Retarget the pruning feature onto the merged compaction foundation.
Adapt content-only tool-result rewrite validation to the session-owned surface manager, migrate the demo wiring to repl-agent, and refresh generated type, catalog, and website contracts while preserving pressure and overflow pruning behavior.
Review round 2 (tianyicui inline comments):
- dsh-system-prompt itself registers the harness:identity (-100) and
deployment:persona (0) sections — they must survive a swapped loop
plugin, so they leave dsh-agent-loop; the persona text is the plugin's
own validated 'persona' config. The model/cwd variables STAY on the
loop: runtime facts of the agents it drives.
- AgentOptions.systemPrompt is deleted with all its forwarding plumbing:
the app configs' systemPrompt keys become 'persona' routed through
dsh-agent-core (schema = z.intersect of the owners'), the ACP bridge
and tool-subagent stop carrying persona configuration, and subagent
children now render the deployment persona like every other agent.
- Example personas drop transport/interface trivia (ACP, CLI) — facts
irrelevant to the model.
- Root CONTEXT.md removed (not idiomatic); its persona definition was
wrong under the new ownership anyway.
- Docs, READMEs, the prompt-variables RFC, and generated catalogs
updated; new loop test pins the assemble-waterfall escape valve
(an emptied assembly sends NO system field).
ImageBlock had no production producer and every consumer dropped it:
the deepseek serializer skipped it, the pi-ai converter skipped it as
unrepresentable, the ACP bridge neither advertises image prompt
capability nor forwards image blocks, and compact-basic charged a flat
85-token estimate and rendered an [image] placeholder. A block
constructed today would silently vanish from the wire — the vocabulary
advertised a capability no path honors, the silent-data-loss shape the
defensive patterns warn against. The only constructors were tests
pinning the skip/estimate branches.
Remove ImageBlock and its ContentBlockMap entry (its cache?: CacheHint
field leaves with it; CacheHint itself and the other two cache? fields
are out of scope). compact-basic loses its explicit image estimate and
placeholder arms (the merge-extensible default arms absorb the case);
the deepseek serializer, pi-ai converter, and ACP codec already handled
image in their default arms, so only their image-naming comments
change. The codec's inbound rejection of ACP-protocol image prompt
content stays — that guards wire content a client can send regardless
of our vocabulary.
Tests that constructed harness image blocks to pin the removed branches
are dropped (the 85-token estimate pin) or retargeted onto plugin-added
block types / other non-text blocks, which the surviving default arms
own. Docs, the type-equiv pastes, and the content-block vocabulary
RFC's block list and multimodal-home consequence are updated in the
same change; the RFC moves to implemented/ and the index is
regenerated. A real multimodal feature reintroduces image via
declaration merging together with the adapter mapping, ACP
advertisement, and compaction pricing that honor it.
Two pieces of dsh-acp surface were unreachable from any shipped config:
- AcpConfig.agentName/agentVersion: the app package hands the bridge only
{ model, systemPrompt }, so no leaf cordis.yml could set them; they were
settable only by direct-mounting the bridge (a unit test). Hardcode
agentInfo at the initialize site and delete the fields, their schema
defaults, the ?? fallbacks, and the TODO(double-default) whose subject
vanishes. The handshake wire value is unchanged (all snapshot initialize
lines byte-identical).
- The toolKindFor name heuristic special-cased bash*/read*/write/edit*
names in the generic-fallback path, violating the bridge's own design
rule ("the bridge never special-cases tool names"). Every first-party
tool ships its kind via presentCall; the fallback now renders the
neutral kind 'other'. The fallback is reachable when a presentCall
throws OR when model args fail the tool schema (defineTool's presentCall
wrapper returns undefined on violations) — the latter shows up in one
committed golden (hook-codex-posttool-block: three bash calls missing
the required description), whose kind cells flip execute->other. That
3-line golden refresh is the whole transcript delta.
The empty-arguments branch of parseToolArguments lost its only exercise
with the deleted heuristic test; it is live behavior (JSON.parse('')
throws, so the guard is what renders a zero-arg call as rawInput {}), so
it gets a dedicated pin instead of deletion.
RFC moved to docs/rfc/implemented/simplification/ and amended to shipped
reality: fallback reachability includes schema-invalid args, and the
golden churn is exactly the three kind cells (the original zero-churn
claim held only for the branding half).
