
||||
The literal types live in the [task data-structure catalog](../../../../docs/core-data-structures/tasks.md). A producer calls `ctx.tasks.start()` with a kind, label, optional owning `Agent`, and a `run()` function. The runtime completes all failable preflight work before calling `run()` and invokes it once. After `run()` returns hooks, registration commits without another failable step; a producer cannot start work that lacks a collectable task id.
|
||||
The literal types live in the [task data-structure catalog](../../../../docs/core-data-structures/tasks.md). A producer calls `ctx.tasks.start()` with a kind, label, optional owning `Agent`, optional positive `outputLimitBytes`, and a `run()` function. The runtime completes all failable preflight work before calling `run()` and invokes it once. After `run()` returns hooks, registration commits without another failable step; a producer cannot start work that lacks a collectable task id.
|
||||
|
||||
`outputLimitBytes` is producer-owned presentation policy, not a registry buffer. The registry validates and projects it unchanged into `TaskSnapshot`; generic control surfaces apply the cap to complete model-facing output after adding their own status or notice metadata. Omitting it preserves the existing surface behavior, so the runtime does not impose a hidden default on unrelated producer families.
|
||||
|
||||
A model-facing producer exposes that committed id in its canonical success value, normally `{ kind: 'background', taskId }`; Native rendering may keep human-readable prose. A pre-aborted background call fails rather than returning a no-op because no task exists to satisfy the promised handle. Once registration publishes the id, cancellation belongs to the task's own controller and the task runtime: later cancellation of the producing tool call must not kill the published task. `task_kill`, owner disposal, and service teardown request cancellation; foreground execution remains coupled to the call's `exec.signal`.
|
||||
|
||||
@@ -75,11 +77,11 @@ Stream reads share one task-scoped consuming cursor because the owning model is
|
||||
|
||||
The system prompt tells the model to retain task ids, continue independent work instead of busy-polling or duplicating a running task, collect relevant tasks before its final answer, and kill work that no longer matters. Completion injects a logged `context/message` into the exact owner's session; it becomes durable context for the next request but does not wake an idle agent.
|
||||
|
||||
The runtime marks a terminal task `reported` when a read or wait delivers it, when a live waiter has claimed delivery at settlement, or when the model explicitly kills it. Reported tasks do not inject redundant completion notices. Listener failures are logged independently, do not stop later listeners, and are not awaited by waiters or teardown.
|
||||
The runtime marks a terminal task `reported` when a read or wait delivers it, when a live waiter has claimed delivery at settlement, or when the model explicitly kills it. Reported tasks do not inject redundant completion notices. Listener failures are logged independently, do not stop later listeners, and are not awaited by waiters or teardown. When a snapshot carries `outputLimitBytes`, `dsh-tool-tasks` preserves UTF-8 boundaries and reuses an existing producer truncation marker rather than duplicating it. Reads reserve status suffixes and retain the output tail; completion notices reserve the stable `background task <id>` prefix and `task_output` instruction before truncating variable kind, label, status, detail, or the truncation marker itself, so the minimum PTY cap still identifies the task to collect. The task surface resolves the caller-visible producer cap in a prepended pre-execute listener before policy can deny or short-circuit dispatch, then applies it through the task definitions' last-mile `finalizeContent` callback so normalized tool errors, outer pipeline failures, and single-text policy results cannot escape the bound; deliberately structured multi-block policy results retain policy ownership of their shape and size.
|
||||
|
||||
## Producer opt-in
|
||||
|
||||
Each producer owns whether its schema exposes `run_in_background` through defaulted config. `dsh-tool-bash` and each `dsh-tool-subagent` instance use `enableRunInBackground`, defaulting to true. A disabled instance omits the parameter and also rejects a forced background argument at execution because the generic argument validator permits undeclared keys. Schema omission advertises the capability; the execution check enforces it.
|
||||
Each producer owns whether its schema exposes `run_in_background` through defaulted config. `dsh-tool-bash`, `dsh-tool-pty`, and each `dsh-tool-subagent` instance use `enableRunInBackground`, defaulting to true. A disabled instance omits the parameter and also rejects a forced background argument at execution because the generic argument validator permits undeclared keys. Schema omission advertises the capability; the execution check enforces it.
|
||||
|
||||
`ctx.tasks` does not rewrite producer schemas. A bundle forwards configuration only for producers it owns. If a background call reaches `start()` without an attached surface, the runtime fence fails before execution.
|
||||
|
||||
@@ -121,7 +123,7 @@ Authorization, not unguessability, is the access boundary, and ids do not derive
|
||||
|
||||
## Testing
|
||||
|
||||
Unit coverage pins preflight atomicity, per-kind ids, stream and final reads, wait timeout and abort races, cancellation, first-wins settlement, listener containment, notice suppression, owner isolation, stale owner instances, owner cleanup, service teardown, and the no-surface fence. Producer tests cover bash process mapping, subagent startup cancellation, terminal mapping, and disposal. Snapshot coverage pins the control-tool schemas and prompt guidance.
|
||||
Unit coverage pins preflight atomicity, per-kind ids, output-limit validation and projection, complete UTF-8 result bounds, stream and final reads, wait timeout and abort races, cancellation, first-wins settlement, listener containment, notice suppression, owner isolation, stale owner instances, owner cleanup, service teardown, and the no-surface fence. Producer tests cover bash process mapping, subagent startup cancellation, terminal mapping, and disposal. Snapshot coverage pins the control-tool schemas and prompt guidance.
|
||||
|
||||
## Consequences
|
||||
|
||||
|
||||
@@ -218,7 +218,7 @@ A fresh registry-assigned Symbol provides collision-free execution identity with
|
||||
|
||||
Arguments are materialized once where model/tool JSON enters the pipeline. Pre-, around-, and post-execute listeners operate on the typed execution and decisions. Call ID correlation, approval, monotonic guards, and Code Mode nesting remain explicit relational checks.
|
||||
|
||||
After the last post-execute listener, the registry materializes and freezes the accepted final result once. Every synchronous `tools/result` observer receives that exact committed object, and observer failures are contained individually. An outer pipeline failure is normalized into a committed error result, so observers can discard staged work against the same authoritative boundary.
|
||||
After post-execute or outer pipeline normalization, the registry losslessly snapshots the candidate result, converting a snapshot failure into an ordinary error, invokes the call's snapshotted optional `ToolDefinition.finalizeContent` callback, then materializes and freezes the accepted final result once. The callback may replace only content, so structured error identity, contexts, and metadata remain registry-owned even when a tool enforces a last-mile result bound. Every synchronous `tools/result` observer receives that exact committed object, and observer failures are contained individually. An outer pipeline or candidate-snapshot failure is normalized before final content, so observers can discard staged work against the same authoritative boundary.
|
||||
|
||||
### The assembly waterfall owns the final model-visible composition
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write
|
||||
2026-07-19-cooperative-tool-cancellation.md: 559012f10d41963698cc932727125de1b9ccfef7
|
||||
2026-07-19-cooperative-tool-cancellation.zh.md: 6af8e57349bba026ab22f257014c084c5c3c3f54
|
||||
2026-07-19-cooperative-tool-cancellation.md: be237f6ca9475699bb4af76896772a1a7409033d
|
||||
2026-07-19-cooperative-tool-cancellation.zh.md: 9ad212c2073063ccb0c838c08ab8f89c9285b26b
|
||||
|
||||
@@ -36,7 +36,7 @@ An around-dispatch wrapper may replace `exec.signal` for its delegated lifetime
|
||||
|
||||
### Pre-aborted entry short-circuits after materialization
|
||||
|
||||
The registry first creates the call token and losslessly snapshots and freezes the arguments. A materialization failure wins even when the caller signal is already aborted. After successful materialization, a pre-aborted signal skips `tools/pre-execute`, approval, `tools/execute`, `tools/post-execute`, and the tool body, then publishes exactly one frozen authoritative `tools/result` with `ABORTED_BEFORE_DISPATCH`.
|
||||
The registry first creates the call token, snapshots the visible definition's optional final-content callback, and losslessly snapshots and freezes the arguments. An argument-materialization failure wins even when the caller signal is already aborted. Before final content, the registry also losslessly snapshots the candidate result and converts a result-snapshot failure into an ordinary error, so the callback can still enforce its content invariant. After successful argument materialization, a pre-aborted signal skips `tools/pre-execute`, approval, `tools/execute`, `tools/post-execute`, and the tool body, then passes `ABORTED_BEFORE_DISPATCH` through that content-only callback before publishing exactly one frozen authoritative `tools/result`.
|
||||
|
||||
### Started work still reaches quiescence
|
||||
|
||||
|
||||
@@ -36,7 +36,7 @@ Status: implemented
|
||||
|
||||
### 进入时已中止会在物化后短路
|
||||
|
||||
注册表先创建调用 token，并对参数进行无损快照和冻结。即使调用方信号已经中止，参数物化失败仍优先返回。物化成功后，进入时已中止的信号会跳过 `tools/pre-execute`、审批、`tools/execute`、`tools/post-execute` 和工具主体，然后发布且只发布一次冻结的权威 `tools/result`，其代码为 `ABORTED_BEFORE_DISPATCH`。
|
||||
注册表先创建调用 token，对可见工具定义的可选 `finalizeContent` callback 做快照，并对参数进行无损快照和冻结。即使调用方信号已经中止，参数物化失败仍优先返回。在最终内容处理之前，注册表还会对候选结果进行无损快照，并把结果快照失败转换为普通错误，从而使该 callback 仍能保证其内容不变量成立。参数物化成功后，进入时已中止的信号会跳过 `tools/pre-execute`、审批、`tools/execute`、`tools/post-execute` 和工具主体，然后先由该仅处理内容的 callback 处理 `ABORTED_BEFORE_DISPATCH`，再发布且只发布一次冻结的权威 `tools/result`。
|
||||
|
||||
### 已启动工作仍必须完全停稳
|
||||
|
||||
|
||||
@@ -38,7 +38,7 @@ This note owns Code Mode's presentation, composition, isolation, and settlement
|
||||
|
||||
### The run_code tool and the dispatch bridge
|
||||
|
||||
Under `'code'` and `'both'` the registry owns `run_code` as a reserved presentation transport with one required parameter, `{ code: string }`. It is represented by a normal `ToolDefinition` for dispatch but stays outside the filterable capability layers, so restrictions cannot accidentally remove Code Mode's only entry point. Calls traverse the complete tool pipeline — `tools/pre-execute` → monotonic guards → `tools/execute` around dispatch → `tools/post-execute` → immutable `tools/result` notification — exactly like native calls; a permission plugin can inspect the program text before it runs, and final-result observers see the normalized outer outcome. Its `execute(args, exec)`:
|
||||
Under `'code'` and `'both'` the registry owns `run_code` as a reserved presentation transport with one required parameter, `{ code: string }`. It is represented by a normal `ToolDefinition` for dispatch but stays outside the filterable capability layers, so restrictions cannot accidentally remove Code Mode's only entry point. Calls traverse the complete tool pipeline — `tools/pre-execute` → monotonic guards → `tools/execute` around dispatch → `tools/post-execute` → optional definition-owned `finalizeContent` → immutable `tools/result` notification — exactly like native calls; a permission plugin can inspect the program text before it runs, and final-result observers see the normalized outer outcome. Its `execute(args, exec)`:
|
||||
|
||||
1. **Build bindings.** One run-scoped signal follows outer cancellation and is aborted whenever the run settles. Each visible tool binding snapshots lossless-JSON arguments, waits on the serialization queue, executes with a deterministic call id and the outer token as `parent`, defers returned contexts through the outer execution, and logs `tool/code-dispatch`. Success returns the tool's final canonical JSON value; failure becomes the program-visible `ToolCallError`. Every sub-call retains its own immutable execution identity and traverses the full tool pipeline.
|
||||
2. **Runs the program**: `ctx.codeRuntime.run({ program: args.code, bindings: [{ global: 'tools', functions }], signal: runController.signal })`. The runtime receives the run-scoped signal, not only the caller's outer signal, so any way the outer run settles also aborts work inside the runtime.
|
||||
|
||||
@@ -14,12 +14,16 @@ Introduce `dsh-user-interaction` as the provider-neutral interface package for `
|
||||
|
||||
The model-facing request vocabulary is deliberately aligned with the product-research schema: `ask_user_question({ questions: [{ id, question, header?, options?: [{ label, description? }], multi_select? }] })`. `id` is supplied per question and echoed in the result so a batch can be routed without relying on question text. `label` is both user-facing display text and the selected value returned to the model; there is no separate `value`, no `recommended`, no `allow_custom`, and no `desc` alias.
|
||||
|
||||
Providers return `{ answers: [{ id, selected, custom? }] }`. `selected` is always an array of selected option labels, so single-select and `multi_select` answers share one result shape. `custom` carries a free-text "Other" answer; optionless questions collect `custom` directly. When `custom` is present, it overrides any selected choices and `selected` is empty.
|
||||
Providers return `{ answers: [{ id, selected, custom? }] }`. `selected` is always an array of selected option labels, so single-select and `multi_select` answers share one result shape. `custom` carries a free-text "Other" answer; optionless questions collect `custom` directly. When `custom` is present, it overrides any selected choices and `selected` is empty. A provider that supports partial completion represents a deliberately skipped item with the existing `{ id, selected: [] }` shape, preserving the other answers without extending the tool result vocabulary.
|
||||
|
||||
`UserInteractionError` extends `HarnessError`, so failures such as `NO_PROVIDER`, `ASK_ABORTED`, ACP cancellation, or missing session routing survive `ctx.tools.execute()` as machine-routable `{ name, code }` tool errors. This matches the structured-error taxonomy and lets the model or a wrapping plugin distinguish "user cancelled" from a generic thrown exception.
|
||||
|
||||
## UI mappings
|
||||
|
||||
`dsh web` mounts `dsh-client-ui-question`, whose host half opts the Web product into the model-facing tool and whose browser half registers a `question` entry in the conversation-owned keyed composer slot. `createApiProxy` implements the Web provider with a process-memory pending table keyed by a host-minted rpcId. It registers the wait before broadcasting `question/requested`, replays the same id on every mux reopen, validates the session and complete answer batch before claiming it, and broadcasts `question/resolved` after answer, cancellation, abort, or disposal. Claiming deletes the entry synchronously, so the first valid response wins and duplicate or late responses return `not-pending`.
|
||||
|
||||
The Web composer shows one question at a time while retaining every request in the session object layer. It supports single-select, multi-select, optionless or explicit custom answers, description text, and a visual recommendation badge without selecting the recommendation automatically. Single-select choices advance to the next item immediately, and Enter submits when every item is answered or explicitly skipped; Enter during IME composition only confirms the input candidate. The footer skips only the current item and preserves earlier drafts; the close control rejects the whole tool call with `ASK_CANCELLED`. The normal composer returns only after the host's resolved frame removes the pending item.
|
||||
|
||||
`dsh-tui` renders each question as a keyboard overlay, shows option descriptions, supports single- and multi-select choices plus free-form custom answers, and rejects pending questions on abort, provider disposal, or terminal shutdown. Batched and simultaneous requests are queued so one overlay owns keyboard focus at a time.
|
||||
|
||||
`dsh-acp` provides the same seam for ACP sessions. It resolves the calling `Agent` through `ownedRecord`, requiring the forward session-map record at `agent.session.id` to own that exact agent object, and calls ACP `unstable_createElicitation` with a session-scoped form for each question. Single-select options become a `choice` string enum; `multi_select` options become a `choice` array enum; optionless questions use a required `custom` text field. If the client returns both `choice` and non-empty `custom`, the custom answer wins. ACP `decline`/`cancel`, a missing answer, a missing session, and a client without elicitation support all become structured `UserInteractionError`s.
|
||||
@@ -42,8 +46,8 @@ ACP elicitation is currently marked unstable in the SDK. The fallback is still s
|
||||
|
||||
The feature gives the model a powerful pause primitive, so prompt guidance matters. The tool description tells the model to ask concise questions and use options when possible. Product policy can later wrap `tools/execute` to restrict when the tool is allowed, but the loop should not special-case it.
|
||||
|
||||
`dsh-user-interaction` and `dsh-tool-ask-user` both live in `packages/ui` because they form one product-facing human-interaction capability. `agent-core` does not load either the tool or a provider. `dsh-tui-demo` opts into the seam, TUI provider, and model-facing tool. `acp-agent` keeps only the `userInteraction` seam/provider by default: ACP elicitation support is still client-dependent, so an ACP leaf must opt into the model-facing tool deliberately once its client can complete elicitation requests.
|
||||
`dsh-user-interaction` and `dsh-tool-ask-user` both live in `packages/ui` because they form one product-facing human-interaction capability. `agent-core` does not load either the tool or a provider. `dsh-tui-demo` opts into the seam, TUI provider, and model-facing tool. `dsh web` boots the seam/provider in the host runtime and exposes the tool through the selected Web question plugin. `acp-agent` keeps only the `userInteraction` seam/provider by default: ACP elicitation support is still client-dependent, so an ACP leaf must opt into the model-facing tool deliberately once its client can complete elicitation requests.
|
||||
|
||||
## Testing
|
||||
|
||||
Unit coverage pins provider registration/disposal, duplicate-provider rejection, abort-before-provider, empty-question rejection, structured tool errors through `ctx.tools.execute()`, batched answers, multi-select answers, custom answers, and the model schema including the removal of `value`, `recommended`, `allow_custom`, and `desc`. TUI tests cover option descriptions, queued requests, shutdown/abort cleanup, optionless free-form input, invalid choices, duplicate multi-select selections, and batched question flows. ACP bridge tests drive a real in-memory ACP connection with the real `ask_user_question` tool and verify selected-option, custom-overrides-choice, multi-select, and optionless free-form elicitation paths continue the agent loop.
|
||||
Unit coverage pins provider registration/disposal, duplicate-provider rejection, abort-before-provider, empty-question rejection, structured tool errors through `ctx.tools.execute()`, batched answers, multi-select answers, custom answers, explicit per-item skips, and the model schema including the removal of `value`, `recommended`, `allow_custom`, and `desc`. TUI tests cover option descriptions, queued requests, shutdown/abort cleanup, optionless free-form input, invalid choices, duplicate multi-select selections, and batched question flows. ACP bridge tests drive a real in-memory ACP connection with the real `ask_user_question` tool and verify selected-option, custom-overrides-choice, multi-select, and optionless free-form elicitation paths continue the agent loop. Web tests pin stable-id replay, response validation, first-wins settlement, duplicate and late responses, whole-request cancellation versus owner abort, single-select advance, IME-safe Enter submission, per-item skip preservation, composer takeover, structured batch submission, and restoration of the normal composer.
|
||||
|
||||
@@ -20,15 +20,16 @@ The canonical surface separates transformable policy, around-dispatch control, a
|
||||
|
||||
### The tool pipeline gives each phase one kind of authority
|
||||
|
||||
Every call follows `tools/pre-execute` → guards → `tools/execute` → dispatch → `tools/post-execute` → `tools/result`. The registry snapshots caller input, materializes and freezes arguments, and assigns an opaque token. Nested calls carry only the parent token. Identity remains immutable; only `signal` may change around dispatch. The log, UI, and tool body therefore agree on what ran.
|
||||
Every call follows `tools/pre-execute` → guards → `tools/execute` → dispatch → `tools/post-execute` → definition-owned `finalizeContent` → `tools/result`. The registry snapshots caller input, materializes and freezes arguments, assigns an opaque token, and snapshots the visible definition's final-content callback before policy begins. Nested calls carry only the parent token. Identity remains immutable; only `signal` may change around dispatch. The log, UI, and tool body therefore agree on what ran.
|
||||
|
||||
- **`tools/pre-execute`** is the extensible waterfall gate. Its `PreToolDecision` allows, denies, or asks. Deny skips `tools/execute` and core dispatch. Ask resolves through the optional approval seam: only `allowed-once` continues through guards and dispatch; rejection, cancellation, an unavailable channel, a missing approval service, or an agent-less call becomes a normalized denial. Every outcome still reaches post-policy and final observers.
|
||||
- **`tools/pre-execute`** is the extensible waterfall gate. Its `PreToolDecision` allows, denies, or asks. Deny skips `tools/execute` and core dispatch. Ask resolves through the optional approval seam: only `allowed-once` continues through guards and dispatch; rejection, cancellation, an unavailable channel, a missing approval service, or an agent-less call becomes a normalized denial. Every resolved decision still reaches post-policy; a throwing listener becomes a final normalized failure.
|
||||
- **`ctx.tools.guard()`** installs synchronous scope-aware policy after the whole pre-execute waterfall. A guard may deny or abstain, never force-allow, so listener ordering cannot resurrect an operation that a final invariant forbids.
|
||||
- **`tools/execute`** is the around-dispatch waterfall for timeout, retry, and metrics plugins. A wrapper delegates to core dispatch with `next()`, may replace and restore the required `exec.signal` before doing so but cannot remove it, and receives the already-normalized canonical success/failure result of a thrown or unknown tool; a wrapper-authored success short-circuits dispatch and is re-normalized through the resolved output declaration.
|
||||
- **`tools/post-execute`** is the inspect/transform waterfall. Its `PostToolDecision` accepts, blocks with feedback, replaces either presentation content or canonical value, or attaches `additionalContexts`. Value replacement revalidates and recomputes presentation; content replacement preserves programmatic value and is not a confidentiality boundary. The returned decision is the supported transform channel; after the waterfall, the registry materializes the complete outcome once before final observation.
|
||||
- **`tools/post-execute`** is the inspect/transform waterfall. Its `PostToolDecision` accepts, blocks with feedback, replaces either presentation content or canonical value, or attaches `additionalContexts`. Value replacement revalidates and recomputes presentation; content replacement preserves programmatic value and is not a confidentiality boundary. The returned decision is the supported transform channel.
|
||||
- **`ToolDefinition.finalizeContent`** is an optional synchronous, total, content-only boundary snapshotted with the visible definition at call creation. It runs exactly once after the registry has normalized and losslessly snapshotted the candidate outcome, including pre-, around-, or post-listener failures that bypass later waterfalls and errors discovered while snapshotting another result field. It may replace `content` or preserve it with `undefined`, but cannot rewrite `isError`, structured error identity, contexts, or presentation metadata. This is where a tool enforces its own last-mile content invariant without converting policy failures into weaker block decisions.
|
||||
- **`tools/result`** is the synchronous contained notification after every transform, lossless-JSON materialization, and the outer error boundary. It receives the same frozen execution identity and an immutable snapshot of the authoritative result; observer failures are contained per listener and cannot change or reject `ToolRegistry.execute()`'s returned outcome.
|
||||
|
||||
Core dispatch and the tool body sit inside normalization boundaries, so tool, listener, invalid canonical value, renderer/projector, non-JSON presentation, and identity-shape failures resolve as JSON-safe `isError` results rather than escaping the turn. A post-execute listener can therefore inspect a thrown tool, and a final observer sees the execution-local canonical value beside exactly the presentation fields the session log can persist. The [canonical tool-output contract](../architecture/2026-07-20-canonical-tool-output-contract.md) owns the value/projection and durability rules.
|
||||
Core dispatch and the tool body sit inside normalization boundaries, so tool, listener, invalid canonical value, renderer/projector, non-JSON presentation, and identity-shape failures resolve as JSON-safe `isError` results rather than escaping the turn. A post-execute listener can therefore inspect a thrown tool; definition-owned final content invariants also cover outer pipeline and candidate-materialization failures; and a final observer sees the execution-local canonical value beside exactly the presentation fields the session log can persist. The [canonical tool-output contract](../architecture/2026-07-20-canonical-tool-output-contract.md) owns the value/projection and durability rules.
|
||||
|
||||
**`TurnEndReason.rejected`** (`dsh-session`): a zero-step turn whose claimed prompt was blocked by `prompt-submit`.
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write
|
||||
2026-07-16-persistent-pty-sessions.md: 76354891f557974b953a1b0b805d94330c9f6e69
|
||||
2026-07-16-persistent-pty-sessions.zh.md: 86200d70c6eda815a440c44e8b55457b0424edb6
|
||||
2026-07-16-persistent-pty-sessions.md: b33993d36753d3195ec52d3b38dda62746a47bf3
|
||||
2026-07-16-persistent-pty-sessions.zh.md: 6ed330d75824a4e6fca9de0d82db61a7c6543322
|
||||
|
||||
@@ -34,14 +34,14 @@ Idle detection is backend behavior, not a second public seam. A remote or contai
|
||||
|
||||
There are no plugin-load auto-start sessions. `terminal_open` creates a session only during an agent tool call, when ownership and the owning event-sourced session are known. A future declarative startup feature must compose through unpublished agent setup rather than create shared global terminals.
|
||||
|
||||
Agent-scope disposal closes registrations first, then awaits quiescent teardown of every owned PTY. Backend or tool-plugin reload does not orphan sessions: ownership lives in `PtyService` until the agent ends, following the same service-owned-record pattern as [`ctx.tasks`](../../../../packages/tasks/tasks/README.md).
|
||||
Agent-scope disposal closes registrations first, then awaits quiescent teardown of every owned PTY. Unpublished backend setup is a tracked lifecycle operation: owner or service disposal aborts its service-owned signal, waits for backend settlement and rollback, and only then returns. Caller cancellation retains its exact `AbortSignal.reason` even when the backend rejects or returns a session whose rollback close fails; that cleanup failure remains tracked for later owner or service disposal instead of replacing the caller reason. A lifecycle-triggered rollback close failure rejects both the spawn and the disposing lifecycle, while `PtyBackendCleanupError` lets a backend preserve its own failed startup cleanup for the disposing lifecycle without replacing a caller cancellation. When caller cancellation settles before disposal, the cleanup failure remains tracked owner activity until later owner or service disposal consumes and reports it, so sandbox-mode policy cannot mistake failed cleanup for quiescence. Backend or tool-plugin reload does not orphan sessions: ownership lives in `PtyService` until the agent ends, following the same service-owned-record pattern as [`ctx.tasks`](../../../../packages/tasks/tasks/README.md). The service reserves the session synchronously for one active send before returning its operation, including before a background task id becomes visible; a second send fails with `SEND_ACTIVE`, so output and cancellation cannot cross operation ownership.
|
||||
|
||||
### Security and process boundary
|
||||
|
||||
A registered `shell` backend constrains how a terminal starts; it does not constrain commands typed after startup. `dsh-pty-local` therefore applies two protections before spawning:
|
||||
|
||||
- It builds a scrubbed child environment using the same credential-shaped-name policy as `bash-local`, removing ambient `*KEY*`, `*SECRET*`, `*TOKEN*`, and harness-managed variables unless an explicit trusted mapping supplies them.
|
||||
- It requires `ctx.sandbox` and the shared `ctx.sandboxPolicy`. At spawn, the backend resolves the owner's effective session mode over the deployment default and wraps the shell argv once; that mode and workspace root remain the process boundary for the PTY lifetime. `danger-full-access` is the existing explicit unconfined choice rather than a PTY-specific bypass.
|
||||
- It requires `ctx.sandbox` and the shared `ctx.sandboxPolicy`. At spawn, the backend resolves the owner's effective session mode over the deployment default and wraps the shell argv once; that mode and workspace root remain the process boundary for the PTY lifetime. A write that would change the effective `sandbox/mode` is rejected before commit while the owner has any open PTY or unpublished spawn, with an instruction to wait for creation to settle and close those sessions first; same-effective-mode writes remain valid. The pending reservation spans backend setup through publication, so there is no race in which a wider terminal appears after a downgrade. `danger-full-access` is the existing explicit unconfined choice rather than a PTY-specific bypass.
|
||||
|
||||
Sandboxing confines local process effects but does not make arbitrary shell input safe: network calls and other external side effects remain governed by deployment policy. Tool descriptions state that PTY sessions are less auditable than one-shot tools and should be used only when persistence or interactive stdin is necessary.
|
||||
|
||||
@@ -58,19 +58,21 @@ The implementation uses only public `node-pty` capabilities: child PID, `data` a
|
||||
| `terminal_close` | Close one session and await process-tree quiescence | `{ killed }` |
|
||||
| `terminal_list` | List the caller's live sessions | owner-scoped session summaries |
|
||||
|
||||
`terminal_send({ sessionId, text, submit?, run_in_background? })` treats `text` as UTF-8 bytes and resolves `submit` to `true` in the tool implementation. When `submit` is true it writes the platform Enter sequence after the text; when false it writes only the text, allowing control characters and REPL fragments without hidden content heuristics.
|
||||
The ACP render contract is exact and location-free. `terminal_send` uses terminal call/result cards only for foreground sends; its background form is generic `execute`. `terminal_open`, `terminal_read`, `terminal_signal`, `terminal_close`, and `terminal_list` use generic `execute`, `read`, `execute`, `delete`, and `read` cards respectively. No PTY tool emits `locations`.
|
||||
|
||||
Foreground sends return a bounded rendered delta and two independent facts: `waitReason` (`stdin_read | inferred_idle | timeout | session_exit`) and `sessionStatus` (`running` or `exited` with exit code or signal). `session_exit` refers to the PTY's top-level shell process, not an arbitrary foreground command whose status the shell consumes. A timeout never implies process exit.
|
||||
`terminal_send({ sessionId, text, submit?, run_in_background? })` treats `text` as UTF-8 bytes and resolves `submit` to `true` in the tool implementation. When `submit` is true it writes the platform Enter sequence after the text; when false it writes only the text, allowing control characters and REPL fragments without hidden content heuristics. `enableRunInBackground` defaults to true; false removes `run_in_background` from the schema and rejects the same undeclared argument if a caller forces it through execution.
|
||||
|
||||
With `run_in_background: true`, `dsh-tool-pty` registers the in-flight send on `ctx.tasks` and returns immediately with `taskId`. `task_output(wait: true)` waits, reads incremental output, and records the final result; `task_kill` forwards cancellation as `SIGINT` and escalates only through the PTY backend's owned teardown path. If the task surface is absent, background mode fails before writing input. No PTY-specific `sleep` tool or general wake-up seam is added.
|
||||
Foreground sends return a bounded rendered delta and two independent facts: `waitReason` (`stdin_read | inferred_idle | timeout | session_exit`) and `sessionStatus` (`running` or `exited` with exit code or signal). `session_exit` refers to the PTY's top-level shell process, not an arbitrary foreground command whose status the shell consumes. A timeout never implies process exit. `dsh-tool-pty.maxResultBytes` defaults to 262144, rejects values below 64 so creation acknowledgements retain registry-issued ids, and caps each single-text UTF-8 result after normalized tool or pipeline errors, wait, session, pagination, truncation, generic task-status wrappers, policy denials or short-circuits, and post-execute replacements or blocks; the terminal definitions' last-mile `finalizeContent` callback leaves deliberately structured multi-block policy content unchanged. The renderer reserves suffix space and preserves code-point boundaries instead of treating the backend payload cap as the final model bound.
|
||||
|
||||
`terminal_read` pages backward from the newest retained line. The backend enforces both line and UTF-8 byte caps on retained scrollback and the complete returned value, so one oversized line cannot bypass the bound. `truncated` distinguishes retention loss from an ordinary viewport delta.
|
||||
With `run_in_background: true`, `dsh-tool-pty` registers the in-flight send on `ctx.tasks` and returns immediately with `taskId`. The producer places `maxResultBytes` on the task snapshot so `task_output`, terminal kill status, and completion notices enforce the same complete-result cap after generic metadata. `task_output(wait: true)` waits, reads incremental output, and records the final result; `task_kill` resolves the current foreground PGID and delivers a real `SIGINT`, including when the application has disabled terminal `ISIG`, and escalates only through the PTY backend's owned teardown path. If the task surface is absent, background mode fails before writing input. No PTY-specific `sleep` tool or general wake-up seam is added.
|
||||
|
||||
`terminal_read` pages backward from the newest retained line. The backend enforces both line and UTF-8 byte caps on retained scrollback and the returned page payload, so one oversized line cannot bypass the backend bound; the tool then caps the fully rendered page including pagination and truncation metadata. `truncated` distinguishes retention loss from an ordinary viewport delta.
|
||||
|
||||
`terminal_signal` accepts the closed set `SIGINT | SIGTERM | SIGKILL | SIGTSTP | SIGHUP`. The backend resolves the terminal foreground process group at execution time. `SIGKILL` is rejected when that group is the top-level shell, directing the caller to `terminal_close`; a failed group lookup fails the operation instead of signaling a guessed PID.
|
||||
|
||||
### Local readiness detection
|
||||
|
||||
The local backend first recognizes a private OSC prompt marker emitted by its controlled bash startup, then runs three bounded fallback tiers. The marker is removed before output reaches the model and avoids a fixed silence delay for ordinary shell commands on both platforms. Unpublished startup does not accept zero-output silence as readiness; timeout rejects the spawn. All timings are validated config fields: `pollIntervalMs`, `exactProbeAfterMs`, `idleSilenceMs`, and `timeoutMs`.
|
||||
The local backend first recognizes a private OSC prompt marker emitted by its controlled bash startup, then requires printable prompt text after that marker before declaring prompt readiness and runs three bounded fallback tiers. Carrying that state across data callbacks covers macOS delivery where the OSC marker and `PS1` arrive separately; the marker alone can no longer publish an empty MOTD. The marker is removed before output reaches the model and avoids a fixed silence delay for ordinary shell commands on both platforms. Unpublished startup does not accept zero-output silence as readiness; timeout rejects the spawn. If caller cancellation wins during startup, the backend closes the private session and propagates the exact `AbortSignal.reason`; a foreground PGID that is not observable yet cannot replace cancellation with a lookup error. All timings are validated config fields: `pollIntervalMs`, `exactProbeAfterMs`, `idleSilenceMs`, and `timeoutMs`.
|
||||
|
||||
On Linux, the inspector reads the shell's terminal foreground PGID from `/proc/<shellPid>/stat`, enumerates every process and thread in that process group, and probes their current syscalls. A positive Tier 1 result requires an observed stdin wait: direct `read(0)`, a permitted read of a `select`/`pselect6` or `poll`/`ppoll` argument containing fd 0, or an epoll interest list containing fd 0. Unreadable process memory and unrecognized syscalls are misses, never positive guesses. Architecture tables contain only syscall numbers defined by the corresponding Linux UAPI; unsupported architectures skip Tier 1.
|
||||
|
||||
@@ -78,7 +80,7 @@ On macOS there is no exact syscall tier. Output silence returns `inferred_idle`
|
||||
|
||||
Tier 2 returns `inferred_idle` after `idleSilenceMs` without output. A sleeping or network-blocked command can therefore look ready. Tier 3 returns `timeout` after `timeoutMs` so a foreground tool call cannot hold the agent indefinitely. The result preserves the distinction; callers may wait through `ctx.tasks`, signal the foreground group, or inspect from another session.
|
||||
|
||||
`node-pty` data notifications feed one streaming decoder and terminal parser. Parser carry state handles UTF-8 and terminal query sequences split across chunks. The implementation normalizes line-oriented output and detects alternate-screen entry, but it does not promise correct interaction with a full-screen application.
|
||||
`node-pty` data notifications feed one terminal parser. Parser carry state handles control sequences and a trailing carriage return split across callbacks, so a divided CRLF produces one newline rather than a pagination-changing blank line. The implementation normalizes line-oriented output, but it does not promise correct interaction with a full-screen application.
|
||||
|
||||
### Model-visible output and durability
|
||||
|
||||
@@ -88,9 +90,9 @@ Background sends use the existing task completion notice and `task_output` resul
|
||||
|
||||
### Process-tree teardown
|
||||
|
||||
The top-level `node-pty` child is the ownership anchor. On close, the backend stops callbacks, snapshots that PID and its transitive descendants by parent PID in children-first order, sends `SIGTERM`, closes the PTY, waits for quiescence, then sends `SIGKILL` to verified survivors after configurable `disposeGraceMs` and waits for them to leave the process table. Every captured PID includes process-start identity so reuse cannot redirect escalation.
|
||||
The top-level `node-pty` child is the ownership anchor. On close, the backend stops callbacks, snapshots its transitive descendants by parent PID in children-first order, sends `SIGTERM`, waits, rescans for children forked during shutdown, sends `SIGKILL` to the remaining descendant tree, and verifies that every non-zombie descendant left the process table while the shell is still alive. A matching Linux zombie has no executable work and therefore counts as quiescent, allowing shell shutdown to reap or reparent it. Only then does the backend stop the shell with its own TERM/grace/KILL sequence. Every captured PID includes process-start identity so reuse cannot redirect escalation.
|
||||
|
||||
Teardown reports root exit and survivor cleanup independently. It does not claim success merely because the shell exited; disposal resolves only after no captured tree member remains or returns a structured cleanup failure naming the survivors. Service disposal still clears its backend, reservation, and owner-detacher registries when a close fails. It never broadens ownership to every member of the root PID's POSIX session.
|
||||
Teardown reports root exit and survivor cleanup independently. It does not claim success merely because the shell exited; disposal resolves only after no captured non-quiescent tree member remains or returns a cleanup failure naming the survivors. A failed close is not cached forever: the registry and local session each clear the fence only when it still names that failed attempt, so a later explicit or lifecycle close retries after the external survivor condition changes without disturbing a newer concurrent attempt. Service disposal still clears its backend, reservation, and owner-detacher registries when a close fails. It never broadens ownership to every member of the root PID's POSIX session.
|
||||
|
||||
### Composition and rollout
|
||||
|
||||
@@ -115,9 +117,12 @@ plugins:
|
||||
timeoutMs: 30000
|
||||
disposeGraceMs: 3000
|
||||
'@deepseek-ai/dsh-tool-pty':
|
||||
config:
|
||||
enableRunInBackground: true
|
||||
maxResultBytes: 262144
|
||||
```
|
||||
|
||||
The package ships concise tool guidance explaining persistent state, owner isolation, uncertain idle results, cleanup, and the preference for existing one-shot tools when interaction is unnecessary. It does not add a global system-prompt recommendation or mount PTY in shipped defaults; dedicated ACP and headless snapshot overlays exercise the opt-in composition.
|
||||
The package ships concise tool guidance explaining persistent state, owner isolation, uncertain idle results, cleanup, and the preference for existing one-shot tools when interaction is unnecessary. It does not mount PTY in the base shipped examples: PTY is opt-in through the dedicated composition, while ACP and headless snapshot overlays exercise it. Within an enabled `dsh-tool-pty` instance, the six tools and `run_in_background` are enabled by default; deployments may disable only the background argument with config.
|
||||
|
||||
### Deferred work
|
||||
|
||||
@@ -147,9 +152,9 @@ The package ships concise tool guidance explaining persistent state, owner isola
|
||||
|
||||
## Verification
|
||||
|
||||
- Per-file coverage pins owner fencing, concurrent reservations, lifecycle cleanup, readiness tiers, sanitizer carry state, UTF-8 bounds, task integration, schemas, and render intents.
|
||||
- Linux process fixtures cover non-leader and non-main-thread stdin waits, unreadable process state, supported syscall tables, unsupported architectures, and false-positive rejection; macOS inspector logic is injected into the same unit suite.
|
||||
- Real `node-pty` tests exercise shell state, shared sandbox policy, environment scrubbing, signals, a TERM-ignoring descendant, and immediate post-disposal quiescence on supported hosts.
|
||||
- Per-file coverage pins owner fencing, concurrent reservations, unpublished-spawn cancellation and awaited teardown, sandbox-mode change rejection, retriable lifecycle cleanup, readiness tiers, sanitizer carry state, complete UTF-8 bounds, task integration, schemas, and exact render intents.
|
||||
- Linux process fixtures cover non-leader and non-main-thread stdin waits, zombie quiescence, unreadable process state, supported syscall tables, unsupported architectures, and false-positive rejection; macOS inspector logic is injected into the same unit suite.
|
||||
- Real `node-pty` tests exercise shell state, shared sandbox policy, environment scrubbing, raw-mode foreground `SIGINT`, a TERM-ignoring descendant, and immediate post-disposal quiescence on supported hosts.
|
||||
- A Loader-driven `cordis.yml` test mounts the real three-package composition, while ACP and headless snapshots pin the six schemas, bounded results, error rendering, and terminal/generic cards through opt-in overlays.
|
||||
- Package contracts, the architecture map, core data structures, generated catalogs, and the website API describe the same shipped surface.
|
||||
- The repository CI-equivalent sequence owns type, lint, coverage, snapshot, documentation, build, hygiene, demo, and built-entry verification.
|
||||
|
||||
@@ -34,14 +34,14 @@ idle 检测属于后端行为，不是第二条公共 seam。远程或容器后
|
||||
|
||||
实现不提供插件加载期 auto-start 会话。`terminal_open` 只在 agent 工具调用期间创建会话，此时所有权和所属的事件溯源会话都已确定。未来的声明式启动功能必须通过尚未发布的 agent setup 组合，而不能创建全局共享终端。
|
||||
|
||||
agent scope dispose 时先关闭注册，再等待全部所属 PTY 静默退出。后端或工具插件 reload 不会遗留会话：所有权持续存放在 `PtyService` 中，直到 agent 结束，与 [`ctx.tasks`](../../../../packages/tasks/tasks/README.md) 的服务持有记录模式一致。
|
||||
agent scope dispose 时先关闭注册，再等待全部所属 PTY 静默退出。未发布的后端 setup 同样是受追踪的生命周期操作：owner 或服务 dispose 会中止服务自有的 signal，等待后端结算与回滚完成后才返回。即使后端 reject，或返回的会话在回滚 close 时失败，调用方取消仍会原样保留其 `AbortSignal.reason`；该清理失败不会替换调用方原因，而会继续受追踪，留待后续 owner 或服务 dispose 处理。由 lifecycle dispose 触发的回滚 close 失败会使 spawn 与该 lifecycle dispose 都 reject，而 `PtyBackendCleanupError` 让后端在不替换调用方取消的前提下，为该 lifecycle dispose 保留自身的启动清理失败。若调用方取消先于 dispose 完成结算，该清理失败会继续作为受追踪的 owner activity 保留，直到后续 owner 或服务 dispose 消费并报告它，因此沙箱模式策略不会把清理失败误判为静默。后端或工具插件 reload 不会遗留会话：所有权持续存放在 `PtyService` 中，直到 agent 结束，与 [`ctx.tasks`](../../../../packages/tasks/tasks/README.md) 的服务持有记录模式一致。服务会先同步把会话预留给一次活跃发送，再返回该操作；后台发送同样会在 task id 对外可见前完成预留。第二次发送会以 `SEND_ACTIVE` 失败，因此输出与取消无法跨越操作所有权。
|
||||
|
||||
### 安全与进程边界
|
||||
|
||||
注册的 `shell` 后端只约束终端如何启动，不约束启动后输入的命令。因此 `dsh-pty-local` 在 spawn 前应用两层保护：
|
||||
|
||||
- 它使用与 `bash-local` 相同的凭证形态名称策略构建清洗后的子进程环境，移除环境中的 `*KEY*`、`*SECRET*`、`*TOKEN*` 和 harness 管理的变量，除非显式的可信映射提供这些值。
|
||||
- 它要求 `ctx.sandbox` 和共享的 `ctx.sandboxPolicy`。后端在 spawn 时，以部署默认值为底折叠 owner 的有效 session mode，并只包装一次 shell argv；该 mode 与 workspace root 在 PTY 的整个生命周期中充当进程边界。`danger-full-access` 是现有的显式无约束选择，不另设 PTY 私有 bypass。
|
||||
- 它要求 `ctx.sandbox` 和共享的 `ctx.sandboxPolicy`。后端在 spawn 时，以部署默认值为底折叠 owner 的有效 session mode，并只包装一次 shell argv；该 mode 与 workspace root 在 PTY 的整个生命周期中充当进程边界。只要 owner 有任何已打开的 PTY 或尚未发布的 spawn，任何会改变生效 `sandbox/mode` 的写入都会在提交前被拒绝，并提示先等待创建操作结算，再关闭这些会话；不会改变生效模式的写入仍然有效。这项进行中的预留从后端 setup 持续到发布完成，因此不存在降级后又出现权限更宽的终端这一竞态。`danger-full-access` 是现有的显式无约束选择，不另设 PTY 私有 bypass。
|
||||
|
||||
沙箱限制本地进程副作用，但不会让任意 shell 输入自动安全：网络调用和其他外部副作用仍由部署策略治理。工具描述会说明 PTY 会话比一次性工具更难审计，只应在确实需要持久状态或交互式 stdin 时使用。
|
||||
|
||||
@@ -58,19 +58,21 @@ agent scope dispose 时先关闭注册，再等待全部所属 PTY 静默退出
|
||||
| `terminal_close` | 关闭一个会话并等待进程树静默退出 | `{ killed }` |
|
||||
| `terminal_list` | 列出调用方的活会话 | 按 owner 隔离的会话摘要 |
|
||||
|
||||
`terminal_send({ sessionId, text, submit?, run_in_background? })` 将 `text` 视为 UTF-8 字节，并由工具实现在解析阶段把 `submit` 默认成 `true`。`submit` 为 true 时先写入文本，再写入平台 Enter 序列；为 false 时只写文本，使控制字符和 REPL 片段无需隐藏的内容启发式即可发送。
|
||||
ACP 渲染契约精确且不携带位置信息。`terminal_send` 只为前台发送使用 terminal 调用卡片和结果卡片；后台形式使用通用 `execute` 卡片。`terminal_open`、`terminal_read`、`terminal_signal`、`terminal_close` 和 `terminal_list` 分别使用通用 `execute`、`read`、`execute`、`delete` 和 `read` 卡片。所有 PTY 工具都不发出 `locations`。
|
||||
|
||||
前台发送返回有界的渲染增量和两个独立事实：`waitReason`（`stdin_read | inferred_idle | timeout | session_exit`）与 `sessionStatus`（`running`，或携带退出码或信号的 `exited`）。`session_exit` 指 PTY 顶层 shell 进程退出，不指由 shell 消费状态的任意前台命令。timeout 从不意味着进程已经退出。
|
||||
`terminal_send({ sessionId, text, submit?, run_in_background? })` 将 `text` 视为 UTF-8 字节，并由工具实现在解析阶段把 `submit` 默认成 `true`。`submit` 为 true 时先写入文本，再写入平台 Enter 序列；为 false 时只写文本，使控制字符和 REPL 片段无需隐藏的内容启发式即可发送。`enableRunInBackground` 默认为 true；设为 false 时，schema 中会移除 `run_in_background`，调用方即使强行把这个未声明参数传入执行流程，也会被拒绝。
|
||||
|
||||
当 `run_in_background: true` 时，`dsh-tool-pty` 在 `ctx.tasks` 上注册进行中的发送，并立即返回 `taskId`。`task_output(wait: true)` 负责等待、读取增量输出并记录最终结果；`task_kill` 将取消转发为 `SIGINT`，只有 PTY 后端拥有的 teardown 路径可以升级信号。若 task 对外接口不存在，后台模式必须在写入输入前失败。设计不新增 PTY 专用的 `sleep` 工具或通用唤醒 seam。
|
||||
前台发送返回有界的渲染增量和两个独立事实：`waitReason`（`stdin_read | inferred_idle | timeout | session_exit`）与 `sessionStatus`（`running`，或携带退出码或信号的 `exited`）。`session_exit` 指 PTY 顶层 shell 进程退出，不指由 shell 消费状态的任意前台命令。timeout 从不意味着进程已经退出。`dsh-tool-pty.maxResultBytes` 默认为 262144；低于 64 的值会被拒绝，以确保创建确认保留 registry 签发的 id；每个单文本 UTF-8 结果在加入规范化的工具或流水线错误、等待、会话、分页、截断、通用 task 状态包装、策略拒绝或短路以及 post-execute 替换或阻断后，仍受该值限制；终端定义自有的末端 `finalizeContent` callback 会原样保留策略刻意返回的结构化多 block 内容。渲染器会为后缀预留空间并保持代码点边界，而不会把后端载荷上限当作面向模型结果的最终上限。
|
||||
|
||||
`terminal_read` 从最新保留行向后分页。后端同时对保留的 scrollback 和完整返回值执行行数与 UTF-8 字节上限，因此单个超长行无法绕过限制。`truncated` 用于区分保留数据丢失与普通 viewport 增量。
|
||||
当 `run_in_background: true` 时，`dsh-tool-pty` 在 `ctx.tasks` 上注册进行中的发送，并立即返回 `taskId`。生产方把 `maxResultBytes` 写入 task 快照，使 `task_output`、kill 返回的终态状态和完成通知在加上通用元数据后，仍对完整结果执行同一上限。`task_output(wait: true)` 负责等待、读取增量输出并记录最终结果；`task_kill` 会解析当前前台 PGID 并发送真正的 `SIGINT`，即使应用已禁用终端 `ISIG` 也同样如此，且后续升级仍只通过 PTY 后端拥有的 teardown 路径进行。若 task 对外接口不存在，后台模式必须在写入输入前失败。设计不新增 PTY 专用的 `sleep` 工具或通用唤醒 seam。
|
||||
|
||||
`terminal_read` 从最新保留行向后分页。后端同时对保留的 scrollback 和返回页载荷执行行数与 UTF-8 字节上限，因此单个超长行无法绕过后端上限；工具随后再限制包含分页与截断元数据的完整渲染页。`truncated` 用于区分保留数据丢失与普通 viewport 增量。
|
||||
|
||||
`terminal_signal` 接受闭合集 `SIGINT | SIGTERM | SIGKILL | SIGTSTP | SIGHUP`。后端在执行时解析终端前台进程组。当目标组是顶层 shell 时拒绝 `SIGKILL`，并指引调用方使用 `terminal_close`；进程组解析失败时操作直接失败，而不是向猜测的 PID 发送信号。
|
||||
|
||||
### 本地就绪检测
|
||||
|
||||
本地后端先识别受控 bash 启动时发出的私有 OSC prompt marker，再执行 3 个有界 fallback 层级。marker 在输出到达模型前被移除，使两个平台上的普通 shell 命令都无需固定等待静默阈值。尚未发布的 startup 不会把零输出静默视为就绪；timeout 会拒绝 spawn。所有时间参数都是经校验的配置字段：`pollIntervalMs`、`exactProbeAfterMs`、`idleSilenceMs` 和 `timeoutMs`。
|
||||
本地后端先识别受控 bash 启动时发出的私有 OSC prompt marker，并且只有在该 marker 后出现可打印的 prompt 文本时才据此声明 prompt 就绪；除此之外，它还运行 3 个有界 fallback 层级。在 data callback 之间保留这项状态，可以适配 macOS 分开交付 OSC marker 与 `PS1` 的情况；单独的 marker 不会发布空 MOTD。marker 在输出到达模型前被移除，使两个平台上的普通 shell 命令都无需固定等待静默阈值。尚未发布的 startup 不会把零输出静默视为就绪；timeout 会拒绝 spawn。若调用方取消在 startup 期间胜出，后端会关闭私有会话并原样抛出 `AbortSignal.reason`；尚不可观察的前台 PGID 不会再用查找错误覆盖取消原因。所有时间参数都是经校验的配置字段：`pollIntervalMs`、`exactProbeAfterMs`、`idleSilenceMs` 和 `timeoutMs`。
|
||||
|
||||
在 Linux 上，检查器从 `/proc/<shellPid>/stat` 读取 shell 的终端前台 PGID，枚举该进程组中的每个进程与线程，并检查它们当前的 syscall。Tier 1 只有观察到 stdin 等待才返回正结果：直接 `read(0)`、获准读取且含 fd 0 的 `select`/`pselect6` 或 `poll`/`ppoll` 参数，或者含 fd 0 的 epoll interest list。无法读取的进程内存和未识别的 syscall 都是 miss，绝不作为正向猜测。架构表只包含对应 Linux UAPI 定义的 syscall number；不支持的架构跳过 Tier 1。
|
||||
|
||||
@@ -78,7 +80,7 @@ macOS 没有精确 syscall 层。任何前台进程组输出静默都会返回 `
|
||||
|
||||
Tier 2 在持续 `idleSilenceMs` 没有输出后返回 `inferred_idle`，因此 sleep 或网络阻塞的命令可能看似 ready。Tier 3 在 `timeoutMs` 后返回 `timeout`，避免前台工具调用无限占住 agent。结果保留这些区别；调用方可以通过 `ctx.tasks` 等待、向前台组发信号，或从另一个会话排查。
|
||||
|
||||
`node-pty` data 通知进入同一个流式 decoder 和终端 parser。parser 的 carry 状态处理跨 chunk 的 UTF-8 与终端查询序列。当前实现只规范化行式输出并检测 alternate-screen 进入，不承诺正确操作全屏应用。
|
||||
`node-pty` data 通知进入同一个终端 parser。parser 的 carry state 会处理跨 callback 的控制序列和位于 callback 末尾的回车；因此，即使 CRLF 被拆开，也只会生成一个换行，而不会产生改变分页的空行。实现会规范化行式输出，但不承诺正确操作全屏应用。
|
||||
|
||||
### 模型可见输出与持久性
|
||||
|
||||
@@ -88,9 +90,9 @@ Tier 2 在持续 `idleSilenceMs` 没有输出后返回 `inferred_idle`，因此
|
||||
|
||||
### 进程树 teardown
|
||||
|
||||
顶层 `node-pty` 子进程是所有权锚点。关闭时，后端先停止 callback，再按父 PID 以子进程优先顺序捕获该 PID 及其传递子进程、发送 `SIGTERM`、关闭 PTY 并等待静默，然后在可配置的 `disposeGraceMs` 后向已验证的存活者发送 `SIGKILL`，并等待它们离开进程表。每个捕获的 PID 都包含进程启动身份，避免 PID 复用把升级信号发给无关进程。
|
||||
顶层 `node-pty` 子进程是所有权锚点。关闭时，后端先停止 callback，再按父 PID 以子进程优先顺序捕获其传递子进程、发送 `SIGTERM` 并等待，然后重新扫描关停期间 fork 出的子进程，向剩余子孙进程树发送 `SIGKILL`，并在 shell 仍存活时验证每个非僵尸子孙进程都已离开进程表。身份匹配的 Linux 僵尸进程已无可执行工作，因此视为静止；shell 关闭时会回收它或将其重新挂接给负责回收的父进程。完成这些步骤后，后端才用 shell 自身的 TERM、宽限等待、KILL 序列停止 shell。每个捕获的 PID 都包含进程启动身份，避免 PID 复用把升级信号发给无关进程。
|
||||
|
||||
teardown 独立报告根进程退出与存活进程清理。它不会只因 shell 退出就声称成功；dispose 只有在已捕获的进程树成员全部消失后才完成，否则返回结构化清理失败并列出存活者。即使某个 close 失败，服务 dispose 仍会清空其后端、预留与 owner detacher 注册表。所有权绝不会扩大到根 PID 所属 POSIX 会话的全部成员。
|
||||
teardown 独立报告根进程退出与存活进程清理。它不会只因 shell 退出就声称成功；dispose 只有在已捕获的进程树中不再存在非静止成员后才完成，否则返回清理失败并列出存活者。失败的 close 不会永久缓存：注册表与本地会话各自仅在关闭围栏仍指向该次失败尝试时才将其清除，因此外部存活进程状态改变后，后续的显式 close 或生命周期 close 会重试，且不会干扰较新的并发尝试。即使某个 close 失败，服务 dispose 仍会清空其后端、预留与 owner detacher 注册表。所有权绝不会扩大到根 PID 所属 POSIX 会话的全部成员。
|
||||
|
||||
### 组合与推行
|
||||
|
||||
@@ -115,9 +117,12 @@ plugins:
|
||||
timeoutMs: 30000
|
||||
disposeGraceMs: 3000
|
||||
'@deepseek-ai/dsh-tool-pty':
|
||||
config:
|
||||
enableRunInBackground: true
|
||||
maxResultBytes: 262144
|
||||
```
|
||||
|
||||
包提供简洁的工具指引，说明持久状态、owner 隔离、不确定的 idle 结果、清理，以及无需交互时优先使用现有一次性工具。它不增加全局 system prompt 推荐，也不在已发布的默认配置中挂载 PTY；专用 ACP 与 headless 快照 overlay 覆盖 opt-in 组合。
|
||||
包提供简洁的工具指引，说明持久状态、owner 隔离、不确定的 idle 结果、清理，以及无需交互时优先使用现有一次性工具。已发布的基础示例不挂载 PTY：PTY 仅通过专用组合 opt-in，ACP 与 headless 快照 overlay 覆盖该组合。`dsh-tool-pty` 实例一旦启用，6 个工具和 `run_in_background` 就会默认启用；部署可通过配置仅禁用后台参数。
|
||||
|
||||
### 推迟的工作
|
||||
|
||||
@@ -147,9 +152,9 @@ plugins:
|
||||
|
||||
## 验证
|
||||
|
||||
- 每文件覆盖率固定 owner 隔离、并发预留、生命周期清理、就绪层级、sanitizer carry state、UTF-8 上限、task 集成、schema 和 render intent。
|
||||
- Linux 进程 fixture 覆盖非 leader 与非主线程的 stdin 等待、不可读进程状态、受支持的 syscall 表、不支持的架构和误报拒绝；同一单元测试套件通过注入覆盖 macOS 检查器逻辑。
|
||||
- 真实 `node-pty` 测试在受支持宿主上覆盖 shell 状态、共享沙箱策略、环境清洗、信号、忽略 `SIGTERM` 的子进程，以及 dispose 返回后立即静默。
|
||||
- 每文件覆盖率固定 owner 隔离、并发预留、未发布 spawn 的取消与等待式 teardown、沙箱模式变更拒绝、可重试的生命周期清理、就绪层级、sanitizer carry state、完整 UTF-8 结果上限、task 集成、schema 和精确 render intent。
|
||||
- Linux 进程 fixture 覆盖非 leader 与非主线程的 stdin 等待、僵尸进程静止性、不可读进程状态、受支持的 syscall 表、不支持的架构和误报拒绝；同一单元测试套件通过注入覆盖 macOS 检查器逻辑。
|
||||
- 真实 `node-pty` 测试在受支持宿主上覆盖 shell 状态、共享沙箱策略、环境清洗、raw mode 下的前台 `SIGINT`、忽略 `SIGTERM` 的子进程，以及 dispose 返回后立即静默。
|
||||
- Loader 驱动的 `cordis.yml` 测试挂载真实三包组合；ACP 与 headless 快照通过 opt-in overlay 固定 6 个 schema、有界结果、错误渲染和 terminal/generic card。
|
||||
- 包契约、架构图、核心数据结构、生成目录和 website API 描述同一个已发布接口。
|
||||
- 仓库 CI 等价序列负责类型、lint、覆盖率、快照、文档、构建、hygiene、demo 和 built-entry 验证。
|
||||
|
||||
@@ -1,10 +1,10 @@
|
||||
// Keyless boot-chain smoke over the REAL carrier: startWebServer + web-plugins
|
||||
// registry surface + __DSH_BOOT__ injection + built shell dist in a real
|
||||
// chromium. First describe: manifest injection + static serving. Second
|
||||
// describe: the settled success pass — seven REAL tsdown bundles (the
|
||||
// infrastructure four + layout/sidebar/conversation) load through the DI
|
||||
// chain in ?fixture mode and the three-column frame appears in one flip. The
|
||||
// full conversation round lands in smoke-real under the W5 real-host standard.
|
||||
// describe: the settled success pass — all nine REAL tsdown bundles load
|
||||
// through the DI chain in ?fixture mode, the three-column frame appears in
|
||||
// one flip, and the resident question completes through the real UI stack.
|
||||
// The full model round lands in smoke-real under the W5 real-host standard.
|
||||
import { existsSync } from 'node:fs'
|
||||
import { fileURLToPath } from 'node:url'
|
||||
import type { Browser, Page } from 'playwright'
|
||||
@@ -17,7 +17,7 @@ import { DIST_INDEX, probeFreePort, requireDist, saveFailureShot } from './suppo
|
||||
const bundlePath = (dir: string): string =>
|
||||
fileURLToPath(new URL(`../../../packages/client/${dir}/lib/client.js`, import.meta.url))
|
||||
|
||||
/** id ↔ bundle table for the success pass (immediately four + layout/sidebar). */
|
||||
/** id ↔ bundle table for the success pass (the complete Web UI assembly). */
|
||||
const REAL_PLUGINS: { id: string; dir: string; inject: string[]; immediately?: boolean }[] = [
|
||||
{ id: '@deepseek-ai/dsh-client-connection', dir: 'connection', inject: [], immediately: true },
|
||||
{ id: '@deepseek-ai/dsh-client-runtime', dir: 'runtime', inject: ['@deepseek-ai/dsh-client-connection'], immediately: true },
|
||||
@@ -26,6 +26,8 @@ const REAL_PLUGINS: { id: string; dir: string; inject: string[]; immediately?: b
|
||||
{ id: '@deepseek-ai/dsh-client-ui-layout', dir: 'ui-layout', inject: ['@deepseek-ai/dsh-client-runtime'] },
|
||||
{ id: '@deepseek-ai/dsh-client-ui-sidebar', dir: 'ui-sidebar', inject: ['@deepseek-ai/dsh-client-ui-layout'] },
|
||||
{ id: '@deepseek-ai/dsh-client-ui-conversation', dir: 'ui-conversation', inject: ['@deepseek-ai/dsh-client-ui-layout'] },
|
||||
{ id: '@deepseek-ai/dsh-client-ui-question', dir: 'ui-question', inject: ['@deepseek-ai/dsh-client-ui-conversation'] },
|
||||
{ id: '@deepseek-ai/dsh-client-ui-trajectory', dir: 'ui-trajectory', inject: ['@deepseek-ai/dsh-client-ui-conversation'] },
|
||||
]
|
||||
|
||||
/** Manifest served by the fake registry: one live bundle row, one missing row. */
|
||||
@@ -84,7 +86,7 @@ describe('web boot chain (keyless, real carrier)', () => {
|
||||
})
|
||||
})
|
||||
|
||||
describe('web boot chain success pass (keyless, seven real bundles, ?fixture)', () => {
|
||||
describe('web boot chain success pass (keyless, nine real bundles, ?fixture)', () => {
|
||||
const missing = REAL_PLUGINS.filter(p => !existsSync(bundlePath(p.dir)))
|
||||
let server: Awaited<ReturnType<typeof startWebServer>>
|
||||
let browser: Browser
|
||||
@@ -216,6 +218,43 @@ describe('web boot chain success pass (keyless, seven real bundles, ?fixture)',
|
||||
expect(await external.getAttribute('rel')).toBe('noopener noreferrer')
|
||||
})
|
||||
|
||||
it('renders and completes the resident question through the composer slot', async () => {
|
||||
onTestFailed(() => saveFailureShot(page, 'smoke-question-composer'))
|
||||
await page.getByText('fixture', { exact: true }).click()
|
||||
await page.locator('[role="treeitem"]').nth(1).click()
|
||||
const composer = page.locator('[data-question-rpc-id]')
|
||||
await composer.waitFor({ timeout: 15_000 })
|
||||
expect({
|
||||
question: await composer.getByRole('heading').innerText(),
|
||||
progress: await composer.getByText('1 / 3', { exact: true }).innerText(),
|
||||
options: await composer.getByRole('radio').allTextContents(),
|
||||
custom: await composer.getByRole('button', { name: '其他，请填写自定义答案' }).innerText(),
|
||||
}).toMatchInlineSnapshot(`
|
||||
{
|
||||
"custom": "其他，请填写自定义答案",
|
||||
"options": [
|
||||
"1工程落地型推荐更看重能直接做 runtime、tool executor、sandbox、trace 和线上问题排查。",
|
||||
"2研究潜力型更看重 Agent 理解、训练评测思路和长期成长空间。",
|
||||
"3均衡型同时要求工程能力和 Agent 认知，但可能筛选门槛更高。",
|
||||
],
|
||||
"progress": "1 / 3",
|
||||
"question": "你现在更想招哪类 Agent/Harness 候选人？",
|
||||
}
|
||||
`)
|
||||
|
||||
await composer.getByRole('radio', { name: '工程落地型' }).click()
|
||||
await composer.getByText('2 / 3', { exact: true }).waitFor()
|
||||
await composer.getByRole('button', { name: '跳过本题', exact: true }).click()
|
||||
await composer.getByRole('checkbox', { name: '系统设计' }).click()
|
||||
await composer.getByRole('checkbox', { name: 'Agent 产品判断' }).click()
|
||||
await composer.getByRole('checkbox', { name: 'Agent 产品判断' }).press('Enter')
|
||||
|
||||
await composer.waitFor({ state: 'detached' })
|
||||
const restoredInput = page.locator('textarea[placeholder]')
|
||||
await restoredInput.waitFor()
|
||||
expect(await restoredInput.getAttribute('placeholder')).toBe('回复生成中，可停止后再输入')
|
||||
})
|
||||
|
||||
it('stayed clean: no page errors across the whole load chain', () => {
|
||||
expect(pageErrors).toEqual([])
|
||||
})
|
||||
|
||||
@@ -95,10 +95,10 @@ async function detailsTrack(page: Page): Promise<number> {
|
||||
return Number(cols.split(' ').pop()!.replace('px', ''))
|
||||
}
|
||||
|
||||
// Readiness gate: `dsh web` serves ALL eight manifest plugins; until every UI
|
||||
// Readiness gate: `dsh web` serves ALL nine manifest plugins; until every UI
|
||||
// plugin's client bundle exists and exports apply, the loader fail-louds and
|
||||
// the frame never appears.
|
||||
const UI_PLUGIN_DIRS = ['connection', 'runtime', 'ui-theme', 'i18n', 'ui-layout', 'ui-sidebar', 'ui-conversation', 'ui-trajectory']
|
||||
const UI_PLUGIN_DIRS = ['connection', 'runtime', 'ui-theme', 'i18n', 'ui-layout', 'ui-sidebar', 'ui-conversation', 'ui-question', 'ui-trajectory']
|
||||
const notReady = UI_PLUGIN_DIRS.filter((dir) => {
|
||||
const bundle = join(REPO_ROOT, 'packages/client', dir, 'lib/client.js')
|
||||
return !existsSync(bundle) || !readFileSync(bundle, 'utf8').includes('exports.apply')
|
||||
|
||||
@@ -1368,6 +1368,22 @@ export interface Config {
|
||||
|
||||
Source: [`packages/lsp/tool-lsp/src/index.ts:58`](../packages/lsp/tool-lsp/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-tool-pty`
|
||||
|
||||
Requires: `pty` · `tools` · `systemPrompt`
|
||||
|
||||
```ts config-catalog
|
||||
/** Model-facing terminal tool configuration. */
|
||||
export interface Config {
|
||||
/** Expose `run_in_background` and accept background sends (default true). */
|
||||
enableRunInBackground?: boolean
|
||||
/** Maximum UTF-8 bytes in one complete terminal or task-output result. */
|
||||
maxResultBytes?: number
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/pty/tool-pty/src/index.ts:35`](../packages/pty/tool-pty/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-tool-ralph`
|
||||
|
||||
Requires: `tools` · `workflows` · `subagents` · `systemPrompt`
|
||||
@@ -1472,7 +1488,7 @@ export interface Config {
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/tasks/tool-tasks/src/index.ts:21`](../packages/tasks/tool-tasks/src/index.ts)
|
||||
Source: [`packages/tasks/tool-tasks/src/index.ts:23`](../packages/tasks/tool-tasks/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-tool-web`
|
||||
|
||||
@@ -1532,7 +1548,7 @@ export interface Config {
|
||||
export type ToolPresentationMode = 'native' | 'code' | 'both'
|
||||
```
|
||||
|
||||
Source: [`packages/core/tools/src/index.ts:517`](../packages/core/tools/src/index.ts)
|
||||
Source: [`packages/core/tools/src/index.ts:529`](../packages/core/tools/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-tui`
|
||||
|
||||
@@ -1862,6 +1878,7 @@ These load from a `cordis.yml` entry with no `config:` block; they declare no co
|
||||
- `@deepseek-ai/dsh-client-runtime` ([`packages/client/runtime/src/index.ts`](../packages/client/runtime/src/index.ts))
|
||||
- `@deepseek-ai/dsh-client-ui-conversation` ([`packages/client/ui-conversation/src/index.ts`](../packages/client/ui-conversation/src/index.ts))
|
||||
- `@deepseek-ai/dsh-client-ui-layout` ([`packages/client/ui-layout/src/index.ts`](../packages/client/ui-layout/src/index.ts))
|
||||
- `@deepseek-ai/dsh-client-ui-question` — requires `tools` · `userInteraction` ([`packages/client/ui-question/src/index.ts`](../packages/client/ui-question/src/index.ts))
|
||||
- `@deepseek-ai/dsh-client-ui-sidebar` ([`packages/client/ui-sidebar/src/index.ts`](../packages/client/ui-sidebar/src/index.ts))
|
||||
- `@deepseek-ai/dsh-client-ui-theme` ([`packages/client/ui-theme/src/index.ts`](../packages/client/ui-theme/src/index.ts))
|
||||
- `@deepseek-ai/dsh-client-ui-trajectory` ([`packages/client/ui-trajectory/src/index.ts`](../packages/client/ui-trajectory/src/index.ts))
|
||||
@@ -1878,7 +1895,6 @@ These load from a `cordis.yml` entry with no `config:` block; they declare no co
|
||||
- `@deepseek-ai/dsh-tasks` ([`packages/tasks/tasks/src/index.ts`](../packages/tasks/tasks/src/index.ts))
|
||||
- `@deepseek-ai/dsh-timeout-policy` — requires `tools` ([`packages/timeout/timeout-policy/src/index.ts`](../packages/timeout/timeout-policy/src/index.ts))
|
||||
- `@deepseek-ai/dsh-tool-ask-user` — requires `tools` · `userInteraction` ([`packages/ui/tool-ask-user/src/index.ts`](../packages/ui/tool-ask-user/src/index.ts))
|
||||
- `@deepseek-ai/dsh-tool-pty` — requires `pty` · `tools` · `systemPrompt` ([`packages/pty/tool-pty/src/index.ts`](../packages/pty/tool-pty/src/index.ts))
|
||||
- `@deepseek-ai/dsh-tool-todo` — requires `tools` ([`packages/todo/tool-todo/src/index.ts`](../packages/todo/tool-todo/src/index.ts))
|
||||
- `@deepseek-ai/dsh-user-interaction` ([`packages/ui/user-interaction/src/index.ts`](../packages/ui/user-interaction/src/index.ts))
|
||||
|
||||
|
||||
@@ -788,6 +788,13 @@ listBackends(): string[]
|
||||
*/
|
||||
async spawn(owner: Agent, request: PtySpawnRequest, signal?: AbortSignal): Promise<PtySpawnResult>
|
||||
|
||||
/**
|
||||
* Test whether an exact owner has a published session or unpublished spawn.
|
||||
* @param owner - exact live owner to inspect.
|
||||
* @returns true across the entire spawn-to-close interval, with no publication gap.
|
||||
*/
|
||||
hasOwnerActivity(owner: Agent): boolean
|
||||
|
||||
/**
|
||||
* Start one exclusive interactive send.
|
||||
* @param owner - exact session owner.
|
||||
@@ -834,7 +841,7 @@ list(owner: Agent): PtySessionSnapshot[]
|
||||
|
||||
Types: [Agent](../core-data-structures/core.md) · [PtyBackend](../core-data-structures/pty.md) · [PtyReadRequest](../core-data-structures/pty.md) · [PtyReadResult](../core-data-structures/pty.md) · [PtySendOperation](../core-data-structures/pty.md) · [PtySendRequest](../core-data-structures/pty.md) · [PtySessionId](../core-data-structures/pty.md) · [PtySessionSnapshot](../core-data-structures/pty.md) · [PtySignal](../core-data-structures/pty.md) · [PtySignalResult](../core-data-structures/pty.md) · [PtySpawnRequest](../core-data-structures/pty.md) · [PtySpawnResult](../core-data-structures/pty.md)
|
||||
|
||||
Source: [`packages/pty/pty/src/index.ts:95`](../../packages/pty/pty/src/index.ts)
|
||||
Source: [`packages/pty/pty/src/index.ts:105`](../../packages/pty/pty/src/index.ts)
|
||||
|
||||
## `ctx.sandbox` — `SandboxProvider` (abstract seam)
|
||||
|
||||
@@ -1458,7 +1465,7 @@ attachSurface(name: string): () => void
|
||||
|
||||
Types: [Agent](../core-data-structures/core.md) · [TaskDoneListener](../core-data-structures/tasks.md) · [TaskId](../core-data-structures/tasks.md) · [TaskRead](../core-data-structures/tasks.md) · [TaskSnapshot](../core-data-structures/tasks.md) · [TaskStart](../core-data-structures/tasks.md)
|
||||
|
||||
Source: [`packages/tasks/tasks/src/index.ts:76`](../../packages/tasks/tasks/src/index.ts)
|
||||
Source: [`packages/tasks/tasks/src/index.ts:77`](../../packages/tasks/tasks/src/index.ts)
|
||||
|
||||
## `ctx.tokenMeter` — `TokenMeterService`
|
||||
|
||||
@@ -1540,7 +1547,7 @@ Tool registry and execution pipeline. Scoped registrations shadow globals; one v
|
||||
/**
|
||||
* Register globally or in the calling agent scope. Scoped tools shadow
|
||||
* globals; duplicates within one layer and the reserved `run_code` name fail.
|
||||
* @param definition - the tool schema, execution, and optional presentation functions.
|
||||
* @param definition - tool schema, execution, and optional finalization/presentation callbacks.
|
||||
* @returns the exact disposer that unregisters the tool.
|
||||
*/
|
||||
register(definition: ToolDefinition): () => void
|
||||
@@ -1595,10 +1602,11 @@ schemas(scope?: ScopeKey): ToolSchema[]
|
||||
executionMode(exec: ToolExecutionInput): ToolExecutionMode
|
||||
|
||||
/**
|
||||
* Execute through pre-policy, guards, around-dispatch, post-policy, and final
|
||||
* notification. Tool and listener failures resolve as materialized error
|
||||
* results; an invisible tool reports `UNKNOWN_TOOL`. The returned outcome is
|
||||
* the same lossless, frozen snapshot final observers receive. Cancellation
|
||||
* Execute through pre-policy, guards, around-dispatch, post-policy,
|
||||
* definition-owned content finalization, and final notification. Tool and
|
||||
* listener failures resolve as materialized error results; an invisible tool
|
||||
* reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen
|
||||
* snapshot final observers receive. Cancellation
|
||||
* arriving after entry and before final result materialization skips a
|
||||
* not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a
|
||||
* successful started outcome with `ABORTED`; already-started work is still
|
||||
@@ -1612,7 +1620,7 @@ async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult>
|
||||
|
||||
Types: [ScopeKey](../core-data-structures/scope.md) · [ToolDefinition](../core-data-structures/tools.md) · [ToolExecutionInput](../core-data-structures/tools.md) · [ToolExecutionMode](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) · [ToolGuard](../core-data-structures/tools.md) · [ToolRestriction](../core-data-structures/tools.md) · [ToolSchema](../core-data-structures/tools.md)
|
||||
|
||||
Source: [`packages/core/tools/src/index.ts:622`](../../packages/core/tools/src/index.ts)
|
||||
Source: [`packages/core/tools/src/index.ts:634`](../../packages/core/tools/src/index.ts)
|
||||
|
||||
## `ctx.tui` — `TuiExtensionService` (abstract seam)
|
||||
|
||||
|
||||
@@ -544,6 +544,6 @@ type SessionStartSource = 'startup' | 'resume' | 'clear' | 'compact'
|
||||
|
||||
## `ToolDefinition`
|
||||
|
||||
The one pipeline-authoring type that is core: what every registered tool *is* — a model-facing `ToolSchema` plus an `execute` function and optional UI presenters. A tool author rarely constructs it by hand (the `defineTool` DSL builds it with typed args), but it is the contract the registry holds and the loop dispatches through.
|
||||
The one pipeline-authoring type that is core: what every registered tool *is* — a model-facing `ToolSchema` plus an `execute` function and optional final-content and UI callbacks. A tool author rarely constructs it by hand (the `defineTool` DSL builds it with typed args), but it is the contract the registry holds and the loop dispatches through.
|
||||
|
||||
Its full fields, the `defineTool`/`ValueSchemaSpec`/`ParameterSchemaSpec` typed schema DSL, the `ToolExecution`/`ToolExecutionResult` waterfall shapes, and the tool-presentation UI vocabulary are on **[tools.md](tools.md)**.
|
||||
|
||||
@@ -22,14 +22,14 @@ type PtySessionStatus =
|
||||
|
||||
## Backend and live session
|
||||
|
||||
A backend owns how one registered type starts and detects readiness. `PtyService` publishes the returned session only after setup succeeds, then owns id authorization and cleanup. A backend session owns terminal state and captured-resource quiescence.
|
||||
A backend owns how one registered type starts and detects readiness. `PtyService` publishes the returned session only after setup succeeds, then owns id authorization and cleanup. A backend that cannot clean partial startup resources rejects with `PtyBackendCleanupError`, allowing disposal to retain the cleanup failure without replacing the caller's cancellation reason. A backend session owns terminal state and captured-resource quiescence.
|
||||
|
||||
```ts type-equiv
|
||||
/** Replaceable provider for one PTY session type. */
|
||||
interface PtyBackend {
|
||||
/** Stable type selected by {@link PtySpawnRequest.type}. */
|
||||
readonly type: string
|
||||
/** Create an unpublished session or reject after cleaning partial resources. */
|
||||
/** Create an unpublished session or reject after cleaning partial resources; cleanup failure uses {@link PtyBackendCleanupError}. */
|
||||
spawn(spec: PtyBackendSpawnSpec): Promise<PtyBackendSession>
|
||||
}
|
||||
```
|
||||
|
||||
@@ -34,6 +34,11 @@ interface TaskStart {
|
||||
kind: TaskKind
|
||||
/** One-line model-facing label (the command; the delegation description). */
|
||||
label: string
|
||||
/**
|
||||
* Optional UTF-8 byte cap for each complete model-facing completion notice or
|
||||
* output read, including control-surface status metadata.
|
||||
*/
|
||||
outputLimitBytes?: number
|
||||
/**
|
||||
* Owning live agent. Access is fenced by its session id, and agent disposal
|
||||
* cancels and awaits the task. The instance must be the one currently
|
||||
@@ -104,6 +109,8 @@ interface TaskSnapshot {
|
||||
kind: TaskKind
|
||||
/** The producer-supplied one-line label. */
|
||||
label: string
|
||||
/** Producer-owned cap for complete model-facing notices and output reads. */
|
||||
outputLimitBytes?: number
|
||||
/**
|
||||
* Owner session id used for authorization and correlation; absent for
|
||||
* unowned tasks. Completion listeners receive the exact {@link Agent}
|
||||
|
||||
@@ -6,7 +6,7 @@ Source: [`packages/core/tools/src/index.ts`](../../packages/core/tools/src/index
|
||||
|
||||
## `ToolDefinition` — a registered tool
|
||||
|
||||
A `ToolSchema` (the model-facing fields) plus a mandatory canonical output declaration, the `execute` function, host-only scheduler metadata, and optional UI presenters. The registry holds these; the loop dispatches calls through them. The registry's `schemas()` builds the model-facing `ToolSchema[]` by an explicit allowlist — `output`/`execute`/`timeoutMs`/`isConcurrencySafe`/`presentCall`/`presentResult` must never leak into a model request.
|
||||
A `ToolSchema` (the model-facing fields) plus a mandatory canonical output declaration, the `execute` function, host-only scheduler metadata, an optional final-content callback, and optional UI presenters. The registry holds these; the loop dispatches calls through them. The registry's `schemas()` builds the model-facing `ToolSchema[]` by an explicit allowlist — `output`/`execute`/`finalizeContent`/`timeoutMs`/`isConcurrencySafe`/`presentCall`/`presentResult` must never leak into a model request.
|
||||
|
||||
```ts type-equiv
|
||||
/** Tool-owned canonical output contract used after the body returns a JSON value. */
|
||||
@@ -36,6 +36,18 @@ interface ToolDefinition extends ToolSchema {
|
||||
* @returns the canonical value declared by `output.schema`.
|
||||
*/
|
||||
execute(args: unknown, exec: ToolRunContext): Promise<unknown>
|
||||
/**
|
||||
* Synchronous last-mile transform for model-facing content. The registry
|
||||
* snapshots this callback when execution starts and invokes it exactly once
|
||||
* for every normalized outcome, including pipeline failures that bypass
|
||||
* `tools/post-execute`, immediately before lossless materialization.
|
||||
* Returning `undefined` preserves the content; every other result field
|
||||
* remains registry-owned. The callback must be total and must not throw.
|
||||
* @param exec - immutable execution identity and arguments.
|
||||
* @param result - complete normalized outcome before materialization.
|
||||
* @returns replacement content, or `undefined` to preserve it.
|
||||
*/
|
||||
finalizeContent?(exec: Readonly<ToolExecution>, result: Readonly<ToolExecutionResult>): ContentBlock[] | undefined
|
||||
/**
|
||||
* Cooperative tool-call timeout budget in milliseconds. Omit for no deadline.
|
||||
* Enforced by `@deepseek-ai/dsh-timeout-policy` (a `tools/execute` wrapper); it
|
||||
@@ -79,7 +91,7 @@ interface ToolDefinition extends ToolSchema {
|
||||
}
|
||||
```
|
||||
|
||||
`execute` receives `args: unknown` — a raw `ToolDefinition` validates its own input. First-party tools don't write that by hand; they use `defineTool`, which validates and narrows the arguments, infers the body return from `output.schema`, and types both output projectors.
|
||||
`execute` receives `args: unknown` — a raw `ToolDefinition` validates its own input. First-party tools don't write that by hand; they use `defineTool`, which validates and narrows the arguments, infers the body return from `output.schema`, and types both output projectors. `finalizeContent` deliberately receives the immutable execution instead of typed arguments because invalid-input and outer pipeline failures reach it too; it may enforce a tool-owned content bound while preserving `isError`, canonical value, structured error identity, deferred contexts, and presentation metadata.
|
||||
|
||||
## The unified JSON-value schema DSL
|
||||
|
||||
@@ -155,7 +167,7 @@ interface ToolRestriction {
|
||||
|
||||
## Execution: extensible waterfalls plus monotonic policy
|
||||
|
||||
`ctx.tools.execute()` accepts a caller-owned `ToolExecutionInput` with a required readonly `signal`, materializes its parsed JSON arguments once into a pipeline-owned `ToolExecution`, and runs that call through `tools/pre-execute` (the reorderable allow/deny/ask waterfall) → registered monotonic guards → `tools/execute` (around-dispatch wrappers) → `tools/post-execute` (inspect/replace the result) → `tools/result` (the immutable authoritative outcome). Only the `tools/execute` view may replace the required signal. The outcome is a `ToolExecutionResult`.
|
||||
`ctx.tools.execute()` accepts a caller-owned `ToolExecutionInput` with a required readonly `signal`, materializes its parsed JSON arguments once into a pipeline-owned `ToolExecution`, and runs that call through `tools/pre-execute` (the reorderable allow/deny/ask waterfall) → registered monotonic guards → `tools/execute` (around-dispatch wrappers) → `tools/post-execute` (inspect/replace the result) → optional definition-owned `finalizeContent` → `tools/result` (the immutable authoritative outcome). Only the `tools/execute` view may replace the required signal. The outcome is a `ToolExecutionResult`.
|
||||
|
||||
```ts type-equiv
|
||||
/** Opaque call identity that permits correlation without exposing mutable execution state. */
|
||||
@@ -303,6 +315,8 @@ The result carries only the outcome. Call identity remains on the immutable `Too
|
||||
|
||||
On success the registry snapshots and validates the body value, freezes it, and invokes the pure renderer plus the optional direct-surface metadata projector. It separately materializes the durable presentation fields immediately before `tools/result`; an invalid value, renderer/projector failure, or non-JSON presentation becomes a JSON-safe `isError`. The final live observer therefore sees the exact execution-local value beside fields safe for the later durable append.
|
||||
|
||||
Before final content, the registry materializes the candidate result; a failure in content, structured error, additional context, or presentation metadata becomes a JSON-safe `isError` result that still reaches `finalizeContent`. The registry invokes that callback exactly once, then materializes and freezes the accepted result immediately before `tools/result`, so the observed live outcome is safe for the later durable `tool/result` append.
|
||||
|
||||
Each interception waterfall returns a typed **Decision** (the idiom shared with the `agent/*` seams). `tools/pre-execute` listeners receive `(exec, next)` and return a `PreToolDecision`; `tools/execute` wrappers return a `ToolExecutionResult`; `tools/post-execute` listeners receive `(exec, result, next)` and return a `PostToolDecision`:
|
||||
|
||||
```ts type-equiv
|
||||
|
||||
@@ -58,14 +58,14 @@ interface AskUserQuestionRequest {
|
||||
|
||||
## Answer
|
||||
|
||||
Providers return one answer per answered question id. `selected` contains selected option labels, and `custom` carries a free-form "Other" answer when the user typed one. When `custom` is present, `selected` is empty; custom text is an answer override, not a supplement to selected choices.
|
||||
Providers return one answer item per question id. `selected` contains selected option labels, and `custom` carries a free-form "Other" answer when the user typed one. When `custom` is present, `selected` is empty; custom text is an answer override, not a supplement to selected choices. A UI may also use an item with empty `selected` and no `custom` to preserve a skipped question in an otherwise completed batch.
|
||||
|
||||
```ts type-equiv
|
||||
/** Answer to one question. */
|
||||
interface AskUserQuestionAnswerItem {
|
||||
/** The answered question id. */
|
||||
id: string
|
||||
/** Selected option labels. Empty when the answer is purely custom text. */
|
||||
/** Selected option labels. Empty for custom or unanswered choices. */
|
||||
selected: string[]
|
||||
/** Optional free-text "Other" answer. */
|
||||
custom?: string
|
||||
|
||||
@@ -44,7 +44,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac
|
||||
| `tools/change` | `emit` | [`packages/core/tools/src/index.ts:143`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - |
|
||||
| `tools/execute` | `waterfall` | [`packages/core/tools/src/index.ts:113`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy), [`timeout-policy`](../packages/timeout/timeout-policy) |
|
||||
| `tools/post-execute` | `waterfall` | [`packages/core/tools/src/index.ts:125`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`spill-policy`](../packages/spill/spill-policy), [`tool-fs-search`](../packages/fs/tool-fs-search), [`workspace-context`](../packages/context/workspace-context) |
|
||||
| `tools/pre-execute` | `waterfall` | [`packages/core/tools/src/index.ts:102`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
|
||||
| `tools/pre-execute` | `waterfall` | [`packages/core/tools/src/index.ts:102`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`tool-tasks`](../packages/tasks/tool-tasks) |
|
||||
| `tools/result` | `emit` | [`packages/core/tools/src/index.ts:133`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`events.dispatch`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`workspace-context`](../packages/context/workspace-context) |
|
||||
| `workflow/agent-end` | `emit` | [`packages/workflow/workflow/src/index.ts:81`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | [`workflow`](../packages/workflow/workflow) |
|
||||
| `workflow/agent-start` | `emit` | [`packages/workflow/workflow/src/index.ts:70`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | [`workflow`](../packages/workflow/workflow) |
|
||||
@@ -57,7 +57,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac
|
||||
|
||||
| Event string | Dispatchers | Listeners |
|
||||
| --- | --- | --- |
|
||||
| `internal/dispatch` | - | [`compact`](../packages/compact/compact), [`fs`](../packages/fs/fs), [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm-retry`](../packages/llm/llm-retry), [`permission`](../packages/ui/permission), [`plan-mode`](../packages/plan/plan-mode), `runtime`, [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`time-context`](../packages/context/time-context), [`tool-todo`](../packages/todo/tool-todo), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval), [`workflow`](../packages/workflow/workflow) |
|
||||
| `internal/dispatch` | - | [`compact`](../packages/compact/compact), [`fs`](../packages/fs/fs), [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm-retry`](../packages/llm/llm-retry), [`permission`](../packages/ui/permission), [`plan-mode`](../packages/plan/plan-mode), [`pty-local`](../packages/pty/pty-local), `runtime`, [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`time-context`](../packages/context/time-context), [`tool-todo`](../packages/todo/tool-todo), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval), [`workflow`](../packages/workflow/workflow) |
|
||||
| `internal/plugin` | - | `webserver` |
|
||||
| `internal/status` | - | [`agent`](../packages/core/agent) |
|
||||
| `slots/changed` | `runtime` (`emit`) | - |
|
||||
|
||||
@@ -137,6 +137,7 @@ flowchart TD
|
||||
pkg_client_ui_conversation["client-ui-conversation"]
|
||||
pkg_client_ui_layout["client-ui-layout"]
|
||||
pkg_client_ui_primitives["client-ui-primitives"]
|
||||
pkg_client_ui_question["client-ui-question"]
|
||||
pkg_client_ui_sidebar["client-ui-sidebar"]
|
||||
pkg_client_ui_slots["client-ui-slots"]
|
||||
pkg_client_ui_theme["client-ui-theme"]
|
||||
@@ -216,6 +217,7 @@ flowchart TD
|
||||
pkg_client_ui_conversation --> pkg_invariants
|
||||
pkg_client_ui_layout --> pkg_invariants
|
||||
pkg_client_ui_primitives --> pkg_invariants
|
||||
pkg_client_ui_question --> pkg_invariants
|
||||
pkg_client_ui_sidebar --> pkg_invariants
|
||||
pkg_client_ui_slots --> pkg_invariants
|
||||
pkg_client_ui_theme --> pkg_invariants
|
||||
@@ -444,10 +446,12 @@ flowchart TD
|
||||
pkg_session_reference --> pkg_retention
|
||||
pkg_session_reference --> pkg_session
|
||||
pkg_session_reference --> pkg_session_query
|
||||
pkg_pty_local --> pkg_agent
|
||||
pkg_pty_local --> pkg_invariants
|
||||
pkg_pty_local --> pkg_pty
|
||||
pkg_pty_local --> pkg_sandbox
|
||||
pkg_pty_local --> pkg_sandbox_policy
|
||||
pkg_pty_local --> pkg_session
|
||||
pkg_agent_loop --> pkg_agent
|
||||
pkg_agent_loop --> pkg_invariants
|
||||
pkg_agent_loop --> pkg_llm
|
||||
@@ -579,11 +583,13 @@ flowchart TD
|
||||
pkg_tool_pty --> pkg_invariants
|
||||
pkg_tool_pty --> pkg_llm
|
||||
pkg_tool_pty --> pkg_pty
|
||||
pkg_tool_pty --> pkg_retention
|
||||
pkg_tool_pty --> pkg_system_prompt
|
||||
pkg_tool_pty --> pkg_tasks
|
||||
pkg_tool_pty --> pkg_tools
|
||||
pkg_tool_tasks --> pkg_agent
|
||||
pkg_tool_tasks --> pkg_invariants
|
||||
pkg_tool_tasks --> pkg_retention
|
||||
pkg_tool_tasks --> pkg_system_prompt
|
||||
pkg_tool_tasks --> pkg_tasks
|
||||
pkg_tool_tasks --> pkg_tools
|
||||
@@ -765,6 +771,7 @@ flowchart TD
|
||||
| [`client-ui-conversation`](../packages/client/ui-conversation) | `client` | [`invariants`](../packages/support/invariants) |
|
||||
| [`client-ui-layout`](../packages/client/ui-layout) | `client` | [`invariants`](../packages/support/invariants) |
|
||||
| [`client-ui-primitives`](../packages/client/ui-primitives) | `client` | [`invariants`](../packages/support/invariants) |
|
||||
| [`client-ui-question`](../packages/client/ui-question) | `client` | [`invariants`](../packages/support/invariants) |
|
||||
| [`client-ui-sidebar`](../packages/client/ui-sidebar) | `client` | [`invariants`](../packages/support/invariants) |
|
||||
| [`client-ui-slots`](../packages/client/ui-slots) | `client` | [`invariants`](../packages/support/invariants) |
|
||||
| [`client-ui-theme`](../packages/client/ui-theme) | `client` | [`invariants`](../packages/support/invariants) |
|
||||
@@ -835,7 +842,7 @@ flowchart TD
|
||||
| [`session-title-first-message-llm`](../packages/session-title/session-title-first-message-llm) | `session-title` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-title`](../packages/session-title/session-title), [`session-title-llm`](../packages/session-title/session-title-llm) |
|
||||
| [`permission`](../packages/ui/permission) | `ui` | [`bash`](../packages/bash/bash), [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`user-approval`](../packages/ui/user-approval) |
|
||||
| [`session-reference`](../packages/context/session-reference) | `context` | [`agent`](../packages/core/agent), [`compact`](../packages/compact/compact), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`session-query`](../packages/session-query/session-query) |
|
||||
| [`pty-local`](../packages/pty/pty-local) | `pty` | [`invariants`](../packages/support/invariants), [`pty`](../packages/pty/pty), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy) |
|
||||
| [`pty-local`](../packages/pty/pty-local) | `pty` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`pty`](../packages/pty/pty), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session) |
|
||||
| [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
|
||||
| [`tool-goal`](../packages/goal/tool-goal) | `goal` | [`agent`](../packages/core/agent), [`goal`](../packages/goal/goal), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
|
||||
| [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`paths`](../packages/util/paths), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) |
|
||||
@@ -857,8 +864,8 @@ flowchart TD
|
||||
| [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | `guard` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`tools`](../packages/core/tools) |
|
||||
| [`tool-lsp`](../packages/lsp/tool-lsp) | `lsp` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`lsp`](../packages/lsp/lsp), [`system-prompt`](../packages/core/system-prompt), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) |
|
||||
| [`mcp-client`](../packages/mcp/mcp-client) | `mcp` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`tools`](../packages/core/tools) |
|
||||
| [`tool-pty`](../packages/pty/tool-pty) | `pty` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`pty`](../packages/pty/pty), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) |
|
||||
| [`tool-tasks`](../packages/tasks/tool-tasks) | `tasks` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) |
|
||||
| [`tool-pty`](../packages/pty/tool-pty) | `pty` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`pty`](../packages/pty/pty), [`retention`](../packages/util/retention), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) |
|
||||
| [`tool-tasks`](../packages/tasks/tool-tasks) | `tasks` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`retention`](../packages/util/retention), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) |
|
||||
| [`tool-workflow`](../packages/workflow/tool-workflow) | `workflow` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) |
|
||||
| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) |
|
||||
| [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
|
||||
# Tool Execution Pipeline
|
||||
|
||||
This graph shows where policy, hooks, sandboxing, filesystem guards, result rewriting, final-outcome observation, and UI rendering fit without changing the loop. The transformable extension points are the `tools/pre-execute`, `tools/execute`, and `tools/post-execute` waterfalls; monotonic guards and `tools/result` are the owner-enforced boundaries around them.
|
||||
This graph shows where policy, hooks, sandboxing, filesystem guards, result rewriting, final-outcome observation, and UI rendering fit without changing the loop. The transformable extension points are the `tools/pre-execute`, `tools/execute`, and `tools/post-execute` waterfalls; monotonic guards, definition-owned `finalizeContent`, and `tools/result` are the owner-enforced boundaries around them.
|
||||
|
||||
```mermaid
|
||||
flowchart TD
|
||||
@@ -19,6 +19,8 @@ flowchart TD
|
||||
fsGate["<code>fs/write-intent</code> or <code>fs/edit-intent</code><br/>tool-fs mutations only"]
|
||||
owned["Tool-owned session events<br/><code>todo/write</code>, <code>fs/observed</code>, <code>hook/invoked</code>, <code>hook/result</code>, <code>tool/code-dispatch</code>"]
|
||||
post["<code>tools/post-execute</code> waterfall<br/>accept, block, replace, add context"]
|
||||
normalized["Registry outer normalization<br/>pipeline/result snapshot throws become isError"]
|
||||
finalize["ToolDefinition.finalizeContent<br/>last content-only invariant"]
|
||||
final["<code>tools/result</code> synchronous notification<br/>frozen authoritative outcome"]
|
||||
context["Active-batch additionalContexts FIFO<br/>context/message after recorded tool results"]
|
||||
toolResult["Session event: <code>tool/result</code><br/>single model-facing outcome"]
|
||||
@@ -30,24 +32,31 @@ flowchart TD
|
||||
pre -->|allow| guards
|
||||
guards -->|allow| around
|
||||
guards -->|deny| denied
|
||||
guards -.->|throw| normalized
|
||||
around --> toolBody
|
||||
pre -->|deny| denied
|
||||
pre -->|ask| approval
|
||||
approval -->|allowed-once| guards
|
||||
approval -->|rejected, cancelled, unavailable| denied
|
||||
approval -.->|throw| normalized
|
||||
denied --> post
|
||||
pre -.->|throw| normalized
|
||||
toolBody --> fsGate
|
||||
fsGate --> toolBody
|
||||
toolBody --> owned
|
||||
toolBody --> around
|
||||
around --> post
|
||||
post --> final
|
||||
around -.->|wrapper throws| normalized
|
||||
post -.->|throw| normalized
|
||||
post --> finalize
|
||||
normalized --> finalize
|
||||
finalize --> final
|
||||
final --> toolResult
|
||||
toolResult --> presentResult
|
||||
toolResult --> allResults
|
||||
allResults --> context
|
||||
```
|
||||
|
||||
Filesystem read-before-edit checks stay below `tool-fs` on `fs/*` events. Generic pre/post waterfalls host hooks and approval policy; `ctx.approval` resolves asks before monotonic guards, and owner policy that must not be reordered remains a registered guard. Around-dispatch concerns such as timeouts wrap `tools/execute`, while `tools/result` observes the immutable outcome after transforms, lossless-JSON validation, and outer error normalization. This lets hooks span tool families without coupling the tools to one policy service. Code Mode sends both the reserved `run_code` transport and its serialized sub-calls through the pipeline; sub-calls carry the parent token, log `tool/code-dispatch`, surface denials as binding rejections, and omit `additionalContexts` to preserve call/result adjacency.