The definitive sweep (audit every AGENTS.md mention in packages/, docs/,
examples/, scripts/) found thirteen more citations of relocated policy
and two citations of rules that never existed as quoted:
- with-key policy comments (web deepseek/perplexity e2e headers) ->
docs/testing.md; real-impl-over-mock comments (acp harness, load,
stream-update specs) -> docs/testing.md; defensive-pattern quotes
(acp index.ts x3, stream-update) -> docs/defensive-patterns.md.
- md-tier repoints: real-api-e2e RFC, tool-schema-catalog RFC,
postmortem 0001 guardrail row, adding-a-package cookbook,
drop-bash-output-spill-files RFC, acp-subagent-backend RFC phrasing.
- Two false attributions dropped in favor of self-contained reasoning:
tool-todo's 'don't validate scenarios that can't happen' and the
bash-stdin-env RFC's 'Don't add features beyond what the task
requires' (neither rule ever existed under those names).
- Citations of the two 'not golden truth' doctrines stay: those bullets
survive verbatim in the root conventions.
Note: packages/support/ui-stdio readline TTY spec flakes under full
coverage on a heavily loaded box (passes standalone and passed the
same tree's coverage run minutes earlier); untouched by this stack.
The result-time diff card sent view.title raw, so a completed edit/write
of an absolute in-workspace path flipped the card header back from the
relativized `Edit src/b.ts` to the absolute path — the pending card
relativizes, the result did not, and tool_call_update.title replaces the
header. Apply displayTitle to the result diff arm using the diff path,
mirroring the call-side card. Regression test proven red on the unfixed
arm.
Also record the overwrite diff-basis pre-read as a bounded follow-up
(TODO(overwrite-diff-bound) + RFC non-goal): overwriting a large file
reads the whole prior text into memory for a UI-only diff.
Three comments still implied the result diff is always an applied hunk or
that write returns undefined on no-hunk: the toolResultUpdate JSDoc (a diff
result "emits the applied-hunk blocks, which replace the call-time snippet"),
the empty-diffs test comment ("an empty write returns undefined" — write now
falls back to a whole-file diff), and diffsFromMeta's JSDoc ("a bad meta
yields no diff card" — only true for edit; write falls back to a whole-file
diff). Each now states the write whole-file fallback. Regenerate the catalog.
fs write/edit now emit a result-time contextual-diff tool_call_update
(the applied hunk with ±3 context lines, one hunk per replace_all site),
matching what claude-agent-acp sends and what makes an editor render the
change in place. The call-time snippet diff stays; the result hunk
supersedes it (ACP content-replace).
Mechanism:
- A persisted tool-private `meta` channel: execute may return
`{ content, meta }`; `meta` (JsonValue) rides on the tool/result event
and is handed back to presentResult, so the diff reproduces on replay
(event-sourced). JsonValue is now exported from dsh-session.
- The backend returns raw before/after text (storage facts) on
FsWriteOutcome/FsEditOutcome; the tool computes the hunk via the npm
`diff` package's structuredPatch. A create has no before → no result
diff; a failed/aborted mutation carries no meta.
- ToolResultView gains a DiffResultView; the bridge's result-side switch
renders it as {type:'diff'} content blocks.
RFC: docs/rfc/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.md
(justifies the npm `diff` runtime dep over vendoring and the meta channel);
the render-intent-union RFC's Non-goal is updated to record this shipped.
All fs snapshot goldens re-recorded; edit/overwrite gain the contextual
result diff, create/read/policy-reject unchanged in structure.
Address the render-intent-union review:
- toolResultUpdate branched on `if (card === 'terminal')` with a generic
fallthrough; ToolResultView is a closed union, so make it an exhaustive
`switch (view.card)` ending in assertNever (matching the call-side
renderer and the § Conventions closed-union rule). Adding a result card
later now fails to compile at the switch. Regression test: a rogue result
card throws.
- displayTitle's `rel.startsWith('..')` guard mis-rejected an in-workspace
target whose relative form merely begins with the chars `..` (e.g.
`..cache/x`, a real sibling name), leaving its title absolute. Test for a
`..` SEGMENT (`..` alone or `..<sep>…`) so such paths relativize, matching
claude-agent-acp's `cwd + sep` prefix check. Regression test added.
Replace the "bag of optional fields" tool-presentation types
(ToolCallPresentation / ToolResultPresentation / ToolTerminal) with a
card-tagged discriminated union — the standing FIXME(tool-presentation).