|
||||
Filesystem read-before-edit checks stay below `tool-fs` on `fs/*` events. Generic pre/post waterfalls host hooks and approval policy; `ctx.approval` resolves asks before monotonic guards, and owner policy that must not be reordered remains a registered guard. Around-dispatch concerns such as timeouts wrap `tools/execute`. The registry losslessly snapshots the candidate result and normalizes a snapshot failure before the visible definition's snapshotted `finalizeContent` callback enforces its synchronous content-only invariant. `tools/result` then observes the immutable, lossless-JSON outcome. This lets hooks span tool families without coupling the tools to one policy service. Code Mode sends both the reserved `run_code` transport and its serialized sub-calls through the pipeline; sub-calls carry the parent token, log `tool/code-dispatch`, surface denials as binding rejections, and omit `additionalContexts` to preserve call/result adjacency.
|
||||
|
||||
Maintenance mode: curated Mermaid flow; exact tool schemas and event signatures live in generated catalogs.
|
||||
|
||||
@@ -14,6 +14,8 @@
|
||||
name: './pty-snapshot-backend.mjs'
|
||||
- id: tool-pty
|
||||
name: '@deepseek-ai/dsh-tool-pty'
|
||||
config:
|
||||
maxResultBytes: 64
|
||||
- id: llm-replay
|
||||
name: '@deepseek-ai/dsh-llm-replay'
|
||||
config:
|
||||
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -21,7 +21,7 @@
|
||||
{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"pty-send","name":"terminal_send","arguments":"{\"sessionId\":\"pty-1\",\"text\":\"printf 'PTY_OK\\\\n'\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-pro"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"pty-send","name":"terminal_send","arguments":"{\"sessionId\":\"pty-1\",\"text\":\"printf 'PTY_OK\\\\n'\"}"}}
|
||||
{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"pty-send","content":[{"type":"text","text":"printf 'PTY_OK\\n'\nPTY_OK\ndsh> \n[wait: stdin_read]\n[session: running]"}],"isError":false,"meta":{"viewport":"printf 'PTY_OK\\n'\nPTY_OK\ndsh> ","waitReason":"stdin_read","sessionStatus":{"kind":"running"},"truncated":false}},"sourceEventSeqs":[21],"surfaceOp":"append"}
|
||||
{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"pty-send","content":[{"type":"text","text":"K\ndsh> \n[wait: stdin_read]\n[session: running]\n[output truncated]"}],"isError":false,"meta":{"viewport":"printf 'PTY_OK\\n'\nPTY_OK\ndsh> ","waitReason":"stdin_read","sessionStatus":{"kind":"running"},"truncated":false}},"sourceEventSeqs":[21],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":23,"time":0,"data":{"turn":1,"step":2}}
|
||||
{"type":"step/start","seq":24,"time":0,"data":{"turn":1,"step":3}}
|
||||
{"type":"assistant/chunk","seq":25,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
|
||||
|
||||
@@ -5,7 +5,7 @@
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"pty-spawn","title":"Open terminal main","kind":"execute","status":"in_progress"}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"pty-spawn","status":"completed","content":[{"type":"content","content":{"type":"text","text":"started terminal session pty-1 (main) [type: shell]\ndsh> "}}]}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"pty-send","title":"printf 'PTY_OK\\n'","kind":"execute","status":"in_progress","rawInput":"printf 'PTY_OK\\n'","content":[{"type":"content","content":{"type":"text","text":"Terminal pty-1"}},{"type":"terminal","terminalId":"pty-send"}],"_meta":{"terminal_info":{"terminal_id":"pty-send","cwd":"{{cwd}}"}}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"pty-send","status":"completed","_meta":{"terminal_output":{"terminal_id":"pty-send","data":"printf 'PTY_OK\\n'\nPTY_OK\ndsh> \n[wait: stdin_read]\n[session: running]"}}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"pty-send","status":"completed","_meta":{"terminal_output":{"terminal_id":"pty-send","data":"K\ndsh> \n[wait: stdin_read]\n[session: running]\n[output truncated]"}}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"pty-read","title":"Read terminal pty-1","kind":"read","status":"in_progress","rawInput":{"sessionId":"pty-1","offset":0,"count":20}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"pty-read","status":"completed","content":[{"type":"content","content":{"type":"text","text":"dsh> printf 'PTY_OK\\n'\nPTY_OK\ndsh> \n[lines: 0-3 of 3]"}}]}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"pty-signal","title":"Signal terminal pty-missing","kind":"execute","status":"in_progress","rawInput":{"sessionId":"pty-missing","signal":"SIGINT"}}}}
|
||||
|
||||
@@ -14,5 +14,7 @@
|
||||
name: '../acp-agent/pty-snapshot-backend.mjs'
|
||||
- id: tool-pty
|
||||
name: '@deepseek-ai/dsh-tool-pty'
|
||||
config:
|
||||
maxResultBytes: 64
|
||||
- id: llm-replay
|
||||
name: '@deepseek-ai/dsh-llm-replay'
|
||||
|
||||
@@ -21,7 +21,7 @@
|
||||
{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"pty-send","name":"terminal_send","arguments":"{\"sessionId\":\"pty-1\",\"text\":\"printf 'PTY_OK\\\\n'\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"pty-send","name":"terminal_send","arguments":"{\"sessionId\":\"pty-1\",\"text\":\"printf 'PTY_OK\\\\n'\"}"}}
|
||||
{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"pty-send","content":[{"type":"text","text":"printf 'PTY_OK\\n'\nPTY_OK\ndsh> \n[wait: stdin_read]\n[session: running]"}],"isError":false,"meta":{"viewport":"printf 'PTY_OK\\n'\nPTY_OK\ndsh> ","waitReason":"stdin_read","sessionStatus":{"kind":"running"},"truncated":false}},"sourceEventSeqs":[21],"surfaceOp":"append"}
|
||||
{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"pty-send","content":[{"type":"text","text":"K\ndsh> \n[wait: stdin_read]\n[session: running]\n[output truncated]"}],"isError":false,"meta":{"viewport":"printf 'PTY_OK\\n'\nPTY_OK\ndsh> ","waitReason":"stdin_read","sessionStatus":{"kind":"running"},"truncated":false}},"sourceEventSeqs":[21],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":23,"time":0,"data":{"turn":1,"step":2}}
|
||||
{"type":"step/start","seq":24,"time":0,"data":{"turn":1,"step":3}}
|
||||
{"type":"assistant/chunk","seq":25,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
|
||||
|
||||
@@ -20,7 +20,7 @@
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"pty-send","name":"terminal_send","arguments":"{\"sessionId\":\"pty-1\",\"text\":\"printf 'PTY_OK\\\\n'\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"pty-send","name":"terminal_send","arguments":"{\"sessionId\":\"pty-1\",\"text\":\"printf 'PTY_OK\\\\n'\"}"}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"pty-send","content":[{"type":"text","text":"printf 'PTY_OK\\n'\nPTY_OK\ndsh> \n[wait: stdin_read]\n[session: running]"}],"isError":false,"meta":{"viewport":"printf 'PTY_OK\\n'\nPTY_OK\ndsh> ","waitReason":"stdin_read","sessionStatus":{"kind":"running"},"truncated":false}},"sourceEventSeqs":[21],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"pty-send","content":[{"type":"text","text":"K\ndsh> \n[wait: stdin_read]\n[session: running]\n[output truncated]"}],"isError":false,"meta":{"viewport":"printf 'PTY_OK\\n'\nPTY_OK\ndsh> ","waitReason":"stdin_read","sessionStatus":{"kind":"running"},"truncated":false}},"sourceEventSeqs":[21],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":23,"time":0,"data":{"turn":1,"step":2}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":24,"time":0,"data":{"turn":1,"step":3}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":25,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
|
||||
|
||||
@@ -2,8 +2,8 @@
|
||||
// RpcRequest<P> and returns RpcResponse<T> (echoing the rpcId); streams yield RpcRequest<frame>
|
||||
// (the fixture IS the fake server, so it mints frame rpcIds); root respond takes ClientResponse
|
||||
// and returns RpcReceipt. fx-alpha carries a hand-built history script (60 turns, pageable);
|
||||
// prompt triggers a chunked streaming replay; cancel stops the replay; one resident pending
|
||||
// approval (placeholder-card material, subscribed-baseline-replay semantics: stable rpcId reuse).
|
||||
// prompt triggers a chunked streaming replay; cancel stops the replay; resident pending
|
||||
// approval/question requests exercise replay and composer takeover with stable rpcIds.
|
||||
|
||||
import type { ContentBlock } from '@deepseek-ai/dsh-llm/types'
|
||||
import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session/types'
|
||||
@@ -281,6 +281,41 @@ export function createFixtureApi(): ApiProxy {
|
||||
const mint = (): ReturnType<typeof RpcId> => RpcId(`fx-rpc-${nextRpc++}`)
|
||||
/** Resident pending approval (stable rpcId: every mux open replays the same id, matching host replay semantics). */
|
||||
const pendingApprovalRpcId = mint()
|
||||
const pendingQuestionRpcId = mint()
|
||||
let questionPending = true
|
||||
const fixtureQuestions: Extract<MuxFrame, { type: 'question/requested' }>['questions'] = [
|
||||
{
|
||||
id: 'harness-profile',
|
||||
header: '偏好',
|
||||
question: '你现在更想招哪类 Agent/Harness 候选人？',
|
||||
options: [
|
||||
{ label: '工程落地型 (Recommended)', description: '更看重能直接做 runtime、tool executor、sandbox、trace 和线上问题排查。' },
|
||||
{ label: '研究潜力型', description: '更看重 Agent 理解、训练评测思路和长期成长空间。' },
|
||||
{ label: '均衡型', description: '同时要求工程能力和 Agent 认知，但可能筛选门槛更高。' },
|
||||
],
|
||||
},
|
||||
{
|
||||
id: 'work-mode',
|
||||
header: '方式',
|
||||
question: '你希望候选人优先展示哪种工作方式？',
|
||||
options: [
|
||||
{ label: '先做小型原型 (Recommended)', description: '用可运行结果尽快验证关键假设。' },
|
||||
{ label: '先写完整设计', description: '先收敛边界、协议和风险，再开始实现。' },
|
||||
],
|
||||
},
|
||||
{
|
||||
id: 'signals',
|
||||
header: '信号',
|
||||
question: '哪些面试信号最重要？',
|
||||
detail: '按当前招聘目标选择；跳过则视为不设偏好。',
|
||||
multiSelect: true,
|
||||
options: [
|
||||
{ label: '系统设计' },
|
||||
{ label: '代码质量' },
|
||||
{ label: 'Agent 产品判断' },
|
||||
],
|
||||
},
|
||||
]
|
||||
|
||||
const muxConns = new Set<StreamConn<MuxFrame>>()
|
||||
const hostConns = new Set<StreamConn<HostFrame>>()
|
||||
@@ -467,7 +502,7 @@ export function createFixtureApi(): ApiProxy {
|
||||
muxConns.add(conn)
|
||||
const breakNow = (): void => { conn.breakNow() }
|
||||
streamBreakers.add(breakNow)
|
||||
// Open baseline: subscribed for attached (running) sessions + pending approval replay (stable rpcId).
|
||||
// Open baseline: subscribed sessions + pending interactions replayed with stable rpcIds.
|
||||
for (const s of sessions) {
|
||||
if (!s.running) continue
|
||||
conn.push({ rpcId: mint(), payload: { type: 'session/subscribed', sessionId: s.sessionId, lastSeq: (logs.get(s.sessionId)?.length ?? 0) - 1 } })
|
||||
@@ -480,6 +515,14 @@ export function createFixtureApi(): ApiProxy {
|
||||
toolName: 'dangerous_tool', reason: 'fixture 常驻占位审批（可见不可答）',
|
||||
},
|
||||
})
|
||||
if (questionPending) {
|
||||
conn.push({
|
||||
rpcId: pendingQuestionRpcId,
|
||||
payload: {
|
||||
type: 'question/requested', sessionId: sid('fx-alpha'), questions: fixtureQuestions,
|
||||
},
|
||||
})
|
||||
}
|
||||
try {
|
||||
yield* conn.drain(signal)
|
||||
} finally {
|
||||
@@ -509,9 +552,16 @@ export function createFixtureApi(): ApiProxy {
|
||||
},
|
||||
},
|
||||
respond(message: ClientResponse): Promise<RpcReceipt> {
|
||||
// The v1 UI never answers (PendingCard is visible but not answerable); implemented for type completeness, always not-pending.
|
||||
void message
|
||||
return Promise.resolve({ accepted: false, reason: 'not-pending' })
|
||||
if (!questionPending || message.rpcId !== pendingQuestionRpcId) {
|
||||
return Promise.resolve({ accepted: false, reason: 'not-pending' })
|
||||
}
|
||||
questionPending = false
|
||||
emitMux({
|
||||
type: 'question/resolved', sessionId: sid('fx-alpha'),
|
||||
questionRpcId: pendingQuestionRpcId,
|
||||
outcome: message.result.ok ? 'answered' : 'cancelled',
|
||||
})
|
||||
return Promise.resolve({ accepted: true })
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
@@ -148,14 +148,14 @@ describe('createFixtureApi', () => {
|
||||
expect(types.at(-1)).toBe('turn/end') // steer did not restart the turn
|
||||
})
|
||||
|
||||
it('mux open replays the baseline: subscribed for running sessions + the resident approval with a stable rpcId', async () => {
|
||||
it('mux open replays subscribed sessions and resident interactions with stable rpcIds', async () => {
|
||||
const api = createFixtureApi()
|
||||
const openOnce = async (): Promise<RpcRequest<MuxFrame>[]> => {
|
||||
const abort = new AbortController()
|
||||
const envelopes: RpcRequest<MuxFrame>[] = []
|
||||
for await (const envelope of api.events.mux(req({}), abort.signal)) {
|
||||
envelopes.push(envelope)
|
||||
if (envelopes.length >= 2) abort.abort()
|
||||
if (envelopes.length >= 3) abort.abort()
|
||||
}
|
||||
return envelopes
|
||||
}
|
||||
@@ -165,6 +165,8 @@ describe('createFixtureApi', () => {
|
||||
expect((first[0]?.payload as { lastSeq: number }).lastSeq).toBeGreaterThan(0)
|
||||
expect(first[1]?.payload).toMatchObject({ type: 'approval/requested', toolName: 'dangerous_tool' })
|
||||
expect(second[1]?.rpcId).toBe(first[1]?.rpcId) // stable rpcId across replays (host replay semantics)
|
||||
expect(first[2]?.payload).toMatchObject({ type: 'question/requested', sessionId: 'fx-alpha' })
|
||||
expect(second[2]?.rpcId).toBe(first[2]?.rpcId)
|
||||
})
|
||||
|
||||
it('steer with no replay in flight falls through to a fresh queued turn; non-text blocks stringify empty', async () => {
|
||||
@@ -217,9 +219,38 @@ describe('createFixtureApi', () => {
|
||||
}
|
||||
})
|
||||
|
||||
it('respond is a typed stub: always not-pending', async () => {
|
||||
it('respond resolves the resident question once and rejects duplicate or unrelated ids', async () => {
|
||||
const api = createFixtureApi()
|
||||
expect(await api.respond({ type: 'client-response', rpcId: RpcId('x'), result: { ok: true, value: {} } })).toEqual({ accepted: false, reason: 'not-pending' })
|
||||
const abort = new AbortController()
|
||||
let question: RpcRequest<MuxFrame> | undefined
|
||||
for await (const envelope of api.events.mux(req({}), abort.signal)) {
|
||||
if (envelope.payload.type !== 'question/requested') continue
|
||||
question = envelope
|
||||
abort.abort()
|
||||
}
|
||||
if (question === undefined) throw new Error('fixture question missing')
|
||||
const response = { type: 'client-response' as const, rpcId: question.rpcId, result: { ok: true as const, value: {} } }
|
||||
expect(await api.respond(response)).toEqual({ accepted: true })
|
||||
expect(await api.respond(response)).toEqual({ accepted: false, reason: 'not-pending' })
|
||||
|
||||
const replayAbort = new AbortController()
|
||||
const replayed = await collect(api.events.mux(req({}), replayAbort.signal), replayAbort, frames => frames.length === 2)
|
||||
expect(replayed.every(frame => frame.type !== 'question/requested')).toBe(true)
|
||||
|
||||
const cancelledApi = createFixtureApi()
|
||||
const cancelAbort = new AbortController()
|
||||
let cancelQuestion: RpcRequest<MuxFrame> | undefined
|
||||
for await (const envelope of cancelledApi.events.mux(req({}), cancelAbort.signal)) {
|
||||
if (envelope.payload.type !== 'question/requested') continue
|
||||
cancelQuestion = envelope
|
||||
cancelAbort.abort()
|
||||
}
|
||||
if (cancelQuestion === undefined) throw new Error('fixture cancellation question missing')
|
||||
expect(await cancelledApi.respond({
|
||||
type: 'client-response', rpcId: cancelQuestion.rpcId,
|
||||
result: { ok: false, error: { code: 'cancelled', message: 'skip', details: {} } },
|
||||
})).toEqual({ accepted: true })
|
||||
})
|
||||
|
||||
it('describe answers the fixture identity', async () => {
|
||||
|
||||
@@ -26,4 +26,4 @@ None; this package neither assembles nor sends a provider request.
|
||||
- **Details panel is the minimal form** — selected call args/result raw display; the Input/Output/Metadata switch, Prev/Next stepping, and See-in-trajectory deep link are deferred.
|
||||
- **Assistant footer extensions (IconActions row, per-message paging) are reserved slots** — drawn in the design, not implemented.
|
||||
- **The sparkle icon for the others tool row is a hand-drawn approximation** — the design glyph's vector geometry is not exportable locally; promotion into ui-primitives waits on an exact export.
|
||||
- **Approval/question cards are display-only placeholders** — web-side answering (composer takeover panel) is the P-II approvals project.
|
||||
- **Approval cards are display-only placeholders** — question requests answer through the composer chain (ui-question), while web-side approval answering is the P-II approvals project.
|
||||
|
||||
@@ -18,8 +18,8 @@ export type {
|
||||
} from './contract/views.ts'
|
||||
export type { ToolCallBlock } from './contract/tool-call-model.ts'
|
||||
export type {
|
||||
ChatStore, ChatViewInjected, ChatViewSlotProps, ConversationInjected, ConversationSlotProps,
|
||||
ConvViewOwnerProps, ConvViewProps, DetailsInjected, DetailsSlotProps,
|
||||
ChatStore, ChatViewInjected, ChatViewSlotProps, ComposerChainProps, ConversationInjected,
|
||||
ConversationSlotProps, ConvViewOwnerProps, ConvViewProps, DetailsInjected, DetailsSlotProps,
|
||||
EmptyStateInjected, EmptyStateSlotProps, ToolRowOwnerProps, ToolRowProps,
|
||||
} from './contract/slots.ts'
|
||||
// Export discipline: packages/client/AGENTS.md.
|
||||
|
||||
20
packages/client/ui-question/README.md
Normal file
20
packages/client/ui-question/README.md
Normal file
@@ -0,0 +1,20 @@
|
||||
# @deepseek-ai/dsh-client-ui-question
|
||||
|
||||
Web `ask_user_question` feature plugin. Its host half mounts `dsh-tool-ask-user` only when the Web feature is selected; its browser half registers the `question` entry in the conversation-owned `conversation.composer` keyed slot.
|
||||
|
||||
The component renders one question at a time with progress navigation, single- and multi-select choices, recommendation badges derived from label suffixes, and custom answers. Single-select choices advance immediately, and Enter submits once every question is answered or skipped; Enter during IME composition confirms the input candidate without advancing. It submits one structured answer batch for the whole request: “Skip this question” retains other drafts and emits the existing blank `{ selected: [] }` shape for that item, while close rejects the whole wait as `ASK_CANCELLED`.
|
||||
|
||||
Selection state is local to a component keyed by the request rpcId. A replay with the same id preserves a still-mounted draft, while `question/resolved` from the host removes the composer. The host remains authoritative: successful HTTP delivery does not remove pending state locally.
|
||||
|
||||
## Model Experience
|
||||
|
||||
Indirectly, through `dsh-tool-ask-user`; that package owns the model-visible tool schema and structured result.
|
||||
|
||||
#### KV Cache effect
|
||||
|
||||
No direct invalidation; `dsh-tool-ask-user` owns the model-visible tool call and result.
|
||||
|
||||
## Known Limitations and Deferred Work
|
||||
|
||||
- **Unsubmitted drafts are not durable** — reconnect resync or a full page reload restores the host-owned pending request with the same rpcId, but a composer unmount resets local option and custom-text drafts.
|
||||
- **One request owns the composer at a time** — later pending requests remain in the session snapshot and become visible after the earlier request resolves.
|
||||
67
packages/client/ui-question/package.json
Normal file
67
packages/client/ui-question/package.json
Normal file
@@ -0,0 +1,67 @@
|
||||
{
|
||||
"name": "@deepseek-ai/dsh-client-ui-question",
|
||||
"description": "Web ask_user_question feature: host tool mount plus composer-takeover question UI",
|
||||
"version": "0.0.1",
|
||||
"private": true,
|
||||
"type": "module",
|
||||
"main": "lib/index.js",
|
||||
"types": "lib/types/index.d.ts",
|
||||
"exports": {
|
||||
".": {
|
||||
"types": "./lib/types/index.d.ts",
|
||||
"default": "./lib/index.js"
|
||||
},
|
||||
"./invariant": {
|
||||
"types": "./lib/types/invariant.d.ts",
|
||||
"default": "./lib/invariant.js"
|
||||
},
|
||||
"./client": {
|
||||
"types": "./lib/types/client/index.d.ts",
|
||||
"default": "./lib/client.js"
|
||||
},
|
||||
"./src/*": "./src/*",
|
||||
"./package.json": "./package.json"
|
||||
},
|
||||
"dshClient": {
|
||||
"inject": [
|
||||
"@deepseek-ai/dsh-client-ui-conversation"
|
||||
],
|
||||
"platform": "web"
|
||||
},
|
||||
"scripts": {
|
||||
"bundle": "tsdown",
|
||||
"watch": "tsdown --watch"
|
||||
},
|
||||
"license": "BSD-3-Clause",
|
||||
"dependencies": {
|
||||
"@deepseek-ai/dsh-client-connection": "workspace:^",
|
||||
"@deepseek-ai/dsh-client-runtime": "workspace:^",
|
||||
"@deepseek-ai/dsh-client-ui-conversation": "workspace:^",
|
||||
"@deepseek-ai/dsh-client-ui-primitives": "workspace:^",
|
||||
"@deepseek-ai/dsh-client-ui-slots": "workspace:^",
|
||||
"@deepseek-ai/dsh-tool-ask-user": "workspace:^",
|
||||
"clsx": "^2.0.0",
|
||||
"react": "^18.2.0"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"@deepseek-ai/dsh-invariants": "^0.0.1",
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@deepseek-ai/dsh-agent": "workspace:^",
|
||||
"@deepseek-ai/dsh-invariants": "workspace:^",
|
||||
"@deepseek-ai/dsh-system-prompt": "workspace:^",
|
||||
"@deepseek-ai/dsh-tools": "workspace:^",
|
||||
"@deepseek-ai/dsh-user-interaction": "workspace:^",
|
||||
"@types/react": "~18.3.1",
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
},
|
||||
"files": [
|
||||
"lib/index.js",
|
||||
"lib/invariant.js",
|
||||
"lib/client.js",
|
||||
"lib/types/**/*.d.ts",
|
||||
"lib/types/**/*.d.ts.map",
|
||||
"src"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,348 @@
|
||||
.frame {
|
||||
display: flex;
|
||||
justify-content: center;
|
||||
padding: 6px 24px 10px;
|
||||
}
|
||||
|
||||
.card {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
width: 100%;
|
||||
max-width: 720px;
|
||||
/* Composer seat sits in a fixed-height conversation column (overflow
|
||||
hidden): cap the card against the viewport and scroll the option list
|
||||
so header and footer actions stay reachable on long batches. */
|
||||
max-height: min(60vh, 520px);
|
||||
padding: 14px 16px 12px;
|
||||
border: 1px solid var(--dsw-alias-border-l2-darkmode-thin);
|
||||
border-radius: 18px;
|
||||
background: var(--dsw-specific-input-major);
|
||||
box-shadow: var(--dsw-shadow-lv1-blur);
|
||||
color: var(--dsw-alias-label-primary);
|
||||
}
|
||||
|
||||
.card,
|
||||
.card * {
|
||||
box-sizing: border-box;
|
||||
}
|
||||
|
||||
.header {
|
||||
display: flex;
|
||||
align-items: flex-start;
|
||||
justify-content: space-between;
|
||||
gap: 16px;
|
||||
flex-shrink: 0;
|
||||
margin-bottom: 8px;
|
||||
}
|
||||
|
||||
.headingBlock {
|
||||
min-width: 0;
|
||||
padding: 1px 2px;
|
||||
}
|
||||
|
||||
.eyebrow {
|
||||
margin-bottom: 2px;
|
||||
color: var(--dsw-alias-label-tertiary);
|
||||
font-size: 11px;
|
||||
line-height: 16px;
|
||||
}
|
||||
|
||||
.title {
|
||||
display: flex;
|
||||
align-items: baseline;
|
||||
flex-wrap: wrap;
|
||||
gap: 6px;
|
||||
margin: 0;
|
||||
font-size: 16px;
|
||||
line-height: 22px;
|
||||
font-weight: 600;
|
||||
}
|
||||
|
||||
.multiSelectHint {
|
||||
color: var(--dsw-alias-label-tertiary);
|
||||
font-size: 14px;
|
||||
line-height: 20px;
|
||||
font-weight: 400;
|
||||
white-space: nowrap;
|
||||
}
|
||||
|
||||
.detail {
|
||||
margin: 2px 0 0;
|
||||
color: var(--dsw-alias-label-tertiary);
|
||||
font-size: 13px;
|
||||
line-height: 20px;
|
||||
font-weight: 400;
|
||||
}
|
||||
|
||||
.headerActions,
|
||||
.footerActions {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 4px;
|
||||
flex-shrink: 0;
|
||||
}
|
||||
|
||||
.progress {
|
||||
padding: 0 6px;
|
||||
color: var(--dsw-alias-label-tertiary);
|
||||
font-size: 12px;
|
||||
line-height: 24px;
|
||||
white-space: nowrap;
|
||||
}
|
||||
|
||||
.iconButton {
|
||||
display: grid;
|
||||
place-items: center;
|
||||
width: 24px;
|
||||
height: 24px;
|
||||
padding: 0;
|
||||
border: none;
|
||||
border-radius: 999px;
|
||||
background: transparent;
|
||||
color: var(--dsw-alias-label-tertiary);
|
||||
cursor: pointer;
|
||||
}
|
||||
|
||||
.iconButton:hover:not(:disabled) {
|
||||
background: var(--dsw-alias-interactive-bg-hover);
|
||||
color: var(--dsw-alias-label-primary);
|
||||
}
|
||||
|
||||
.iconButton:disabled {
|
||||
color: var(--dsw-alias-label-dimmed);
|
||||
cursor: default;
|
||||
}
|
||||
|
||||
.options {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 4px;
|
||||
/* The scrollable region of the capped card (ChatView list pattern). */
|
||||
min-height: 0;
|
||||
overflow-y: auto;
|
||||
}
|
||||
|
||||
.option {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 10px;
|
||||
width: 100%;
|
||||
min-height: 42px;
|
||||
padding: 5px 8px;
|
||||
border: 1px solid transparent;
|
||||
border-radius: 12px;
|
||||
background: transparent;
|
||||
color: inherit;
|
||||
text-align: left;
|
||||
cursor: pointer;
|
||||
transition: background-color 120ms ease, border-color 120ms ease;
|
||||
}
|
||||
|
||||
.option:hover:not(:disabled),
|
||||
.optionSelected {
|
||||
background: var(--dsw-alias-interactive-bg-hover);
|
||||
}
|
||||
|
||||
.optionSelected {
|
||||
border-color: var(--dsw-alias-border-l2);
|
||||
}
|
||||
|
||||
.option:disabled,
|
||||
.customTrigger:disabled {
|
||||
cursor: default;
|
||||
}
|
||||
|
||||
.number {
|
||||
display: grid;
|
||||
place-items: center;
|
||||
flex: 0 0 28px;
|
||||
width: 28px;
|
||||
height: 28px;
|
||||
border: 1px solid var(--dsw-alias-border-l2);
|
||||
border-radius: 999px;
|
||||
background: var(--dsw-alias-bg-module-platform);
|
||||
color: var(--dsw-alias-label-tertiary);
|
||||
font-size: 12px;
|
||||
line-height: 18px;
|
||||
}
|
||||
|
||||
.optionCopy {
|
||||
min-width: 0;
|
||||
flex: 1;
|
||||
}
|
||||
|
||||
.optionLine {
|
||||
display: flex;
|
||||
align-items: baseline;
|
||||
flex-wrap: wrap;
|
||||
gap: 2px 6px;
|
||||
}
|
||||
|
||||
.optionLabel {
|
||||
font-size: 14px;
|
||||
line-height: 20px;
|
||||
font-weight: 600;
|
||||
}
|
||||
|
||||
.badge {
|
||||
padding: 0 6px;
|
||||
border-radius: 999px;
|
||||
background: var(--dsw-alias-bg-module-platform);
|
||||
color: var(--dsw-alias-label-secondary);
|
||||
font-size: 11px;
|
||||
line-height: 18px;
|
||||
}
|
||||
|
||||
.description {
|
||||
color: var(--dsw-alias-label-tertiary);
|
||||
font-size: 13px;
|
||||
line-height: 20px;
|
||||
font-weight: 400;
|
||||
}
|
||||
|
||||
.choiceIcon {
|
||||
display: grid;
|
||||
place-items: center;
|
||||
width: 20px;
|
||||
color: var(--dsw-alias-label-tertiary);
|
||||
}
|
||||
|
||||
.custom {
|
||||
border: 1px solid transparent;
|
||||
border-radius: 12px;
|
||||
}
|
||||
|
||||
.customOpen {
|
||||
border-color: var(--dsw-alias-border-l2);
|
||||
background: var(--dsw-alias-bg-module-platform);
|
||||
}
|
||||
|
||||
.customOptionless {
|
||||
border: none;
|
||||
background: transparent;
|
||||
}
|
||||
|
||||
.customTrigger {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 10px;
|
||||
width: 100%;
|
||||
min-height: 42px;
|
||||
padding: 5px 8px;
|
||||
border: none;
|
||||
background: transparent;
|
||||
color: var(--dsw-alias-label-tertiary);
|
||||
font-size: 14px;
|
||||
line-height: 20px;
|
||||
text-align: left;
|
||||
cursor: pointer;
|
||||
}
|
||||
|
||||
.customTrigger:hover:not(:disabled) {
|
||||
color: var(--dsw-alias-label-primary);
|
||||
}
|
||||
|
||||
.customInput {
|
||||
display: block;
|
||||
width: calc(100% - 20px);
|
||||
min-height: 54px;
|
||||
max-height: 140px;
|
||||
margin: 0 10px 10px;
|
||||
padding: 7px 10px;
|
||||
resize: vertical;
|
||||
border: 1px solid var(--dsw-alias-border-l2);
|
||||
border-radius: 10px;
|
||||
outline: none;
|
||||
background: var(--dsw-specific-input-major);
|
||||
color: var(--dsw-alias-label-primary);
|
||||
caret-color: var(--dsw-alias-state-business-primary);
|
||||
font: inherit;
|
||||
font-size: 13px;
|
||||
line-height: 20px;
|
||||
}
|
||||
|
||||
.customInput:focus {
|
||||
border-color: var(--dsw-alias-state-business-primary);
|
||||
}
|
||||
|
||||
.customInput::placeholder {
|
||||
color: var(--dsw-alias-label-caption);
|
||||
}
|
||||
|
||||
.customOptionless .customInput {
|
||||
width: 100%;
|
||||
min-height: 58px;
|
||||
margin: 0;
|
||||
background: var(--dsw-alias-bg-module-platform);
|
||||
}
|
||||
|
||||
.footer {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: space-between;
|
||||
gap: 12px;
|
||||
flex-shrink: 0;
|
||||
margin-top: 8px;
|
||||
padding: 0 2px;
|
||||
}
|
||||
|
||||
.feedback {
|
||||
min-height: 16px;
|
||||
color: var(--dsw-alias-state-error-primary);
|
||||
font-size: 11px;
|
||||
line-height: 16px;
|
||||
}
|
||||
|
||||
@media (max-width: 720px) {
|
||||
.frame {
|
||||
padding: 6px 10px 10px;
|
||||
}
|
||||
|
||||
.card {
|
||||
padding: 12px 10px 10px;
|
||||
border-radius: 16px;
|
||||
}
|
||||
|
||||
.header {
|
||||
display: block;
|
||||
}
|
||||
|
||||
.headerActions {
|
||||
justify-content: flex-end;
|
||||
margin-top: 8px;
|
||||
}
|
||||
|
||||
.headingBlock {
|
||||
padding: 0 2px;
|
||||
}
|
||||
|
||||
.title {
|
||||
font-size: 15px;
|
||||
line-height: 21px;
|
||||
}
|
||||
|
||||
.option,
|
||||
.customTrigger {
|
||||
align-items: flex-start;
|
||||
gap: 8px;
|
||||
padding: 6px;
|
||||
}
|
||||
|
||||
.choiceIcon {
|
||||
margin-top: 3px;
|
||||
}
|
||||
|
||||
.footer {
|
||||
align-items: flex-end;
|
||||
}
|
||||
|
||||
.footerActions {
|
||||
flex-shrink: 0;
|
||||
}
|
||||
}
|
||||
|
||||
@media (prefers-reduced-motion: reduce) {
|
||||
.option {
|
||||
transition: none;
|
||||
}
|
||||
}
|
||||
297
packages/client/ui-question/src/client/QuestionComposer.tsx
Normal file
297
packages/client/ui-question/src/client/QuestionComposer.tsx
Normal file
@@ -0,0 +1,297 @@
|
||||
import { useMemo, useState, type KeyboardEvent } from 'react'
|
||||
import clsx from 'clsx'
|
||||
import {
|
||||
Button, IconCheckOutline16, IconChevronLeftOutline14, IconChevronRightOutline14,
|
||||
IconCloseOutline16, IconEditOutline16,
|
||||
} from '@deepseek-ai/dsh-client-ui-primitives'
|
||||
import { PendingQuestion, type QuestionAnswer, type QuestionComposerProps } from './contract/slots.ts'
|
||||
import css from './QuestionComposer.module.css'
|
||||
|
||||
interface DraftAnswer {
|
||||
selected: string[]
|
||||
custom: string
|
||||
customOpen: boolean
|
||||
skipped: boolean
|
||||
}
|
||||
|
||||
/**
|
||||
* Split the conventional recommendation suffix without changing the answer value.
|
||||
* @param label - Original option label returned if selected.
|
||||
* @returns Display label plus recommendation state.
|
||||
*/
|
||||
export function parseRecommendedLabel(label: string): { label: string; recommended: boolean } {
|
||||
const suffix = /\s*(?:\((?:recommended|推荐)\)|（(?:recommended|推荐)）)\s*$/i
|
||||
return suffix.test(label)
|
||||
? { label: label.replace(suffix, ''), recommended: true }
|
||||
: { label, recommended: false }
|
||||
}
|
||||
|
||||
/**
|
||||
* Remove a conventional multi-select suffix so the hint can be styled separately.
|
||||
* @param title - Question title supplied by the interaction request.
|
||||
* @returns Question title without a trailing multi-select marker.
|
||||
*/
|
||||
export function parseQuestionTitle(title: string): string {
|
||||
return title.replace(/\s*[（(]可多选[）)]\s*$/, '')
|
||||
}
|
||||
|
||||
/** Return whether a textarea key event belongs to an active IME composition. */
|
||||
function isComposing(event: KeyboardEvent<HTMLTextAreaElement>): boolean {
|
||||
return event.nativeEvent.isComposing || event.nativeEvent.keyCode === 229
|
||||
}
|
||||
|
||||
/**
|
||||
* Composer takeover boundary; the carrier key keys local drafts, so a
|
||||
* same-request replay (same key, new carrier object) preserves them.
|
||||
* @param props - the selector-matched pending question carrier plus the framework standard kit.
|
||||
* @returns The question flow for this request.
|
||||
*/
|
||||
export function QuestionComposer(props: QuestionComposerProps) {
|
||||
// Domain-face mint rides the carrier's stable identity (never minted in a
|
||||
// select/render dispatch — per-dispatch minting would churn memo identity).
|
||||
const question = useMemo(() => new PendingQuestion(props.matched), [props.matched])
|
||||
return <QuestionFlow key={question.key} pending={question} />
|
||||
}
|
||||
|
||||
function QuestionFlow({ pending }: { pending: PendingQuestion }) {
|
||||
const questions = pending.questions
|
||||
const [index, setIndex] = useState(0)
|
||||
const [drafts, setDrafts] = useState<DraftAnswer[]>(() => questions.map(question => ({
|
||||
selected: [], custom: '', customOpen: (question.options?.length ?? 0) === 0, skipped: false,
|
||||
})))
|
||||
const [busy, setBusy] = useState<'answer' | 'cancel' | null>(null)
|
||||
const [error, setError] = useState<string | null>(null)
|
||||
const question = questions[index]!
|
||||
const draft = drafts[index]!
|
||||
const hasOptions = (question.options?.length ?? 0) > 0
|
||||
|
||||
const cancelFlow = (): void => {
|
||||
setBusy('cancel')
|
||||
setError(null)
|
||||
void pending.cancel().catch((cause: unknown) => {
|
||||
setBusy(null)
|
||||
setError(cause instanceof Error ? cause.message : String(cause))
|
||||
})
|
||||
}
|
||||
|
||||
const updateDraft = (update: (current: DraftAnswer) => DraftAnswer): void => {
|
||||
setDrafts(current => current.map((item, itemIndex) => itemIndex === index ? update(item) : item))
|
||||
setError(null)
|
||||
}
|
||||
|
||||
const choose = (label: string): void => {
|
||||
updateDraft((current) => {
|
||||
const selected = question.multiSelect === true
|
||||
? current.selected.includes(label)
|
||||
? current.selected.filter(item => item !== label)
|
||||
: [...current.selected, label]
|
||||
: [label]
|
||||
return { selected, custom: '', customOpen: false, skipped: false }
|
||||
})
|
||||
if (question.multiSelect !== true && index < questions.length - 1) {
|
||||
setIndex(current => current + 1)
|
||||
}
|
||||
}
|
||||
|
||||
const openCustom = (): void => {
|
||||
updateDraft(current => ({ ...current, selected: [], customOpen: true, skipped: false }))
|
||||
}
|
||||
|
||||
const answered = (item: DraftAnswer): boolean =>
|
||||
item.selected.length > 0 || item.custom.trim() !== ''
|
||||
|
||||
const completed = (item: DraftAnswer): boolean => answered(item) || item.skipped
|
||||
|
||||
const submitDrafts = (values: DraftAnswer[]): void => {
|
||||
const missing = values.findIndex(item => !completed(item))
|
||||
if (missing >= 0) {
|
||||
setIndex(missing)
|
||||
setError('请先完成这道问题。')
|
||||
return
|
||||
}
|
||||
const answer: QuestionAnswer = {
|
||||
answers: questions.map((item, itemIndex) => {
|
||||
const value = values[itemIndex] as DraftAnswer
|
||||
if (value.skipped) return { id: item.id, selected: [] }
|
||||
const custom = value.custom.trim()
|
||||
return {
|
||||
id: item.id,
|
||||
selected: custom === '' ? value.selected : [],
|
||||
...(custom === '' ? {} : { custom }),
|
||||
}
|
||||
}),
|
||||
}
|
||||
setBusy('answer')
|
||||
setError(null)
|
||||
void pending.answer(answer).catch((cause: unknown) => {
|
||||
setBusy(null)
|
||||
setError(cause instanceof Error ? cause.message : String(cause))
|
||||
})
|
||||
}
|
||||
|
||||
const continueFlow = (): void => {
|
||||
if (!answered(draft)) {
|
||||
setError('请选择一个选项或填写自定义答案。')
|
||||
return
|
||||
}
|
||||
if (index < questions.length - 1) {
|
||||
setIndex(current => current + 1)
|
||||
setError(null)
|
||||
return
|
||||
}
|
||||
submitDrafts(drafts)
|
||||
}
|
||||
|
||||
const skipQuestion = (): void => {
|
||||
const nextDrafts = drafts.map((item, itemIndex) => itemIndex === index
|
||||
? {
|
||||
selected: [], custom: '',
|
||||
customOpen: (question.options?.length ?? 0) === 0,
|
||||
skipped: true,
|
||||
}
|
||||
: item)
|
||||
setDrafts(nextDrafts)
|
||||
setError(null)
|
||||
if (index < questions.length - 1) {
|
||||
setIndex(current => current + 1)
|
||||
return
|
||||
}
|
||||
submitDrafts(nextDrafts)
|
||||
}
|
||||
|
||||
return (
|
||||
<div className={css.frame} data-question-key={pending.key}>
|
||||
<section className={css.card} aria-labelledby={`question-${pending.key}-${String(index)}`}>
|
||||
<header className={css.header}>
|
||||
<div className={css.headingBlock}>
|
||||
{question.header !== undefined && <div className={css.eyebrow}>{question.header}</div>}
|
||||
<h2 className={css.title} id={`question-${pending.key}-${String(index)}`}>
|
||||
<span>{question.multiSelect === true
|
||||
? parseQuestionTitle(question.question)
|
||||
: question.question}</span>
|
||||
{question.multiSelect === true && <span className={css.multiSelectHint}>可多选</span>}
|
||||
</h2>
|
||||
{question.detail !== undefined && <p className={css.detail}>{question.detail}</p>}
|
||||
</div>
|
||||
<div className={css.headerActions}>
|
||||
<span className={css.progress}>{index + 1} / {questions.length}</span>
|
||||
<button
|
||||
type="button" className={css.iconButton} aria-label="上一题"
|
||||
disabled={index === 0 || busy !== null}
|
||||
onClick={() => { setIndex(index - 1); setError(null) }}
|
||||
>
|
||||
<IconChevronLeftOutline14 />
|
||||
</button>
|
||||
<button
|
||||
type="button" className={css.iconButton} aria-label="下一题"
|
||||
disabled={index === questions.length - 1 || busy !== null}
|
||||
onClick={() => { setIndex(index + 1); setError(null) }}
|
||||
>
|
||||
<IconChevronRightOutline14 />
|
||||
</button>
|
||||
<button
|
||||
type="button" className={css.iconButton} aria-label="放弃整组问题"
|
||||
title="放弃整组问题"
|
||||
disabled={busy !== null} onClick={cancelFlow}
|
||||
>
|
||||
<IconCloseOutline16 />
|
||||
</button>
|
||||
</div>
|
||||
</header>
|
||||
|
||||
<div className={css.options} role={question.multiSelect === true ? 'group' : 'radiogroup'}>
|
||||
{(question.options ?? []).map((option, optionIndex) => {
|
||||
const selected = draft.selected.includes(option.label)
|
||||
const display = parseRecommendedLabel(option.label)
|
||||
return (
|
||||
<button
|
||||
type="button" key={`${option.label}-${String(optionIndex)}`}
|
||||
className={clsx(css.option, selected && css.optionSelected)}
|
||||
role={question.multiSelect === true ? 'checkbox' : 'radio'}
|
||||
aria-checked={selected}
|
||||
aria-label={display.label}
|
||||
disabled={busy !== null}
|
||||
onClick={() => { choose(option.label) }}
|
||||
onKeyDown={(event) => {
|
||||
if (event.key !== 'Enter' || !drafts.every(completed)) return
|
||||
event.preventDefault()
|
||||
submitDrafts(drafts)
|
||||
}}
|
||||
>
|
||||
<span className={css.number}>{optionIndex + 1}</span>
|
||||
<span className={css.optionCopy}>
|
||||
<span className={css.optionLine}>
|
||||
<span className={css.optionLabel}>{display.label}</span>
|
||||
{display.recommended && <span className={css.badge}>推荐</span>}
|
||||
{option.description !== undefined && (
|
||||
<span className={css.description}>{option.description}</span>
|
||||
)}
|
||||
</span>
|
||||
</span>
|
||||
<span className={css.choiceIcon}>
|
||||
{selected ? <IconCheckOutline16 /> : <IconChevronRightOutline14 />}
|
||||
</span>
|
||||
</button>
|
||||
)
|
||||
})}
|
||||
|
||||
<div className={clsx(
|
||||
css.custom,
|
||||
draft.customOpen && css.customOpen,
|
||||
!hasOptions && css.customOptionless,
|
||||
)}>
|
||||
{hasOptions && (
|
||||
<button
|
||||
type="button" className={css.customTrigger}
|
||||
disabled={busy !== null} onClick={openCustom}
|
||||
aria-expanded={draft.customOpen}
|
||||
>
|
||||
<span className={css.number}><IconEditOutline16 /></span>
|
||||
<span>其他，请填写自定义答案</span>
|
||||
</button>
|
||||
)}
|
||||
{draft.customOpen && (
|
||||
<textarea
|
||||
autoFocus
|
||||
className={css.customInput}
|
||||
value={draft.custom}
|
||||
disabled={busy !== null}
|
||||
rows={2}
|
||||
placeholder="输入你的答案"
|
||||
onChange={(event) => {
|
||||
const value = event.target.value
|
||||
updateDraft(current => ({
|
||||
...current, selected: [], custom: value, customOpen: true, skipped: false,
|
||||
}))
|
||||
}}
|
||||
onKeyDown={(event) => {
|
||||
if (event.key === 'Enter' && !event.shiftKey && !isComposing(event)) {
|
||||
event.preventDefault()
|
||||
continueFlow()
|
||||
}
|
||||
}}
|
||||
/>
|
||||
)}
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<footer className={css.footer}>
|
||||
<div className={css.feedback} role="status">{error}</div>
|
||||
<div className={css.footerActions}>
|
||||
<Button variant="ghost" size="sm" disabled={busy !== null} onClick={skipQuestion}>
|
||||
跳过本题
|
||||
</Button>
|
||||
<Button
|
||||
variant="primary" size="sm"
|
||||
disabled={busy !== null || !answered(draft)} onClick={continueFlow}
|
||||
>
|
||||
{busy === 'answer'
|
||||
? '正在提交…'
|
||||
: index === questions.length - 1 ? '提交' : '下一题'}
|
||||
</Button>
|
||||
</div>
|
||||
</footer>
|
||||
</section>
|
||||
</div>
|
||||
)
|
||||
}
|
||||
77
packages/client/ui-question/src/client/contract/slots.ts
Normal file
77
packages/client/ui-question/src/client/contract/slots.ts
Normal file
@@ -0,0 +1,77 @@
|
||||
/**
|
||||
* Question-composer slot contract: the registrant-side props composition for
|
||||
* the conversation-owned `conversation.composer` slot, plus the question
|
||||
* domain face over the runtime's carrier object. The carrier (PendingWait)
|
||||
* owns envelope transport only; the question protocol — answer value shape,
|
||||
* cancelled error encoding, receipt checks — lives HERE, with the package
|
||||
* that consumes it.
|
||||
*/
|
||||
import type { PropsRuntime } from '@deepseek-ai/dsh-client-ui-slots'
|
||||
// Also pulls ui-conversation's SlotMap merge (the 'conversation.composer'
|
||||
// entry) into every program that sees this contract, so PropsRuntime resolves.
|
||||
import type {} from '@deepseek-ai/dsh-client-ui-conversation/client'
|
||||
import type { PendingWait } from '@deepseek-ai/dsh-client-runtime/client'
|
||||
import type { QuestionResponsePayload } from '@deepseek-ai/dsh-client-connection/client'
|
||||
|
||||
/** The pending question carrier the owner dispatches into the composer slot. */
|
||||
export type QuestionWait = PendingWait<'question'>
|
||||
|
||||
/** One structured answer batch covering every question of the request. */
|
||||
export type QuestionAnswer = QuestionResponsePayload['answer']
|
||||
|
||||
/**
|
||||
* Question domain face over the carrier: render identity and questions
|
||||
* transparently forwarded; answer/cancel own the wire encoding (the ok value
|
||||
* shape and the cancelled error) and turn a rejected carrier receipt into a
|
||||
* thrown error. Components mint one per carrier via useMemo (never inside a
|
||||
* select — a per-dispatch mint would churn identity and break memoization).
|
||||
*/
|
||||
export class PendingQuestion {
|
||||
/**
|
||||
* @param wait - the runtime carrier for one pending question request.
|
||||
*/
|
||||
constructor(private readonly wait: QuestionWait) {}
|
||||
|
||||
/** Opaque render identity (React key / draft remount axis), forwarded from the carrier. */
|
||||
get key(): string {
|
||||
return this.wait.key
|
||||
}
|
||||
|
||||
/** The request's question list, forwarded from the carrier payload. */
|
||||
get questions(): QuestionWait['payload']['questions'] {
|
||||
return this.wait.payload.questions
|
||||
}
|
||||
|
||||
/**
|
||||
* Deliver the whole answer batch; a rejected carrier receipt throws.
|
||||
* @param answer - complete structured answer batch.
|
||||
*/
|
||||
async answer(answer: QuestionAnswer): Promise<void> {
|
||||
const receipt = await this.wait.respond({
|
||||
ok: true, value: { sessionId: this.wait.sessionId, answer },
|
||||
})
|
||||
if (!receipt.accepted) {
|
||||
throw new Error(`question response rejected: ${receipt.reason}`)
|
||||
}
|
||||
}
|
||||
|
||||
/** Reject the whole wait (the host resolves the tool call as cancelled); a rejected receipt throws. */
|
||||
async cancel(): Promise<void> {
|
||||
const receipt = await this.wait.respond({
|
||||
ok: false,
|
||||
error: { code: 'cancelled', message: 'the user closed this question request', details: {} },
|
||||
})
|
||||
if (!receipt.accepted) {
|
||||
throw new Error(`question cancellation rejected: ${receipt.reason}`)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Full component props: the framework runtime share (chain currency +
|
||||
* session/global standard kit) plus the chain `matched` share — the entry's
|
||||
* selector result, already narrowed to the question carrier. No injected
|
||||
* share: the carrier plus the domain face above carry the whole behavior
|
||||
* surface.
|
||||
*/
|
||||
export type QuestionComposerProps = PropsRuntime<'conversation.composer'> & { matched: QuestionWait }
|
||||
36
packages/client/ui-question/src/client/index.ts
Normal file
36
packages/client/ui-question/src/client/index.ts
Normal file
@@ -0,0 +1,36 @@
|
||||
/**
|
||||
* Web question plugin, browser half: QuestionComposer registered as a
|
||||
* selector-routed entry of the conversation-declared composer chain. Pure
|
||||
* consumer — the selector narrows the owner's currency to the question
|
||||
* carrier (matched prop), and the whole behavior surface rides the carrier
|
||||
* (domain encoding in contract/slots.ts PendingQuestion); no inject face, no
|
||||
* service dependency beyond slots. Export discipline: packages/client/AGENTS.md.
|
||||
*/
|
||||
import type { ClientContext } from '@deepseek-ai/dsh-client-runtime/client'
|
||||
import type { ComposerChainProps } from '@deepseek-ai/dsh-client-ui-conversation/client'
|
||||
import type { QuestionWait } from './contract/slots.ts'
|
||||
import { QuestionComposer } from './QuestionComposer.tsx'
|
||||
|
||||
export { PendingQuestion } from './contract/slots.ts'
|
||||
export type { QuestionAnswer, QuestionComposerProps, QuestionWait } from './contract/slots.ts'
|
||||
|
||||
/** Required services (cordis fiber inject — the loader passes the whole export surface as an object plugin). */
|
||||
export const inject = ['slots']
|
||||
|
||||
/** Chain routing: claim the composer while a question wait is pending (pure — owner props only). */
|
||||
function selectQuestion({ interactions }: ComposerChainProps): QuestionWait | null {
|
||||
return interactions.find((i): i is QuestionWait => i.kind === 'question') ?? null
|
||||
}
|
||||
|
||||
/**
|
||||
* Client plugin body: register the question composer into the composer chain.
|
||||
* Zero business face — data and verbs both live on the matched carrier.
|
||||
* @param ctx - client root context.
|
||||
*/
|
||||
export function apply(ctx: ClientContext): void {
|
||||
const slots = ctx.slots
|
||||
ctx.effect(
|
||||
() => slots.register({ name: 'conversation.composer', select: selectQuestion }, QuestionComposer),
|
||||
'ui-question: composer chain registration',
|
||||
)
|
||||
}
|
||||
4
packages/client/ui-question/src/css-modules.d.ts
vendored
Normal file
4
packages/client/ui-question/src/css-modules.d.ts
vendored
Normal file
@@ -0,0 +1,4 @@
|
||||
declare module '*.module.css' {
|
||||
const classes: Readonly<Record<string, string>>
|
||||
export default classes
|
||||
}
|
||||
17
packages/client/ui-question/src/index.ts
Normal file
17
packages/client/ui-question/src/index.ts
Normal file
@@ -0,0 +1,17 @@
|
||||
/**
|
||||
* Web question plugin, node half: enabling this UI feature also exposes the
|
||||
* model-facing ask_user_question tool on the host composition.
|
||||
*/
|
||||
import type { Context } from 'cordis'
|
||||
import * as toolAskUser from '@deepseek-ai/dsh-tool-ask-user'
|
||||
|
||||
/** Host services required by the model-facing tool. */
|
||||
export const inject = ['tools', 'userInteraction']
|
||||
|
||||
/**
|
||||
* Mount ask_user_question for hosts that selected the Web question plugin.
|
||||
* @param ctx - Host plugin context carrying tools and userInteraction.
|
||||
*/
|
||||
export function apply(ctx: Context): void {
|
||||
toolAskUser.apply(ctx)
|
||||
}
|
||||
31
packages/client/ui-question/src/invariant.ts
Normal file
31
packages/client/ui-question/src/invariant.ts
Normal file
@@ -0,0 +1,31 @@
|
||||
/**
|
||||
* Package-owned invariant companion for `@deepseek-ai/dsh-client-ui-question`.
|
||||
* @module @deepseek-ai/dsh-client-ui-question/invariant
|
||||
*/
|
||||
|
||||
/* jscpd:ignore-start */
|
||||
import type { Context } from 'cordis'
|
||||
import type { InvariantInstaller } from '@deepseek-ai/dsh-invariants'
|
||||
|
||||
const PACKAGE_NAME = '@deepseek-ai/dsh-client-ui-question'
|
||||
|
||||
/** Cordis companion plugin name. */
|
||||
export const name = 'client-ui-question-invariant'
|
||||
/** Service required before the companion can reserve package ownership. */
|
||||
export const inject = ['invariants']
|
||||
|
||||
/**
|
||||
* No runtime invariant: tool and slot registrations are effects
|
||||
* owned and observed by their respective registries; the host pending table is
|
||||
* exercised through the public wire protocol.
|
||||
*/
|
||||
const install: InvariantInstaller = () => {}
|
||||
|
||||
/**
|
||||
* Register this package's invariant companion.
|
||||
* @param ctx - Cordis context carrying the invariant service.
|
||||
* @returns The installed registration's disposer after setup succeeds.
|
||||
*/
|
||||
export const apply = (ctx: Context): Promise<() => void> =>
|
||||
Promise.resolve(ctx.invariants.register(PACKAGE_NAME, install))
|
||||
/* jscpd:ignore-end */
|
||||
64
packages/client/ui-question/tests/browser-plugin.spec.ts
Normal file
64
packages/client/ui-question/tests/browser-plugin.spec.ts
Normal file
@@ -0,0 +1,64 @@
|
||||
/**
|
||||
* apply wiring on a real cordis Context + SlotsService: QuestionComposer
|
||||
* registered as the `question` entry of the conversation-declared composer
|
||||
* slot with ZERO business face (data and verbs ride the dispatched carrier),
|
||||
* load-order fail-loud, and fiber-teardown unregistration. Component and
|
||||
* domain-face behavior is covered props-direct in question-composer.spec.tsx;
|
||||
* no renderer machinery here.
|
||||
*/
|
||||
import { Context } from 'cordis'
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { SlotsService } from '@deepseek-ai/dsh-client-runtime/client'
|
||||
import { QuestionComposer } from '../src/client/QuestionComposer.tsx'
|
||||
import { apply, inject } from '../src/client/index.ts'
|
||||
|
||||
async function bench() {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SlotsService).await()
|
||||
const slots = ctx.get('slots') as SlotsService
|
||||
// Stand-in for ui-conversation's conversation entry: the composer slot only
|
||||
// exists while a live entry declares it in children (declaration account:
|
||||
// design §2.2).
|
||||
slots.register(
|
||||
{ name: 'root', children: { 'conversation.composer': { kind: 'chain', scope: 'session' } } } as never,
|
||||
() => null,
|
||||
)
|
||||
return { ctx, slots }
|
||||
}
|
||||
|
||||
describe('apply', () => {
|
||||
it('declares the services it binds', () => {
|
||||
expect(inject).toEqual(['slots'])
|
||||
})
|
||||
|
||||
it('fails loud when no live entry has declared the composer slot', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SlotsService).await()
|
||||
await expect(ctx.plugin({ inject: [...inject], apply }))
|
||||
.rejects.toThrow(/slot "conversation.composer" is not declared/)
|
||||
})
|
||||
|
||||
it('registers the question entry: routing selector, no inject face', async () => {
|
||||
const { ctx, slots } = await bench()
|
||||
await ctx.plugin({ inject: [...inject], apply }).await()
|
||||
const entry = slots.entries('conversation.composer')[0]!
|
||||
expect(entry.component).toBe(QuestionComposer)
|
||||
// The whole behavior surface rides the matched carrier: no business face.
|
||||
expect(entry.inject).toBeUndefined()
|
||||
// The selector narrows the chain currency: question wait in → that wait; none → null.
|
||||
const select = entry.select as (owner: { interactions: readonly { kind: string }[] }) => unknown
|
||||
const question = { kind: 'question' }
|
||||
expect(select({ interactions: [{ kind: 'approval' }, question] })).toBe(question)
|
||||
expect(select({ interactions: [{ kind: 'approval' }] })).toBeNull()
|
||||
expect(select({ interactions: [] })).toBeNull()
|
||||
})
|
||||
|
||||
it('teardown unregisters the slot entry', async () => {
|
||||
const { ctx, slots } = await bench()
|
||||
const fiber = ctx.plugin({ inject: [...inject], apply })
|
||||
await fiber.await()
|
||||
expect(slots.entries('conversation.composer')).toHaveLength(1)
|
||||
await fiber.dispose()
|
||||
expect(slots.entries('conversation.composer')).toHaveLength(0)
|
||||
})
|
||||
})
|
||||
28
packages/client/ui-question/tests/node-plugin.spec.ts
Normal file
28
packages/client/ui-question/tests/node-plugin.spec.ts
Normal file
@@ -0,0 +1,28 @@
|
||||
import { Context } from 'cordis'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import UserInteractionService from '@deepseek-ai/dsh-user-interaction'
|
||||
import { apply, inject } from '../src/index.ts'
|
||||
|
||||
let ctx: Context | undefined
|
||||
|
||||
afterEach(async () => {
|
||||
await ctx?.fiber.dispose()
|
||||
ctx = undefined
|
||||
})
|
||||
|
||||
describe('ui-question node plugin', () => {
|
||||
it('exposes ask_user_question only for the selected Web feature lifecycle', async () => {
|
||||
ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(UserInteractionService)
|
||||
const feature = ctx.plugin({ inject: [...inject], apply })
|
||||
await feature.await()
|
||||
expect(ctx.tools.get('ask_user_question')).toBeDefined()
|
||||
|
||||
await feature.dispose()
|
||||
expect(ctx.tools.get('ask_user_question')).toBeUndefined()
|
||||
})
|
||||
})
|
||||
265
packages/client/ui-question/tests/question-composer.spec.tsx
Normal file
265
packages/client/ui-question/tests/question-composer.spec.tsx
Normal file
@@ -0,0 +1,265 @@
|
||||
// @vitest-environment jsdom
|
||||
import { afterEach, describe, expect, it, vi } from 'vitest'
|
||||
import { cleanup, fireEvent, render, screen } from '@testing-library/react'
|
||||
import type { ConversationSnapshot, SessionId, SessionListState } from '@deepseek-ai/dsh-client-runtime/client'
|
||||
import { PendingWait } from '@deepseek-ai/dsh-client-runtime/client'
|
||||
import type { RpcReceipt } from '@deepseek-ai/dsh-client-connection/client'
|
||||
import { RpcId } from '@deepseek-ai/dsh-client-connection/client'
|
||||
import type { SnapshotSelectorHook } from '@deepseek-ai/dsh-client-ui-slots'
|
||||
import { PendingQuestion } from '../src/client/contract/slots.ts'
|
||||
import {
|
||||
QuestionComposer, parseQuestionTitle, parseRecommendedLabel,
|
||||
} from '../src/client/QuestionComposer.tsx'
|
||||
|
||||
afterEach(cleanup)
|
||||
|
||||
const SID = 's1' as SessionId
|
||||
|
||||
/** Framework standard-kit stubs: the composer consumes none of them, the
|
||||
* composed props type mandates their delivery (framework hooks are plain
|
||||
* stubs per the client testing discipline). */
|
||||
const kit = {
|
||||
sessionId: SID,
|
||||
useSession: (() => { throw new Error('unused') }) as unknown as SnapshotSelectorHook<ConversationSnapshot>,
|
||||
useSessions: (() => { throw new Error('unused') }) as unknown as SnapshotSelectorHook<SessionListState>,
|
||||
}
|
||||
|
||||
const QUESTIONS = [
|
||||
{
|
||||
id: 'profile', header: '偏好', question: '选择候选人类型',
|
||||
detail: '按当前空缺岗位的优先级选择。',
|
||||
options: [
|
||||
{ label: '工程落地型 (Recommended)', description: '优先工程交付。' },
|
||||
{ label: '研究潜力型', description: '优先研究能力。' },
|
||||
],
|
||||
},
|
||||
{
|
||||
id: 'detail', question: '补充你的要求',
|
||||
},
|
||||
{
|
||||
id: 'signals', question: '选择重要信号（可多选）', multiSelect: true,
|
||||
options: [{ label: '系统设计' }, { label: '代码质量' }, { label: '产品判断' }],
|
||||
},
|
||||
]
|
||||
|
||||
/** Carrier fixture: a real PendingWait over a scripted respond carrier. */
|
||||
function wait(rpcId = 'question-1', respond = vi.fn(() => Promise.resolve<RpcReceipt>({ accepted: true }))) {
|
||||
const carrier = new PendingWait(
|
||||
'question', RpcId(rpcId), SID, { questions: QUESTIONS } as PendingWait<'question'>['payload'], respond)
|
||||
return { carrier, respond }
|
||||
}
|
||||
|
||||
/** The client-response envelope respond must have received for an answer batch. */
|
||||
function answeredEnvelope(rpcId: string, answers: object[]) {
|
||||
return {
|
||||
type: 'client-response', rpcId: RpcId(rpcId),
|
||||
result: { ok: true, value: { sessionId: SID, answer: { answers } } },
|
||||
}
|
||||
}
|
||||
|
||||
describe('QuestionComposer', () => {
|
||||
it('collects single, custom, and multi-select answers before one batch submit', () => {
|
||||
const { carrier, respond } = wait()
|
||||
render(<QuestionComposer matched={carrier} interactions={[carrier]} {...kit} />)
|
||||
|
||||
expect(screen.getByText('1 / 3')).toBeTruthy()
|
||||
expect(screen.getByText('推荐')).toBeTruthy()
|
||||
expect(screen.getByText('工程落地型')).toBeTruthy()
|
||||
expect(screen.getByText('按当前空缺岗位的优先级选择。')).toBeTruthy()
|
||||
fireEvent.keyDown(screen.getByRole('radio', { name: /工程落地型/ }), { key: 'Enter' })
|
||||
expect(respond).not.toHaveBeenCalled()
|
||||
fireEvent.click(screen.getByRole('radio', { name: /工程落地型/ }))
|
||||
|
||||
expect(screen.getByText('2 / 3')).toBeTruthy()
|
||||
// detail is per-question: the second question carries none.
|
||||
expect(screen.queryByText('按当前空缺岗位的优先级选择。')).toBeNull()
|
||||
expect(screen.queryByRole('button', { name: '填写答案' })).toBeNull()
|
||||
const custom = screen.getByPlaceholderText('输入你的答案')
|
||||
fireEvent.change(custom, { target: { value: '要能独立排查线上问题' } })
|
||||
fireEvent.keyDown(custom, { key: 'Enter' })
|
||||
|
||||
expect(screen.getByText('3 / 3')).toBeTruthy()
|
||||
expect(screen.getByText('选择重要信号')).toBeTruthy()
|
||||
expect(screen.getByText('可多选')).toBeTruthy()
|
||||
expect(screen.queryByText('（可多选）')).toBeNull()
|
||||
fireEvent.click(screen.getByRole('checkbox', { name: '系统设计' }))
|
||||
fireEvent.click(screen.getByRole('checkbox', { name: '系统设计' }))
|
||||
fireEvent.click(screen.getByRole('checkbox', { name: '系统设计' }))
|
||||
fireEvent.click(screen.getByRole('checkbox', { name: '代码质量' }))
|
||||
fireEvent.keyDown(screen.getByRole('checkbox', { name: '代码质量' }), { key: 'Enter' })
|
||||
|
||||
// The domain face encoded the whole batch into one carrier envelope.
|
||||
expect(respond).toHaveBeenCalledWith(answeredEnvelope('question-1', [
|
||||
{ id: 'profile', selected: ['工程落地型 (Recommended)'] },
|
||||
{ id: 'detail', selected: [], custom: '要能独立排查线上问题' },
|
||||
{ id: 'signals', selected: ['系统设计', '代码质量'] },
|
||||
]))
|
||||
expect((screen.getByRole('button', { name: '正在提交…' }) as HTMLButtonElement).disabled).toBe(true)
|
||||
})
|
||||
|
||||
it('skips individual questions without discarding earlier answers', () => {
|
||||
const { carrier, respond } = wait()
|
||||
render(<QuestionComposer matched={carrier} interactions={[carrier]} {...kit} />)
|
||||
|
||||
expect((screen.getByText('下一题').closest('button') as HTMLButtonElement).disabled).toBe(true)
|
||||
fireEvent.click(screen.getByRole('radio', { name: '研究潜力型' }))
|
||||
expect(screen.getByText('2 / 3')).toBeTruthy()
|
||||
fireEvent.click(screen.getByRole('button', { name: '跳过本题' }))
|
||||
expect(screen.getByText('3 / 3')).toBeTruthy()
|
||||
fireEvent.click(screen.getByRole('button', { name: '跳过本题' }))
|
||||
|
||||
expect(respond).toHaveBeenCalledWith(answeredEnvelope('question-1', [
|
||||
{ id: 'profile', selected: ['研究潜力型'] },
|
||||
{ id: 'detail', selected: [] },
|
||||
{ id: 'signals', selected: [] },
|
||||
]))
|
||||
})
|
||||
|
||||
it('keeps IME Enter inside the custom input until composition finishes', () => {
|
||||
const { carrier, respond } = wait()
|
||||
render(<QuestionComposer matched={carrier} interactions={[carrier]} {...kit} />)
|
||||
|
||||
fireEvent.click(screen.getByRole('radio', { name: '研究潜力型' }))
|
||||
const custom = screen.getByPlaceholderText('输入你的答案')
|
||||
fireEvent.change(custom, { target: { value: '中文输入' } })
|
||||
|
||||
fireEvent.keyDown(custom, { key: 'Enter', isComposing: true })
|
||||
expect(screen.getByText('2 / 3')).toBeTruthy()
|
||||
expect(respond).not.toHaveBeenCalled()
|
||||
|
||||
fireEvent.keyDown(custom, { key: 'Enter', keyCode: 229 })
|
||||
expect(screen.getByText('2 / 3')).toBeTruthy()
|
||||
expect(respond).not.toHaveBeenCalled()
|
||||
|
||||
fireEvent.keyDown(custom, { key: 'Enter' })
|
||||
expect(screen.getByText('3 / 3')).toBeTruthy()
|
||||
})
|
||||
|
||||
it('opens custom input, reports missing skipped answers, and supports header navigation', () => {
|
||||
const { carrier, respond } = wait()
|
||||
render(<QuestionComposer matched={carrier} interactions={[carrier]} {...kit} />)
|
||||
|
||||
fireEvent.click(screen.getByRole('button', { name: '其他，请填写自定义答案' }))
|
||||
expect(screen.getByPlaceholderText('输入你的答案')).toBeTruthy()
|
||||
fireEvent.click(screen.getByRole('radio', { name: '工程落地型' }))
|
||||
const emptyCustom = screen.getByPlaceholderText('输入你的答案')
|
||||
fireEvent.keyDown(emptyCustom, { key: 'Enter', shiftKey: true })
|
||||
expect(screen.getByText('2 / 3')).toBeTruthy()
|
||||
fireEvent.keyDown(emptyCustom, { key: 'Enter' })
|
||||
expect(screen.getByText('请选择一个选项或填写自定义答案。')).toBeTruthy()
|
||||
|
||||
fireEvent.click(screen.getByLabelText('下一题'))
|
||||
fireEvent.click(screen.getByRole('checkbox', { name: '产品判断' }))
|
||||
fireEvent.click(screen.getByRole('button', { name: '提交' }))
|
||||
expect(screen.getByText('请先完成这道问题。')).toBeTruthy()
|
||||
expect(screen.getByText('2 / 3')).toBeTruthy()
|
||||
fireEvent.click(screen.getByLabelText('上一题'))
|
||||
expect(screen.getByText('1 / 3')).toBeTruthy()
|
||||
expect(respond).not.toHaveBeenCalled()
|
||||
})
|
||||
|
||||
it('surfaces cancellation failures: rejected receipt text and raw transport reasons', async () => {
|
||||
const respond = vi.fn()
|
||||
.mockResolvedValueOnce({ accepted: false, reason: 'bad-response' })
|
||||
.mockRejectedValueOnce(new Error('第二次取消失败'))
|
||||
const { carrier } = wait('question-1', respond)
|
||||
render(<QuestionComposer matched={carrier} interactions={[carrier]} {...kit} />)
|
||||
|
||||
// Receipt rejection surfaces through the domain face's thrown message.
|
||||
fireEvent.click(screen.getByRole('button', { name: '放弃整组问题' }))
|
||||
expect(await screen.findByText('question cancellation rejected: bad-response')).toBeTruthy()
|
||||
expect((screen.getByRole('button', { name: '跳过本题' }) as HTMLButtonElement).disabled).toBe(false)
|
||||
|
||||
fireEvent.click(screen.getByRole('button', { name: '放弃整组问题' }))
|
||||
expect(await screen.findByText('第二次取消失败')).toBeTruthy()
|
||||
})
|
||||
|
||||
it('surfaces transport rejection and resets local drafts for a different request', async () => {
|
||||
const respond = vi.fn()
|
||||
.mockRejectedValueOnce(new Error('网络中断'))
|
||||
.mockRejectedValueOnce('字符串错误')
|
||||
const first = wait('first', respond)
|
||||
const view = render(<QuestionComposer matched={first.carrier} interactions={[first.carrier]} {...kit} />)
|
||||
|
||||
fireEvent.click(screen.getByRole('radio', { name: /研究潜力型/ }))
|
||||
expect(screen.getByText('2 / 3')).toBeTruthy()
|
||||
const second = wait('second', respond)
|
||||
view.rerender(<QuestionComposer matched={second.carrier} interactions={[second.carrier]} {...kit} />)
|
||||
expect(screen.getByRole('radio', { name: /研究潜力型/ }).getAttribute('aria-checked')).toBe('false')
|
||||
|
||||
fireEvent.click(screen.getByRole('radio', { name: /工程落地型/ }))
|
||||
const custom = screen.getByPlaceholderText('输入你的答案')
|
||||
fireEvent.change(custom, { target: { value: 'x' } })
|
||||
fireEvent.keyDown(custom, { key: 'Enter' })
|
||||
fireEvent.click(screen.getByRole('checkbox', { name: '系统设计' }))
|
||||
fireEvent.click(screen.getByRole('button', { name: '提交' }))
|
||||
expect(await screen.findByText('网络中断')).toBeTruthy()
|
||||
expect((screen.getByRole('button', { name: '提交' }) as HTMLButtonElement).disabled).toBe(false)
|
||||
|
||||
fireEvent.click(screen.getByRole('button', { name: '提交' }))
|
||||
expect(await screen.findByText('字符串错误')).toBeTruthy()
|
||||
})
|
||||
|
||||
it('same-key carrier replacement (baseline replay) keeps drafts', () => {
|
||||
const first = wait('same-id')
|
||||
const view = render(<QuestionComposer matched={first.carrier} interactions={[first.carrier]} {...kit} />)
|
||||
fireEvent.click(screen.getByRole('radio', { name: /研究潜力型/ }))
|
||||
expect(screen.getByText('2 / 3')).toBeTruthy()
|
||||
// Replay mints a NEW carrier for the same request; same key = no remount.
|
||||
const replayed = wait('same-id')
|
||||
view.rerender(<QuestionComposer matched={replayed.carrier} interactions={[replayed.carrier]} {...kit} />)
|
||||
expect(screen.getByText('2 / 3')).toBeTruthy()
|
||||
})
|
||||
})
|
||||
|
||||
describe('PendingQuestion domain face', () => {
|
||||
it('encodes the answer batch into the ok envelope and throws on a rejected receipt', async () => {
|
||||
const respond = vi.fn()
|
||||
.mockResolvedValueOnce({ accepted: true })
|
||||
.mockResolvedValueOnce({ accepted: false, reason: 'not-pending' })
|
||||
const question = new PendingQuestion(wait('rq', respond).carrier)
|
||||
const batch = { answers: [{ id: 'mode', selected: ['Fast'] }] }
|
||||
await expect(question.answer(batch)).resolves.toBeUndefined()
|
||||
expect(respond).toHaveBeenCalledWith(answeredEnvelope('rq', batch.answers))
|
||||
await expect(question.answer(batch)).rejects.toThrow(/question response rejected: not-pending/)
|
||||
})
|
||||
|
||||
it('encodes cancellation as the cancelled error envelope and throws on a rejected receipt', async () => {
|
||||
const respond = vi.fn()
|
||||
.mockResolvedValueOnce({ accepted: true })
|
||||
.mockResolvedValueOnce({ accepted: false, reason: 'bad-response' })
|
||||
const question = new PendingQuestion(wait('rc', respond).carrier)
|
||||
await expect(question.cancel()).resolves.toBeUndefined()
|
||||
expect(respond).toHaveBeenCalledWith({
|
||||
type: 'client-response', rpcId: RpcId('rc'),
|
||||
result: {
|
||||
ok: false,
|
||||
error: { code: 'cancelled', message: 'the user closed this question request', details: {} },
|
||||
},
|
||||
})
|
||||
await expect(question.cancel()).rejects.toThrow(/question cancellation rejected: bad-response/)
|
||||
})
|
||||
|
||||
it('forwards key and questions from the carrier', () => {
|
||||
const question = new PendingQuestion(wait('rk').carrier)
|
||||
expect(question.key).toBe('q:rk')
|
||||
expect(question.questions).toBe(wait('rk').carrier.payload.questions)
|
||||
})
|
||||
})
|
||||
|
||||
describe('parseRecommendedLabel', () => {
|
||||
it('recognizes English and Chinese suffixes without changing ordinary labels', () => {
|
||||
expect(parseRecommendedLabel('Fast (Recommended)')).toEqual({ label: 'Fast', recommended: true })
|
||||
expect(parseRecommendedLabel('稳妥（推荐）')).toEqual({ label: '稳妥', recommended: true })
|
||||
expect(parseRecommendedLabel('稳妥 (推荐)')).toEqual({ label: '稳妥', recommended: true })
|
||||
expect(parseRecommendedLabel('Plain')).toEqual({ label: 'Plain', recommended: false })
|
||||
})
|
||||
})
|
||||
|
||||
describe('parseQuestionTitle', () => {
|
||||
it('removes Chinese and ASCII multi-select suffixes', () => {
|
||||
expect(parseQuestionTitle('选择信号（可多选）')).toBe('选择信号')
|
||||
expect(parseQuestionTitle('选择信号 (可多选)')).toBe('选择信号')
|
||||
expect(parseQuestionTitle('选择信号')).toBe('选择信号')
|
||||
})
|
||||
})
|
||||
36
packages/client/ui-question/tsconfig.json
Normal file
36
packages/client/ui-question/tsconfig.json
Normal file
@@ -0,0 +1,36 @@
|
||||
{
|
||||
"extends": "../../../tsconfig.base.client.json",
|
||||
"compilerOptions": {
|
||||
"rootDir": "src",
|
||||
"outDir": "lib/types"
|
||||
},
|
||||
"include": [
|
||||
"src"
|
||||
],
|
||||
"references": [
|
||||
{
|
||||
"path": "../../../vendor/cordis"
|
||||
},
|
||||
{
|
||||
"path": "../connection"
|
||||
},
|
||||
{
|
||||
"path": "../runtime"
|
||||
},
|
||||
{
|
||||
"path": "../ui-conversation"
|
||||
},
|
||||
{
|
||||
"path": "../ui-primitives"
|
||||
},
|
||||
{
|
||||
"path": "../ui-slots"
|
||||
},
|
||||
{
|
||||
"path": "../../ui/tool-ask-user"
|
||||
},
|
||||
{
|
||||
"path": "../../support/invariants"
|
||||
}
|
||||
]
|
||||
}
|
||||
3
packages/client/ui-question/tsdown.config.ts
Normal file
3
packages/client/ui-question/tsdown.config.ts
Normal file
@@ -0,0 +1,3 @@
|
||||
import { clientBundle } from '../tsdown.client.ts'
|
||||
|
||||
export default clientBundle('@deepseek-ai/dsh-client-ui-question', ['lib/types/index.js', 'lib/types/invariant.js'])
|
||||
@@ -402,6 +402,10 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
|
||||
signature: 'async spawn(owner: Agent, request: PtySpawnRequest, signal?: AbortSignal): Promise<PtySpawnResult>',
|
||||
jsDoc: '/**\n * Create and publish one owner-scoped session after backend setup succeeds.\n * @param owner - exact registered Agent that owns access and cleanup.\n * @param request - backend type plus optional owner-local name and cwd.\n * @param signal - cancellation of unpublished setup.\n * @returns published identity, metadata, status, and MOTD.\n */',
|
||||
},
|
||||
{
|
||||
signature: 'hasOwnerActivity(owner: Agent): boolean',
|
||||
jsDoc: '/**\n * Test whether an exact owner has a published session or unpublished spawn.\n * @param owner - exact live owner to inspect.\n * @returns true across the entire spawn-to-close interval, with no publication gap.\n */',
|
||||
},
|
||||
{
|
||||
signature: 'startSend(owner: Agent, id: PtySessionId, request: PtySendRequest): PtySendOperation',
|
||||
jsDoc: '/**\n * Start one exclusive interactive send.\n * @param owner - exact session owner.\n * @param id - target PTY identity.\n * @param request - explicit text, submit behavior, and cancellation.\n * @returns live operation handle for foreground await or task registration.\n */',
|
||||
@@ -730,7 +734,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
|
||||
methods: [
|
||||
{
|
||||
signature: 'register(definition: ToolDefinition): () => void',
|
||||
jsDoc: '/**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - the tool schema, execution, and optional presentation functions.\n * @returns the exact disposer that unregisters the tool.\n */',
|
||||
jsDoc: '/**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - tool schema, execution, and optional finalization/presentation callbacks.\n * @returns the exact disposer that unregisters the tool.\n */',
|
||||
},
|
||||
{
|
||||
signature: 'restrict(filter: ToolRestriction): () => void',
|
||||
@@ -754,7 +758,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
|
||||
},
|
||||
{
|
||||
signature: 'async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult>',
|
||||
jsDoc: '/**\n * Execute through pre-policy, guards, around-dispatch, post-policy, and final\n * notification. Tool and listener failures resolve as materialized error\n * results; an invisible tool reports `UNKNOWN_TOOL`. The returned outcome is\n * the same lossless, frozen snapshot final observers receive. Cancellation\n * arriving after entry and before final result materialization skips a\n * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a\n * successful started outcome with `ABORTED`; already-started work is still\n * drained and may retain a tool-owned structured error.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */',
|
||||
jsDoc: '/**\n * Execute through pre-policy, guards, around-dispatch, post-policy,\n * definition-owned content finalization, and final notification. Tool and\n * listener failures resolve as materialized error results; an invisible tool\n * reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen\n * snapshot final observers receive. Cancellation\n * arriving after entry and before final result materialization skips a\n * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a\n * successful started outcome with `ABORTED`; already-started work is still\n * drained and may retain a tool-owned structured error.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */',
|
||||
},
|
||||
],
|
||||
},
|
||||
@@ -1935,11 +1939,11 @@ export const TYPE_API: readonly TypeApiEntry[] = [
|
||||
},
|
||||
{
|
||||
name: 'TaskSnapshot',
|
||||
declaration: 'export interface TaskSnapshot {\n id: TaskId;\n kind: TaskKind;\n label: string;\n ownerSession?: SessionId;\n status: TaskStatus;\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n reported: boolean;\n}',
|
||||
declaration: 'export interface TaskSnapshot {\n id: TaskId;\n kind: TaskKind;\n label: string;\n outputLimitBytes?: number;\n ownerSession?: SessionId;\n status: TaskStatus;\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n reported: boolean;\n}',
|
||||
},
|
||||
{
|
||||
name: 'TaskStart',
|
||||
declaration: 'export interface TaskStart {\n kind: TaskKind;\n label: string;\n owner?: Agent;\n run(): TaskHooks;\n}',
|
||||
declaration: 'export interface TaskStart {\n kind: TaskKind;\n label: string;\n outputLimitBytes?: number;\n owner?: Agent;\n run(): TaskHooks;\n}',
|
||||
},
|
||||
{
|
||||
name: 'TaskStatus',
|
||||
@@ -1987,7 +1991,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [
|
||||
},
|
||||
{
|
||||
name: 'ToolDefinition',
|
||||
declaration: 'export interface ToolDefinition extends ToolSchema {\n readonly output: ToolOutputDefinition;\n execute(args: unknown, exec: ToolRunContext): Promise<unknown>;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n}',
|
||||
declaration: 'export interface ToolDefinition extends ToolSchema {\n readonly output: ToolOutputDefinition;\n execute(args: unknown, exec: ToolRunContext): Promise<unknown>;\n finalizeContent?(exec: Readonly<ToolExecution>, result: Readonly<ToolExecutionResult>): ContentBlock[] | undefined;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n}',
|
||||
},
|
||||
{
|
||||
name: 'ToolErrorInfo',
|
||||
|
||||
@@ -78,7 +78,7 @@ describe('cordis_inspect', () => {
|
||||
expect(report).toContain('- tools — Tool registry and execution pipeline.')
|
||||
expect(report).toContain('/**')
|
||||
expect(report).toContain('Register globally or in the calling agent scope.')
|
||||
expect(report).toContain('@param definition - the tool schema')
|
||||
expect(report).toContain('@param definition - tool schema, execution, and optional finalization/presentation callbacks')
|
||||
expect(report).toContain('@returns the exact disposer')
|
||||
expect(report).toContain('register(definition: ToolDefinition)')
|
||||
expect(report).toContain('type shapes (referenced by the signatures above')
|
||||
|
||||
@@ -67,7 +67,7 @@ Within a step, exclusive calls form barriers; parallel-safe calls use a bounded
|
||||
### What belongs to plugins
|
||||
|
||||
Everything that goes beyond "call the model, run the tools, repeat" belongs to plugins listening on the event taxonomy:
|
||||
- Hooks and policy: the relevant `agent/*` checkpoints plus the guarded `tools/pre-execute` → `tools/execute` → `tools/post-execute` → `tools/result` pipeline; exact signatures and modes live in the [generated event catalog](../../../docs/cordis-catalog/events.md)
|
||||
- Hooks and policy: the relevant `agent/*` checkpoints plus the guarded `tools/pre-execute` → `tools/execute` → `tools/post-execute` → definition-owned `finalizeContent` → `tools/result` pipeline; exact event signatures and modes live in the [generated event catalog](../../../docs/cordis-catalog/events.md)
|
||||
- Compaction: pressure on `agent/post-step`; canonical context overflow on `agent/request-error`
|
||||
- Transient model recovery: `dsh-llm-retry` on `agent/request-error`, with finite code-specific budgets and non-surface `llm/retry` status events
|
||||
- Sandbox, permission, plan mode: `tools/pre-execute` for extensible deny/ask, `tools.guard()` for monotonic owner policy, `tools/post-execute` for result decisions, and `tools/result` for final observation
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# dsh-tools
|
||||
|
||||
Tool registry and execution pipeline. Tool plugins register their schemas and executors; the agent loop executes each call through `tools/pre-execute` (the extensible allow/deny gate) → monotonic registered guards → `tools/execute` (an around-dispatch wrapper for timeout/retry/metrics plugins) → `tools/post-execute` (inspect/replace the result, attach context) → the observe-only `tools/result` notification. The registry also owns HOW its tools are presented to the model — its `mode` config selects native function calling, [Code Mode](#code-mode), or both.
|
||||
Tool registry and execution pipeline. Tool plugins register their schemas and executors; the agent loop executes each call through `tools/pre-execute` (the extensible allow/deny gate) → monotonic registered guards → `tools/execute` (an around-dispatch wrapper for timeout/retry/metrics plugins) → `tools/post-execute` (inspect/replace the result, attach context) → the definition-owned `finalizeContent` boundary → the observe-only `tools/result` notification. The registry also owns HOW its tools are presented to the model — its `mode` config selects native function calling, [Code Mode](#code-mode), or both.
|
||||
|
||||
## Service: `ToolRegistry` (ctx key: `tools`)
|
||||
|
||||
@@ -15,7 +15,7 @@ tools:
|
||||
|
||||
### Public API
|
||||
|
||||
- `ctx.tools.register(definition: ToolDefinition): () => void` Register a trusted typed same-process definition with a mandatory canonical `output` declaration. The layer is the calling context's scope: a plain plugin context registers globally; an agent's `agent.ctx` registers for that agent alone, shadowing a same-named global tool there. Duplicate names within one layer throw; non-native modes also reject the reserved `run_code` transport name. Missing/unsupported output declarations and a non-positive/non-finite `timeoutMs` fail at registration. Disposed with the calling fiber.
|
||||
- `ctx.tools.register(definition: ToolDefinition): () => void` Register a trusted typed same-process definition with a mandatory canonical `output` declaration. The layer is the calling context's scope: a plain plugin context registers globally; an agent's `agent.ctx` registers for that agent alone, shadowing a same-named global tool there. Duplicate names within one layer throw; non-native modes also reject the reserved `run_code` transport name. Missing or unsupported output declarations and a non-positive or non-finite `timeoutMs` fail at registration. The optional synchronous `finalizeContent` callback is snapshotted when a call starts and may replace only final model-facing content after every pipeline outcome is normalized, including an error discovered while materializing another result field. Disposed with the calling fiber.
|
||||
- `ctx.tools.restrict(filter)` applies an agent-scoped allow/deny mask to global tools and throws from a plain context. The filter is snapshotted at registration; multiple masks intersect and scope-local tools merge afterwards. Deny masks admit later unnamed globals, while allow masks exclude later names. Unknown, local, or reserved names and empty filters reject. This is live visibility composition, not an authority boundary; see the [scope security non-goal](../../../.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md#security-and-authority-are-explicit-non-goals).
|
||||
- `ctx.tools.get(name: string, scope?: ScopeKey): ToolDefinition | undefined` Resolution as one scope sees it (shadowing applied; a restricted-away global reads as absent) — presenters pass the calling agent so the card matches what executed.
|
||||
- `ctx.tools.schemas(scope?: ScopeKey): ToolSchema[]` Schemas of everything the scope can see (without the `execute` functions). The shipped tools' schemas are catalogued in [docs/tool-catalog.md](../../../docs/tool-catalog.md), generated by booting each tool plugin and harvesting this method (see [the tool-schema-catalog Agent Note](../../../.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.md)).
|
||||
@@ -33,11 +33,11 @@ Cancellation is cooperative and quiescent. Every typed invocation supplies a cal
|
||||
|
||||
### Live events
|
||||
|
||||
The live registry pipeline has three transformable waterfalls followed by the observe-only `tools/result` boundary; registry changes are deliberately unfiltered shared-state notifications. Exact signatures, dispatch modes, scope filtering, and failure-containment contracts live in the generated [Cordis event catalog](../../../docs/cordis-catalog/events.md), while the complete ordering is visualized in the generated [tool execution pipeline](../../../docs/tool-execution-pipeline.md). `tools/result` is live; the similarly named `tool/result` is the durable session event the agent loop appends afterwards.
|
||||
The live registry pipeline has three transformable waterfalls, then the definition-owned content finalizer, then the observe-only `tools/result` boundary; registry changes are deliberately unfiltered shared-state notifications. Exact signatures, dispatch modes, scope filtering, and failure-containment contracts live in the generated [Cordis event catalog](../../../docs/cordis-catalog/events.md), while the complete ordering is visualized in the generated [tool execution pipeline](../../../docs/tool-execution-pipeline.md). `tools/result` is live; the similarly named `tool/result` is the durable session event the agent loop appends afterwards.
|
||||
|
||||
### Key types
|
||||
|
||||
- `ToolDefinition` — `ToolSchema` + mandatory `output { schema, render, presentationMeta? }` + `execute(args, exec)`, optional presentation callbacks, cooperative `timeoutMs`, and optional per-call `isConcurrencySafe(args)` classification. A body returns only the canonical JSON value declared by the output schema and cooperatively stops through `exec.signal`.
|
||||
- `ToolDefinition` — `ToolSchema` + mandatory `output { schema, render, presentationMeta? }` + `execute(args, exec)`, optional final-content and presentation callbacks, cooperative `timeoutMs`, and optional per-call `isConcurrencySafe(args)` classification. A body returns only the canonical JSON value declared by the output schema and cooperatively stops through `exec.signal`. `finalizeContent(exec, result)` runs exactly once for every normalized result, including failures that bypass post-policy, and can replace only `content`; it must be synchronous and total.
|
||||
- `ToolExecutionInput` — the caller-supplied call description: `{ callId, name, arguments, signal, agent?, parent? }`; `signal` is required and readonly, callers may pass an enclosing execution's opaque token as `parent`, and callers never choose the new execution's own token.
|
||||
- `ToolExecutionToken` — a fresh branded `Symbol` assigned by the registry. It supports equality correlation only and never crosses a model, log, or worker boundary.
|
||||
- `ToolExecution` — the readonly pipeline view: immutable `{ token, callId, name, arguments, signal, agent?, parent? }`; the registry separately retains and re-fuses the original caller signal. `ToolDispatchExecution` is the `tools/execute`-only view whose required signal is mutable, so a wrapper may replace and restore it but cannot delete it. A nested call's `parent` is a `ToolExecutionToken`, not an execution object.
|
||||
@@ -53,7 +53,7 @@ The live registry pipeline has three transformable waterfalls followed by the ob
|
||||
- Tool plugins call `ctx.tools.register()` — schemas flow into the assembly automatically.
|
||||
- `tools/pre-execute` is the reorderable allow/deny/ask gate; `ctx.tools.guard()` adds monotonic owner policy after it.
|
||||
- `tools/execute` wraps normalized canonical dispatch for timeout, retry, or metrics. Wrappers may replace only the operational signal; a wrapper-authored success is normalized through the resolved tool's output declaration. Canonical-result provenance belongs to one immutable dispatch token, so a cached result from another call or tool is revalidated under the active declaration.
|
||||
- `tools/post-execute` may replace presentation content, replace the canonical value, block with feedback, or attach ordered contexts; `tools/result` observes the immutable final outcome. Content replacement is not a confidentiality boundary: block or replace the value when programmatic consumers must not receive it.
|
||||
- `tools/post-execute` may replace presentation content, replace the canonical value, block with feedback, or attach ordered contexts. A definition's optional `finalizeContent` then owns its last content-only invariant across normal results and outer pipeline failures; `tools/result` observes the immutable final outcome. Content replacement is not a confidentiality boundary: block or replace the value when programmatic consumers must not receive it.
|
||||
- Exact signatures and ordering live in the generated [event catalog](../../../docs/cordis-catalog/events.md) and [pipeline](../../../docs/tool-execution-pipeline.md).
|
||||
- MCP servers: one plugin per server, discover tools, call `ctx.tools.register()` with the server's schemas.
|
||||
|
||||
|
||||
@@ -169,6 +169,18 @@ export interface ToolDefinition extends ToolSchema {
|
||||
* @returns the canonical value declared by `output.schema`.
|
||||
*/
|
||||
execute(args: unknown, exec: ToolRunContext): Promise<unknown>
|
||||
/**
|
||||
* Synchronous last-mile transform for model-facing content. The registry
|
||||
* snapshots this callback when execution starts and invokes it exactly once
|
||||
* for every normalized outcome, including pipeline failures that bypass
|
||||
* `tools/post-execute`, immediately before lossless materialization.
|
||||
* Returning `undefined` preserves the content; every other result field
|
||||
* remains registry-owned. The callback must be total and must not throw.
|
||||
* @param exec - immutable execution identity and arguments.
|
||||
* @param result - complete normalized outcome before materialization.
|
||||
* @returns replacement content, or `undefined` to preserve it.
|
||||
*/
|
||||
finalizeContent?(exec: Readonly<ToolExecution>, result: Readonly<ToolExecutionResult>): ContentBlock[] | undefined
|
||||
/**
|
||||
* Cooperative tool-call timeout budget in milliseconds. Omit for no deadline.
|
||||
* Enforced by `@deepseek-ai/dsh-timeout-policy` (a `tools/execute` wrapper); it
|
||||
@@ -330,9 +342,9 @@ export interface ToolRegistryScheduler {
|
||||
prepare(exec: ToolExecutionInput): Promise<ScheduledToolPreparation>
|
||||
/** Run only the around-dispatch/body stage. */
|
||||
dispatch(exec: ToolRunContext): Promise<ScheduledToolDispatch>
|
||||
/** Run ordered post-execute finalization, then materialize and notify the final outcome. */
|
||||
/** Run post-execute and definition-owned content finalization, then materialize and notify. */
|
||||
finalize(exec: ToolRunContext, result: ToolExecutionResult): Promise<ToolExecutionResult>
|
||||
/** Materialize and notify a final outcome that must bypass post-execute. */
|
||||
/** Run definition-owned content finalization, then materialize and notify without post-execute. */
|
||||
finish(exec: ToolRunContext, result: ToolExecutionResult): ToolExecutionResult
|
||||
}
|
||||
|
||||
@@ -638,6 +650,8 @@ export class ToolRegistry extends Service {
|
||||
private deferredContexts = new WeakMap<ToolRunContext, HookContext[]>()
|
||||
/** Original caller cancellation, kept outside the wrapper-mutable execution object. */
|
||||
private cancellationStates = new WeakMap<ToolRunContext, ToolCancellationState>()
|
||||
/** Definition-owned final content transform snapshotted before policy begins. */
|
||||
private contentFinalizers = new WeakMap<ToolRunContext, ToolDefinition['finalizeContent']>()
|
||||
private readonly layers = new ScopedLayers(
|
||||
scope => new ToolLayer(scope),
|
||||
() => { this.ctx.emit('tools/change') },
|
||||
@@ -715,7 +729,7 @@ export class ToolRegistry extends Service {
|
||||
/**
|
||||
* Register globally or in the calling agent scope. Scoped tools shadow
|
||||
* globals; duplicates within one layer and the reserved `run_code` name fail.
|
||||
* @param definition - the tool schema, execution, and optional presentation functions.
|
||||
* @param definition - tool schema, execution, and optional finalization/presentation callbacks.
|
||||
* @returns the exact disposer that unregisters the tool.
|
||||
*/
|
||||
register(definition: ToolDefinition): () => void {
|
||||
@@ -910,10 +924,11 @@ export class ToolRegistry extends Service {
|
||||
}
|
||||
|
||||
/**
|
||||
* Execute through pre-policy, guards, around-dispatch, post-policy, and final
|
||||
* notification. Tool and listener failures resolve as materialized error
|
||||
* results; an invisible tool reports `UNKNOWN_TOOL`. The returned outcome is
|
||||
* the same lossless, frozen snapshot final observers receive. Cancellation
|
||||
* Execute through pre-policy, guards, around-dispatch, post-policy,
|
||||
* definition-owned content finalization, and final notification. Tool and
|
||||
* listener failures resolve as materialized error results; an invisible tool
|
||||
* reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen
|
||||
* snapshot final observers receive. Cancellation
|
||||
* arriving after entry and before final result materialization skips a
|
||||
* not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a
|
||||
* successful started outcome with `ABORTED`; already-started work is still
|
||||
@@ -952,6 +967,8 @@ export class ToolRegistry extends Service {
|
||||
const agent = exec.agent
|
||||
const parent = exec.parent
|
||||
const signal = exec.signal
|
||||
const definition = this.get(name, agent)
|
||||
const finalizeContent = definition?.finalizeContent?.bind(definition)
|
||||
const base = {
|
||||
token,
|
||||
callId,
|
||||
@@ -970,6 +987,7 @@ export class ToolRegistry extends Service {
|
||||
}
|
||||
const execution: MutableToolRunContext = { ...base, arguments: deepFreeze(detached) }
|
||||
this.deferredContexts.set(execution, deferredContexts)
|
||||
this.contentFinalizers.set(execution, finalizeContent)
|
||||
this.cancellationStates.set(execution, {
|
||||
callerSignal: signal,
|
||||
bodyInvoked: false,
|
||||
@@ -977,6 +995,7 @@ export class ToolRegistry extends Service {
|
||||
return { kind: 'ready', exec: execution }
|
||||
} catch (error: unknown) {
|
||||
const execution: MutableToolRunContext = { ...base, arguments: undefined }
|
||||
this.contentFinalizers.set(execution, finalizeContent)
|
||||
return { kind: 'final-result', exec: execution, result: toolErrorResult(error) }
|
||||
}
|
||||
}
|
||||
@@ -1130,7 +1149,8 @@ export class ToolRegistry extends Service {
|
||||
}
|
||||
|
||||
/**
|
||||
* Run ordered post-execute, then materialize and notify the final outcome.
|
||||
* Run ordered post-execute, then apply definition-owned content finalization,
|
||||
* materialize, and notify the final outcome.
|
||||
* @param exec - the prepared execution.
|
||||
* @param result - dispatch/pre result that still needs post-execute.
|
||||
* @returns the materialized final result.
|
||||
@@ -1151,16 +1171,23 @@ export class ToolRegistry extends Service {
|
||||
}
|
||||
|
||||
/**
|
||||
* Materialize and notify a final result that must bypass post-execute.
|
||||
* Materialize the candidate, apply definition-owned content finalization,
|
||||
* then materialize and notify the authoritative result.
|
||||
* @param exec - the prepared execution.
|
||||
* @param result - final result.
|
||||
* @returns the materialized final result.
|
||||
* @internal
|
||||
*/
|
||||
private finishScheduledExecution(exec: ToolRunContext, result: ToolExecutionResult): ToolExecutionResult {
|
||||
let materializedResult: ToolExecutionResult
|
||||
try {
|
||||
materializedResult = this.materializeFinalResult(result)
|
||||
} catch (error: unknown) {
|
||||
materializedResult = this.materializeFinalResult(toolErrorResult(error))
|
||||
}
|
||||
let finalResult: ToolExecutionResult
|
||||
try {
|
||||
finalResult = this.materializeFinalResult(result)
|
||||
finalResult = this.materializeFinalResult(this.applyFinalContent(exec, materializedResult))
|
||||
} catch (error: unknown) {
|
||||
finalResult = this.materializeFinalResult(toolErrorResult(error))
|
||||
}
|
||||
@@ -1168,6 +1195,14 @@ export class ToolRegistry extends Service {
|
||||
return finalResult
|
||||
}
|
||||
|
||||
/** Apply the snapshotted tool-owned content transform without exposing other result fields. */
|
||||
private applyFinalContent(exec: ToolRunContext, result: ToolExecutionResult): ToolExecutionResult {
|
||||
const finalizeContent = this.contentFinalizers.get(exec)
|
||||
if (finalizeContent === undefined) return result
|
||||
const content = finalizeContent(exec, result)
|
||||
return content === undefined ? result : { ...result, content }
|
||||
}
|
||||
|
||||
/** Notify observers without exposing a mutation or error channel into the outcome. */
|
||||
private notifyResult(exec: ToolExecution, result: ToolExecutionResult): void {
|
||||
// Freeze the registry's live object before observers receive its readonly
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
import { HarnessError } from '@deepseek-ai/dsh-llm'
|
||||
import type { ContentBlock } from '@deepseek-ai/dsh-llm'
|
||||
import type { JsonValue } from '@deepseek-ai/dsh-session'
|
||||
import type { ToolDefinition, ToolRunContext, ToolResult } from './index.ts'
|
||||
import type { ToolDefinition, ToolExecution, ToolExecutionResult, ToolRunContext, ToolResult } from './index.ts'
|
||||
import { assertSupportedJsonSchema, isJsonSchemaRecord, isPlainJsonArray, JsonSchemaError, validateJsonSchemaValue } from './json-schema.ts'
|
||||
import type { JsonSchemaNode, JsonSchemaScalar, ObjectJsonSchema } from './json-schema.ts'
|
||||
import type { ToolCallView, ToolResultView } from './presentation.ts'
|
||||
@@ -511,6 +511,15 @@ export interface DefineToolOptions<S extends ParameterSchemaSpec, O extends Valu
|
||||
* @returns The canonical value declared by `output.schema`.
|
||||
*/
|
||||
execute(args: InferArgs<S>, exec: ToolRunContext): Promise<InferValue<NoInfer<O>>>
|
||||
/**
|
||||
* Optional last-mile content transform for every normalized outcome. Unlike
|
||||
* `execute`, arguments remain `unknown` because invalid-input failures also
|
||||
* reach this callback. See {@link ToolDefinition.finalizeContent}.
|
||||
* @param exec - immutable execution identity and arguments.
|
||||
* @param result - complete normalized outcome before materialization.
|
||||
* @returns replacement content, or `undefined` to preserve it.
|
||||
*/
|
||||
finalizeContent?(exec: Readonly<ToolExecution>, result: Readonly<ToolExecutionResult>): ContentBlock[] | undefined
|
||||
/**
|
||||
* Pure pending-state presenter.
|
||||
* @param args - typed validated arguments.
|
||||
@@ -530,7 +539,7 @@ export interface DefineToolOptions<S extends ParameterSchemaSpec, O extends Valu
|
||||
* Define a first-party tool with inferred arguments and strict execution
|
||||
* validation. Replay-only presenters validate softly and fall back to generic
|
||||
* rendering for obsolete logged arguments.
|
||||
* @param options - typed definition and optional presenters.
|
||||
* @param options - typed definition and optional finalizer and presenters.
|
||||
* @returns A registry-ready definition.
|
||||
*/
|
||||
export function defineTool<const S extends ParameterSchemaSpec, const O extends ValueSchemaSpec>(
|
||||
@@ -540,6 +549,8 @@ export function defineTool<const S extends ParameterSchemaSpec, const O extends
|
||||
// eslint-disable-next-line @typescript-eslint/unbound-method
|
||||
const userExecute = options.execute
|
||||
// eslint-disable-next-line @typescript-eslint/unbound-method
|
||||
const userFinalizeContent = options.finalizeContent
|
||||
// eslint-disable-next-line @typescript-eslint/unbound-method
|
||||
const userRender = options.output.render
|
||||
// eslint-disable-next-line @typescript-eslint/unbound-method
|
||||
const userPresentationMeta = options.output.presentationMeta
|
||||
@@ -577,6 +588,13 @@ export function defineTool<const S extends ParameterSchemaSpec, const O extends
|
||||
return userExecute(args as InferArgs<S>, exec) as Promise<JsonValue>
|
||||
},
|
||||
}
|
||||
if (userFinalizeContent) {
|
||||
tool.finalizeContent = (exec, result) => userFinalizeContent(exec, result)
|
||||
}
|
||||
// Presentation is display-only and may run on REPLAY of arbitrary logged args
|
||||
// (possibly from an older schema), so it must never throw: validate softly and
|
||||
// fall back to `undefined` (a generic UI presentation) on any mismatch, rather
|
||||
// than the hard `ToolArgsError` the execute path raises.
|
||||
if (userPresentCall) {
|
||||
tool.presentCall = (args: unknown): ToolCallView | undefined => {
|
||||
if (validate(args).length > 0) return undefined
|
||||
|
||||
@@ -51,22 +51,22 @@ describe('ToolRegistry', () => {
|
||||
expect(assembly.tools.map(t => t.name)).toEqual(['echo'])
|
||||
})
|
||||
|
||||
it('schemas() drops the UI presentation callbacks — they must never reach the model', async () => {
|
||||
it('schemas() drops host callbacks — they must never reach the model', async () => {
|
||||
const ctx = await setup()
|
||||
// A tool that declares presentCall/presentResult (functions). schemas() feeds
|
||||
// the system-prompt assembly → the model request, so those callbacks (and
|
||||
// `execute`) must be stripped: a function in the JSON tool schema would
|
||||
// corrupt the request. schemas() is an explicit allowlist, so it can't leak.
|
||||
// Tool definitions contain output, finalization, execution, and presentation
|
||||
// callbacks. schemas() is an explicit allowlist so none can reach the model.
|
||||
ctx.tools.register(defineContentToolFixture({
|
||||
name: 'present',
|
||||
description: 'has presenters',
|
||||
parameters: { x: { type: 'string', required: true } },
|
||||
async execute() { return [] },
|
||||
finalizeContent: (_exec, result) => result.content,
|
||||
presentCall: args => ({ card: 'generic', title: args.x }),
|
||||
presentResult: (args, result) => ({ card: 'generic', title: args.x, content: result.content }),
|
||||
}))
|
||||
const schema = ctx.tools.schemas()[0] as unknown as Record<string, unknown>
|
||||
expect(Object.keys(schema).sort()).toEqual(['description', 'name', 'parameters'])
|
||||
expect(schema.finalizeContent).toBeUndefined()
|
||||
expect(schema.presentCall).toBeUndefined()
|
||||
expect(schema.presentResult).toBeUndefined()
|
||||
expect(schema.execute).toBeUndefined()
|
||||
@@ -155,6 +155,72 @@ describe('ToolRegistry', () => {
|
||||
expect(observedError).toBe(true)
|
||||
})
|
||||
|
||||
it('finalizes errors discovered while snapshotting non-content result fields', async () => {
|
||||
const ctx = await setup()
|
||||
let finalizeCalls = 0
|
||||
ctx.tools.register({
|
||||
...echoTool,
|
||||
name: 'throwing-meta',
|
||||
output: {
|
||||
...echoTool.output,
|
||||
presentationMeta() {
|
||||
const meta = {}
|
||||
Object.defineProperty(meta, 'value', {
|
||||
enumerable: true,
|
||||
get() { throw new Error('snapshot failed: '.repeat(100)) },
|
||||
})
|
||||
return meta
|
||||
},
|
||||
},
|
||||
finalizeContent(_exec, result) {
|
||||
finalizeCalls += 1
|
||||
const block = result.content[0]
|
||||
if (block?.type !== 'text') return undefined
|
||||
return [{ type: 'text', text: block.text.slice(0, 32) }]
|
||||
},
|
||||
async execute() {
|
||||
return 'body'
|
||||
},
|
||||
})
|
||||
|
||||
const result = await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: CallId('throwing-meta'), name: 'throwing-meta', arguments: {},
|
||||
})
|
||||
|
||||
expect(result.isError).toBe(true)
|
||||
const block = result.content[0]
|
||||
expect(block?.type).toBe('text')
|
||||
expect(block?.type === 'text' ? block.text : '').toMatch(/^Error: tool "throwing-meta"/)
|
||||
expect(block?.type === 'text' ? block.text : '').toHaveLength(32)
|
||||
expect(finalizeCalls).toBe(1)
|
||||
})
|
||||
|
||||
it('normalizes a throwing final content callback without invoking it again', async () => {
|
||||
const ctx = await setup()
|
||||
let finalizeCalls = 0
|
||||
ctx.tools.register({
|
||||
...echoTool,
|
||||
name: 'throwing-finalizer',
|
||||
finalizeContent() {
|
||||
finalizeCalls += 1
|
||||
throw new Error('finalizer violated its total contract')
|
||||
},
|
||||
})
|
||||
|
||||
const result = await ctx.tools.execute({
|
||||
signal: testToolSignal,
|
||||
callId: CallId('throwing-finalizer'), name: 'throwing-finalizer', arguments: {},
|
||||
})
|
||||
|
||||
expect(result).toEqual({
|
||||
content: [{ type: 'text', text: 'Error: finalizer violated its total contract' }],
|
||||
isError: true,
|
||||
error: { message: 'finalizer violated its total contract' },
|
||||
})
|
||||
expect(finalizeCalls).toBe(1)
|
||||
})
|
||||
|
||||
it('requires every raw registration to declare its canonical output', async () => {
|
||||
const ctx = await setup()
|
||||
const missingOutput = {
|
||||
@@ -747,6 +813,36 @@ describe('ToolRegistry', () => {
|
||||
expect(result.content[0]).toMatchObject({ text: 'output rejected: try again' })
|
||||
})
|
||||
|
||||
it('runs the snapshotted final content transform after outer pipeline normalization', async () => {
|
||||
const ctx = await setup()
|
||||
const dispose = ctx.tools.register(defineContentToolFixture({
|
||||
name: 'bounded',
|
||||
description: 'bounded result',
|
||||
parameters: {},
|
||||
async execute() { return [{ type: 'text', text: 'body' }] },
|
||||
finalizeContent(exec, result) {
|
||||
expect(exec.name).toBe('bounded')
|
||||
expect(result.isError).toBe(true)
|
||||
return [{ type: 'text', text: 'bounded failure' }]
|
||||
},
|
||||
}))
|
||||
ctx.on('tools/pre-execute', async () => {
|
||||
dispose()
|
||||
throw new HarnessError('policy failed', 'POLICY_FAILED')
|
||||
})
|
||||
|
||||
const result = await ctx.tools.execute({ signal: testToolSignal, callId: CallId('bounded'), name: 'bounded', arguments: {} })
|
||||
|
||||
expect(result).toEqual({
|
||||
content: [{ type: 'text', text: 'bounded failure' }],
|
||||
isError: true,
|
||||
error: {
|
||||
message: 'policy failed',
|
||||
info: { name: 'HarnessError', code: 'POLICY_FAILED' },
|
||||
},
|
||||
})
|
||||
})
|
||||
|
||||
it('a block decision can ALSO attach additionalContexts', async () => {
|
||||
const ctx = await setup()
|
||||
ctx.tools.register(echoTool)
|
||||
|
||||
@@ -17,6 +17,7 @@ export const askUserQuestionItemSchema = z.object({
|
||||
id: z.string(),
|
||||
question: z.string(),
|
||||
header: z.string().optional(),
|
||||
detail: z.string().optional(),
|
||||
options: z.array(z.object({ label: z.string(), description: z.string().optional() })).optional(),
|
||||
multiSelect: z.boolean().optional(),
|
||||
}) satisfies z.ZodType<Wire<AskUserQuestionItem>>
|
||||
@@ -27,7 +28,10 @@ export const muxFrameSchema = z.discriminatedUnion('type', [
|
||||
z.object({ type: z.literal('session/subscribed'), sessionId: sessionIdSchema, lastSeq: z.number().int() }),
|
||||
z.object({ type: z.literal('approval/requested'), sessionId: sessionIdSchema, approvalId: approvalRequestIdSchema, toolName: z.string(), callId: z.string().optional(), reason: z.string().optional() }),
|
||||
z.object({ type: z.literal('approval/resolved'), sessionId: sessionIdSchema, approvalId: approvalRequestIdSchema, outcome: z.union([z.literal('allowed-once'), z.literal('rejected'), z.literal('cancelled'), z.literal('unavailable')]) }),
|
||||
z.object({ type: z.literal('question/requested'), sessionId: sessionIdSchema, questions: z.array(askUserQuestionItemSchema) }),
|
||||
// Non-empty by wire contract: the user-interaction service rejects empty
|
||||
// batches at ask() (EMPTY_QUESTIONS), so an empty frame is host breakage
|
||||
// and must fail loud here, not reach the composer.
|
||||
z.object({ type: z.literal('question/requested'), sessionId: sessionIdSchema, questions: z.array(askUserQuestionItemSchema).min(1) }),
|
||||
z.object({ type: z.literal('question/resolved'), sessionId: sessionIdSchema, questionRpcId: rpcIdSchema, outcome: z.union([z.literal('answered'), z.literal('cancelled')]) }),
|
||||
z.object({ type: z.literal('stream/error'), error: rpcErrorSchema }),
|
||||
]) as unknown as z.ZodType<MuxFrame>
|
||||
|
||||
@@ -33,6 +33,7 @@ export const rpcIdSchema = z.string() as unknown as z.ZodType<RpcId>
|
||||
/** Error body: discriminated by code, per-branch details aligned to RpcErrorDetailsMap; details is required. */
|
||||
export const rpcErrorSchema: z.ZodType<RpcError> = z.discriminatedUnion('code', [
|
||||
z.object({ code: z.literal('bad-request'), message: z.string(), details: z.object({ issues: z.array(z.custom<ZodIssue>()) }) }),
|
||||
z.object({ code: z.literal('cancelled'), message: z.string(), details: z.object({}) }),
|
||||
z.object({ code: z.literal('session-not-found'), message: z.string(), details: z.object({ sessionId: z.string() }) }),
|
||||
z.object({ code: z.literal('agent-busy'), message: z.string(), details: z.object({ reason: z.string() }) }),
|
||||
z.object({ code: z.literal('internal'), message: z.string(), details: z.object({}) }),
|
||||
|
||||
@@ -30,6 +30,7 @@ export function RpcId(id: string): RpcId {
|
||||
/** Error code → details type map (a second table isomorphic to RpcMethodMap). New code = one row here + one branch in the error schema. */
|
||||
export interface RpcErrorDetailsMap {
|
||||
'bad-request': { issues: ZodIssue[] }
|
||||
'cancelled': {}
|
||||
'session-not-found': { sessionId: SessionId }
|
||||
'agent-busy': { reason: string }
|
||||
'internal': {}
|
||||
|
||||
@@ -29,6 +29,7 @@ describe('RpcId', () => {
|
||||
describe('rpcErrorSchema', () => {
|
||||
it('accepts every code branch with its required details', () => {
|
||||
expect(rpcErrorSchema.parse({ code: 'bad-request', message: 'm', details: { issues: [] } }).code).toBe('bad-request')
|
||||
expect(rpcErrorSchema.parse({ code: 'cancelled', message: 'm', details: {} }).code).toBe('cancelled')
|
||||
expect(rpcErrorSchema.parse({ code: 'session-not-found', message: 'm', details: { sessionId: 's' } }).code).toBe('session-not-found')
|
||||
expect(rpcErrorSchema.parse({ code: 'agent-busy', message: 'm', details: { reason: 'r' } }).code).toBe('agent-busy')
|
||||
expect(rpcErrorSchema.parse({ code: 'internal', message: 'm', details: {} }).code).toBe('internal')
|
||||
@@ -134,6 +135,10 @@ describe('events frame schemas', () => {
|
||||
expect(askUserQuestionItemSchema.parse({ id: 'q', question: 'Q?' }).id).toBe('q')
|
||||
})
|
||||
|
||||
it('rejects an empty question batch (ask() guarantees at least one, so an empty frame is host breakage)', () => {
|
||||
expect(() => muxFrameSchema.parse({ type: 'question/requested', sessionId: 's', questions: [] })).toThrow()
|
||||
})
|
||||
|
||||
it('accepts every host frame branch', () => {
|
||||
const frames = [
|
||||
{ type: 'host/session-added', sessionId: 's', parentSessionId: 'p' },
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# @deepseek-ai/dsh-host-runtime
|
||||
|
||||
Host runtime assembly for `dsh`: `bootHost` composes the core plugin spine (LLM service + DeepSeek adapter, sessions with JSONL persistence, system prompt, tools, agents, agent loop, workspace instructions, local bash), `createApiProxy` implements the [`dsh-host-apiproxy`](../apiproxy/README.md) contract over that composition, and `startHost` is the one-step shell seam returning `{ api, handler, defaults, ctx, dispose }`.
|
||||
Host runtime assembly for `dsh`: `bootHost` composes the core plugin spine (LLM service + DeepSeek adapter, sessions with JSONL persistence, system prompt, tools, agents, agent loop, workspace instructions, local bash, and the provider-neutral user-interaction service), `createApiProxy` implements the [`dsh-host-apiproxy`](../apiproxy/README.md) contract over that composition, and `startHost` is the one-step shell seam returning `{ api, handler, defaults, ctx, dispose }`.
|
||||
|
||||
Which plugins mount and with what defaults is decided only here — shells must not `ctx.plugin` to alter the assembly. `RunningHost.ctx` is a formal seam with exactly two sanctioned uses: mounting protocol front-door plugins (e.g. a future `dsh acp`) and headless session-event subscription; consuming clients must not bypass `api` through it.
|
||||
|
||||
@@ -15,7 +15,7 @@ Which plugins mount and with what defaults is decided only here — shells must
|
||||
|
||||
## ApiProxy implementation notes
|
||||
|
||||
Unary methods take the narrow `RpcRequest<P>` and echo `request.rpcId`; a prompt's rpcId rides `MessageSource` into the `user/message` event so clients can promote optimistic echoes. `history`/`prompt` on a cold session implicitly resume it, deduplicating concurrent calls through an in-flight table; `history` paginates backwards on message boundaries (never mid-message). The mux stream replays a `session/subscribed` baseline per attached session on open; the host stream carries session lifecycle, running flips, and `agent/error` as the only outlet for live failures with no turn position.
|
||||
Unary methods take the narrow `RpcRequest<P>` and echo `request.rpcId`; a prompt's rpcId rides `MessageSource` into the `user/message` event so clients can promote optimistic echoes. `history`/`prompt` on a cold session implicitly resume it, deduplicating concurrent calls through an in-flight table; `history` paginates backwards on message boundaries (never mid-message). The mux stream replays a `session/subscribed` baseline per attached session and every still-pending question with its original rpcId. Question responses, including blank per-item answers, are validated against the owning session and exact request before an atomic first-wins claim; answer, whole-request cancellation, owner abort, and provider disposal broadcast `question/resolved`. The host stream carries session lifecycle, running flips, and `agent/error` as the only outlet for live failures with no turn position.
|
||||
|
||||
## Model Experience
|
||||
|
||||
@@ -27,6 +27,6 @@ No direct invalidation; the mounted model-facing plugins own their request-prefi
|
||||
|
||||
## Known Limitations and Deferred Work
|
||||
|
||||
- **`respond` is a stub** — it always returns `not-pending`; the approval/question pending registry (stable-rpcId mint on accept, baseline replay on stream reopen, wire answerer) is the next host-side step.
|
||||
- **Question waits are process-memory state** — browser reconnects recover them, but a host process restart aborts the owning tool call instead of restoring the wait from persistence.
|
||||
- **`host.describe.version` is a placeholder** — it does not yet report the `apps/cli` package version.
|
||||
- **The assembly is fixed** — per-deployment plugin selection (user profile, log sinks, alternative persistence) has a documented home here but no configuration surface yet.
|
||||
|
||||
@@ -36,6 +36,7 @@
|
||||
"@deepseek-ai/dsh-client-i18n": "workspace:^",
|
||||
"@deepseek-ai/dsh-client-runtime": "workspace:^",
|
||||
"@deepseek-ai/dsh-client-ui-conversation": "workspace:^",
|
||||
"@deepseek-ai/dsh-client-ui-question": "workspace:^",
|
||||
"@deepseek-ai/dsh-client-ui-layout": "workspace:^",
|
||||
"@deepseek-ai/dsh-client-ui-sidebar": "workspace:^",
|
||||
"@deepseek-ai/dsh-client-ui-theme": "workspace:^",
|
||||
@@ -69,6 +70,7 @@
|
||||
"@deepseek-ai/dsh-tool-todo": "workspace:^",
|
||||
"@deepseek-ai/dsh-tool-workflow": "workspace:^",
|
||||
"@deepseek-ai/dsh-tools": "workspace:^",
|
||||
"@deepseek-ai/dsh-user-interaction": "workspace:^",
|
||||
"@deepseek-ai/dsh-workspace-context": "workspace:^",
|
||||
"@deepseek-ai/dsh-workflow-workerthread": "workspace:^"
|
||||
},
|
||||
|
||||
@@ -1,8 +1,6 @@
|
||||
/**
|
||||
* Host-side ApiProxy implementation (minimal-first —
|
||||
* describe/list/create/history/prompt/cancel and both streams are real,
|
||||
* respond is a stub). Signature discipline: unary takes the narrow
|
||||
* RpcRequest<P> and echoes request.rpcId on the RpcResponse<T>.
|
||||
* Host-side ApiProxy implementation. Signature discipline: unary takes the
|
||||
* narrow RpcRequest<P> and echoes request.rpcId on the RpcResponse<T>.
|
||||
*/
|
||||
|
||||
import { randomUUID } from 'node:crypto'
|
||||
@@ -12,9 +10,16 @@ import type { Agent, AgentStatus } from '@deepseek-ai/dsh-agent'
|
||||
import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm'
|
||||
import type { JsonValue, Session, SessionEvent, SessionHeader, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import type { SessionPersistence } from '@deepseek-ai/dsh-session-persistence'
|
||||
import type { ApiProxy, HistoryEntry, HostFrame, MuxFrame, SessionSummary, ToolEventView } from '@deepseek-ai/dsh-host-apiproxy/api'
|
||||
import type {
|
||||
ApiProxy, HistoryEntry, HostFrame, MuxFrame, QuestionResponsePayload, SessionSummary, ToolEventView,
|
||||
} from '@deepseek-ai/dsh-host-apiproxy/api'
|
||||
import { questionResponsePayloadSchema } from '@deepseek-ai/dsh-host-apiproxy/api/questions.schema'
|
||||
import type { ClientResponse, RpcError, RpcReceipt, RpcRequest, RpcResponse } from '@deepseek-ai/dsh-host-apiproxy/api/rpc'
|
||||
import { RpcId } from '@deepseek-ai/dsh-host-apiproxy/api/rpc'
|
||||
import type {
|
||||
AskUserQuestionAnswer, AskUserQuestionItem, AskUserQuestionRequest,
|
||||
} from '@deepseek-ai/dsh-user-interaction'
|
||||
import { UserInteractionError } from '@deepseek-ai/dsh-user-interaction'
|
||||
|
||||
/** Page size when history is called without maxMessages. */
|
||||
const DEFAULT_MAX_MESSAGES = 50
|
||||
@@ -155,6 +160,35 @@ interface ToolCallData { callId: string; name: string; arguments: string }
|
||||
/** The tool/result payload fields the presenter path reads. */
|
||||
interface ToolResultData { callId: string; content: ContentBlock[]; isError: boolean; meta?: JsonValue }
|
||||
|
||||
/** One host-owned question wait, addressed by the stable server-request id. */
|
||||
interface PendingQuestion {
|
||||
rpcId: RpcId
|
||||
sessionId: SessionId
|
||||
questions: AskUserQuestionItem[]
|
||||
resolve: (answer: AskUserQuestionAnswer) => void
|
||||
reject: (error: UserInteractionError) => void
|
||||
signal?: AbortSignal
|
||||
onAbort?: () => void
|
||||
}
|
||||
|
||||
/** Validate one answer batch against the exact question request it resolves. */
|
||||
function matchesQuestions(payload: QuestionResponsePayload, pending: PendingQuestion): boolean {
|
||||
if (payload.sessionId !== pending.sessionId) return false
|
||||
const answers = payload.answer.answers
|
||||
if (answers.length !== pending.questions.length) return false
|
||||
return answers.every((answer, index) => {
|
||||
const question = pending.questions[index] as AskUserQuestionItem
|
||||
if (answer.id !== question.id) return false
|
||||
if (new Set(answer.selected).size !== answer.selected.length) return false
|
||||
const custom = answer.custom?.trim()
|
||||
if (custom !== undefined && custom === '') return false
|
||||
if (custom !== undefined && answer.selected.length > 0) return false
|
||||
if (question.multiSelect !== true && answer.selected.length > 1) return false
|
||||
const labels = new Set(question.options?.map(option => option.label) ?? [])
|
||||
return answer.selected.every(label => labels.has(label))
|
||||
})
|
||||
}
|
||||
|
||||
/**
|
||||
* Compute the render intent for a tool/call or tool/result event through the
|
||||
* presenters registered at this moment; every other event type gets none. A
|
||||
@@ -219,12 +253,70 @@ class SessionNotFound extends Error {}
|
||||
* @param ctx - the root context returned by bootHost (sessions/agents services mounted).
|
||||
* @param defaults - host-level default provider/model: injected as
|
||||
* agentOptions on create/resume, reported by describe from the same source.
|
||||
* @returns the ApiProxy implementation (minimal-first; stubs noted per method).
|
||||
* @returns the ApiProxy implementation.
|
||||
*/
|
||||
export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiProxy {
|
||||
const agentOptions = { provider: defaults.provider, model: defaults.model }
|
||||
/** Implicit resume of cold sessions, deduplicating concurrent calls (follows the jsonrpc sessionCreations precedent). */
|
||||
const resumes = new Map<SessionId, Promise<Agent>>()
|
||||
const pendingQuestions = new Map<RpcId, PendingQuestion>()
|
||||
const muxQueues = new Set<FrameQueue<RpcRequest<MuxFrame>>>()
|
||||
|
||||
/** Send one transient frame to every connected mux consumer. */
|
||||
function broadcast(payload: MuxFrame): void {
|
||||
const envelope = frame(payload)
|
||||
for (const queue of muxQueues) queue.push(envelope)
|
||||
}
|
||||
|
||||
/** Remove a wait before settling it: synchronous deletion makes the first claimant win. */
|
||||
function claimQuestion(pending: PendingQuestion, outcome: 'answered' | 'cancelled'): void {
|
||||
pendingQuestions.delete(pending.rpcId)
|
||||
if (pending.signal !== undefined && pending.onAbort !== undefined) {
|
||||
pending.signal.removeEventListener('abort', pending.onAbort)
|
||||
}
|
||||
broadcast({
|
||||
type: 'question/resolved', sessionId: pending.sessionId,
|
||||
questionRpcId: pending.rpcId, outcome,
|
||||
})
|
||||
}
|
||||
|
||||
const disposeProvider = ctx.userInteraction.registerProvider({
|
||||
ask(request: AskUserQuestionRequest): Promise<AskUserQuestionAnswer> {
|
||||
const sessionId = request.agent?.id
|
||||
if (sessionId === undefined) {
|
||||
return Promise.reject(new UserInteractionError(
|
||||
'web user interaction requires an agent-owned session', 'ASK_MISSING_AGENT'))
|
||||
}
|
||||
return new Promise<AskUserQuestionAnswer>((resolve, reject) => {
|
||||
const rpcId = RpcId(randomUUID())
|
||||
const pending: PendingQuestion = {
|
||||
rpcId, sessionId, questions: request.questions, resolve, reject,
|
||||
...(request.signal === undefined ? {} : { signal: request.signal }),
|
||||
}
|
||||
const onAbort = (): void => {
|
||||
claimQuestion(pending, 'cancelled')
|
||||
reject(new UserInteractionError(
|
||||
'ask_user_question was aborted before the user answered', 'ASK_ABORTED'))
|
||||
}
|
||||
pending.onAbort = onAbort
|
||||
pendingQuestions.set(rpcId, pending)
|
||||
request.signal?.addEventListener('abort', onAbort, { once: true })
|
||||
const envelope: RpcRequest<MuxFrame> = {
|
||||
rpcId,
|
||||
payload: { type: 'question/requested', sessionId, questions: request.questions },
|
||||
}
|
||||
for (const queue of muxQueues) queue.push(envelope)
|
||||
})
|
||||
},
|
||||
})
|
||||
ctx.effect(() => () => {
|
||||
disposeProvider()
|
||||
for (const pending of [...pendingQuestions.values()]) {
|
||||
claimQuestion(pending, 'cancelled')
|
||||
pending.reject(new UserInteractionError(
|
||||
'web user-interaction provider was disposed', 'ASK_ABORTED'))
|
||||
}
|
||||
}, 'api-proxy: user-interaction provider')
|
||||
|
||||
/**
|
||||
* Gate the cold path on the store: an id absent from it, or naming a legacy
|
||||
@@ -361,9 +453,19 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
events: {
|
||||
mux(_request, signal) {
|
||||
const queue = new FrameQueue<RpcRequest<MuxFrame>>()
|
||||
muxQueues.add(queue)
|
||||
for (const session of ctx.sessions.list()) {
|
||||
queue.push(frame({ type: 'session/subscribed', sessionId: session.id, lastSeq: session.seq - 1 }))
|
||||
}
|
||||
for (const pending of pendingQuestions.values()) {
|
||||
queue.push({
|
||||
rpcId: pending.rpcId,
|
||||
payload: {
|
||||
type: 'question/requested', sessionId: pending.sessionId,
|
||||
questions: pending.questions,
|
||||
},
|
||||
})
|
||||
}
|
||||
// Per-session open-call table for result-view pairing. Bounded by the
|
||||
// per-turn call count: entries clear on turn/end; a table miss (stream
|
||||
// opened mid-turn) backscans the session's in-memory events instead.
|
||||
@@ -393,7 +495,10 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
openCalls.delete(session.id)
|
||||
}),
|
||||
]
|
||||
return queue.iterate(signal, () => { for (const dispose of disposers) dispose() })
|
||||
return queue.iterate(signal, () => {
|
||||
muxQueues.delete(queue)
|
||||
for (const dispose of disposers) dispose()
|
||||
})
|
||||
},
|
||||
|
||||
host(_request, signal) {
|
||||
@@ -421,9 +526,38 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
},
|
||||
},
|
||||
|
||||
// TODO(step2): approval/question pending registry (wire answerer + proxy provider).
|
||||
respond(_message: ClientResponse): Promise<RpcReceipt> {
|
||||
return Promise.resolve({ accepted: false, reason: 'not-pending' })
|
||||
respond(message: ClientResponse): Promise<RpcReceipt> {
|
||||
const pending = pendingQuestions.get(message.rpcId)
|
||||
if (pending === undefined) return Promise.resolve({ accepted: false, reason: 'not-pending' })
|
||||
if (!message.result.ok) {
|
||||
if (message.result.error.code !== 'cancelled') {
|
||||
return Promise.resolve({ accepted: false, reason: 'bad-response' })
|
||||
}
|
||||
claimQuestion(pending, 'cancelled')
|
||||
pending.reject(new UserInteractionError(
|
||||
'the user cancelled ask_user_question', 'ASK_CANCELLED'))
|
||||
return Promise.resolve({ accepted: true })
|
||||
}
|
||||
const parsed = questionResponsePayloadSchema.safeParse(message.result.value)
|
||||
if (!parsed.success) {
|
||||
return Promise.resolve({ accepted: false, reason: 'bad-response' })
|
||||
}
|
||||
const payload: QuestionResponsePayload = {
|
||||
sessionId: parsed.data.sessionId,
|
||||
answer: {
|
||||
answers: parsed.data.answer.answers.map(answer => ({
|
||||
id: answer.id,
|
||||
selected: answer.selected,
|
||||
...(answer.custom === undefined ? {} : { custom: answer.custom }),
|
||||
})),
|
||||
},
|
||||
}
|
||||
if (!matchesQuestions(payload, pending)) {
|
||||
return Promise.resolve({ accepted: false, reason: 'bad-response' })
|
||||
}
|
||||
claimQuestion(pending, 'answered')
|
||||
pending.resolve(payload.answer)
|
||||
return Promise.resolve({ accepted: true })
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
@@ -38,6 +38,7 @@ import * as toolWorkflow from '@deepseek-ai/dsh-tool-workflow'
|
||||
import * as timeoutPolicy from '@deepseek-ai/dsh-timeout-policy'
|
||||
import SpillLocal from '@deepseek-ai/dsh-spill-local'
|
||||
import * as spillPolicy from '@deepseek-ai/dsh-spill-policy'
|
||||
import UserInteractionService from '@deepseek-ai/dsh-user-interaction'
|
||||
|
||||
/** Options for bootHost — the assembly-layer composition knobs. */
|
||||
export interface BootHostOptions {
|
||||
@@ -94,6 +95,7 @@ export async function bootHost(options: BootHostOptions): Promise<HostHandle> {
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(SystemPrompt, { persona: '' })
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(UserInteractionService)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(TaskService)
|
||||
await ctx.plugin(AgentLoop, { agents: [] })
|
||||
|
||||
@@ -1,16 +1,16 @@
|
||||
/**
|
||||
* Web UI plugin assembly: mounts @cordisjs/plugin-loader with an in-memory
|
||||
* entry tree listing the eight UI plugin packages (the P-I config-source bar —
|
||||
* entry tree listing the nine UI plugin packages (the P-I config-source bar —
|
||||
* a cordis.yml file form comes later; install/remove currently means editing
|
||||
* this list and restarting). The web plugin registry discovers the entries by
|
||||
* their package.json dshClient declarations; node halves are empty applies,
|
||||
* so mounting them here costs nothing beyond Loader governance.
|
||||
* their package.json dshClient declarations; feature packages may also mount
|
||||
* their interface-specific host half through the same lifecycle.
|
||||
*/
|
||||
import { createRequire } from 'node:module'
|
||||
import type { Context } from 'cordis'
|
||||
import Loader from '@cordisjs/plugin-loader'
|
||||
|
||||
/** The eight UI plugin packages served to the browser (order = manifest order). */
|
||||
/** The nine UI plugin packages served to the browser (order = manifest order). */
|
||||
export const WEB_UI_PLUGINS = [
|
||||
'@deepseek-ai/dsh-client-connection',
|
||||
'@deepseek-ai/dsh-client-runtime',
|
||||
@@ -19,6 +19,7 @@ export const WEB_UI_PLUGINS = [
|
||||
'@deepseek-ai/dsh-client-ui-layout',
|
||||
'@deepseek-ai/dsh-client-ui-sidebar',
|
||||
'@deepseek-ai/dsh-client-ui-conversation',
|
||||
'@deepseek-ai/dsh-client-ui-question',
|
||||
'@deepseek-ai/dsh-client-ui-trajectory',
|
||||
] as const
|
||||
|
||||
@@ -41,7 +42,7 @@ export interface MountedWebPlugins {
|
||||
export async function mountWebPlugins(ctx: Context): Promise<MountedWebPlugins> {
|
||||
// The Loader resolves bare specifiers against ctx.baseUrl; without one the
|
||||
// import silently fails and every entry stays fiber-less. This package
|
||||
// depends on all eight UI plugins, so its own URL is the right anchor.
|
||||
// depends on all nine UI plugins, so its own URL is the right anchor.
|
||||
ctx.baseUrl ??= import.meta.url
|
||||
if (ctx.get('loader') === undefined) await ctx.plugin(Loader)
|
||||
const existing = new Set([...ctx.loader.entries()].map(entry => entry.options.name))
|
||||
|
||||
@@ -12,6 +12,7 @@ import { describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import SessionStore from '@deepseek-ai/dsh-session'
|
||||
import AgentRegistry from '@deepseek-ai/dsh-agent'
|
||||
import UserInteractionService from '@deepseek-ai/dsh-user-interaction'
|
||||
import type { SessionHeader, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import type { RpcRequest } from '@deepseek-ai/dsh-host-apiproxy/api/rpc'
|
||||
import { RpcId } from '@deepseek-ai/dsh-host-apiproxy/api/rpc'
|
||||
@@ -32,6 +33,7 @@ describe('sessions.list cold merge', () => {
|
||||
it('summarizes unattached sessions: log mtime, locate-less and vanished-log createdAt fallbacks, lineage', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(UserInteractionService)
|
||||
const root = mkdtempSync(join(tmpdir(), 'dsh-cold-'))
|
||||
const logPath = join(root, 'a.log')
|
||||
writeFileSync(logPath, 'log-bytes')
|
||||
@@ -76,6 +78,7 @@ describe('degenerate composition (no persistence, no factory)', () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(UserInteractionService)
|
||||
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp' })
|
||||
|
||||
const listed = await api.sessions.list(request({}))
|
||||
|
||||
@@ -18,6 +18,7 @@ import type { ContentBlock } from '@deepseek-ai/dsh-llm'
|
||||
import { CallId } from '@deepseek-ai/dsh-llm'
|
||||
import type { Session, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import type { ToolDefinition } from '@deepseek-ai/dsh-tools'
|
||||
import UserInteractionService from '@deepseek-ai/dsh-user-interaction'
|
||||
import type { MuxFrame, RpcRequest } from '@deepseek-ai/dsh-host-apiproxy/api'
|
||||
import { RpcId } from '@deepseek-ai/dsh-host-apiproxy/api/rpc'
|
||||
import { createApiProxy } from '../src/api-proxy.ts'
|
||||
@@ -39,6 +40,7 @@ async function harness(): Promise<{ ctx: Context }> {
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(SystemPrompt, { persona: '' })
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(UserInteractionService)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
ctx.tools.register(tool('gen', {
|
||||
presentCall: () => ({ card: 'generic', title: 'gen call' }),
|
||||
|
||||
@@ -418,10 +418,175 @@ describe('events streams', () => {
|
||||
})
|
||||
})
|
||||
|
||||
describe('respond stub', () => {
|
||||
it('always reports not-pending (step2 registry pending)', async () => {
|
||||
const { api } = await boot()
|
||||
const receipt = await api.respond({ type: 'client-response', rpcId: RpcId('r'), result: { ok: true, value: null } })
|
||||
expect(receipt).toEqual({ accepted: false, reason: 'not-pending' })
|
||||
describe('question request / response', () => {
|
||||
const questions = [{
|
||||
id: 'mode', question: 'Choose a mode',
|
||||
options: [
|
||||
{ label: 'Fast (Recommended)', description: 'Move quickly.' },
|
||||
{ label: 'Careful', description: 'Review first.' },
|
||||
],
|
||||
}]
|
||||
|
||||
it('waits, replays the same rpcId on reconnect, validates, and resolves first-wins', async () => {
|
||||
const running = await boot()
|
||||
const { api, ctx } = running
|
||||
const { sessionId } = expectOk(await api.sessions.create(request({})))
|
||||
const agent = ctx.agents.get(sessionId) as Agent
|
||||
const ac = new AbortController()
|
||||
const stream = api.events.mux(request({}), ac.signal)[Symbol.asyncIterator]()
|
||||
await stream.next() // subscribed baseline starts the generator and installs the queue
|
||||
|
||||
const answerPromise = ctx.userInteraction.ask({ questions, agent })
|
||||
const requested = (await stream.next()).value as RpcRequest<MuxFrame>
|
||||
expect(requested.payload).toMatchObject({ type: 'question/requested', sessionId, questions })
|
||||
|
||||
const wrongSession = await api.respond({
|
||||
type: 'client-response', rpcId: requested.rpcId,
|
||||
result: {
|
||||
ok: true,
|
||||
value: { sessionId: 'session-other', answer: { answers: [{ id: 'mode', selected: ['Fast (Recommended)'] }] } },
|
||||
},
|
||||
})
|
||||
expect(wrongSession).toEqual({ accepted: false, reason: 'bad-response' })
|
||||
const badChoice = await api.respond({
|
||||
type: 'client-response', rpcId: requested.rpcId,
|
||||
result: {
|
||||
ok: true,
|
||||
value: { sessionId, answer: { answers: [{ id: 'mode', selected: ['Unknown'] }] } },
|
||||
},
|
||||
})
|
||||
expect(badChoice).toEqual({ accepted: false, reason: 'bad-response' })
|
||||
const invalidResults = [
|
||||
{ ok: true as const, value: null },
|
||||
{ ok: true as const, value: { sessionId, answer: { answers: [] } } },
|
||||
{ ok: true as const, value: { sessionId, answer: { answers: [{ id: 'wrong', selected: ['Fast (Recommended)'] }] } } },
|
||||
{ ok: true as const, value: { sessionId, answer: { answers: [{ id: 'mode', selected: ['Fast (Recommended)', 'Fast (Recommended)'] }] } } },
|
||||
{ ok: true as const, value: { sessionId, answer: { answers: [{ id: 'mode', selected: ['Fast (Recommended)', 'Careful'] }] } } },
|
||||
{ ok: true as const, value: { sessionId, answer: { answers: [{ id: 'mode', selected: [], custom: ' ' }] } } },
|
||||
{ ok: true as const, value: { sessionId, answer: { answers: [{ id: 'mode', selected: ['Careful'], custom: 'Other' }] } } },
|
||||
{ ok: false as const, error: { code: 'internal' as const, message: 'wrong error', details: {} } },
|
||||
]
|
||||
for (const result of invalidResults) {
|
||||
expect(await api.respond({
|
||||
type: 'client-response', rpcId: requested.rpcId, result,
|
||||
})).toEqual({ accepted: false, reason: 'bad-response' })
|
||||
}
|
||||
|
||||
const reconnectAbort = new AbortController()
|
||||
const replay = api.events.mux(request({}), reconnectAbort.signal)[Symbol.asyncIterator]()
|
||||
await replay.next()
|
||||
const replayed = (await replay.next()).value as RpcRequest<MuxFrame>
|
||||
expect(replayed.rpcId).toBe(requested.rpcId)
|
||||
expect(replayed.payload).toEqual(requested.payload)
|
||||
|
||||
const response = {
|
||||
type: 'client-response' as const,
|
||||
rpcId: requested.rpcId,
|
||||
result: {
|
||||
ok: true as const,
|
||||
value: { sessionId, answer: { answers: [{ id: 'mode', selected: ['Fast (Recommended)'] }] } },
|
||||
},
|
||||
}
|
||||
const [first, duplicate] = await Promise.all([api.respond(response), api.respond(response)])
|
||||
expect([first, duplicate]).toContainEqual({ accepted: true })
|
||||
expect([first, duplicate]).toContainEqual({ accepted: false, reason: 'not-pending' })
|
||||
await expect(answerPromise).resolves.toEqual({
|
||||
answers: [{ id: 'mode', selected: ['Fast (Recommended)'] }],
|
||||
})
|
||||
|
||||
const resolved = (await stream.next()).value as RpcRequest<MuxFrame>
|
||||
expect(resolved.payload).toMatchObject({
|
||||
type: 'question/resolved', sessionId, questionRpcId: requested.rpcId, outcome: 'answered',
|
||||
})
|
||||
expect(await api.respond(response)).toEqual({ accepted: false, reason: 'not-pending' })
|
||||
|
||||
const customQuestions = [{ id: 'detail', question: 'What else?' }]
|
||||
const customAnswer = ctx.userInteraction.ask({ questions: customQuestions, agent })
|
||||
const customRequested = (await stream.next()).value as RpcRequest<MuxFrame>
|
||||
expect(await api.respond({
|
||||
type: 'client-response', rpcId: customRequested.rpcId,
|
||||
result: {
|
||||
ok: true,
|
||||
value: { sessionId, answer: { answers: [{ id: 'detail', selected: [], custom: 'Keep traces' }] } },
|
||||
},
|
||||
})).toEqual({ accepted: true })
|
||||
await expect(customAnswer).resolves.toEqual({
|
||||
answers: [{ id: 'detail', selected: [], custom: 'Keep traces' }],
|
||||
})
|
||||
expect(((await stream.next()).value as RpcRequest<MuxFrame>).payload).toMatchObject({
|
||||
type: 'question/resolved', questionRpcId: customRequested.rpcId, outcome: 'answered',
|
||||
})
|
||||
|
||||
const blankAnswer = ctx.userInteraction.ask({ questions, agent })
|
||||
const blankRequested = (await stream.next()).value as RpcRequest<MuxFrame>
|
||||
expect(await api.respond({
|
||||
type: 'client-response', rpcId: blankRequested.rpcId,
|
||||
result: {
|
||||
ok: true,
|
||||
value: { sessionId, answer: { answers: [{ id: 'mode', selected: [] }] } },
|
||||
},
|
||||
})).toEqual({ accepted: true })
|
||||
await expect(blankAnswer).resolves.toEqual({
|
||||
answers: [{ id: 'mode', selected: [] }],
|
||||
})
|
||||
expect(((await stream.next()).value as RpcRequest<MuxFrame>).payload).toMatchObject({
|
||||
type: 'question/resolved', questionRpcId: blankRequested.rpcId, outcome: 'answered',
|
||||
})
|
||||
ac.abort()
|
||||
reconnectAbort.abort()
|
||||
})
|
||||
|
||||
it('distinguishes user cancellation from owner abort and rejects late responses', async () => {
|
||||
const running = await boot()
|
||||
const { api, ctx } = running
|
||||
const { sessionId } = expectOk(await api.sessions.create(request({})))
|
||||
const agent = ctx.agents.get(sessionId) as Agent
|
||||
const streamAbort = new AbortController()
|
||||
const stream = api.events.mux(request({}), streamAbort.signal)[Symbol.asyncIterator]()
|
||||
await stream.next()
|
||||
|
||||
const cancelled = ctx.userInteraction.ask({ questions, agent }).catch((error: unknown) => error)
|
||||
const requested = (await stream.next()).value as RpcRequest<MuxFrame>
|
||||
expect(await api.respond({
|
||||
type: 'client-response', rpcId: requested.rpcId,
|
||||
result: { ok: false, error: { code: 'cancelled', message: 'skip', details: {} } },
|
||||
})).toEqual({ accepted: true })
|
||||
await expect(cancelled).resolves.toMatchObject({ code: 'ASK_CANCELLED' })
|
||||
expect(((await stream.next()).value as RpcRequest<MuxFrame>).payload).toMatchObject({
|
||||
type: 'question/resolved', outcome: 'cancelled',
|
||||
})
|
||||
|
||||
const ownerAbort = new AbortController()
|
||||
const aborted = ctx.userInteraction.ask({ questions, agent, signal: ownerAbort.signal })
|
||||
.catch((error: unknown) => error)
|
||||
const abortRequest = (await stream.next()).value as RpcRequest<MuxFrame>
|
||||
ownerAbort.abort()
|
||||
await expect(aborted).resolves.toMatchObject({ code: 'ASK_ABORTED' })
|
||||
expect(((await stream.next()).value as RpcRequest<MuxFrame>).payload).toMatchObject({
|
||||
type: 'question/resolved', questionRpcId: abortRequest.rpcId, outcome: 'cancelled',
|
||||
})
|
||||
expect(await api.respond({
|
||||
type: 'client-response', rpcId: abortRequest.rpcId,
|
||||
result: { ok: false, error: { code: 'cancelled', message: 'late', details: {} } },
|
||||
})).toEqual({ accepted: false, reason: 'not-pending' })
|
||||
streamAbort.abort()
|
||||
})
|
||||
|
||||
it('rejects missing routing and pre-abort, then aborts outstanding waits on disposal', async () => {
|
||||
const running = await boot()
|
||||
const { ctx } = running
|
||||
await expect(ctx.userInteraction.ask({ questions })).rejects.toMatchObject({ code: 'ASK_MISSING_AGENT' })
|
||||
const { sessionId } = expectOk(await running.api.sessions.create(request({})))
|
||||
const agent = ctx.agents.get(sessionId) as Agent
|
||||
const alreadyAborted = new AbortController()
|
||||
alreadyAborted.abort()
|
||||
await expect(ctx.userInteraction.ask({ questions, agent, signal: alreadyAborted.signal }))
|
||||
.rejects.toMatchObject({ code: 'ASK_ABORTED' })
|
||||
|
||||
const outstanding = ctx.userInteraction.ask({ questions, agent })
|
||||
const disposed = running.dispose()
|
||||
host = undefined
|
||||
await expect(outstanding).rejects.toMatchObject({ code: 'ASK_ABORTED' })
|
||||
await disposed
|
||||
})
|
||||
})
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
/**
|
||||
* Web UI plugin assembly: the in-memory Loader tree mounts all eight UI
|
||||
* Web UI plugin assembly: the in-memory Loader tree mounts all nine UI
|
||||
* packages (node halves), and the webserver registry built over it yields the
|
||||
* full __DSH_BOOT__ manifest — the P-I config-source bar end to end.
|
||||
*
|
||||
@@ -10,6 +10,9 @@
|
||||
import { existsSync } from 'node:fs'
|
||||
import { createRequire } from 'node:module'
|
||||
import { Context } from 'cordis'
|
||||
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import UserInteractionService from '@deepseek-ai/dsh-user-interaction'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
import { createHostWebPluginRegistry } from '@deepseek-ai/dsh-host-webserver'
|
||||
import { WEB_UI_PLUGINS, mountWebPlugins } from '../src/web-plugins.ts'
|
||||
@@ -31,8 +34,16 @@ afterEach(async () => {
|
||||
})
|
||||
|
||||
describe.skipIf(!built)('mountWebPlugins + registry', () => {
|
||||
it('mounts the eight-package in-memory Loader tree and projects the boot manifest', async () => {
|
||||
async function rootWithHostServices(): Promise<Context> {
|
||||
root = new Context()
|
||||
await root.plugin(SystemPrompt)
|
||||
await root.plugin(ToolRegistry)
|
||||
await root.plugin(UserInteractionService)
|
||||
return root
|
||||
}
|
||||
|
||||
it('mounts the nine-package in-memory Loader tree and projects the boot manifest', async () => {
|
||||
root = await rootWithHostServices()
|
||||
const mounted = await mountWebPlugins(root)
|
||||
const registry = createHostWebPluginRegistry({
|
||||
ctx: root,
|
||||
@@ -59,7 +70,7 @@ describe.skipIf(!built)('mountWebPlugins + registry', () => {
|
||||
})
|
||||
|
||||
it('is idempotent: a second mount reuses the loader and creates no duplicate entries', async () => {
|
||||
root = new Context()
|
||||
root = await rootWithHostServices()
|
||||
await mountWebPlugins(root)
|
||||
const second = await mountWebPlugins(root)
|
||||
// ctx.loader hands out a fresh traced proxy per access, so loader identity
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
/**
|
||||
* mountWebPlugins unit coverage (keyless; the real eight-package walk is the
|
||||
* mountWebPlugins unit coverage (keyless; the real nine-package walk is the
|
||||
* built-artifact e2e). The Loader-facing behavior — baseUrl anchoring, entry
|
||||
* creation with idempotent reuse, the fiber-less fail-loud sweep, and the
|
||||
* resolver seam — is exercised against a stubbed loader service so it runs
|
||||
@@ -85,7 +85,7 @@ describe('mountWebPlugins (stubbed loader)', () => {
|
||||
|
||||
it('mounts the real Loader when none is present (the ctx.plugin(Loader) branch)', async () => {
|
||||
root = new Context()
|
||||
// Environment-dependent outcome: with built lib/ the eight imports load
|
||||
// Environment-dependent outcome: with built lib/ the nine imports load
|
||||
// and the mount resolves; without them every entry stays fiber-less and
|
||||
// the sweep throws its loud list. Either way the branch under test is the
|
||||
// Loader auto-mount. Manual try/catch keeps cordis-traced proxies out of
|
||||
@@ -100,7 +100,7 @@ describe('mountWebPlugins (stubbed loader)', () => {
|
||||
}
|
||||
expect(outcome === 'resolved' || /UI plugin\(s\) failed to load/.test(outcome)).toBe(true)
|
||||
expect(root.get('loader') !== undefined).toBe(true)
|
||||
}, 30_000) // built-env run imports eight real plugin packages through the Loader
|
||||
}, 30_000) // built-env run imports nine real plugin packages through the Loader
|
||||
|
||||
it('keeps a caller-set baseUrl (anchors only when absent)', async () => {
|
||||
const entriesList: FakeEntry[] = []
|
||||
|
||||
@@ -140,6 +140,9 @@
|
||||
{
|
||||
"path": "../../client/ui-conversation"
|
||||
},
|
||||
{
|
||||
"path": "../../client/ui-question"
|
||||
},
|
||||
{
|
||||
"path": "../../client/ui-trajectory"
|
||||
}
|
||||
|
||||
@@ -4,9 +4,11 @@ Local `node-pty` backend for `ctx.pty`. It starts an interactive shell under the
|
||||
|
||||
## Plugin (`pty-local`)
|
||||
|
||||
The plugin injects `pty`, `sandbox`, and `sandboxPolicy`, then registers the configured backend type (`shell`). `danger-full-access` starts the shell directly; confined modes wrap the exact shell argv through `ctx.sandbox`. The current session-level sandbox override is resolved at spawn and remains fixed for the PTY lifetime.
|
||||
The plugin injects `pty`, `sandbox`, and `sandboxPolicy`, then registers the configured backend type (`shell`). `danger-full-access` starts the shell directly; confined modes wrap the exact shell argv through `ctx.sandbox`. The effective session mode is resolved at spawn. A change to a different effective mode is rejected before its `sandbox/mode` event commits while that owner has an open PTY or a spawn in progress; the fence is attached to the exact owner and therefore outlives a local-provider reload that retains existing sessions. Wait for creation to settle and close the sessions before changing modes, so a terminal opened with wider access cannot survive a downgrade.
|
||||
|
||||
Linux readiness combines a foreground-verified private bash prompt marker, foreground-process-group syscall inspection, silence fallback, and absolute timeout. macOS uses the verified prompt marker plus silence/timeout because it has no `/proc` syscall surface. Unrecognized or unreadable process state is never a positive exact-idle signal. During unpublished startup, a fallback requires observed output; zero-output silence cannot publish an empty session, and timeout rejects the spawn. Incomplete terminal-control sequences are bounded by `maxReadBytes` and discarded through their terminator after crossing that limit.
|
||||
Linux readiness combines a foreground-verified private bash prompt marker, foreground-process-group syscall inspection, silence fallback, and absolute timeout. macOS uses the verified prompt marker plus silence/timeout because it has no `/proc` syscall surface. A marker is not ready until printable prompt text arrives, including when the OSC marker and `PS1` are split across data callbacks. Unrecognized or unreadable process state is never a positive exact-idle signal. During unpublished startup, a fallback requires observed output; zero-output silence cannot publish an empty session, and timeout rejects the spawn. Cancellation closes the unpublished shell and rejects with the caller's exact abort reason even when its foreground process group is not observable yet; if that close fails, `PtyBackendCleanupError` separately preserves the cleanup failure for registry disposal. Incomplete terminal-control sequences are bounded by `maxReadBytes` and discarded through their terminator after crossing that limit; a trailing carriage return is carried across callbacks so split CRLF becomes one newline.
|
||||
|
||||
Send cancellation resolves the current foreground process group and delivers a real `SIGINT`; it never emulates interruption by writing `\x03`, so raw-mode programs remain cancellable. Close sends `SIGTERM` to descendants, waits, then sends `SIGKILL` to the union of captured survivors and newly scanned descendants so reparenting cannot hide a process from teardown. It verifies that every retained identity is gone or, on Linux, a non-executing zombie before stopping the shell; zombie entries are quiescent and are reaped as the shell exits. A survivor failure does not cache a permanently rejected close; a later close retries the teardown.
|
||||
|
||||
## Model Experience
|
||||
|
||||
|
||||
@@ -30,10 +30,12 @@
|
||||
},
|
||||
"license": "BSD-3-Clause",
|
||||
"peerDependencies": {
|
||||
"@deepseek-ai/dsh-agent": "^0.0.1",
|
||||
"@deepseek-ai/dsh-invariants": "^0.0.1",
|
||||
"@deepseek-ai/dsh-pty": "^0.0.1",
|
||||
"@deepseek-ai/dsh-sandbox": "^0.0.1",
|
||||
"@deepseek-ai/dsh-sandbox-policy": "^0.0.1",
|
||||
"@deepseek-ai/dsh-session": "^0.0.1",
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
},
|
||||
"dependencies": {
|
||||
|
||||
@@ -7,6 +7,9 @@
|
||||
import { Context } from 'cordis'
|
||||
import * as nodePty from 'node-pty'
|
||||
import type { IPtyForkOptions } from 'node-pty'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import type { Session, SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import { PtyBackendCleanupError } from '@deepseek-ai/dsh-pty'
|
||||
import type { PtyBackend, PtyBackendSpawnSpec } from '@deepseek-ai/dsh-pty'
|
||||
import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
|
||||
import { effectiveSandboxMode } from '@deepseek-ai/dsh-sandbox-policy'
|
||||
@@ -20,10 +23,37 @@ export type { Config as PtyLocalConfig } from './config.ts'
|
||||
|
||||
/** Cordis plugin name. */
|
||||
export const name = 'pty-local'
|
||||
/** Required services: registry plus the one shared confinement policy. */
|
||||
/** Required services: PTY registry plus the one shared confinement policy. */
|
||||
export const inject = ['pty', 'sandbox', 'sandboxPolicy']
|
||||
|
||||
const SENSITIVE_ENV_PATTERN = /KEY|SECRET|TOKEN/i
|
||||
interface SandboxModeFenceState {
|
||||
pty: Context['pty']
|
||||
sandboxPolicy: Context['sandboxPolicy']
|
||||
}
|
||||
|
||||
const sandboxModeFences = new WeakMap<Agent, SandboxModeFenceState>()
|
||||
|
||||
function ensureSandboxModeFence(ctx: Context, owner: Agent): void {
|
||||
const existing = sandboxModeFences.get(owner)
|
||||
if (existing !== undefined) {
|
||||
existing.pty = ctx.pty
|
||||
existing.sandboxPolicy = ctx.sandboxPolicy
|
||||
return
|
||||
}
|
||||
const state: SandboxModeFenceState = { pty: ctx.pty, sandboxPolicy: ctx.sandboxPolicy }
|
||||
sandboxModeFences.set(owner, state)
|
||||
owner.ctx.on('internal/dispatch', (_mode, eventName, args) => {
|
||||
if (eventName !== 'session/event') return
|
||||
const [session, event] = args as [Session, SessionEvent]
|
||||
if (session !== owner.session || event.type !== 'sandbox/mode') return
|
||||
const currentMode = effectiveSandboxMode(session.events) ?? state.sandboxPolicy.defaultMode
|
||||
if (event.data.mode === currentMode || !state.pty.hasOwnerActivity(owner)) return
|
||||
throw new Error(
|
||||
`cannot change sandbox mode from "${currentMode}" to "${event.data.mode}" while persistent terminal sessions are open or being created; wait for creation to settle and close them first`,
|
||||
)
|
||||
}, { global: true })
|
||||
}
|
||||
|
||||
function childEnvironment(spec: PtyBackendSpawnSpec): NodeJS.ProcessEnv {
|
||||
const env: NodeJS.ProcessEnv = {}
|
||||
@@ -73,7 +103,8 @@ export class LocalPtyBackend implements PtyBackend {
|
||||
}
|
||||
|
||||
async spawn(spec: PtyBackendSpawnSpec): Promise<LocalPtySession> {
|
||||
if (spec.signal?.aborted === true) throw new Error('PTY spawn aborted')
|
||||
spec.signal?.throwIfAborted()
|
||||
ensureSandboxModeFence(this.ctx, spec.owner)
|
||||
const argv = spawnArgv(this.ctx, this.config, spec)
|
||||
const file = argv[0]
|
||||
if (file === undefined) throw new Error('pty-local: sandbox returned empty argv')
|
||||
@@ -93,7 +124,7 @@ export class LocalPtyBackend implements PtyBackend {
|
||||
try {
|
||||
await session.close('PTY startup failed')
|
||||
} catch (closeError: unknown) {
|
||||
throw new AggregateError([error, closeError], 'PTY startup and cleanup both failed')
|
||||
throw new PtyBackendCleanupError(error, closeError)
|
||||
}
|
||||
throw error
|
||||
}
|
||||
|
||||
@@ -16,6 +16,7 @@ export interface ProcessInspector {
|
||||
isStdinWaiting(pgid: number): boolean
|
||||
/** Return the root and its current transitive descendants, children first. */
|
||||
processTree(rootPid: number): ProcessIdentity[]
|
||||
/** Return whether the exact identity remains a non-quiescent process. */
|
||||
isAlive(identity: ProcessIdentity): boolean
|
||||
signalGroup(pgid: number, signal: PtySignal): void
|
||||
signalProcess(identity: ProcessIdentity, signal: 'SIGTERM' | 'SIGKILL'): void
|
||||
@@ -49,6 +50,7 @@ interface ProcStat {
|
||||
parentPid: number
|
||||
pgrp: number
|
||||
session: number
|
||||
state: string
|
||||
tpgid: number
|
||||
started: string
|
||||
}
|
||||
@@ -64,13 +66,15 @@ export function parseProcStat(text: string): ProcStat | undefined {
|
||||
if (open <= 0 || close <= open) return undefined
|
||||
const pid = Number(text.slice(0, open).trim())
|
||||
const rest = text.slice(close + 2).trim().split(/\s+/)
|
||||
const state = rest[0] || ''
|
||||
const parentPid = Number(rest[1])
|
||||
const pgrp = Number(rest[2])
|
||||
const session = Number(rest[3])
|
||||
const tpgid = Number(rest[5])
|
||||
const started = rest[19]
|
||||
if (![pid, parentPid, pgrp, session, tpgid].every(Number.isSafeInteger) || started === undefined) return undefined
|
||||
return { pid, parentPid, pgrp, session, tpgid, started }
|
||||
if (![pid, parentPid, pgrp, session, tpgid].every(Number.isSafeInteger)
|
||||
|| state.length !== 1 || started === undefined) return undefined
|
||||
return { pid, parentPid, pgrp, session, state, tpgid, started }
|
||||
}
|
||||
|
||||
function readLinuxStat(internals: ProcessInspectorInternals, pid: number): ProcStat | undefined {
|
||||
@@ -269,7 +273,8 @@ class LinuxProcessInspector extends PosixProcessInspector {
|
||||
}
|
||||
|
||||
isAlive(identity: ProcessIdentity): boolean {
|
||||
return readLinuxStat(this.internals, identity.pid)?.started === identity.started
|
||||
const stat = readLinuxStat(this.internals, identity.pid)
|
||||
return stat?.started === identity.started && !/^[ZXx]$/.test(stat.state)
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
@@ -9,6 +9,8 @@ export const PROMPT_MARKER_PREFIX = '133;D;'
|
||||
export interface SanitizedChunk {
|
||||
text: string
|
||||
prompt: boolean
|
||||
/** Present when printable text followed the latest owned prompt marker. */
|
||||
promptText?: true
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -20,6 +22,8 @@ export class TerminalSanitizer {
|
||||
private pending = ''
|
||||
private discardMode: 'osc' | 'csi' | undefined
|
||||
private discardOscEscape = false
|
||||
private trailingCarriageReturn = false
|
||||
private awaitingPromptText = false
|
||||
|
||||
constructor(private readonly maxPendingBytes: number) {}
|
||||
|
||||
@@ -32,15 +36,24 @@ export class TerminalSanitizer {
|
||||
this.pending += this.discardPrefix(chunk)
|
||||
let text = ''
|
||||
let prompt = false
|
||||
let promptText = false
|
||||
let index = 0
|
||||
const appendText = (value: string): boolean => {
|
||||
text += value
|
||||
if (this.awaitingPromptText && value.replace(/[\r\n\x07]/g, '').length > 0) {
|
||||
this.awaitingPromptText = false
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
while (index < this.pending.length) {
|
||||
const escape = this.pending.indexOf('\x1b', index)
|
||||
if (escape < 0) {
|
||||
text += this.pending.slice(index)
|
||||
promptText = appendText(this.pending.slice(index)) || promptText
|
||||
index = this.pending.length
|
||||
break
|
||||
}
|
||||
text += this.pending.slice(index, escape)
|
||||
promptText = appendText(this.pending.slice(index, escape)) || promptText
|
||||
if (escape + 1 >= this.pending.length) {
|
||||
index = escape
|
||||
break
|
||||
@@ -59,7 +72,11 @@ export class TerminalSanitizer {
|
||||
}
|
||||
const terminatorBytes = this.pending[end - 1] === '\x07' ? 1 : 2
|
||||
const content = this.pending.slice(escape + 2, end - terminatorBytes)
|
||||
if (content.startsWith(PROMPT_MARKER_PREFIX)) prompt = true
|
||||
if (content.startsWith(PROMPT_MARKER_PREFIX)) {
|
||||
prompt = true
|
||||
promptText = false
|
||||
this.awaitingPromptText = true
|
||||
}
|
||||
index = end
|
||||
continue
|
||||
}
|
||||
@@ -82,7 +99,7 @@ export class TerminalSanitizer {
|
||||
}
|
||||
this.pending = this.pending.slice(index)
|
||||
this.enforcePendingBound()
|
||||
return { text: normalizeTerminalText(text), prompt }
|
||||
return { text: this.normalizeText(text), prompt, ...promptText ? { promptText: true } : {} }
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -94,7 +111,21 @@ export class TerminalSanitizer {
|
||||
this.pending = ''
|
||||
this.discardMode = undefined
|
||||
this.discardOscEscape = false
|
||||
return normalizeTerminalText(text)
|
||||
this.awaitingPromptText = false
|
||||
const normalized = this.normalizeText(text)
|
||||
if (!this.trailingCarriageReturn) return normalized
|
||||
this.trailingCarriageReturn = false
|
||||
return `${normalized}\n`
|
||||
}
|
||||
|
||||
private normalizeText(text: string): string {
|
||||
let complete = this.trailingCarriageReturn ? `\r${text}` : text
|
||||
this.trailingCarriageReturn = false
|
||||
if (complete.endsWith('\r')) {
|
||||
complete = complete.slice(0, -1)
|
||||
this.trailingCarriageReturn = true
|
||||
}
|
||||
return normalizeTerminalText(complete)
|
||||
}
|
||||
|
||||
private enforcePendingBound(): void {
|
||||
|
||||
@@ -17,7 +17,7 @@ import type {
|
||||
PtyWaitReason,
|
||||
} from '@deepseek-ai/dsh-pty'
|
||||
import type { ResolvedConfig } from './config.ts'
|
||||
import type { ProcessInspector } from './process-inspector.ts'
|
||||
import type { ProcessIdentity, ProcessInspector } from './process-inspector.ts'
|
||||
import { TerminalSanitizer } from './sanitize.ts'
|
||||
|
||||
function delay(ms: number): Promise<void> {
|
||||
@@ -148,9 +148,11 @@ export class LocalPtySession implements PtyBackendSession {
|
||||
private activeTimer: NodeJS.Timeout | undefined
|
||||
private activeAbort: (() => void) | undefined
|
||||
private promptSeen = false
|
||||
private promptTextSeen = false
|
||||
private shellPgid: number | undefined
|
||||
private initializing = false
|
||||
private lastOutputAt = Date.now()
|
||||
private closing = false
|
||||
private closePromise: Promise<void> | undefined
|
||||
|
||||
constructor(
|
||||
@@ -184,27 +186,29 @@ export class LocalPtySession implements PtyBackendSession {
|
||||
if (result.waitReason === 'session_exit') throw new Error('PTY shell exited during startup')
|
||||
if (result.waitReason === 'timeout') throw new Error('PTY shell did not reach readiness before startup timeout')
|
||||
this.motd = result.viewport
|
||||
} catch (error: unknown) {
|
||||
signal?.throwIfAborted()
|
||||
throw error
|
||||
} finally {
|
||||
this.initializing = false
|
||||
}
|
||||
}
|
||||
|
||||
startSend(request: PtySendRequest): PtySendOperation {
|
||||
if (this.closePromise !== undefined) throw new Error('PTY session is closing')
|
||||
if (this.closing) throw new Error('PTY session is closing')
|
||||
if (this.statusValue.kind === 'exited') throw new Error('PTY session has exited')
|
||||
if (this.active !== undefined) throw new Error('PTY session already has an active send')
|
||||
if (request.signal?.aborted === true) throw new Error('PTY send aborted before write')
|
||||
|
||||
const operation = new LocalSendOperation(this.config.maxReadBytes, Date.now(), () => {
|
||||
try {
|
||||
this.terminal.write('\x03')
|
||||
} catch (error: unknown) {
|
||||
operation.fail(error)
|
||||
}
|
||||
})
|
||||
const operation = new LocalSendOperation(
|
||||
this.config.maxReadBytes,
|
||||
Date.now(),
|
||||
() => { this.interrupt(operation) },
|
||||
)
|
||||
this.active = operation
|
||||
this.lastOutputAt = Date.now()
|
||||
this.promptSeen = false
|
||||
this.promptTextSeen = false
|
||||
|
||||
if (request.signal !== undefined) {
|
||||
const onAbort = (): void => { operation.cancel() }
|
||||
@@ -267,8 +271,15 @@ export class LocalPtySession implements PtyBackendSession {
|
||||
}
|
||||
|
||||
close(reason: string): Promise<void> {
|
||||
this.closePromise ??= this.closeOnce(reason)
|
||||
return this.closePromise
|
||||
this.closing = true
|
||||
if (this.closePromise !== undefined) return this.closePromise
|
||||
const closing = this.closeOnce(reason).catch((error: unknown) => {
|
||||
this.closePromise = undefined
|
||||
this.failActive(error)
|
||||
throw error
|
||||
})
|
||||
this.closePromise = closing
|
||||
return closing
|
||||
}
|
||||
|
||||
private onData(data: string): void {
|
||||
@@ -279,8 +290,11 @@ export class LocalPtySession implements PtyBackendSession {
|
||||
if (this.shellPgid === undefined) this.shellPgid = foregroundPgid
|
||||
if (foregroundPgid !== undefined && foregroundPgid === this.shellPgid) {
|
||||
this.promptSeen = true
|
||||
this.promptTextSeen = sanitized.promptText === true
|
||||
this.lastOutputAt = Date.now()
|
||||
}
|
||||
} else if (this.promptSeen && sanitized.promptText === true) {
|
||||
this.promptTextSeen = true
|
||||
}
|
||||
}
|
||||
|
||||
@@ -297,7 +311,7 @@ export class LocalPtySession implements PtyBackendSession {
|
||||
this.settleActive('session_exit')
|
||||
return
|
||||
}
|
||||
if (this.promptSeen && Date.now() - this.lastOutputAt >= this.config.pollIntervalMs) {
|
||||
if (this.promptSeen && this.promptTextSeen && Date.now() - this.lastOutputAt >= this.config.pollIntervalMs) {
|
||||
this.settleActive('stdin_read')
|
||||
return
|
||||
}
|
||||
@@ -337,58 +351,113 @@ export class LocalPtySession implements PtyBackendSession {
|
||||
this.active = undefined
|
||||
}
|
||||
|
||||
private failActive(error: unknown): void {
|
||||
const operation = this.active
|
||||
if (operation === undefined) return
|
||||
this.clearActive()
|
||||
operation.fail(error)
|
||||
}
|
||||
|
||||
private interrupt(operation: LocalSendOperation): void {
|
||||
if (this.active !== operation) return
|
||||
try {
|
||||
const pgid = this.inspector.foregroundPgid(this.pid)
|
||||
if (pgid === undefined) throw new Error(`cannot resolve foreground process group for PTY ${this.pid}`)
|
||||
this.inspector.signalGroup(pgid, 'SIGINT')
|
||||
} catch (error: unknown) {
|
||||
this.failActive(error)
|
||||
}
|
||||
}
|
||||
|
||||
private survivors(members: ProcessIdentity[]): ProcessIdentity[] {
|
||||
return members.filter(member => this.inspector.isAlive(member))
|
||||
}
|
||||
|
||||
private descendants(): ProcessIdentity[] {
|
||||
return this.inspector.processTree(this.pid).filter(member => member.pid !== this.pid)
|
||||
}
|
||||
|
||||
private async waitForExit(members: ProcessIdentity[]): Promise<ProcessIdentity[]> {
|
||||
const deadline = Date.now() + this.config.disposeGraceMs
|
||||
let survivors = this.survivors(members)
|
||||
while (survivors.length > 0 && Date.now() < deadline) {
|
||||
await delay(Math.min(25, Math.max(1, deadline - Date.now())))
|
||||
survivors = this.survivors(members)
|
||||
}
|
||||
return survivors
|
||||
}
|
||||
|
||||
private signalMembers(members: ProcessIdentity[], signal: 'SIGTERM' | 'SIGKILL'): void {
|
||||
for (const member of members) {
|
||||
try {
|
||||
this.inspector.signalProcess(member, signal)
|
||||
} catch (_alreadyExitedDuringSignal) {
|
||||
// Identity is rechecked by the inspector; a same-tick exit is success.
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private unionMembers(...groups: ProcessIdentity[][]): ProcessIdentity[] {
|
||||
const members: ProcessIdentity[] = []
|
||||
const seen = new Set<string>()
|
||||
for (const group of groups) {
|
||||
for (const member of group) {
|
||||
const key = JSON.stringify([member.pid, member.started])
|
||||
if (seen.has(key)) continue
|
||||
seen.add(key)
|
||||
members.push(member)
|
||||
}
|
||||
}
|
||||
return members
|
||||
}
|
||||
|
||||
private async stopDescendants(): Promise<ProcessIdentity[]> {
|
||||
const captured = this.descendants()
|
||||
this.signalMembers(captured, 'SIGTERM')
|
||||
const capturedSurvivors = await this.waitForExit(captured)
|
||||
// A TERM-handling descendant may have forked while winding down. Rescan
|
||||
// while the shell can still reap every member, then kill both the fresh
|
||||
// tree and captured survivors that were reparented out of that tree.
|
||||
const members = this.unionMembers(capturedSurvivors, this.descendants())
|
||||
this.signalMembers(members, 'SIGKILL')
|
||||
const survivors = await this.waitForExit(members)
|
||||
return this.survivors(this.unionMembers(survivors, this.descendants()))
|
||||
}
|
||||
|
||||
private async stopShell(): Promise<void> {
|
||||
try {
|
||||
this.terminal.kill('SIGTERM')
|
||||
} catch (_topLevelAlreadyExitedDuringTerm) {
|
||||
// The exit notification remains authoritative.
|
||||
}
|
||||
if (this.statusValue.kind === 'running') {
|
||||
await Promise.race([this.exitPromise.promise, delay(this.config.disposeGraceMs)])
|
||||
}
|
||||
if (this.statusValue.kind === 'running') {
|
||||
try {
|
||||
this.terminal.kill('SIGKILL')
|
||||
} catch (_topLevelAlreadyExitedDuringKill) {
|
||||
// The exit notification remains authoritative.
|
||||
}
|
||||
await Promise.race([this.exitPromise.promise, delay(this.config.disposeGraceMs)])
|
||||
}
|
||||
if (this.statusValue.kind === 'running') {
|
||||
throw new Error(`PTY cleanup failed; surviving pids: ${this.pid}`)
|
||||
}
|
||||
}
|
||||
|
||||
private async closeOnce(reason: string): Promise<void> {
|
||||
this.dataDisposable.dispose()
|
||||
// Stop readiness polling but retain the active operation: teardown settles
|
||||
// it as session_exit below, so an in-flight send is never mis-settled as
|
||||
// stdin_read/inferred_idle/timeout during the grace period.
|
||||
this.stopPolling()
|
||||
const members = this.inspector.processTree(this.pid)
|
||||
for (const member of members) {
|
||||
try {
|
||||
this.inspector.signalProcess(member, 'SIGTERM')
|
||||
} catch (_alreadyExitedDuringTerm) {
|
||||
// Identity is rechecked by the inspector; a same-tick exit is success.
|
||||
}
|
||||
}
|
||||
try {
|
||||
this.terminal.kill('SIGTERM')
|
||||
} catch (_topLevelAlreadyExited) {
|
||||
// onExit or identity checks below remain authoritative.
|
||||
}
|
||||
|
||||
const deadline = Date.now() + this.config.disposeGraceMs
|
||||
let survivors = members.filter(member => this.inspector.isAlive(member))
|
||||
while (survivors.length > 0 && Date.now() < deadline) {
|
||||
await delay(Math.min(25, this.config.disposeGraceMs))
|
||||
survivors = members.filter(member => this.inspector.isAlive(member))
|
||||
}
|
||||
for (const survivor of survivors) {
|
||||
try {
|
||||
this.inspector.signalProcess(survivor, 'SIGKILL')
|
||||
} catch (_alreadyExitedDuringKill) {
|
||||
// Final identity check below decides success.
|
||||
}
|
||||
}
|
||||
try {
|
||||
this.terminal.kill('SIGKILL')
|
||||
} catch (_topLevelAlreadyKilled) {
|
||||
// The root may already have delivered onExit.
|
||||
}
|
||||
|
||||
const killDeadline = Date.now() + this.config.disposeGraceMs
|
||||
survivors = members.filter(member => this.inspector.isAlive(member))
|
||||
while (survivors.length > 0 && Date.now() < killDeadline) {
|
||||
await delay(Math.min(25, this.config.disposeGraceMs))
|
||||
survivors = members.filter(member => this.inspector.isAlive(member))
|
||||
}
|
||||
const exitWaitMs = Math.max(0, killDeadline - Date.now())
|
||||
await Promise.race([this.exitPromise.promise, delay(exitWaitMs)])
|
||||
survivors = members.filter(member => this.inspector.isAlive(member))
|
||||
this.settleActive('session_exit')
|
||||
this.exitDisposable.dispose()
|
||||
const survivors = await this.stopDescendants()
|
||||
if (survivors.length > 0) {
|
||||
throw new Error(`PTY cleanup failed (${reason}); surviving pids: ${survivors.map(member => member.pid).join(', ')}`)
|
||||
}
|
||||
await this.stopShell()
|
||||
this.settleActive('session_exit')
|
||||
this.exitDisposable.dispose()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -2,12 +2,13 @@ import { describe, expect, it, vi } from 'vitest'
|
||||
import type { IPty, IPtyForkOptions } from 'node-pty'
|
||||
import { Context } from 'cordis'
|
||||
import Loader from '@cordisjs/plugin-loader'
|
||||
import { Session, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import AgentRegistry from '@deepseek-ai/dsh-agent'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import SandboxProvider from '@deepseek-ai/dsh-sandbox'
|
||||
import type { ConfinedArgv, SandboxPolicy } from '@deepseek-ai/dsh-sandbox'
|
||||
import SandboxPolicyService from '@deepseek-ai/dsh-sandbox-policy'
|
||||
import PtyService, { PtySessionId } from '@deepseek-ai/dsh-pty'
|
||||
import SandboxPolicyService, { setSandboxMode } from '@deepseek-ai/dsh-sandbox-policy'
|
||||
import PtyService, { PtyBackendCleanupError, PtySessionId } from '@deepseek-ai/dsh-pty'
|
||||
import { LocalPtyBackend } from '@deepseek-ai/dsh-pty-local'
|
||||
import * as ptyLocal from '@deepseek-ai/dsh-pty-local'
|
||||
import type { ResolvedConfig } from '@deepseek-ai/dsh-pty-local/src/config.ts'
|
||||
@@ -62,6 +63,30 @@ function spec(owner: Agent, signal?: AbortSignal) {
|
||||
}
|
||||
}
|
||||
|
||||
function stubLocalSession(initialize: () => Promise<void> = () => Promise.resolve()): LocalPtySession {
|
||||
return {
|
||||
motd: '',
|
||||
initialize,
|
||||
startSend: () => { throw new Error('unused') },
|
||||
read: () => { throw new Error('unused') },
|
||||
signal: () => Promise.resolve({ delivered: true, targetPgid: 1 }),
|
||||
status: () => ({ kind: 'running' as const }),
|
||||
close: () => Promise.resolve(),
|
||||
} as unknown as LocalPtySession
|
||||
}
|
||||
|
||||
function registerStubLocalBackend(ctx: Context, createSession: () => LocalPtySession) {
|
||||
return ctx.inject(['pty', 'sandbox', 'sandboxPolicy'], (providerCtx) => {
|
||||
providerCtx.pty.registerBackend(new LocalPtyBackend(
|
||||
providerCtx,
|
||||
{ ...config(), backendType: 'stub' },
|
||||
inspector,
|
||||
(() => ({})) as never,
|
||||
createSession,
|
||||
))
|
||||
})
|
||||
}
|
||||
|
||||
describe('LocalPtyBackend startup rollback', () => {
|
||||
it('rejects pre-aborted setup and empty sandbox argv', async () => {
|
||||
const ctx = new Context()
|
||||
@@ -69,8 +94,9 @@ describe('LocalPtyBackend startup rollback', () => {
|
||||
await ctx.plugin(SandboxPolicyService, { mode: 'read-only', workspaceRoot: '/tmp' })
|
||||
const backend = new LocalPtyBackend(ctx, config(), inspector)
|
||||
const controller = new AbortController()
|
||||
controller.abort()
|
||||
await expect(backend.spawn(spec(agent(ctx), controller.signal))).rejects.toThrow('spawn aborted')
|
||||
const abortReason = new Error('spawn aborted')
|
||||
controller.abort(abortReason)
|
||||
await expect(backend.spawn(spec(agent(ctx), controller.signal))).rejects.toBe(abortReason)
|
||||
await expect(backend.spawn(spec(agent(ctx)))).rejects.toThrow('empty argv')
|
||||
})
|
||||
|
||||
@@ -86,12 +112,18 @@ describe('LocalPtyBackend startup rollback', () => {
|
||||
await expect(backend.spawn(spec(agent(ctx)))).rejects.toThrow('startup failed')
|
||||
expect(closed).toHaveBeenCalledWith('PTY startup failed')
|
||||
|
||||
const startupFailure = new Error('startup failed')
|
||||
const cleanupFailure = new Error('cleanup failed')
|
||||
const doublyFailed = {
|
||||
initialize: () => Promise.reject(new Error('startup failed')),
|
||||
close: () => Promise.reject(new Error('cleanup failed')),
|
||||
initialize: () => Promise.reject(startupFailure),
|
||||
close: () => Promise.reject(cleanupFailure),
|
||||
} as unknown as LocalPtySession
|
||||
const aggregate = new LocalPtyBackend(ctx, config(), inspector, spawnTerminal, () => doublyFailed)
|
||||
await expect(aggregate.spawn(spec(agent(ctx)))).rejects.toThrow('startup and cleanup both failed')
|
||||
await expect(aggregate.spawn(spec(agent(ctx)))).rejects.toEqual(expect.objectContaining({
|
||||
name: 'PtyBackendCleanupError',
|
||||
spawnError: startupFailure,
|
||||
cleanupError: cleanupFailure,
|
||||
} satisfies Partial<PtyBackendCleanupError>))
|
||||
})
|
||||
|
||||
it('wraps confined argv, scrubs the environment, and returns initialized sessions', async () => {
|
||||
@@ -175,6 +207,7 @@ describe('pty-local plugin shape', () => {
|
||||
|
||||
it('validates config and registers the configured backend', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(PtyService)
|
||||
await ctx.plugin(EmptySandbox)
|
||||
await ctx.plugin(SandboxPolicyService, { mode: 'danger-full-access', workspaceRoot: '/tmp' })
|
||||
@@ -183,4 +216,90 @@ describe('pty-local plugin shape', () => {
|
||||
await fiber.dispose()
|
||||
expect(ctx.pty.listBackends()).toEqual([])
|
||||
})
|
||||
|
||||
it('ignores unrelated session events and mode changes without a live owner', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(PtyService)
|
||||
await ctx.plugin(EmptySandbox)
|
||||
await ctx.plugin(SandboxPolicyService, { mode: 'danger-full-access', workspaceRoot: '/tmp' })
|
||||
await ctx.plugin(ptyLocal, config())
|
||||
|
||||
const session = ctx.sessions.create(SessionId('unowned-mode'))
|
||||
expect(() => {
|
||||
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
}).not.toThrow()
|
||||
expect(() => { setSandboxMode(session, 'read-only') }).not.toThrow()
|
||||
})
|
||||
|
||||
it('keeps the owner-lifetime sandbox fence after the local provider unloads', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(PtyService)
|
||||
await ctx.plugin(RecordingSandbox)
|
||||
await ctx.plugin(SandboxPolicyService, { mode: 'danger-full-access', workspaceRoot: '/tmp' })
|
||||
|
||||
const session = ctx.sessions.create(SessionId('mode-owner'))
|
||||
const ownerFiber = await ctx.plugin(() => {})
|
||||
const owner: Agent = {
|
||||
id: session.id, options: {}, session, status: 'idle', ctx: ownerFiber.ctx,
|
||||
send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(),
|
||||
}
|
||||
ctx.agents.register(owner)
|
||||
const providerFiber = await registerStubLocalBackend(ctx, () => stubLocalSession())
|
||||
const created = await ctx.pty.spawn(owner, { type: 'stub' })
|
||||
|
||||
const unrelated = ctx.sessions.create(SessionId('unrelated-mode'))
|
||||
expect(() => { setSandboxMode(unrelated, 'read-only') }).not.toThrow()
|
||||
expect(() => {
|
||||
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
}).not.toThrow()
|
||||
|
||||
expect(() => { setSandboxMode(session, 'danger-full-access') }).not.toThrow()
|
||||
await providerFiber.dispose()
|
||||
expect(ctx.pty.listBackends()).toEqual([])
|
||||
expect(() => { setSandboxMode(session, 'read-only') }).toThrow(
|
||||
'cannot change sandbox mode from "danger-full-access" to "read-only" while persistent terminal sessions are open or being created; wait for creation to settle and close them first',
|
||||
)
|
||||
expect(session.events.filter(event => event.type === 'sandbox/mode')).toHaveLength(1)
|
||||
|
||||
const replacementFiber = await registerStubLocalBackend(ctx, () => stubLocalSession())
|
||||
const second = await ctx.pty.spawn(owner, { type: 'stub' })
|
||||
await replacementFiber.dispose()
|
||||
expect(() => { setSandboxMode(session, 'read-only') }).toThrow('open or being created')
|
||||
|
||||
await ctx.pty.kill(owner, created.sessionId)
|
||||
await ctx.pty.kill(owner, second.sessionId)
|
||||
expect(() => { setSandboxMode(session, 'read-only') }).not.toThrow()
|
||||
expect(session.events.filter(event => event.type === 'sandbox/mode')).toHaveLength(2)
|
||||
})
|
||||
|
||||
it('also fences sandbox-mode changes across unpublished PTY creation', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(PtyService)
|
||||
await ctx.plugin(RecordingSandbox)
|
||||
await ctx.plugin(SandboxPolicyService, { mode: 'danger-full-access', workspaceRoot: '/tmp' })
|
||||
|
||||
const session = ctx.sessions.create(SessionId('pending-mode-owner'))
|
||||
const ownerFiber = await ctx.plugin(() => {})
|
||||
const owner: Agent = {
|
||||
id: session.id, options: {}, session, status: 'idle', ctx: ownerFiber.ctx,
|
||||
send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(),
|
||||
}
|
||||
ctx.agents.register(owner)
|
||||
const gate = Promise.withResolvers<undefined>()
|
||||
await registerStubLocalBackend(ctx, () => stubLocalSession(() => gate.promise))
|
||||
const spawning = ctx.pty.spawn(owner, { type: 'stub' })
|
||||
|
||||
expect(ctx.pty.hasOwnerActivity(owner)).toBe(true)
|
||||
expect(() => { setSandboxMode(session, 'read-only') }).toThrow('open or being created')
|
||||
gate.resolve(undefined)
|
||||
const created = await spawning
|
||||
await ctx.pty.kill(owner, created.sessionId)
|
||||
expect(ctx.pty.hasOwnerActivity(owner)).toBe(false)
|
||||
})
|
||||
})
|
||||
|
||||
@@ -7,6 +7,7 @@ import { Session, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import AgentRegistry from '@deepseek-ai/dsh-agent'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import PtyService from '@deepseek-ai/dsh-pty'
|
||||
import type { PtySendOperation } from '@deepseek-ai/dsh-pty'
|
||||
import SandboxProvider from '@deepseek-ai/dsh-sandbox'
|
||||
import type { ConfinedArgv, SandboxPolicy } from '@deepseek-ai/dsh-sandbox'
|
||||
import SandboxPolicyService from '@deepseek-ai/dsh-sandbox-policy'
|
||||
@@ -62,6 +63,16 @@ async function harness(mode: 'danger-full-access' | 'workspace-write') {
|
||||
return { ctx, root, agent, fiber, sandbox: ctx.sandbox as PassthroughSandbox }
|
||||
}
|
||||
|
||||
async function waitForOutput(operation: PtySendOperation, expected: string): Promise<void> {
|
||||
const deadline = Date.now() + 2_000
|
||||
let output = ''
|
||||
while (!output.includes(expected) && Date.now() < deadline) {
|
||||
output += operation.readOutput().delta
|
||||
if (!output.includes(expected)) await new Promise(resolve => setTimeout(resolve, 10))
|
||||
}
|
||||
expect(output).toContain(expected)
|
||||
}
|
||||
|
||||
describe('pty-local real shell', () => {
|
||||
it('persists cwd and environment across sends, scrubs secrets, and closes', async () => {
|
||||
const previous = process.env.DSH_TEST_SECRET
|
||||
@@ -119,4 +130,26 @@ describe('pty-local real shell', () => {
|
||||
await ctx.pty.kill(agent, created.sessionId)
|
||||
expect(() => process.kill(pid, 0)).toThrow()
|
||||
}, 10_000)
|
||||
|
||||
it('cancels a raw-mode foreground process with a real SIGINT', async () => {
|
||||
const { ctx, agent } = await harness('danger-full-access')
|
||||
const created = await ctx.pty.spawn(agent, { type: 'shell' })
|
||||
const controller = new AbortController()
|
||||
const foreground = ctx.pty.startSend(agent, created.sessionId, {
|
||||
text: 'python3 -c \'import signal,sys,termios,time; signal.signal(signal.SIGINT, lambda *_: (print("SIGINT_SEEN", flush=True), sys.exit(0))); attrs=termios.tcgetattr(0); attrs[3] &= ~termios.ISIG; termios.tcsetattr(0, termios.TCSANOW, attrs); print("RAW_READY", flush=True); time.sleep(60)\'',
|
||||
submit: true,
|
||||
signal: controller.signal,
|
||||
})
|
||||
await waitForOutput(foreground, 'RAW_READY')
|
||||
controller.abort()
|
||||
const result = await foreground.done
|
||||
expect(result.waitReason).toBe('stdin_read')
|
||||
const after = await ctx.pty.startSend(agent, created.sessionId, {
|
||||
text: 'echo AFTER_SIGINT',
|
||||
submit: true,
|
||||
}).done
|
||||
expect(after.viewport).toContain('AFTER_SIGINT')
|
||||
expect(after.waitReason).toBe('stdin_read')
|
||||
await ctx.pty.kill(agent, created.sessionId)
|
||||
}, 10_000)
|
||||
})
|
||||
|
||||
@@ -2,8 +2,8 @@ import { describe, expect, it } from 'vitest'
|
||||
import { createProcessInspector, parseProcStat } from '@deepseek-ai/dsh-pty-local/src/process-inspector.ts'
|
||||
import type { ProcessInspectorInternals } from '@deepseek-ai/dsh-pty-local/src/process-inspector.ts'
|
||||
|
||||
function stat(pid: number, pgrp: number, session: number, tpgid: number, started: string, parentPid = 1): string {
|
||||
const rest = ['S', String(parentPid), String(pgrp), String(session), '99', String(tpgid)]
|
||||
function stat(pid: number, pgrp: number, session: number, tpgid: number, started: string, parentPid = 1, state = 'S'): string {
|
||||
const rest = [state, String(parentPid), String(pgrp), String(session), '99', String(tpgid)]
|
||||
while (rest.length < 19) rest.push('0')
|
||||
rest.push(started)
|
||||
return `${pid} (command with space) ${rest.join(' ')}`
|
||||
@@ -65,8 +65,10 @@ function fakeInternals() {
|
||||
describe('Linux process inspector', () => {
|
||||
it('parses stat safely, captures only the rooted process tree, and signals identities', () => {
|
||||
expect(parseProcStat('bad')).toBeUndefined()
|
||||
expect(parseProcStat('1 () ')).toBeUndefined()
|
||||
expect(parseProcStat('1 () S')).toBeUndefined()
|
||||
expect(parseProcStat(stat(10, 20, 30, 40, '500'))).toEqual({ pid: 10, parentPid: 1, pgrp: 20, session: 30, tpgid: 40, started: '500' })
|
||||
expect(parseProcStat(stat(10, 20, 30, 40, '500', 1, 'SS'))).toBeUndefined()
|
||||
expect(parseProcStat(stat(10, 20, 30, 40, '500'))).toEqual({ pid: 10, parentPid: 1, pgrp: 20, session: 30, state: 'S', tpgid: 40, started: '500' })
|
||||
|
||||
const fake = fakeInternals()
|
||||
fake.dirs.set('/proc', ['x', '10', '11', '12', '13', '14'])
|
||||
@@ -90,6 +92,10 @@ describe('Linux process inspector', () => {
|
||||
inspector.signalProcess({ pid: 10, started: '500' }, 'SIGTERM')
|
||||
inspector.signalProcess({ pid: 10, started: 'old' }, 'SIGKILL')
|
||||
expect(fake.kills).toEqual([[-40, 'SIGINT'], [10, 'SIGTERM']])
|
||||
fake.files.set('/proc/10/stat', stat(10, 20, 30, 40, '500', 1, 'Z'))
|
||||
expect(inspector.isAlive({ pid: 10, started: '500' })).toBe(false)
|
||||
inspector.signalProcess({ pid: 10, started: '500' }, 'SIGKILL')
|
||||
expect(fake.kills).toEqual([[-40, 'SIGINT'], [10, 'SIGTERM']])
|
||||
})
|
||||
|
||||
it('detects read, select, poll, and epoll waits across non-leader threads', () => {
|
||||
|
||||
@@ -7,7 +7,7 @@ describe('TerminalSanitizer', () => {
|
||||
expect(sanitizer.push('red\x1b[3')).toEqual({ text: 'red', prompt: false })
|
||||
expect(sanitizer.push('1m text\x1b[0m\r\n')).toEqual({ text: ' text\n', prompt: false })
|
||||
expect(sanitizer.push('\x1b]133;')).toEqual({ text: '', prompt: false })
|
||||
expect(sanitizer.push('D;0\x07dsh> ')).toEqual({ text: 'dsh> ', prompt: true })
|
||||
expect(sanitizer.push('D;0\x07dsh> ')).toEqual({ text: 'dsh> ', prompt: true, promptText: true })
|
||||
})
|
||||
|
||||
it('drops unrelated OSC, short escapes, BEL, and incomplete trailing escape', () => {
|
||||
@@ -25,6 +25,20 @@ describe('TerminalSanitizer', () => {
|
||||
expect(normalizeTerminalText('a\r\nb\rc\x07')).toBe('a\nb\nc')
|
||||
})
|
||||
|
||||
it('carries a trailing carriage return across data chunks and flushes standalone CR', () => {
|
||||
const sanitizer = new TerminalSanitizer(64)
|
||||
expect(sanitizer.push('a\r')).toEqual({ text: 'a', prompt: false })
|
||||
expect(sanitizer.push('\nb')).toEqual({ text: '\nb', prompt: false })
|
||||
expect(sanitizer.push('\r')).toEqual({ text: '', prompt: false })
|
||||
expect(sanitizer.flush()).toBe('\n')
|
||||
})
|
||||
|
||||
it('reports printable prompt text that follows a marker in a later chunk', () => {
|
||||
const sanitizer = new TerminalSanitizer(64)
|
||||
expect(sanitizer.push('\x1b]133;D;0\x07')).toEqual({ text: '', prompt: true })
|
||||
expect(sanitizer.push('dsh> ')).toEqual({ text: 'dsh> ', prompt: false, promptText: true })
|
||||
})
|
||||
|
||||
it('bounds and discards unterminated control sequences through their terminators', () => {
|
||||
const oscBel = new TerminalSanitizer(8)
|
||||
expect(oscBel.push(`\x1b]0;${'x'.repeat(16)}`)).toEqual({ text: '', prompt: false })
|
||||
|
||||
@@ -15,6 +15,7 @@ class FakeTerminal {
|
||||
kills: string[] = []
|
||||
throwWrite = false
|
||||
throwKill = false
|
||||
autoExitOnKill = true
|
||||
private dataListeners = new Set<(data: string) => void>()
|
||||
private exitListeners = new Set<(event: { exitCode: number; signal?: number }) => void>()
|
||||
|
||||
@@ -44,7 +45,7 @@ class FakeTerminal {
|
||||
kill(signal?: string): void {
|
||||
if (this.throwKill) throw new Error('kill failed')
|
||||
this.kills.push(signal ?? 'SIGHUP')
|
||||
this.emitExit(0, signal === 'SIGKILL' ? 9 : 15)
|
||||
if (this.autoExitOnKill) this.emitExit(0, signal === 'SIGKILL' ? 9 : 15)
|
||||
}
|
||||
|
||||
resize() {}
|
||||
@@ -148,7 +149,7 @@ describe('LocalPtySession readiness and output', () => {
|
||||
expect(() => session.startSend({ text: '', submit: false })).toThrow('has exited')
|
||||
})
|
||||
|
||||
it('cancels with Ctrl-C, observes AbortSignal, and contains write failures', async () => {
|
||||
it('cancels with foreground-group SIGINT, observes AbortSignal, and contains write failures', async () => {
|
||||
vi.useFakeTimers()
|
||||
const terminal = new FakeTerminal()
|
||||
const inspector = new FakeInspector()
|
||||
@@ -159,7 +160,8 @@ describe('LocalPtySession readiness and output', () => {
|
||||
const operation = session.startSend({ text: 'sleep', submit: true, signal: controller.signal })
|
||||
expect(() => session.startSend({ text: 'again', submit: true })).toThrow('active send')
|
||||
controller.abort()
|
||||
expect(terminal.writes.at(-1)).toBe('\x03')
|
||||
expect(inspector.groups).toContainEqual([456, 'SIGINT'])
|
||||
expect(terminal.writes).not.toContain('\x03')
|
||||
terminal.emitData('\x1b]133;D;130\x07dsh> ')
|
||||
await vi.advanceTimersByTimeAsync(10)
|
||||
await operation.done
|
||||
@@ -196,11 +198,13 @@ describe('LocalPtySession readiness and output', () => {
|
||||
operationInternal.append('')
|
||||
const sessionInternal = session as unknown as {
|
||||
pollReadiness(operation: PtySendOperation): void
|
||||
interrupt(operation: PtySendOperation): void
|
||||
statusValue: PtySessionStatus
|
||||
appendOutput(text: string): void
|
||||
}
|
||||
sessionInternal.appendOutput('')
|
||||
sessionInternal.pollReadiness({} as PtySendOperation)
|
||||
sessionInternal.interrupt({} as PtySendOperation)
|
||||
sessionInternal.statusValue = { kind: 'exited', exitCode: 2, signal: null }
|
||||
sessionInternal.pollReadiness(operation)
|
||||
await operation.done
|
||||
@@ -212,12 +216,23 @@ describe('LocalPtySession readiness and output', () => {
|
||||
expect(unknown.status()).toEqual({ kind: 'exited', exitCode: 1, signal: null })
|
||||
|
||||
const cancelTerminal = new FakeTerminal()
|
||||
const cancel = new LocalPtySession(cancelTerminal.asPty(), new FakeInspector(), config())
|
||||
const cancelInspector = new FakeInspector()
|
||||
const cancel = new LocalPtySession(cancelTerminal.asPty(), cancelInspector, config())
|
||||
await initialize(cancel, cancelTerminal)
|
||||
const cancellable = cancel.startSend({ text: '', submit: false })
|
||||
cancelTerminal.throwWrite = true
|
||||
cancelInspector.throwGroup = true
|
||||
expect(cancellable.cancel()).toBe(true)
|
||||
await expect(cancellable.done).rejects.toThrow('write failed')
|
||||
await expect(cancellable.done).rejects.toThrow('group failed')
|
||||
expect(cancellable.cancel()).toBe(false)
|
||||
|
||||
const missingGroupTerminal = new FakeTerminal()
|
||||
const missingGroupInspector = new FakeInspector()
|
||||
const missingGroup = new LocalPtySession(missingGroupTerminal.asPty(), missingGroupInspector, config())
|
||||
await initialize(missingGroup, missingGroupTerminal)
|
||||
missingGroupInspector.pgid = undefined
|
||||
const unresolved = missingGroup.startSend({ text: '', submit: false })
|
||||
expect(unresolved.cancel()).toBe(true)
|
||||
await expect(unresolved.done).rejects.toThrow('cannot resolve foreground process group')
|
||||
})
|
||||
|
||||
it('does not treat zero-output startup silence as readiness and fails on startup timeout', async () => {
|
||||
@@ -239,6 +254,38 @@ describe('LocalPtySession readiness and output', () => {
|
||||
await timedOut
|
||||
})
|
||||
|
||||
it('preserves the caller abort reason when startup cannot resolve a foreground group', async () => {
|
||||
const terminal = new FakeTerminal()
|
||||
const inspector = new FakeInspector()
|
||||
inspector.pgid = undefined
|
||||
const session = new LocalPtySession(terminal.asPty(), inspector, config())
|
||||
const controller = new AbortController()
|
||||
const reason = new Error('startup cancelled')
|
||||
|
||||
const initializing = session.initialize(controller.signal)
|
||||
const rejected = expect(initializing).rejects.toBe(reason)
|
||||
controller.abort(reason)
|
||||
|
||||
await rejected
|
||||
})
|
||||
|
||||
it('waits for printable prompt text when the startup marker is split from PS1', async () => {
|
||||
vi.useFakeTimers()
|
||||
const terminal = new FakeTerminal()
|
||||
const session = new LocalPtySession(terminal.asPty(), new FakeInspector(), config())
|
||||
let settled = false
|
||||
const initializing = session.initialize().then(() => { settled = true })
|
||||
|
||||
terminal.emitData('\x1b]133;D;0\x07')
|
||||
await vi.advanceTimersByTimeAsync(20)
|
||||
expect(settled).toBe(false)
|
||||
|
||||
terminal.emitData('dsh> ')
|
||||
await vi.advanceTimersByTimeAsync(10)
|
||||
await initializing
|
||||
expect(session.motd).toBe('dsh> ')
|
||||
})
|
||||
|
||||
it('trusts prompt markers only while the startup shell owns the foreground group', async () => {
|
||||
vi.useFakeTimers()
|
||||
const terminal = new FakeTerminal()
|
||||
@@ -328,14 +375,15 @@ describe('LocalPtySession bounds, signals, and teardown', () => {
|
||||
// readiness poll would otherwise mis-settle this as stdin_read once close
|
||||
// begins, so teardown must stop polling before its grace period.
|
||||
terminal.emitData('\x1b]133;D;0\x07dsh> ')
|
||||
terminal.throwKill = true
|
||||
terminal.autoExitOnKill = false
|
||||
const closing = session.close('mid-send')
|
||||
await vi.advanceTimersByTimeAsync(60)
|
||||
await vi.advanceTimersByTimeAsync(20)
|
||||
terminal.emitExit(0, 15)
|
||||
expect((await operation.done).waitReason).toBe('session_exit')
|
||||
await closing
|
||||
})
|
||||
|
||||
it('waits for SIGKILL recipients to leave the process table after the shell exits', async () => {
|
||||
it('keeps the shell alive until SIGKILL recipients leave the process table', async () => {
|
||||
vi.useFakeTimers()
|
||||
const terminal = new FakeTerminal()
|
||||
const inspector = new FakeInspector()
|
||||
@@ -348,11 +396,81 @@ describe('LocalPtySession bounds, signals, and teardown', () => {
|
||||
const closing = session.close('test').then(() => { settled = true })
|
||||
await vi.advanceTimersByTimeAsync(20)
|
||||
expect(inspector.processes).toContainEqual([124, 'SIGKILL'])
|
||||
expect(terminal.kills).toEqual([])
|
||||
expect(settled).toBe(false)
|
||||
|
||||
inspector.alive.delete(124)
|
||||
await vi.advanceTimersByTimeAsync(20)
|
||||
await closing
|
||||
expect(terminal.kills).toEqual(['SIGTERM'])
|
||||
expect(settled).toBe(true)
|
||||
})
|
||||
|
||||
it('rescans for descendants forked during TERM before stopping the shell', async () => {
|
||||
const terminal = new FakeTerminal()
|
||||
const inspector = new FakeInspector()
|
||||
let reads = 0
|
||||
inspector.processTree = () => {
|
||||
reads += 1
|
||||
if (reads === 1) {
|
||||
inspector.alive.add(124)
|
||||
return [{ pid: 124, started: 'first' }]
|
||||
}
|
||||
if (reads === 2) {
|
||||
inspector.alive.add(125)
|
||||
return [{ pid: 125, started: 'late' }]
|
||||
}
|
||||
return []
|
||||
}
|
||||
const session = new LocalPtySession(terminal.asPty(), inspector, config())
|
||||
|
||||
await session.close('test')
|
||||
|
||||
expect(inspector.processes).toEqual([[124, 'SIGTERM'], [125, 'SIGKILL']])
|
||||
expect(terminal.kills).toEqual(['SIGTERM'])
|
||||
})
|
||||
|
||||
it('retains captured survivors that are reparented out of the teardown rescan', async () => {
|
||||
vi.useFakeTimers()
|
||||
const terminal = new FakeTerminal()
|
||||
const inspector = new FakeInspector()
|
||||
const captured = { pid: 124, started: 'captured' }
|
||||
let reads = 0
|
||||
inspector.alive.add(captured.pid)
|
||||
inspector.processTree = () => reads++ === 0 ? [captured] : []
|
||||
inspector.signalProcess = (identity, signal) => {
|
||||
inspector.processes.push([identity.pid, signal])
|
||||
if (signal === 'SIGKILL') inspector.alive.delete(identity.pid)
|
||||
}
|
||||
const session = new LocalPtySession(terminal.asPty(), inspector, config({ disposeGraceMs: 20 }))
|
||||
|
||||
const closing = session.close('test')
|
||||
await vi.advanceTimersByTimeAsync(25)
|
||||
await closing
|
||||
|
||||
expect(inspector.processes).toEqual([[124, 'SIGTERM'], [124, 'SIGKILL']])
|
||||
expect(terminal.kills).toEqual(['SIGTERM'])
|
||||
})
|
||||
|
||||
it('allows teardown to retry after a descendant-survivor failure', async () => {
|
||||
vi.useFakeTimers()
|
||||
const terminal = new FakeTerminal()
|
||||
const inspector = new FakeInspector()
|
||||
inspector.members = [{ pid: 124, started: 'child' }]
|
||||
inspector.alive.add(124)
|
||||
inspector.removeOnSignal = false
|
||||
const session = new LocalPtySession(terminal.asPty(), inspector, config({ disposeGraceMs: 10 }))
|
||||
|
||||
const first = session.close('first')
|
||||
const rejected = expect(first).rejects.toThrow('surviving pids: 124')
|
||||
await vi.advanceTimersByTimeAsync(25)
|
||||
await rejected
|
||||
expect(terminal.kills).toEqual([])
|
||||
|
||||
inspector.alive.delete(124)
|
||||
const second = session.close('retry')
|
||||
expect(second).not.toBe(first)
|
||||
await second
|
||||
expect(terminal.kills).toEqual(['SIGTERM'])
|
||||
})
|
||||
})
|
||||
|
||||
@@ -17,6 +17,12 @@
|
||||
{
|
||||
"path": "../../../vendor/schemastery"
|
||||
},
|
||||
{
|
||||
"path": "../../core/agent"
|
||||
},
|
||||
{
|
||||
"path": "../../core/session"
|
||||
},
|
||||
{
|
||||
"path": "../pty"
|
||||
},
|
||||
|
||||
@@ -4,11 +4,16 @@ Owner-scoped persistent PTY seam. `PtyService` registers as `ctx.pty`, mints opa
|
||||
|
||||
## Contract
|
||||
|
||||
- Backends register one stable `type` and return an unpublished `PtyBackendSession`; failed or cancelled setup must clean partial resources.
|
||||
- Backends register one stable `type` and return an unpublished `PtyBackendSession`; failed or cancelled setup must clean partial resources, and a failed cleanup rejects with `PtyBackendCleanupError` so the registry can retain it across cancellation.
|
||||
- Spawn cancellation preserves the caller's exact abort reason. Service disposal and owner loss remain distinct machine-routable failures after backend setup.
|
||||
- Owner and service disposal abort unpublished setup through a service-owned signal and await backend settlement plus rollback before returning.
|
||||
- A rollback-close or backend-reported startup cleanup failure rejects the disposing lifecycle instead of claiming quiescence. Caller-triggered cancellation still receives its exact reason; lifecycle-triggered rollback failure also rejects the pending spawn.
|
||||
- A backend cleanup failure that follows caller cancellation remains owner activity until owner or service disposal consumes and reports it, so lifecycle policy cannot mistake failed cleanup for quiescence.
|
||||
- `hasOwnerActivity(owner)` spans unpublished setup through final close, so lifecycle policy can fence the exact owner without a publication race.
|
||||
- A successful spawn publishes one `PtySessionId`. The optional `name` is owner-local display metadata, never authority.
|
||||
- One session accepts at most one live send operation. Reads and signals may observe it; another send fails until the operation settles.
|
||||
- `PtySendResult.waitReason` and `sessionStatus` are independent. `session_exit` describes the top-level PTY process, not an arbitrary foreground command.
|
||||
- `kill()` and disposal resolve only after the backend's captured process tree is quiescent. A cleanup failure rejects instead of claiming success.
|
||||
- `kill()` and disposal resolve only after the backend's captured process tree is quiescent. A cleanup failure rejects instead of claiming success and clears the matching backend and registry fences so a later close can retry without disturbing a newer attempt.
|
||||
|
||||
The seam contains no `node-pty`, sandbox, tool-schema, prompt, task, or terminal-rendering policy. Implementations own terminal mechanics; consumers own model presentation and optional background-task registration.
|
||||
|
||||
|
||||
@@ -6,6 +6,7 @@
|
||||
|
||||
import { Context, Service } from 'cordis'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import { PtyBackendCleanupError } from './types.ts'
|
||||
import type {
|
||||
PtyBackend,
|
||||
PtyBackendSession,
|
||||
@@ -39,6 +40,7 @@ export type {
|
||||
PtySpawnResult,
|
||||
PtyWaitReason,
|
||||
} from './types.ts'
|
||||
export { PtyBackendCleanupError } from './types.ts'
|
||||
|
||||
/** Opaque identity minted by {@link PtyService} for one live PTY session. */
|
||||
export type PtySessionId = PtySessionIdValue
|
||||
@@ -77,10 +79,6 @@ export function PtySessionId(value: string): PtySessionId {
|
||||
return value as PtySessionId
|
||||
}
|
||||
|
||||
function isAborted(signal: AbortSignal | undefined): boolean {
|
||||
return signal?.aborted === true
|
||||
}
|
||||
|
||||
interface SessionRecord {
|
||||
readonly id: PtySessionId
|
||||
readonly owner: Agent
|
||||
@@ -91,11 +89,24 @@ interface SessionRecord {
|
||||
closing: Promise<void> | undefined
|
||||
}
|
||||
|
||||
interface PendingSpawn {
|
||||
readonly owner: Agent
|
||||
readonly controller: AbortController
|
||||
readonly settled: Promise<void>
|
||||
cleanupFailure: { error: unknown } | undefined
|
||||
}
|
||||
|
||||
interface SpawnReservation {
|
||||
readonly signal: AbortSignal
|
||||
release(cleanupFailure: { error: unknown } | undefined): void
|
||||
}
|
||||
|
||||
/** In-process registry for replaceable PTY backends and exact-Agent sessions. */
|
||||
export class PtyService extends Service {
|
||||
private readonly backends = new Map<string, PtyBackend>()
|
||||
private readonly sessions = new Map<PtySessionId, SessionRecord>()
|
||||
private readonly reservedNames = new Map<Agent, Set<string>>()
|
||||
private readonly pendingSpawns = new Map<Agent, Set<PendingSpawn>>()
|
||||
private readonly ownerCleanups = new Map<Agent, () => Promise<void> | void>()
|
||||
private readonly disposedOwners = new WeakSet<Agent>()
|
||||
private nextId = 0
|
||||
@@ -142,15 +153,19 @@ export class PtyService extends Service {
|
||||
*/
|
||||
async spawn(owner: Agent, request: PtySpawnRequest, signal?: AbortSignal): Promise<PtySpawnResult> {
|
||||
this.assertActive()
|
||||
signal?.throwIfAborted()
|
||||
this.ensureOwnerCleanup(owner)
|
||||
const backend = this.backends.get(request.type)
|
||||
if (backend === undefined) throw new PtyError(`no PTY backend registered for "${request.type}"`, 'NO_BACKEND')
|
||||
if (request.name !== undefined && request.name.length === 0) throw new Error('PTY session name must be non-empty')
|
||||
if (isAborted(signal)) throw new Error('PTY spawn aborted')
|
||||
|
||||
const releaseName = this.reserveName(owner, request.name)
|
||||
const spawnReservation = this.reserveSpawn(owner)
|
||||
const backendSignal = signal === undefined
|
||||
? spawnReservation.signal
|
||||
: AbortSignal.any([signal, spawnReservation.signal])
|
||||
const sessionId = PtySessionId(`pty-${++this.nextId}`)
|
||||
let session: PtyBackendSession | undefined
|
||||
let cleanupFailure: { error: unknown } | undefined
|
||||
try {
|
||||
session = await backend.spawn({
|
||||
sessionId,
|
||||
@@ -158,9 +173,13 @@ export class PtyService extends Service {
|
||||
type: request.type,
|
||||
...request.name !== undefined ? { name: request.name } : {},
|
||||
...request.cwd !== undefined ? { cwd: request.cwd } : {},
|
||||
...signal !== undefined ? { signal } : {},
|
||||
signal: backendSignal,
|
||||
})
|
||||
if (this.disposing || isAborted(signal) || !this.isLiveOwner(owner)) {
|
||||
signal?.throwIfAborted()
|
||||
if (this.disposing) {
|
||||
throw new PtyError('PTY service is disposing', 'SERVICE_DISPOSING')
|
||||
}
|
||||
if (!this.isLiveOwner(owner)) {
|
||||
throw new PtyError('PTY owner is no longer live', 'OWNER_NOT_LIVE')
|
||||
}
|
||||
const record: SessionRecord = {
|
||||
@@ -175,19 +194,45 @@ export class PtyService extends Service {
|
||||
this.sessions.set(sessionId, record)
|
||||
return this.snapshot(record, session.motd)
|
||||
} catch (error) {
|
||||
if (error instanceof PtyBackendCleanupError) {
|
||||
cleanupFailure = { error: error.cleanupError }
|
||||
}
|
||||
let rollbackFailure: { error: unknown } | undefined
|
||||
if (session !== undefined && !this.sessions.has(sessionId)) {
|
||||
try {
|
||||
await session.close('PTY spawn rolled back')
|
||||
} catch (closeError: unknown) {
|
||||
throw new AggregateError([error, closeError], 'PTY spawn and rollback both failed')
|
||||
rollbackFailure = { error: closeError }
|
||||
cleanupFailure = rollbackFailure
|
||||
}
|
||||
}
|
||||
throw error
|
||||
let failure: unknown = error
|
||||
try {
|
||||
signal?.throwIfAborted()
|
||||
spawnReservation.signal.throwIfAborted()
|
||||
} catch (cancellation: unknown) {
|
||||
failure = cancellation
|
||||
}
|
||||
if (rollbackFailure !== undefined && signal?.aborted !== true) {
|
||||
throw new AggregateError([failure, rollbackFailure.error], 'PTY spawn and rollback both failed')
|
||||
}
|
||||
throw failure
|
||||
} finally {
|
||||
spawnReservation.release(cleanupFailure)
|
||||
releaseName()
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Test whether an exact owner has a published session or unpublished spawn.
|
||||
* @param owner - exact live owner to inspect.
|
||||
* @returns true across the entire spawn-to-close interval, with no publication gap.
|
||||
*/
|
||||
hasOwnerActivity(owner: Agent): boolean {
|
||||
return (this.pendingSpawns.get(owner)?.size ?? 0) > 0
|
||||
|| [...this.sessions.values()].some(record => record.owner === owner)
|
||||
}
|
||||
|
||||
/**
|
||||
* Start one exclusive interactive send.
|
||||
* @param owner - exact session owner.
|
||||
@@ -302,6 +347,43 @@ export class PtyService extends Service {
|
||||
}
|
||||
}
|
||||
|
||||
private reserveSpawn(owner: Agent): SpawnReservation {
|
||||
const controller = new AbortController()
|
||||
const settlement = Promise.withResolvers<void>()
|
||||
const pending: PendingSpawn = { owner, controller, settled: settlement.promise, cleanupFailure: undefined }
|
||||
const owned = this.pendingSpawns.get(owner) ?? new Set<PendingSpawn>()
|
||||
owned.add(pending)
|
||||
this.pendingSpawns.set(owner, owned)
|
||||
return {
|
||||
signal: controller.signal,
|
||||
release: (cleanupFailure) => {
|
||||
pending.cleanupFailure = cleanupFailure
|
||||
if (cleanupFailure === undefined) this.removePendingSpawn(pending)
|
||||
settlement.resolve()
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
private removePendingSpawn(pending: PendingSpawn): void {
|
||||
const owned = this.pendingSpawns.get(pending.owner)
|
||||
if (owned === undefined) return
|
||||
owned.delete(pending)
|
||||
if (owned.size === 0) this.pendingSpawns.delete(pending.owner)
|
||||
}
|
||||
|
||||
private async abortPendingSpawns(owner: Agent | undefined, reason: PtyError): Promise<void> {
|
||||
const pending = owner === undefined
|
||||
? [...this.pendingSpawns.values()].flatMap(owned => [...owned])
|
||||
: [...(this.pendingSpawns.get(owner) ?? [])]
|
||||
for (const spawn of pending) spawn.controller.abort(reason)
|
||||
await Promise.all(pending.map(spawn => spawn.settled))
|
||||
const failures = pending.flatMap(spawn => spawn.cleanupFailure === undefined ? [] : [spawn.cleanupFailure.error])
|
||||
for (const spawn of pending) this.removePendingSpawn(spawn)
|
||||
if (failures.length > 0) {
|
||||
throw new AggregateError(failures, 'failed to roll back unpublished PTY setup')
|
||||
}
|
||||
}
|
||||
|
||||
private expectOwned(owner: Agent, id: PtySessionId): SessionRecord {
|
||||
const record = this.sessions.get(id)
|
||||
if (record === undefined) throw new PtyError(`unknown PTY session ${id}`, 'NO_SESSION')
|
||||
@@ -322,23 +404,49 @@ export class PtyService extends Service {
|
||||
}
|
||||
}
|
||||
|
||||
private async abortAndClose(owner: Agent | undefined, abortReason: PtyError, closeReason: string): Promise<void> {
|
||||
const failures: unknown[] = []
|
||||
try {
|
||||
await this.abortPendingSpawns(owner, abortReason)
|
||||
} catch (error: unknown) {
|
||||
failures.push(error)
|
||||
}
|
||||
const records = [...this.sessions.values()].filter(record => owner === undefined || record.owner === owner)
|
||||
try {
|
||||
await this.closeRecords(records, closeReason)
|
||||
} catch (error: unknown) {
|
||||
failures.push(error)
|
||||
}
|
||||
if (failures.length > 0) throw new AggregateError(failures, 'failed to clean up PTY lifecycle')
|
||||
}
|
||||
|
||||
private async disposeOwned(owner: Agent): Promise<void> {
|
||||
const owned = [...this.sessions.values()].filter(record => record.owner === owner)
|
||||
await this.closeRecords(owned, 'PTY owner disposed')
|
||||
this.reservedNames.delete(owner)
|
||||
try {
|
||||
await this.abortAndClose(
|
||||
owner,
|
||||
new PtyError('PTY owner is no longer live', 'OWNER_NOT_LIVE'),
|
||||
'PTY owner disposed',
|
||||
)
|
||||
} finally {
|
||||
this.reservedNames.delete(owner)
|
||||
}
|
||||
}
|
||||
|
||||
private async disposeAll(): Promise<void> {
|
||||
this.disposing = true
|
||||
const records = [...this.sessions.values()]
|
||||
// Teardown is best-effort: a close failure still clears registries and runs
|
||||
// owner cleanups before the aggregated error propagates, so one stuck
|
||||
// session cannot orphan backends, reservations, or owner detachers.
|
||||
try {
|
||||
await this.closeRecords(records, 'PTY service disposed')
|
||||
await this.abortAndClose(
|
||||
undefined,
|
||||
new PtyError('PTY service is disposing', 'SERVICE_DISPOSING'),
|
||||
'PTY service disposed',
|
||||
)
|
||||
} finally {
|
||||
this.backends.clear()
|
||||
this.reservedNames.clear()
|
||||
this.pendingSpawns.clear()
|
||||
const cleanups = [...this.ownerCleanups.values()]
|
||||
this.ownerCleanups.clear()
|
||||
await Promise.all(cleanups.map(cleanup => Promise.resolve(cleanup())))
|
||||
@@ -349,8 +457,14 @@ export class PtyService extends Service {
|
||||
const results = await Promise.allSettled(records.map(async (record) => {
|
||||
const closing = record.closing ?? record.session.close(reason)
|
||||
record.closing = closing
|
||||
await closing
|
||||
this.sessions.delete(record.id)
|
||||
try {
|
||||
await closing
|
||||
this.sessions.delete(record.id)
|
||||
} catch (error: unknown) {
|
||||
// A concurrent retry may already own a newer fence; never clear it.
|
||||
if (record.closing === closing) record.closing = undefined
|
||||
throw error
|
||||
}
|
||||
}))
|
||||
const failures = results
|
||||
.filter((result): result is PromiseRejectedResult => result.status === 'rejected')
|
||||
|
||||
@@ -10,6 +10,21 @@ import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
/** Internal exported basis for the public `PtySessionId` type/value pair. */
|
||||
export type PtySessionIdValue = Branded<'PtySessionId'>
|
||||
|
||||
/**
|
||||
* Backend-reported failure to clean partial resources after unpublished setup failed.
|
||||
* @param spawnError - original setup or cancellation failure.
|
||||
* @param cleanupError - failure that may leave backend-owned resources alive.
|
||||
*/
|
||||
export class PtyBackendCleanupError extends AggregateError {
|
||||
constructor(
|
||||
readonly spawnError: unknown,
|
||||
readonly cleanupError: unknown,
|
||||
) {
|
||||
super([spawnError, cleanupError], 'PTY backend startup and cleanup both failed')
|
||||
this.name = 'PtyBackendCleanupError'
|
||||
}
|
||||
}
|
||||
|
||||
/** Why one interactive send returned control to its caller. */
|
||||
export type PtyWaitReason = 'stdin_read' | 'inferred_idle' | 'timeout' | 'session_exit'
|
||||
|
||||
@@ -147,7 +162,7 @@ export interface PtyBackendSession {
|
||||
export interface PtyBackend {
|
||||
/** Stable type selected by {@link PtySpawnRequest.type}. */
|
||||
readonly type: string
|
||||
/** Create an unpublished session or reject after cleaning partial resources. */
|
||||
/** Create an unpublished session or reject after cleaning partial resources; cleanup failure uses {@link PtyBackendCleanupError}. */
|
||||
spawn(spec: PtyBackendSpawnSpec): Promise<PtyBackendSession>
|
||||
}
|
||||
|
||||
|
||||
@@ -3,7 +3,7 @@ import { Context } from 'cordis'
|
||||
import { Session, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import AgentRegistry from '@deepseek-ai/dsh-agent'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import PtyService, { PtyError, PtySessionId } from '@deepseek-ai/dsh-pty'
|
||||
import PtyService, { PtyBackendCleanupError, PtyError, PtySessionId } from '@deepseek-ai/dsh-pty'
|
||||
import type {
|
||||
PtyBackend,
|
||||
PtyBackendSession,
|
||||
@@ -160,6 +160,7 @@ describe('PtyService ownership and lifecycle', () => {
|
||||
|
||||
const created = await ctx.pty.spawn(owner, { type: 'stub', name: 'main', cwd: '/tmp' })
|
||||
expect(created).toMatchObject({ sessionId: 'pty-1', name: 'main', type: 'stub', pid: 123, motd: 'stub ready', status: { kind: 'running' } })
|
||||
expect(ctx.pty.hasOwnerActivity(owner)).toBe(true)
|
||||
expect(ctx.pty.list(owner)).toHaveLength(1)
|
||||
expect(ctx.pty.list(foreign)).toEqual([])
|
||||
expect(() => ctx.pty.read(foreign, created.sessionId)).toThrow('belongs to another agent')
|
||||
@@ -178,8 +179,9 @@ describe('PtyService ownership and lifecycle', () => {
|
||||
const created = await ctx.pty.spawn(owner, { type: 'stub', name: 'main' })
|
||||
await expect(ctx.pty.spawn(owner, { type: 'stub', name: '' })).rejects.toThrow('must be non-empty')
|
||||
const aborted = new AbortController()
|
||||
aborted.abort()
|
||||
await expect(ctx.pty.spawn(owner, { type: 'stub' }, aborted.signal)).rejects.toThrow('spawn aborted')
|
||||
const abortReason = new Error('spawn aborted')
|
||||
aborted.abort(abortReason)
|
||||
await expect(ctx.pty.spawn(owner, { type: 'stub' }, aborted.signal)).rejects.toBe(abortReason)
|
||||
await expect(ctx.pty.spawn(owner, { type: 'stub', name: 'main' })).rejects.toMatchObject({ code: 'DUPLICATE_NAME' })
|
||||
|
||||
const operation = ctx.pty.startSend(owner, created.sessionId, { text: 'echo hi', submit: true })
|
||||
@@ -205,12 +207,222 @@ describe('PtyService ownership and lifecycle', () => {
|
||||
ctx.agents.register(owner)
|
||||
const pending = ctx.pty.spawn(owner, { type: 'slow', name: 'main' })
|
||||
await expect(ctx.pty.spawn(owner, { type: 'slow', name: 'main' })).rejects.toMatchObject({ code: 'DUPLICATE_NAME' })
|
||||
await disposeAgentScope(owner)
|
||||
const disposal = disposeAgentScope(owner)
|
||||
gate.resolve(session)
|
||||
await expect(pending).rejects.toMatchObject({ code: 'OWNER_NOT_LIVE' })
|
||||
await disposal
|
||||
expect(session.closed).toEqual(['PTY spawn rolled back'])
|
||||
})
|
||||
|
||||
it('preserves caller cancellation when a pending backend spawn completes', async () => {
|
||||
const ctx = await harness()
|
||||
const gate = Promise.withResolvers<PtyBackendSession>()
|
||||
const session = new StubSession()
|
||||
ctx.pty.registerBackend({ type: 'slow', spawn: () => gate.promise })
|
||||
const owner = stubAgent(ctx, 'owner')
|
||||
ctx.agents.register(owner)
|
||||
const controller = new AbortController()
|
||||
const reason = new Error('cancelled by caller')
|
||||
|
||||
const pending = ctx.pty.spawn(owner, { type: 'slow' }, controller.signal)
|
||||
controller.abort(reason)
|
||||
gate.resolve(session)
|
||||
|
||||
await expect(pending).rejects.toBe(reason)
|
||||
expect(session.closed).toEqual(['PTY spawn rolled back'])
|
||||
expect(ctx.agents.get(owner.id)).toBe(owner)
|
||||
})
|
||||
|
||||
it('preserves caller cancellation when unpublished rollback fails', async () => {
|
||||
const ctx = await harness()
|
||||
const gate = Promise.withResolvers<PtyBackendSession>()
|
||||
const session = new StubSession()
|
||||
session.rejectClose = true
|
||||
ctx.pty.registerBackend({ type: 'slow', spawn: () => gate.promise })
|
||||
const owner = stubAgent(ctx, 'owner')
|
||||
ctx.agents.register(owner)
|
||||
const controller = new AbortController()
|
||||
const reason = new Error('cancelled by caller')
|
||||
|
||||
const pending = ctx.pty.spawn(owner, { type: 'slow' }, controller.signal)
|
||||
controller.abort(reason)
|
||||
gate.resolve(session)
|
||||
|
||||
await expect(pending).rejects.toBe(reason)
|
||||
expect(ctx.pty.hasOwnerActivity(owner)).toBe(true)
|
||||
const internal = ctx.pty as unknown as { disposeAll(): Promise<void> }
|
||||
await expect(internal.disposeAll()).rejects.toThrow('failed to clean up PTY lifecycle')
|
||||
expect(ctx.pty.hasOwnerActivity(owner)).toBe(false)
|
||||
expect(session.closed).toEqual(['PTY spawn rolled back'])
|
||||
})
|
||||
|
||||
it('preserves caller cancellation when a backend rejects in response to it', async () => {
|
||||
const ctx = await harness()
|
||||
const started = Promise.withResolvers<undefined>()
|
||||
const backendFailure = new Error('backend observed cancellation')
|
||||
ctx.pty.registerBackend({
|
||||
type: 'abortable',
|
||||
spawn: ({ signal }) => new Promise((_resolve, reject) => {
|
||||
if (signal === undefined) throw new Error('missing spawn signal')
|
||||
started.resolve(undefined)
|
||||
signal.addEventListener('abort', () => { reject(backendFailure) }, { once: true })
|
||||
}),
|
||||
})
|
||||
const owner = stubAgent(ctx, 'owner')
|
||||
ctx.agents.register(owner)
|
||||
const controller = new AbortController()
|
||||
const reason = new Error('cancelled by caller')
|
||||
|
||||
const pending = ctx.pty.spawn(owner, { type: 'abortable' }, controller.signal)
|
||||
await started.promise
|
||||
controller.abort(reason)
|
||||
|
||||
await expect(pending).rejects.toBe(reason)
|
||||
})
|
||||
|
||||
it.each(['owner', 'service'] as const)('retains caller-triggered backend cleanup failure until %s disposal', async (scope) => {
|
||||
const ctx = await harness()
|
||||
const started = Promise.withResolvers<undefined>()
|
||||
const cleanupFailure = new Error('backend cleanup failed')
|
||||
ctx.pty.registerBackend({
|
||||
type: 'cleanup-failing',
|
||||
spawn: ({ signal }) => new Promise((_resolve, reject) => {
|
||||
if (signal === undefined) throw new Error('missing spawn signal')
|
||||
started.resolve(undefined)
|
||||
signal.addEventListener('abort', () => {
|
||||
reject(new PtyBackendCleanupError(signal.reason, cleanupFailure))
|
||||
}, { once: true })
|
||||
}),
|
||||
})
|
||||
const owner = stubAgent(ctx, 'owner')
|
||||
ctx.agents.register(owner)
|
||||
const controller = new AbortController()
|
||||
const reason = new Error('cancelled by caller')
|
||||
|
||||
const pending = ctx.pty.spawn(owner, { type: 'cleanup-failing' }, controller.signal)
|
||||
await started.promise
|
||||
controller.abort(reason)
|
||||
|
||||
await expect(pending).rejects.toBe(reason)
|
||||
expect(ctx.pty.hasOwnerActivity(owner)).toBe(true)
|
||||
const internal = ctx.pty as unknown as {
|
||||
disposeOwned(owner: Agent): Promise<void>
|
||||
disposeAll(): Promise<void>
|
||||
}
|
||||
const disposal = scope === 'owner' ? internal.disposeOwned(owner) : internal.disposeAll()
|
||||
await expect(disposal).rejects.toThrow('failed to clean up PTY lifecycle')
|
||||
expect(ctx.pty.hasOwnerActivity(owner)).toBe(false)
|
||||
})
|
||||
|
||||
it.each([
|
||||
{ scope: 'owner', code: 'OWNER_NOT_LIVE' },
|
||||
{ scope: 'service', code: 'SERVICE_DISPOSING' },
|
||||
] as const)('$scope disposal aborts and awaits unpublished backend setup', async ({ scope, code }) => {
|
||||
const ctx = await harness()
|
||||
const gate = Promise.withResolvers<PtyBackendSession>()
|
||||
const started = Promise.withResolvers<undefined>()
|
||||
const session = new StubSession()
|
||||
let backendSignal: AbortSignal | undefined
|
||||
ctx.pty.registerBackend({
|
||||
type: 'slow',
|
||||
spawn: (spec) => {
|
||||
backendSignal = spec.signal
|
||||
started.resolve(undefined)
|
||||
return gate.promise
|
||||
},
|
||||
})
|
||||
const owner = stubAgent(ctx, 'owner')
|
||||
ctx.agents.register(owner)
|
||||
|
||||
const pending = ctx.pty.spawn(owner, { type: 'slow' })
|
||||
const pendingFailure = pending.then(
|
||||
() => { throw new Error('pending spawn unexpectedly succeeded') },
|
||||
(error: unknown) => error,
|
||||
)
|
||||
await started.promise
|
||||
let disposalSettled = false
|
||||
const disposal = (scope === 'owner' ? disposeAgentScope(owner) : disposePtyService(ctx))
|
||||
.then(() => { disposalSettled = true })
|
||||
await new Promise(resolve => setTimeout(resolve, 0))
|
||||
const signalAbortedBeforeRelease = backendSignal?.aborted ?? false
|
||||
const signalReasonBeforeRelease = backendSignal?.reason as unknown
|
||||
const disposalSettledBeforeRelease = disposalSettled
|
||||
gate.resolve(session)
|
||||
|
||||
expect(await pendingFailure).toMatchObject({ code })
|
||||
await disposal
|
||||
expect(signalAbortedBeforeRelease).toBe(true)
|
||||
expect(signalReasonBeforeRelease).toMatchObject({ code })
|
||||
expect(disposalSettledBeforeRelease).toBe(false)
|
||||
expect(session.closed).toEqual(['PTY spawn rolled back'])
|
||||
})
|
||||
|
||||
it('reports unpublished rollback failure through service disposal', async () => {
|
||||
const ctx = await harness()
|
||||
const gate = Promise.withResolvers<PtyBackendSession>()
|
||||
const session = new StubSession()
|
||||
session.rejectClose = true
|
||||
ctx.pty.registerBackend({ type: 'slow', spawn: () => gate.promise })
|
||||
const owner = stubAgent(ctx, 'owner')
|
||||
ctx.agents.register(owner)
|
||||
|
||||
const pending = ctx.pty.spawn(owner, { type: 'slow' })
|
||||
const pendingFailure = expect(pending).rejects.toThrow('PTY spawn and rollback both failed')
|
||||
const internal = ctx.pty as unknown as { disposeAll(): Promise<void> }
|
||||
const disposalFailure = expect(internal.disposeAll()).rejects.toThrow('failed to clean up PTY lifecycle')
|
||||
gate.resolve(session)
|
||||
|
||||
await pendingFailure
|
||||
await disposalFailure
|
||||
expect(session.closed).toEqual(['PTY spawn rolled back'])
|
||||
})
|
||||
|
||||
it.each([
|
||||
{ scope: 'owner', code: 'OWNER_NOT_LIVE' },
|
||||
{ scope: 'service', code: 'SERVICE_DISPOSING' },
|
||||
] as const)('$scope disposal retains backend-side startup cleanup failure', async ({ scope, code }) => {
|
||||
const ctx = await harness()
|
||||
const started = Promise.withResolvers<undefined>()
|
||||
const cleanupFailure = new Error('backend cleanup failed')
|
||||
let backendAbortReason: unknown
|
||||
ctx.pty.registerBackend({
|
||||
type: 'cleanup-failing',
|
||||
spawn: ({ signal }) => new Promise((_resolve, reject) => {
|
||||
if (signal === undefined) throw new Error('missing spawn signal')
|
||||
started.resolve(undefined)
|
||||
signal.addEventListener('abort', () => {
|
||||
backendAbortReason = signal.reason
|
||||
reject(new PtyBackendCleanupError(signal.reason, cleanupFailure))
|
||||
}, { once: true })
|
||||
}),
|
||||
})
|
||||
const owner = stubAgent(ctx, 'owner')
|
||||
ctx.agents.register(owner)
|
||||
|
||||
const pending = ctx.pty.spawn(owner, { type: 'cleanup-failing' })
|
||||
await started.promise
|
||||
const internal = ctx.pty as unknown as {
|
||||
disposeOwned(owner: Agent): Promise<void>
|
||||
disposeAll(): Promise<void>
|
||||
}
|
||||
const disposal = scope === 'owner' ? internal.disposeOwned(owner) : internal.disposeAll()
|
||||
const pendingError = await pending.then(
|
||||
() => { throw new Error('pending spawn unexpectedly succeeded') },
|
||||
(error: unknown) => error,
|
||||
)
|
||||
|
||||
expect(pendingError).toBe(backendAbortReason)
|
||||
expect(pendingError).toMatchObject({ code })
|
||||
const disposalError = await disposal.then(
|
||||
() => { throw new Error('disposal unexpectedly succeeded') },
|
||||
(error: unknown) => error,
|
||||
)
|
||||
expect(disposalError).toMatchObject({ message: 'failed to clean up PTY lifecycle' })
|
||||
const rollbackError = (disposalError as AggregateError).errors[0] as unknown
|
||||
const cleanupErrors = (rollbackError as AggregateError).errors as unknown[]
|
||||
expect(cleanupErrors).toEqual([cleanupFailure])
|
||||
})
|
||||
|
||||
it('keeps independent reservations and handles provider failure before publication', async () => {
|
||||
const ctx = await harness()
|
||||
const firstGate = Promise.withResolvers<PtyBackendSession>()
|
||||
@@ -254,14 +466,27 @@ describe('PtyService ownership and lifecycle', () => {
|
||||
ctx.agents.register(owner)
|
||||
const failedSpawn = new StubSession()
|
||||
failedSpawn.rejectClose = true
|
||||
let ownerDisposal = Promise.resolve()
|
||||
const internal = ctx.pty as unknown as {
|
||||
disposedOwners: WeakSet<Agent>
|
||||
disposeOwned(owner: Agent): Promise<void>
|
||||
}
|
||||
ctx.pty.registerBackend({
|
||||
type: 'bad-spawn',
|
||||
async spawn() {
|
||||
await disposeAgentScope(owner)
|
||||
async spawn({ signal }) {
|
||||
if (signal === undefined) throw new Error('missing spawn signal')
|
||||
internal.disposedOwners.add(owner)
|
||||
ownerDisposal = internal.disposeOwned(owner)
|
||||
if (!signal.aborted) {
|
||||
await new Promise<undefined>((resolve) => {
|
||||
signal.addEventListener('abort', () => { resolve(undefined) }, { once: true })
|
||||
})
|
||||
}
|
||||
return failedSpawn
|
||||
},
|
||||
})
|
||||
await expect(ctx.pty.spawn(owner, { type: 'bad-spawn' })).rejects.toThrow('spawn and rollback both failed')
|
||||
await expect(ownerDisposal).rejects.toThrow('failed to clean up PTY lifecycle')
|
||||
|
||||
const nextOwner = stubAgent(ctx, 'next')
|
||||
ctx.agents.register(nextOwner)
|
||||
@@ -338,8 +563,15 @@ describe('PtyService ownership and lifecycle', () => {
|
||||
sessions: Map<PtySessionIdType, unknown>
|
||||
closeRecords(records: unknown[], reason: string): Promise<void>
|
||||
}
|
||||
await expect(internal.closeRecords([...internal.sessions.values()], 'test failure')).rejects.toThrow('failed to close 1 PTY session')
|
||||
const records = [...internal.sessions.values()]
|
||||
const firstFailure = expect(internal.closeRecords(records, 'test failure')).rejects.toThrow('failed to close 1 PTY session')
|
||||
const joinedFailure = expect(internal.closeRecords(records, 'joined failure')).rejects.toThrow('failed to close 1 PTY session')
|
||||
await firstFailure
|
||||
await joinedFailure
|
||||
b.sessions[0]!.rejectClose = false
|
||||
await expect(internal.closeRecords([...internal.sessions.values()], 'retry')).resolves.toBeUndefined()
|
||||
expect(b.sessions[0]!.closed).toEqual(['test failure', 'retry'])
|
||||
expect(internal.sessions.size).toBe(0)
|
||||
await disposePtyService(ctx)
|
||||
await expect(service.spawn(owner, { type: 'stub' })).rejects.toMatchObject({ code: 'SERVICE_DISPOSING' })
|
||||
})
|
||||
@@ -360,7 +592,7 @@ describe('PtyService ownership and lifecycle', () => {
|
||||
}
|
||||
// Teardown surfaces the close failure, but its finally still clears the
|
||||
// backend and owner-cleanup registries instead of orphaning them.
|
||||
await expect(internal.disposeAll()).rejects.toThrow('failed to close 1 PTY session')
|
||||
await expect(internal.disposeAll()).rejects.toThrow('failed to clean up PTY lifecycle')
|
||||
expect(internal.backends.size).toBe(0)
|
||||
expect(internal.ownerCleanups.size).toBe(0)
|
||||
})
|
||||
|
||||
@@ -2,7 +2,16 @@
|
||||
|
||||
Six model-facing tools over `ctx.pty`: `terminal_open`, `terminal_send`, `terminal_read`, `terminal_signal`, `terminal_close`, and `terminal_list`. Every operation requires the exact initiating `Agent`, so a model cannot address another agent's terminal even if it learns the id.
|
||||
|
||||
`terminal_send(run_in_background: true)` reuses `ctx.tasks`; task preflight occurs before any terminal write, completion is collected with `task_output`, and `task_kill` requests `Ctrl-C`. Foreground sends use terminal ACP cards; lifecycle, history, signal, and list calls use generic cards.
|
||||
`terminal_send(run_in_background: true)` reuses `ctx.tasks`; task preflight and the PTY service's exclusive per-session send reservation occur before the task id is returned, completion is collected with `task_output`, and `task_kill` delivers `SIGINT` to the foreground process group. Foreground sends use terminal ACP call/result cards. Background sends use a generic execute card; open, read, signal, close, and list use generic `execute`, `read`, `execute`, `delete`, and `read` cards respectively. None declares source locations.
|
||||
|
||||
## Config
|
||||
|
||||
| key | default | meaning |
|
||||
|---|---:|---|
|
||||
| `enableRunInBackground` | `true` | expose and accept `run_in_background`; false omits the schema field and rejects a forced undeclared argument |
|
||||
| `maxResultBytes` | `262144` | UTF-8 cap (minimum `64`) for each complete terminal result or PTY task output after wait, session, pagination, truncation, and task-status metadata |
|
||||
|
||||
Both values are validated at load. The minimum result cap keeps every registry-issued session or task id visible in its creation acknowledgement. When a result exceeds `maxResultBytes`, rendering reserves space for control metadata and a truncation marker when they fit; cuts preserve UTF-8 boundaries. Each terminal definition's final-content callback applies the same cap after normalized pre-, around-, and post-execute policy failures, denials, short-circuits, replacements, or blocks; a structured multi-block policy result retains its shape.
|
||||
|
||||
## Model Experience
|
||||
|
||||
@@ -44,11 +53,11 @@ Prefix-stable while tool visibility and definitions are unchanged.
|
||||
|
||||
#### What the model sees
|
||||
|
||||
Spawn returns the id and bounded MOTD. Send/read return bounded terminal text plus readiness/history markers. Background mode returns a generic task id. Results remain in session history until compaction; incremental task reads do not repeat consumed output. Programmatic callers receive typed session snapshots, bounded send/read DTOs, signal and close outcomes, or `{ kind: "background", taskId }`; Native rendering preserves the text above.
|
||||
Spawn returns the id and bounded MOTD. Send/read return bounded terminal text plus readiness/history markers. Background mode returns a generic task id. Every terminal-owned or policy-produced single-text result is capped by `maxResultBytes` after normalized tool or pipeline errors, denials, short-circuits, replacements, blocks, and generic task status text. Structured multi-block policy results retain their shape. Results remain in session history until compaction; incremental task reads do not repeat consumed output. Programmatic callers receive typed session snapshots, bounded provider read/send DTOs, signal and close outcomes, or `{ kind: "background", taskId }`; Native rendering applies the presentation cap above.
|
||||
|
||||
#### Token effect
|
||||
|
||||
Data-dependent and bounded by the backend; each returned result remains in history until compaction.
|
||||
Terminal-owned and policy-produced single-text results are data-dependent and bounded by `maxResultBytes`; a policy that deliberately substitutes structured multi-block content owns that content's bound. Each returned result remains in history until compaction.
|
||||
|
||||
#### KV Cache effect
|
||||
|
||||
|
||||
@@ -26,11 +26,15 @@
|
||||
"src"
|
||||
],
|
||||
"license": "BSD-3-Clause",
|
||||
"dependencies": {
|
||||
"schemastery": "^3.18.0"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"@deepseek-ai/dsh-agent": "^0.0.1",
|
||||
"@deepseek-ai/dsh-invariants": "^0.0.1",
|
||||
"@deepseek-ai/dsh-llm": "^0.0.1",
|
||||
"@deepseek-ai/dsh-pty": "^0.0.1",
|
||||
"@deepseek-ai/dsh-retention": "^0.0.1",
|
||||
"@deepseek-ai/dsh-system-prompt": "^0.0.1",
|
||||
"@deepseek-ai/dsh-tasks": "^0.0.1",
|
||||
"@deepseek-ai/dsh-tools": "^0.0.1",
|
||||
@@ -44,6 +48,7 @@
|
||||
"@deepseek-ai/dsh-llm": "workspace:^",
|
||||
"@deepseek-ai/dsh-pty": "workspace:^",
|
||||
"@deepseek-ai/dsh-pty-local": "workspace:^",
|
||||
"@deepseek-ai/dsh-retention": "workspace:^",
|
||||
"@deepseek-ai/dsh-sandbox": "workspace:^",
|
||||
"@deepseek-ai/dsh-sandbox-policy": "workspace:^",
|
||||
"@deepseek-ai/dsh-session": "workspace:^",
|
||||
|
||||
@@ -5,13 +5,15 @@
|
||||
*/
|
||||
|
||||
import { Context } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import type { ContentBlock } from '@deepseek-ai/dsh-llm'
|
||||
import { PtySessionId } from '@deepseek-ai/dsh-pty'
|
||||
import type { PtySendResult, PtySessionId as PtySessionIdType, PtySignal } from '@deepseek-ai/dsh-pty'
|
||||
import type {} from '@deepseek-ai/dsh-tasks'
|
||||
import { defineTool } from '@deepseek-ai/dsh-tools'
|
||||
import type { ToolResult } from '@deepseek-ai/dsh-tools'
|
||||
import { renderList, renderRead, renderSend, renderSendRead, renderSpawn } from './render.ts'
|
||||
import type { ToolDefinition } from '@deepseek-ai/dsh-tools'
|
||||
import { boundTerminalText, renderList, renderRead, renderSend, renderSendRead, renderSpawn } from './render.ts'
|
||||
|
||||
declare module '@deepseek-ai/dsh-tasks' {
|
||||
interface TaskKindMap {
|
||||
@@ -24,6 +26,25 @@ export const name = 'tool-pty'
|
||||
/** Required capability, registry, and prompt services. */
|
||||
export const inject = ['pty', 'tools', 'systemPrompt']
|
||||
|
||||
/** Default cap for one complete model-facing terminal result. */
|
||||
export const DEFAULT_MAX_RESULT_BYTES = 256 * 1024
|
||||
/** Smallest cap that preserves every counter-backed PTY and task id in its creation acknowledgement. */
|
||||
export const MIN_MAX_RESULT_BYTES = 64
|
||||
|
||||
/** Model-facing terminal tool configuration. */
|
||||
export interface Config {
|
||||
/** Expose `run_in_background` and accept background sends (default true). */
|
||||
enableRunInBackground?: boolean
|
||||
/** Maximum UTF-8 bytes in one complete terminal or task-output result. */
|
||||
maxResultBytes?: number
|
||||
}
|
||||
|
||||
/** Schemastery configuration for the terminal tool consumer. */
|
||||
export const Config: z<Config> = z.object({
|
||||
enableRunInBackground: z.boolean().default(true),
|
||||
maxResultBytes: z.number().step(1).min(MIN_MAX_RESULT_BYTES).max(Number.MAX_SAFE_INTEGER).default(DEFAULT_MAX_RESULT_BYTES),
|
||||
})
|
||||
|
||||
interface SpawnArgs {
|
||||
type: string
|
||||
name?: string
|
||||
@@ -105,9 +126,13 @@ function sessionId(args: SessionArgs): PtySessionIdType {
|
||||
return PtySessionId(args.sessionId)
|
||||
}
|
||||
|
||||
function rawResultText(result: ToolResult): string | undefined {
|
||||
if (result.content.length !== 1) return undefined
|
||||
const block = result.content[0]
|
||||
function textResult(text: string, maxBytes: number): ContentBlock[] {
|
||||
return [{ type: 'text', text: boundTerminalText(text, maxBytes) }]
|
||||
}
|
||||
|
||||
function rawContentText(content: readonly ContentBlock[]): string | undefined {
|
||||
if (content.length !== 1) return undefined
|
||||
const block = content[0]
|
||||
return block?.type === 'text' ? block.text : undefined
|
||||
}
|
||||
|
||||
@@ -118,7 +143,16 @@ function sendDetail(result: PtySendResult): string {
|
||||
}
|
||||
|
||||
/** Register all terminal tools and the minimal usage guidance. */
|
||||
export function apply(ctx: Context): void {
|
||||
export function apply(ctx: Context, config: Config = {}): void {
|
||||
const enableRunInBackground = config.enableRunInBackground ?? true
|
||||
const maxResultBytes = config.maxResultBytes ?? DEFAULT_MAX_RESULT_BYTES
|
||||
if (!Number.isSafeInteger(maxResultBytes) || maxResultBytes < MIN_MAX_RESULT_BYTES) {
|
||||
throw new Error(`tool-pty: maxResultBytes must be a safe integer of at least ${MIN_MAX_RESULT_BYTES}`)
|
||||
}
|
||||
const finalizeContent: NonNullable<ToolDefinition['finalizeContent']> = (_exec, result) => {
|
||||
const raw = rawContentText(result.content)
|
||||
return raw === undefined ? undefined : textResult(raw, maxResultBytes)
|
||||
}
|
||||
ctx.systemPrompt.section({
|
||||
name: 'tool:pty',
|
||||
order: 106,
|
||||
@@ -133,6 +167,7 @@ export function apply(ctx: Context): void {
|
||||
name: { type: 'string', description: 'Optional owner-local display name such as "main" or "gdb".' },
|
||||
cwd: { type: 'string', description: 'Initial working directory. Defaults to the deployment workspace root.' },
|
||||
},
|
||||
finalizeContent,
|
||||
output: {
|
||||
schema: {
|
||||
type: 'object',
|
||||
@@ -142,7 +177,7 @@ export function apply(ctx: Context): void {
|
||||
motd: { type: 'string', required: true },
|
||||
},
|
||||
},
|
||||
render: (_args, value) => [{ type: 'text', text: renderSpawn(value) }],
|
||||
render: (_args, value) => [{ type: 'text', text: renderSpawn(value, maxResultBytes) }],
|
||||
},
|
||||
async execute(args: SpawnArgs, exec) {
|
||||
if (args.type.length === 0) throw new Error('type must be a non-empty string')
|
||||
@@ -161,13 +196,17 @@ export function apply(ctx: Context): void {
|
||||
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'terminal_send',
|
||||
description: 'Send text to a persistent terminal. By default Enter is submitted and the call waits for a prompt, stdin wait, output silence, timeout, or session exit. Background mode returns a task id for task_output/task_kill.',
|
||||
description: 'Send text to a persistent terminal. By default Enter is submitted and the call waits for a prompt, stdin wait, output silence, timeout, or session exit.'
|
||||
+ (enableRunInBackground ? ' Background mode returns a task id for task_output/task_kill.' : ''),
|
||||
parameters: {
|
||||
sessionId: { type: 'string', required: true, description: 'Terminal session id returned by terminal_open or terminal_list.' },
|
||||
text: { type: 'string', required: true, description: 'UTF-8 text to write to the terminal.' },
|
||||
submit: { type: 'boolean', description: 'Submit Enter after text (default true). Set false for control characters or incomplete REPL input.' },
|
||||
run_in_background: { type: 'boolean', description: 'Return a task id immediately; collect with task_output or stop with task_kill.' },
|
||||
...enableRunInBackground
|
||||
? { run_in_background: { type: 'boolean' as const, description: 'Return a task id immediately; collect with task_output or stop with task_kill.' } }
|
||||
: {},
|
||||
},
|
||||
finalizeContent,
|
||||
output: {
|
||||
schema: {
|
||||
oneOf: [
|
||||
@@ -193,7 +232,7 @@ export function apply(ctx: Context): void {
|
||||
type: 'text',
|
||||
text: value.kind === 'background'
|
||||
? `started background task ${value.taskId}`
|
||||
: renderSend(value),
|
||||
: renderSend(value, maxResultBytes),
|
||||
}],
|
||||
presentationMeta: (_args, value) => value.kind === 'foreground'
|
||||
? {
|
||||
@@ -209,6 +248,7 @@ export function apply(ctx: Context): void {
|
||||
const id = sessionId(args)
|
||||
const request = { text: args.text, submit: args.submit ?? true }
|
||||
if (args.run_in_background === true) {
|
||||
if (!enableRunInBackground) throw new Error('background terminal sends are disabled by tool-pty configuration')
|
||||
const tasks = ctx.get('tasks')
|
||||
if (tasks === undefined) throw new Error('background terminal sends require @deepseek-ai/dsh-tasks and @deepseek-ai/dsh-tool-tasks')
|
||||
let cancelRequested = false
|
||||
@@ -216,6 +256,7 @@ export function apply(ctx: Context): void {
|
||||
kind: 'pty-send',
|
||||
label: `${id}: ${args.text || '(input)'}`,
|
||||
owner,
|
||||
outputLimitBytes: maxResultBytes,
|
||||
run: () => {
|
||||
const operation = ctx.pty.startSend(owner, id, request)
|
||||
return {
|
||||
@@ -247,7 +288,7 @@ export function apply(ctx: Context): void {
|
||||
},
|
||||
presentResult(args, result) {
|
||||
if ((args as Partial<SendArgs>).run_in_background === true || result.isError) return undefined
|
||||
const raw = rawResultText(result)
|
||||
const raw = rawContentText(result.content)
|
||||
return raw === undefined ? undefined : { card: 'terminal', output: raw }
|
||||
},
|
||||
}))
|
||||
@@ -260,6 +301,7 @@ export function apply(ctx: Context): void {
|
||||
offset: { type: 'number', description: 'Newest-relative line offset (default 0).' },
|
||||
count: { type: 'number', description: 'Requested line count (default 500; backend caps apply).' },
|
||||
},
|
||||
finalizeContent,
|
||||
output: {
|
||||
schema: {
|
||||
type: 'object',
|
||||
@@ -272,7 +314,7 @@ export function apply(ctx: Context): void {
|
||||
truncated: { type: 'boolean', required: true },
|
||||
},
|
||||
},
|
||||
render: (_args, value) => [{ type: 'text', text: renderRead(value) }],
|
||||
render: (_args, value) => [{ type: 'text', text: renderRead(value, maxResultBytes) }],
|
||||
},
|
||||
execute(args: ReadArgs, exec) {
|
||||
const result = ctx.pty.read(requireAgent(exec.agent), sessionId(args), {
|
||||
@@ -291,6 +333,7 @@ export function apply(ctx: Context): void {
|
||||
sessionId: { type: 'string', required: true, description: 'Terminal session id.' },
|
||||
signal: { type: 'string', required: true, enum: ['SIGINT', 'SIGTERM', 'SIGKILL', 'SIGTSTP', 'SIGHUP'], description: 'Signal to deliver. Shell-targeted SIGKILL is rejected; use terminal_close.' },
|
||||
},
|
||||
finalizeContent,
|
||||
output: {
|
||||
schema: {
|
||||
type: 'object',
|
||||
@@ -314,6 +357,7 @@ export function apply(ctx: Context): void {
|
||||
parameters: {
|
||||
sessionId: { type: 'string', required: true, description: 'Terminal session id.' },
|
||||
},
|
||||
finalizeContent,
|
||||
output: {
|
||||
schema: {
|
||||
type: 'object',
|
||||
@@ -342,9 +386,10 @@ export function apply(ctx: Context): void {
|
||||
name: 'terminal_list',
|
||||
description: 'List persistent terminal sessions owned by the current agent.',
|
||||
parameters: {},
|
||||
finalizeContent,
|
||||
output: {
|
||||
schema: { type: 'array', items: SESSION_SNAPSHOT_SCHEMA },
|
||||
render: (_args, value) => [{ type: 'text', text: renderList(value) }],
|
||||
render: (_args, value) => [{ type: 'text', text: renderList(value, maxResultBytes) }],
|
||||
},
|
||||
execute(_args: Record<string, never>, exec) {
|
||||
return Promise.resolve(ctx.pty.list(requireAgent(exec.agent)))
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
/** Model and ACP rendering for persistent terminal tool results. */
|
||||
|
||||
import { TextRetainer } from '@deepseek-ai/dsh-retention'
|
||||
|
||||
interface RenderedSessionStatusRunning {
|
||||
kind: 'running'
|
||||
}
|
||||
@@ -44,56 +46,126 @@ interface RenderedReadResult {
|
||||
truncated: boolean
|
||||
}
|
||||
|
||||
const encoder = new TextEncoder()
|
||||
const TRUNCATED = '\n[output truncated]'
|
||||
|
||||
function byteLength(text: string): number {
|
||||
return encoder.encode(text).byteLength
|
||||
}
|
||||
|
||||
function retain(text: string, maxBytes: number, kind: 'head' | 'tail'): string {
|
||||
const retainer = new TextRetainer({ kind, maxBytes })
|
||||
retainer.push(text)
|
||||
return retainer.finish().text
|
||||
}
|
||||
|
||||
function fitWithSuffix(content: string, suffix: string, maxBytes: number): string {
|
||||
const fixedBytes = byteLength(suffix)
|
||||
if (fixedBytes >= maxBytes) return retain(suffix, maxBytes, 'tail')
|
||||
return `${retain(content, maxBytes - fixedBytes, 'tail')}${suffix}`
|
||||
}
|
||||
|
||||
function fitWithPrefix(prefix: string, content: string, maxBytes: number): string {
|
||||
const fixed = `${prefix}${TRUNCATED}`
|
||||
const fixedBytes = byteLength(fixed)
|
||||
if (fixedBytes >= maxBytes) return retain(fixed, maxBytes, 'head')
|
||||
return `${prefix}${retain(content, maxBytes - fixedBytes, 'tail')}${TRUNCATED}`
|
||||
}
|
||||
|
||||
function boundBodyWithSuffix(
|
||||
content: string,
|
||||
metadata: string,
|
||||
upstreamTruncated: boolean,
|
||||
maxBytes: number,
|
||||
): string {
|
||||
const suffix = `${metadata}${upstreamTruncated ? TRUNCATED : ''}`
|
||||
const complete = `${content}${suffix}`
|
||||
if (byteLength(complete) <= maxBytes) return complete
|
||||
return fitWithSuffix(content, `${metadata}${TRUNCATED}`, maxBytes)
|
||||
}
|
||||
|
||||
/**
|
||||
* Bound one complete terminal acknowledgement while preserving UTF-8 cuts.
|
||||
* @param text - complete acknowledgement text.
|
||||
* @param maxBytes - positive final result cap.
|
||||
* @returns bounded text with a truncation marker when it fits.
|
||||
*/
|
||||
export function boundTerminalText(text: string, maxBytes: number): string {
|
||||
if (byteLength(text) <= maxBytes) return text
|
||||
const markerBytes = byteLength(TRUNCATED)
|
||||
if (markerBytes >= maxBytes) return retain(TRUNCATED, maxBytes, 'tail')
|
||||
return `${retain(text, maxBytes - markerBytes, 'head')}${TRUNCATED}`
|
||||
}
|
||||
|
||||
/**
|
||||
* Render one created session and its bounded MOTD.
|
||||
* @param result - published spawn result.
|
||||
* @param maxBytes - complete UTF-8 result cap.
|
||||
* @returns Model-facing session acknowledgement.
|
||||
*/
|
||||
export function renderSpawn(result: RenderedSpawnResult): string {
|
||||
export function renderSpawn(result: RenderedSpawnResult, maxBytes: number): string {
|
||||
const label = result.name === undefined ? result.sessionId : `${result.sessionId} (${result.name})`
|
||||
return `started terminal session ${label} [type: ${result.type}]\n${result.motd || '(no startup output)'}`
|
||||
const prefix = `started terminal session ${label} [type: ${result.type}]\n`
|
||||
const motd = result.motd || '(no startup output)'
|
||||
const complete = `${prefix}${motd}`
|
||||
return byteLength(complete) <= maxBytes ? complete : fitWithPrefix(prefix, motd, maxBytes)
|
||||
}
|
||||
|
||||
/**
|
||||
* Render one settled interactive send.
|
||||
* @param result - settled send outcome.
|
||||
* @param maxBytes - complete UTF-8 result cap.
|
||||
* @returns Terminal output plus wait/session markers.
|
||||
*/
|
||||
export function renderSend(result: RenderedSendResult): string {
|
||||
export function renderSend(result: RenderedSendResult, maxBytes: number): string {
|
||||
const output = result.viewport || '(no new output)'
|
||||
const status = result.sessionStatus.kind === 'running'
|
||||
? 'running'
|
||||
: `exited code=${result.sessionStatus.exitCode ?? 'null'} signal=${result.sessionStatus.signal ?? 'null'}`
|
||||
return `${output}\n[wait: ${result.waitReason}]\n[session: ${status}]${result.truncated ? '\n[output truncated]' : ''}`
|
||||
return boundBodyWithSuffix(
|
||||
output,
|
||||
`\n[wait: ${result.waitReason}]\n[session: ${status}]`,
|
||||
result.truncated,
|
||||
maxBytes,
|
||||
)
|
||||
}
|
||||
|
||||
/**
|
||||
* Render one incremental background operation read.
|
||||
* @param read - consuming operation delta.
|
||||
* @returns Delta plus truncation marker when needed.
|
||||
* @returns Delta plus its upstream truncation marker. The generic task control
|
||||
* applies the producer's complete-result cap after adding task status.
|
||||
*/
|
||||
export function renderSendRead(read: RenderedSendRead): string {
|
||||
return `${read.delta}${read.truncated ? `${read.delta.endsWith('\n') || read.delta.length === 0 ? '' : '\n'}[output truncated]` : ''}`
|
||||
const separator = read.delta.endsWith('\n') || read.delta.length === 0 ? '' : '\n'
|
||||
return `${read.delta}${read.truncated ? `${separator}[output truncated]` : ''}`
|
||||
}
|
||||
|
||||
/**
|
||||
* Render one bounded historical page.
|
||||
* @param result - retained scrollback page.
|
||||
* @param maxBytes - complete UTF-8 result cap.
|
||||
* @returns Page text plus pagination and truncation markers.
|
||||
*/
|
||||
export function renderRead(result: RenderedReadResult): string {
|
||||
export function renderRead(result: RenderedReadResult, maxBytes: number): string {
|
||||
const output = result.text || '(no retained output)'
|
||||
return `${output}\n[lines: ${result.lineBegin}-${result.lineEnd} of ${result.totalLines}]${result.truncated ? '\n[output truncated]' : ''}`
|
||||
return boundBodyWithSuffix(
|
||||
output,
|
||||
`\n[lines: ${result.lineBegin}-${result.lineEnd} of ${result.totalLines}]`,
|
||||
result.truncated,
|
||||
maxBytes,
|
||||
)
|
||||
}
|
||||
|
||||
/**
|
||||
* Render owner-visible live sessions.
|
||||
* @param sessions - fresh owner-scoped snapshots.
|
||||
* @param maxBytes - complete UTF-8 result cap.
|
||||
* @returns One line per session or the empty marker.
|
||||
*/
|
||||
export function renderList(sessions: readonly RenderedSessionSnapshot[]): string {
|
||||
export function renderList(sessions: readonly RenderedSessionSnapshot[], maxBytes: number): string {
|
||||
if (sessions.length === 0) return '(no terminal sessions)'
|
||||
return sessions.map((session) => {
|
||||
const text = sessions.map((session) => {
|
||||
const name = session.name === undefined ? '' : ` (${session.name})`
|
||||
const pid = session.pid === undefined ? '' : ` pid=${session.pid}`
|
||||
const status = session.status.kind === 'running'
|
||||
@@ -101,4 +173,5 @@ export function renderList(sessions: readonly RenderedSessionSnapshot[]): string
|
||||
: `exited code=${session.status.exitCode ?? 'null'} signal=${session.status.signal ?? 'null'}`
|
||||
return `${session.sessionId}${name} [${session.type}] ${status}${pid}`
|
||||
}).join('\n')
|
||||
return boundBodyWithSuffix(text, '', false, maxBytes)
|
||||
}
|
||||
|
||||
@@ -1,23 +1,23 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { PtySessionId } from '@deepseek-ai/dsh-pty'
|
||||
import { renderList, renderRead, renderSend, renderSendRead, renderSpawn } from '@deepseek-ai/dsh-tool-pty/src/render.ts'
|
||||
import { boundTerminalText, renderList, renderRead, renderSend, renderSendRead, renderSpawn } from '@deepseek-ai/dsh-tool-pty/src/render.ts'
|
||||
|
||||
describe('tool-pty rendering', () => {
|
||||
it('renders spawn with and without names or MOTD', () => {
|
||||
expect(renderSpawn({ sessionId: PtySessionId('pty-1'), type: 'shell', status: { kind: 'running' }, motd: '' }))
|
||||
expect(renderSpawn({ sessionId: PtySessionId('pty-1'), type: 'shell', status: { kind: 'running' }, motd: '' }, 1024))
|
||||
.toBe('started terminal session pty-1 [type: shell]\n(no startup output)')
|
||||
expect(renderSpawn({ sessionId: PtySessionId('pty-2'), name: 'main', type: 'shell', pid: 2, status: { kind: 'running' }, motd: 'ready' }))
|
||||
expect(renderSpawn({ sessionId: PtySessionId('pty-2'), name: 'main', type: 'shell', pid: 2, status: { kind: 'running' }, motd: 'ready' }, 1024))
|
||||
.toContain('pty-2 (main)')
|
||||
})
|
||||
|
||||
it('renders running, exited, empty, and truncated sends', () => {
|
||||
expect(renderSend({ viewport: '', waitReason: 'timeout', sessionStatus: { kind: 'running' }, truncated: true }))
|
||||
expect(renderSend({ viewport: '', waitReason: 'timeout', sessionStatus: { kind: 'running' }, truncated: true }, 1024))
|
||||
.toBe('(no new output)\n[wait: timeout]\n[session: running]\n[output truncated]')
|
||||
expect(renderSend({ viewport: 'bye', waitReason: 'session_exit', sessionStatus: { kind: 'exited', exitCode: null, signal: 'SIGTERM' }, truncated: false }))
|
||||
expect(renderSend({ viewport: 'bye', waitReason: 'session_exit', sessionStatus: { kind: 'exited', exitCode: null, signal: 'SIGTERM' }, truncated: false }, 1024))
|
||||
.toContain('exited code=null signal=SIGTERM')
|
||||
expect(renderSend({ viewport: 'bye', waitReason: 'session_exit', sessionStatus: { kind: 'exited', exitCode: 2, signal: null }, truncated: false }))
|
||||
expect(renderSend({ viewport: 'bye', waitReason: 'session_exit', sessionStatus: { kind: 'exited', exitCode: 2, signal: null }, truncated: false }, 1024))
|
||||
.toContain('exited code=2 signal=null')
|
||||
expect(renderSend({ viewport: 'bye', waitReason: 'session_exit', sessionStatus: { kind: 'exited', exitCode: null, signal: null }, truncated: false }))
|
||||
expect(renderSend({ viewport: 'bye', waitReason: 'session_exit', sessionStatus: { kind: 'exited', exitCode: null, signal: null }, truncated: false }, 1024))
|
||||
.toContain('exited code=null signal=null')
|
||||
expect(renderSendRead({ delta: '', truncated: true })).toBe('[output truncated]')
|
||||
expect(renderSendRead({ delta: 'x', truncated: true })).toBe('x\n[output truncated]')
|
||||
@@ -26,14 +26,48 @@ describe('tool-pty rendering', () => {
|
||||
})
|
||||
|
||||
it('renders history and every list status shape', () => {
|
||||
expect(renderRead({ text: '', totalLines: 0, lineBegin: 0, lineEnd: 0, truncated: true }))
|
||||
expect(renderRead({ text: '', totalLines: 0, lineBegin: 0, lineEnd: 0, truncated: true }, 1024))
|
||||
.toBe('(no retained output)\n[lines: 0-0 of 0]\n[output truncated]')
|
||||
expect(renderList([])).toBe('(no terminal sessions)')
|
||||
expect(renderList([], 1024)).toBe('(no terminal sessions)')
|
||||
expect(renderList([
|
||||
{ sessionId: PtySessionId('pty-1'), type: 'shell', status: { kind: 'running' } },
|
||||
{ sessionId: PtySessionId('pty-2'), name: 'done', type: 'shell', pid: 9, status: { kind: 'exited', exitCode: 2, signal: null } },
|
||||
{ sessionId: PtySessionId('pty-3'), type: 'shell', status: { kind: 'exited', exitCode: null, signal: 'SIGTERM' } },
|
||||
{ sessionId: PtySessionId('pty-4'), type: 'shell', status: { kind: 'exited', exitCode: null, signal: null } },
|
||||
])).toBe('pty-1 [shell] running\npty-2 (done) [shell] exited code=2 signal=null pid=9\npty-3 [shell] exited code=null signal=SIGTERM\npty-4 [shell] exited code=null signal=null')
|
||||
], 1024)).toBe('pty-1 [shell] running\npty-2 (done) [shell] exited code=2 signal=null pid=9\npty-3 [shell] exited code=null signal=SIGTERM\npty-4 [shell] exited code=null signal=null')
|
||||
})
|
||||
|
||||
it('bounds complete UTF-8 results while retaining terminal metadata when it fits', () => {
|
||||
const send = renderSend({
|
||||
viewport: `prefix-${'界'.repeat(40)}`,
|
||||
waitReason: 'stdin_read',
|
||||
sessionStatus: { kind: 'running' },
|
||||
truncated: false,
|
||||
}, 64)
|
||||
expect(Buffer.byteLength(send)).toBeLessThanOrEqual(64)
|
||||
expect(send).toContain('[wait: stdin_read]')
|
||||
expect(send).toContain('[output truncated]')
|
||||
|
||||
const read = renderRead({
|
||||
text: 'x'.repeat(200), totalLines: 20, lineBegin: 0, lineEnd: 10, truncated: false,
|
||||
}, 48)
|
||||
expect(Buffer.byteLength(read)).toBeLessThanOrEqual(48)
|
||||
expect(read).toContain('[lines: 0-10 of 20]')
|
||||
|
||||
expect(Buffer.byteLength(renderSpawn({
|
||||
sessionId: PtySessionId('pty-1'), type: 'shell', status: { kind: 'running' }, motd: 'x'.repeat(200),
|
||||
}, 32))).toBeLessThanOrEqual(32)
|
||||
|
||||
const boundedSpawn = renderSpawn({
|
||||
sessionId: PtySessionId('pty-1'), type: 'shell', status: { kind: 'running' }, motd: 'x'.repeat(200),
|
||||
}, 96)
|
||||
expect(boundedSpawn).toContain('started terminal session pty-1')
|
||||
expect(boundedSpawn).toContain('[output truncated]')
|
||||
|
||||
expect(Buffer.byteLength(renderSend({
|
||||
viewport: 'x'.repeat(200), waitReason: 'stdin_read', sessionStatus: { kind: 'running' }, truncated: false,
|
||||
}, 8))).toBeLessThanOrEqual(8)
|
||||
expect(boundTerminalText('x'.repeat(200), 8)).toHaveLength(8)
|
||||
expect(boundTerminalText('x'.repeat(200), 32).endsWith('[output truncated]')).toBe(true)
|
||||
})
|
||||
})
|
||||
|
||||
@@ -32,20 +32,23 @@ class StubSession implements PtyBackendSession {
|
||||
autoSettle = true
|
||||
rejectOperation = false
|
||||
closeGate: PromiseWithResolvers<undefined> | undefined
|
||||
viewport = 'command output'
|
||||
delta = 'live output'
|
||||
deltaTruncated = false
|
||||
|
||||
startSend(_request: PtySendRequest): PtySendOperation {
|
||||
let settle!: () => void
|
||||
let reject!: (error: unknown) => void
|
||||
let cancelled = false
|
||||
const done = new Promise<void>((resolve, rejectPromise) => { settle = resolve; reject = rejectPromise }).then(() => ({
|
||||
viewport: cancelled ? '^C' : 'command output',
|
||||
viewport: cancelled ? '^C' : this.viewport,
|
||||
waitReason: 'stdin_read' as const,
|
||||
sessionStatus: this.statusValue,
|
||||
truncated: false,
|
||||
}))
|
||||
const operation: PtySendOperation = {
|
||||
done,
|
||||
readOutput: () => ({ delta: 'live output', truncated: false }),
|
||||
readOutput: () => ({ delta: this.delta, truncated: this.deltaTruncated }),
|
||||
cancel: () => {
|
||||
if (cancelled) return false
|
||||
cancelled = true
|
||||
@@ -88,7 +91,13 @@ function stubBackend() {
|
||||
return { backend, sessions }
|
||||
}
|
||||
|
||||
async function setup(tasks: boolean) {
|
||||
async function setup(tasks: boolean, config: ToolPty.Config = {}) {
|
||||
const base = await setupBase(tasks)
|
||||
await base.ctx.plugin(ToolPty, config)
|
||||
return base
|
||||
}
|
||||
|
||||
async function setupBase(tasks: boolean) {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
@@ -100,7 +109,6 @@ async function setup(tasks: boolean) {
|
||||
await ctx.plugin(TaskService)
|
||||
await ctx.plugin(ToolTasks)
|
||||
}
|
||||
await ctx.plugin(ToolPty)
|
||||
return { ctx, stub, agent: fakeAgent(ctx, tasks ? 'with-tasks' : 'foreground') }
|
||||
}
|
||||
|
||||
@@ -291,6 +299,101 @@ describe('tool-pty foreground surface', () => {
|
||||
expect(ctx.tools.get('terminal_close')?.presentCall?.({ sessionId: 'pty-1' })).toMatchObject({ card: 'generic', title: 'Close terminal pty-1' })
|
||||
expect(ctx.tools.get('terminal_list')?.presentCall?.({})).toMatchObject({ card: 'generic', title: 'List terminal sessions' })
|
||||
})
|
||||
|
||||
it('configuration-gates background sends and validates the final result bound', async () => {
|
||||
const disabled = await setup(true, { enableRunInBackground: false })
|
||||
const definition = disabled.ctx.tools.get('terminal_send')
|
||||
expect(definition?.parameters).not.toHaveProperty('properties.run_in_background')
|
||||
expect(definition?.description).not.toContain('Background mode')
|
||||
await call(disabled.ctx, 'terminal_open', { type: 'stub' }, disabled.agent)
|
||||
expect((await call(disabled.ctx, 'terminal_send', {
|
||||
sessionId: 'pty-1', text: 'work', run_in_background: true,
|
||||
}, disabled.agent)).isError).toBe(true)
|
||||
|
||||
const defaults = await setupBase(false)
|
||||
ToolPty.apply(defaults.ctx)
|
||||
expect(defaults.ctx.tools.get('terminal_send')?.parameters).toHaveProperty('properties.run_in_background')
|
||||
|
||||
const invalid = await setupBase(false)
|
||||
expect(() => { ToolPty.apply(invalid.ctx, { maxResultBytes: 0 }) }).toThrow('maxResultBytes')
|
||||
expect(() => { ToolPty.apply(invalid.ctx, { maxResultBytes: 63 }) }).toThrow('at least 64')
|
||||
})
|
||||
|
||||
it('bounds normalized errors and preserves allocated ids at the minimum result cap', async () => {
|
||||
const { ctx, agent } = await setup(true, { maxResultBytes: 64 })
|
||||
const failed = await call(ctx, 'terminal_open', { type: 'x'.repeat(1_000) }, agent)
|
||||
expect(failed.isError).toBe(true)
|
||||
expect(Buffer.byteLength(text(failed))).toBeLessThanOrEqual(64)
|
||||
expect(text(failed)).toContain('[output truncated]')
|
||||
|
||||
const opened = await call(ctx, 'terminal_open', { type: 'stub', name: 'n'.repeat(1_000) }, agent)
|
||||
expect(text(opened)).toContain('pty-1')
|
||||
expect(Buffer.byteLength(text(opened))).toBeLessThanOrEqual(64)
|
||||
const background = await call(ctx, 'terminal_send', {
|
||||
sessionId: 'pty-1', text: 'work', run_in_background: true,
|
||||
}, agent)
|
||||
expect(text(background)).toContain('pty-send-1')
|
||||
expect(Buffer.byteLength(text(background))).toBeLessThanOrEqual(64)
|
||||
})
|
||||
|
||||
it('bounds terminal results after policy decisions and pipeline failures', async () => {
|
||||
const { ctx, agent } = await setup(false, { maxResultBytes: 64 })
|
||||
ctx.on('tools/pre-execute', async (exec, next) => {
|
||||
if (exec.name === 'terminal_list') return { kind: 'deny', reason: 'd'.repeat(1_000) }
|
||||
if (exec.name === 'terminal_signal') throw new Error(`pre failed: ${'p'.repeat(1_000)}`)
|
||||
return next()
|
||||
})
|
||||
ctx.on('tools/execute', async (exec, next) => {
|
||||
if (exec.name === 'terminal_close') throw new Error(`around failed: ${'e'.repeat(1_000)}`)
|
||||
return next()
|
||||
})
|
||||
ctx.on('tools/post-execute', async (exec, _result, next) => {
|
||||
if (exec.name === 'terminal_open') {
|
||||
return { kind: 'accept', content: [{ type: 'text', text: 'a'.repeat(1_000) }] }
|
||||
}
|
||||
if (exec.name === 'terminal_read') {
|
||||
return { kind: 'block', feedback: [{ type: 'text', text: 'b'.repeat(1_000) }] }
|
||||
}
|
||||
if (exec.name === 'terminal_send') throw new Error(`post failed: ${'o'.repeat(1_000)}`)
|
||||
return next()
|
||||
})
|
||||
|
||||
const denied = await call(ctx, 'terminal_list', {}, agent)
|
||||
expect(denied.isError).toBe(true)
|
||||
expect(Buffer.byteLength(text(denied))).toBeLessThanOrEqual(64)
|
||||
expect(text(denied)).toContain('[output truncated]')
|
||||
|
||||
const replaced = await call(ctx, 'terminal_open', { type: 'stub' }, agent)
|
||||
expect(replaced.isError).toBe(false)
|
||||
expect(Buffer.byteLength(text(replaced))).toBeLessThanOrEqual(64)
|
||||
expect(text(replaced)).toContain('[output truncated]')
|
||||
|
||||
const blocked = await call(ctx, 'terminal_read', { sessionId: 'pty-1' }, agent)
|
||||
expect(blocked.isError).toBe(true)
|
||||
expect(Buffer.byteLength(text(blocked))).toBeLessThanOrEqual(64)
|
||||
expect(text(blocked)).toContain('[output truncated]')
|
||||
|
||||
const failures = [
|
||||
await call(ctx, 'terminal_signal', { sessionId: 'pty-1', signal: 'SIGINT' }, agent),
|
||||
await call(ctx, 'terminal_close', { sessionId: 'pty-1' }, agent),
|
||||
await call(ctx, 'terminal_send', { sessionId: 'pty-1', text: 'work' }, agent),
|
||||
]
|
||||
for (const failure of failures) {
|
||||
expect(failure.isError).toBe(true)
|
||||
expect(Buffer.byteLength(text(failure))).toBeLessThanOrEqual(64)
|
||||
expect(text(failure)).toContain('[output truncated]')
|
||||
}
|
||||
})
|
||||
|
||||
it('leaves a structured around-dispatch failure unchanged', async () => {
|
||||
const { ctx, agent } = await setup(false, { maxResultBytes: 64 })
|
||||
ctx.on('tools/execute', async (exec, next) => exec.name === 'terminal_list'
|
||||
? { content: [], isError: true, error: { message: 'structured failure' } }
|
||||
: next())
|
||||
const result = await call(ctx, 'terminal_list', {}, agent)
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.content).toEqual([])
|
||||
})
|
||||
})
|
||||
|
||||
describe('tool-pty task integration', () => {
|
||||
@@ -305,6 +408,23 @@ describe('tool-pty task integration', () => {
|
||||
expect(text(output)).toContain('[status: completed, wait: stdin_read]')
|
||||
})
|
||||
|
||||
it('bounds foreground and background results after terminal and task metadata', async () => {
|
||||
const { ctx, agent, stub } = await setup(true, { maxResultBytes: 64 })
|
||||
await call(ctx, 'terminal_open', { type: 'stub' }, agent)
|
||||
stub.sessions[0]!.viewport = '界'.repeat(100)
|
||||
const foreground = await call(ctx, 'terminal_send', { sessionId: 'pty-1', text: 'foreground' }, agent)
|
||||
expect(Buffer.byteLength(text(foreground))).toBeLessThanOrEqual(64)
|
||||
|
||||
stub.sessions[0]!.delta = '界'.repeat(100)
|
||||
stub.sessions[0]!.deltaTruncated = true
|
||||
await call(ctx, 'terminal_send', { sessionId: 'pty-1', text: 'background', run_in_background: true }, agent)
|
||||
const background = await call(ctx, 'task_output', { task_id: 'pty-send-1', wait: true }, agent)
|
||||
expect(Buffer.byteLength(text(background))).toBeLessThanOrEqual(64)
|
||||
expect(text(background)).toContain('[status: completed')
|
||||
expect(text(background).match(/\[output truncated\]/g)).toHaveLength(1)
|
||||
expect(text(background)).toContain('[output truncated]\n[status: completed')
|
||||
})
|
||||
|
||||
it('rejects pre-aborted background calls, maps task cancellation, and contains operation failure', async () => {
|
||||
const { ctx, agent, stub } = await setup(true)
|
||||
await call(ctx, 'terminal_open', { type: 'stub' }, agent)
|
||||
|
||||
@@ -14,6 +14,9 @@
|
||||
{
|
||||
"path": "../../../vendor/cordis"
|
||||
},
|
||||
{
|
||||
"path": "../../util/retention"
|
||||
},
|
||||
{
|
||||
"path": "../pty"
|
||||
},
|
||||
|
||||
@@ -4,7 +4,7 @@ The process-local background task registry (`ctx.tasks`). It gives long-running
|
||||
|
||||
## Service API
|
||||
|
||||
- `start(spec): TaskId` validates the control surface, spec, and exact live owner before calling the producer's `run()` once. A starter throw leaves nothing registered; successful return commits without another failable step.
|
||||
- `start(spec): TaskId` validates the control surface, spec, exact live owner, and optional positive `outputLimitBytes` before calling the producer's `run()` once. A starter throw leaves nothing registered; successful return commits without another failable step.
|
||||
- `get(id, caller?)` and `list(caller?)` return non-consuming snapshots. Listing includes only caller-owned and unowned tasks.
|
||||
- `read(id, caller?)` consumes the single cursor for stream tasks and reads terminal output idempotently for final-output tasks.
|
||||
- `kill(id, caller?, reason?)` invokes producer cancellation before changing status. A cancellation throw leaves the task running; success changes it to `stopping` and marks terminal delivery reported.
|
||||
@@ -14,6 +14,8 @@ The process-local background task registry (`ctx.tasks`). It gives long-running
|
||||
|
||||
Owned access compares the task's `SessionId` with the caller's. Ids such as `bash-1` are predictable, so this fence is the boundary. Unowned tasks are open to callers and last until service disposal.
|
||||
|
||||
`outputLimitBytes` is producer-owned model-presentation policy carried unchanged into snapshots. A control surface applies it after adding status or notice metadata; the registry does not rewrite producer output or invent a default for producers that omit it.
|
||||
|
||||
## Lifecycle
|
||||
|
||||
Tasks belong to their owner and backend, not the producer tool fiber, so producer and surface reloads do not stop them. The first task for an owner attaches one awaited effect to the exact `Agent` scope. Owner disposal cancels that object's tasks, awaits producer quiescence, and removes their snapshots; reused agent or session ids cannot redirect an old cleanup.
|
||||
|
||||
@@ -42,6 +42,7 @@ interface TrackedTask {
|
||||
id: TaskId
|
||||
kind: TaskKind
|
||||
label: string
|
||||
outputLimitBytes: number | undefined
|
||||
/** Exact lifecycle owner; session-id authorization is derived from it. */
|
||||
owner: Agent | undefined
|
||||
cancel: (reason?: string) => void
|
||||
@@ -104,6 +105,10 @@ export class TaskService extends Service {
|
||||
}
|
||||
if (spec.kind.length === 0) throw new Error('invalid task kind: expected a non-empty string')
|
||||
if (spec.label.length === 0) throw new Error('invalid task label: expected a non-empty string')
|
||||
if (spec.outputLimitBytes !== undefined
|
||||
&& (!Number.isSafeInteger(spec.outputLimitBytes) || spec.outputLimitBytes <= 0)) {
|
||||
throw new Error(`invalid outputLimitBytes: expected a positive safe integer, got ${JSON.stringify(spec.outputLimitBytes)}`)
|
||||
}
|
||||
if (spec.owner !== undefined) this.ensureOwnerCleanup(spec.owner)
|
||||
|
||||
const hooks = spec.run()
|
||||
@@ -117,6 +122,7 @@ export class TaskService extends Service {
|
||||
id,
|
||||
kind: spec.kind,
|
||||
label: spec.label,
|
||||
outputLimitBytes: spec.outputLimitBytes,
|
||||
owner: spec.owner,
|
||||
cancel: hooks.cancel.bind(hooks),
|
||||
readOutput: hooks.readOutput?.bind(hooks),
|
||||
@@ -329,6 +335,7 @@ export class TaskService extends Service {
|
||||
id: task.id,
|
||||
kind: task.kind,
|
||||
label: task.label,
|
||||
...task.outputLimitBytes !== undefined ? { outputLimitBytes: task.outputLimitBytes } : {},
|
||||
...ownerSession !== undefined ? { ownerSession } : {},
|
||||
status: task.status,
|
||||
...task.detail !== undefined ? { detail: task.detail } : {},
|
||||
|
||||
@@ -61,6 +61,11 @@ export interface TaskStart {
|
||||
kind: TaskKind
|
||||
/** One-line model-facing label (the command; the delegation description). */
|
||||
label: string
|
||||
/**
|
||||
* Optional UTF-8 byte cap for each complete model-facing completion notice or
|
||||
* output read, including control-surface status metadata.
|
||||
*/
|
||||
outputLimitBytes?: number
|
||||
/**
|
||||
* Owning live agent. Access is fenced by its session id, and agent disposal
|
||||
* cancels and awaits the task. The instance must be the one currently
|
||||
@@ -109,6 +114,8 @@ export interface TaskSnapshot {
|
||||
kind: TaskKind
|
||||
/** The producer-supplied one-line label. */
|
||||
label: string
|
||||
/** Producer-owned cap for complete model-facing notices and output reads. */
|
||||
outputLimitBytes?: number
|
||||
/**
|
||||
* Owner session id used for authorization and correlation; absent for
|
||||
* unowned tasks. Completion listeners receive the exact {@link Agent}
|
||||
|
||||
@@ -44,13 +44,19 @@ function producer(overrides: Partial<Omit<TaskStart, 'run'> & TaskHooks> = {}) {
|
||||
let settle!: (outcome: TaskOutcome) => void
|
||||
let reject!: (error: unknown) => void
|
||||
const cancels: (string | undefined)[] = []
|
||||
const { kind = 'bash', label = 'sleep 60', owner, ...hookOverrides } = overrides
|
||||
const { kind = 'bash', label = 'sleep 60', owner, outputLimitBytes, ...hookOverrides } = overrides
|
||||
const hooks: TaskHooks = {
|
||||
cancel(reason) { cancels.push(reason) },
|
||||
done: new Promise<TaskOutcome>((res, rej) => { settle = res; reject = rej }),
|
||||
...hookOverrides,
|
||||
}
|
||||
const spec: TaskStart = { kind, label, ...owner !== undefined ? { owner } : {}, run: () => hooks }
|
||||
const spec: TaskStart = {
|
||||
kind,
|
||||
label,
|
||||
...owner !== undefined ? { owner } : {},
|
||||
...outputLimitBytes !== undefined ? { outputLimitBytes } : {},
|
||||
run: () => hooks,
|
||||
}
|
||||
return { spec, settle, reject, cancels }
|
||||
}
|
||||
|
||||
@@ -85,10 +91,11 @@ describe('TaskService.start', () => {
|
||||
.toThrow('background tasks unavailable: no control surface is attached (load @deepseek-ai/dsh-tool-tasks)')
|
||||
})
|
||||
|
||||
it('rejects an empty kind and an empty label', async () => {
|
||||
it('rejects an empty kind, empty label, and invalid output limit', async () => {
|
||||
const ctx = await harness()
|
||||
expect(() => ctx.tasks.start(producer({ kind: '' as TaskKind }).spec)).toThrow('invalid task kind')
|
||||
expect(() => ctx.tasks.start(producer({ label: '' }).spec)).toThrow('invalid task label')
|
||||
expect(() => ctx.tasks.start(producer({ outputLimitBytes: 0 }).spec)).toThrow('outputLimitBytes')
|
||||
})
|
||||
|
||||
it('issues kind-prefixed ids from per-kind counters', async () => {
|
||||
@@ -118,6 +125,16 @@ describe('TaskService reads and settlement', () => {
|
||||
expect(read.snapshot.finishedAt).toBeTypeOf('number')
|
||||
})
|
||||
|
||||
it('projects a producer-owned model output limit into reads and snapshots', async () => {
|
||||
const ctx = await harness()
|
||||
const p = producer({ outputLimitBytes: 64, readOutput: () => 'delta' })
|
||||
const id = ctx.tasks.start(p.spec)
|
||||
expect(ctx.tasks.read(id)).toMatchObject({
|
||||
text: 'delta', snapshot: { outputLimitBytes: 64 },
|
||||
})
|
||||
expect(ctx.tasks.get(id)).toMatchObject({ outputLimitBytes: 64 })
|
||||
})
|
||||
|
||||
it('final-output kinds read empty while live, the outcome output idempotently once settled', async () => {
|
||||
const ctx = await harness()
|
||||
const p = producer({ kind: 'subagent', label: 'research task' })
|
||||
|
||||
@@ -12,9 +12,11 @@ All three use generic ACP cards: `read` for output and list, `execute` for kill.
|
||||
|
||||
Their canonical values are `{ text, task }`, `PublicTaskSnapshot[]`, and `{ outcome: 'cancellation-requested' | 'already-finished', task }`. A public snapshot carries id, kind, label, status/detail, and start/finish times; it deliberately omits `ownerSession` and the internal `reported` notice bit. Native renderers preserve the status and acknowledgement text above.
|
||||
|
||||
When a producer supplies `outputLimitBytes`, `task_output`, terminal `task_kill`, and completion notices cap the complete Native UTF-8 result after adding status or notice text. Reads retain the output tail and control suffix when they fit; a bounded completion notice instead reserves `background task <id>` and the `task_output` collection instruction before spending remaining bytes on its variable kind, label, status, detail, and truncation marker. A prepended pre-execute listener captures the caller-visible task before policy, and each task-control definition's final-content callback applies its producer cap to single-text denials, short-circuits, normalized tool or pipeline failures, replacements, and blocks; structured multi-block policy results retain their shape. An existing producer truncation marker is reused rather than duplicated. Producers that omit the field retain the existing unbounded control-surface behavior.
|
||||
|
||||
## Completion notices
|
||||
|
||||
An unreported completion injects `background task <id> (<kind>: <label>) finished [status: ...]. Read its output with task_output.` into the exact owner's session. Injection is durable context for the next request, not a wake-up. A kill or terminal read/wait marks delivery reported and suppresses the redundant notice; owner-disposal races are contained.
|
||||
An unreported completion injects `background task <id> (<kind>: <label>) finished [status: ...]. Read its output with task_output.` into the exact owner's session. When bounded, the stable id prefix and collection command outrank variable label/detail so the notice remains actionable at PTY's supported 64-byte minimum. Injection is durable context for the next request, not a wake-up. A kill or terminal read/wait marks delivery reported and suppresses the redundant notice; owner-disposal races are contained.
|
||||
|
||||
## Config
|
||||
|
||||
@@ -69,7 +71,7 @@ Reads return output or `(no new output)` followed by `[status: <status>]` and op
|
||||
|
||||
#### Token effect
|
||||
|
||||
Results and notices remain in parent history until compaction. Stream reads do not repeat consumed output.
|
||||
Results and notices remain in parent history until compaction. Stream reads do not repeat consumed output; a producer-supplied `outputLimitBytes` bounds each complete read or notice.
|
||||
|
||||
#### KV Cache effect
|
||||
|
||||
|
||||
@@ -26,21 +26,23 @@
|
||||
"src"
|
||||
],
|
||||
"license": "BSD-3-Clause",
|
||||
"dependencies": {
|
||||
"schemastery": "^3.18.0"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"@deepseek-ai/dsh-agent": "^0.0.1",
|
||||
"@deepseek-ai/dsh-invariants": "^0.0.1",
|
||||
"@deepseek-ai/dsh-retention": "^0.0.1",
|
||||
"@deepseek-ai/dsh-system-prompt": "^0.0.1",
|
||||
"@deepseek-ai/dsh-tasks": "^0.0.1",
|
||||
"@deepseek-ai/dsh-tools": "^0.0.1",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
},
|
||||
"dependencies": {
|
||||
"schemastery": "^3.18.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@deepseek-ai/dsh-agent": "workspace:^",
|
||||
"@deepseek-ai/dsh-invariants": "workspace:^",
|
||||
"@deepseek-ai/dsh-llm": "workspace:^",
|
||||
"@deepseek-ai/dsh-retention": "workspace:^",
|
||||
"@deepseek-ai/dsh-session": "workspace:^",
|
||||
"@deepseek-ai/dsh-system-prompt": "workspace:^",
|
||||
"@deepseek-ai/dsh-tasks": "workspace:^",
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user