A tool declares one render intent per call/result and the ACP bridge
switches on `card`:
ToolCallView = generic | terminal | diff
ToolResultView = generic | terminal
The `diff` card is new: fs write/edit now emit an ACP {type:'diff'}
content block (an editor's inline diff), which the old shapes could not
express. The bridge also relativizes a file card's title against the
session cwd (mirroring claude-agent-acp's toDisplayPath) while keeping
locations/diff paths raw, and derives the no-capability fenced console
fallback from a terminal result's output. read gains the window-in-title
(`Read foo.txt (5 - 8)`) and an always-set location line, matching the
reference adapter field-for-field.
Migrates all three producer families (tool-fs, tool-bash, tool-todo) and
the sole consumer (the ACP bridge) together — the source does not compile
piecewise. Adds snapshot coverage for the terminal _meta path (a new
capability-advertising scenario) and re-records the fs goldens to show the
diff cards. Applied-hunk (result-time, context-line) diffs need a new
result/event shape and are a follow-up.
RFC: docs/rfc/implemented/architecture/2026-07-02-tool-render-intent-union.md
The fs tools rendered as generic cards (title = tool name, raw file content) in
an ACP editor. Give them tool-owned presentation like bash/subagent have:
- read → title "Read <path>", kind read, offset/limit as rawInput
- write → title "Write <path>", kind edit
- edit → title "Edit <path>", kind edit, a clipped old→new rawInput summary
Add a provider-neutral `locations: { path, line? }[]` to ToolCallPresentation —
the files a call reads/modifies — so a capable editor can follow along / jump to
the file (read carries its offset as the line). The ACP bridge forwards it onto
the wire `tool_call` (ResolvedCallPresentation + call() + the tool_call build in
streamSessionEventUpdate). This flips the `locations` cell in the ACP feature
matrix to supported. The SDK already carries `tool_call.locations`
(ToolCallLocation `{ path, line? }`), so no ACP types leak into dsh-tools.
presentResult is intentionally omitted: it only receives `{ content, isError }`,
not the write/edit outcome, so titling by create-vs-overwrite or replacement
count would mean parsing the model-facing text — the static title stays.
Tests: pure presentCall assertions for all three tools incl. locations and the
edit rawInput clip; a bridge test drives the REAL fs tools through ToolPresenter
and asserts locations reaches the wire tool_call (proven to fail without the
forwarding line). New withFs harness option + dsh-fs devDeps on dsh-acp.
Add @deepseek-ai/dsh-tool-todo (a new packages/todo/ group): a model-facing
todo_write(todos: [{content, status}]) tool with whole-list-replace semantics.
Each call appends the full list as a todo/write event to the calling agent's
session log; the current list is the most recent such event (last-write-wins).
Single-owner — a non-agent caller is rejected. Beyond the schema's
type/required/enum checks, execute rejects empty/duplicate content and more than
one in_progress task, narrowing the loosely-typed args into a real TodoItem[].
Both UIs render off the existing session/event: the stdio UI prints a glyphed
checklist; the ACP bridge maps the list to a `plan` sessionUpdate (todosToPlan
synthesizes the priority ACP requires; status maps 1:1). Wired into the
coding-agent, acp-agent, and snapshot example configs with a system-prompt nudge.
Tests: unit (schema, validation, append/replace, no-agent rejection, presentCall,
HMR-safety, Loader export-shape guard), full-loop integration through the agent
loop, the ACP todosToPlan mapping + stream-update arm, the stdio render arm, and
a session/load replay that re-emits the plan. New-group TS wiring added to
tsconfig.base/json/build. RFC + a doc-inventory sweep (architecture, packages
README, AGENTS layout, cookbook group list, example READMEs) ship with it.
The todo-plan ACP snapshot scenario is recorded separately (needs an API key).
The session event vocabulary carried two standalone trace-only events that
were not load-bearing as separate records. Fold their facts into nearby
load-bearing events and delete the standalone variants.
- Token usage now rides on `assistant/message` as an optional `usage` field —
the assembled model output and its accounting travel together. The loop folds
`assembler.usage` onto the append instead of emitting a separate `usage`
event.
- The max-tokens path is the no-data-loss host: a step cut off with usage but
EMPTY content (e.g. only a dropped tool call) previously emitted a standalone
`usage`; it now records an empty-content `assistant/message { content: [],
usage }`. `deriveMessages()` skips empty-content assistant messages, so the
usage host never injects a spurious content-less assistant turn into the
provider transcript. A step with neither content nor usage appends nothing.
- An operational error's step number now rides on `turn/end.reason` for
`kind: 'error'` (`{ kind: 'error', step, message, code? }`) — the durable
turn outcome ACP and resume already consume. `failTurn` sets the reason
directly (no separate session `error` event). `agent/error` + logging are
unchanged for live diagnostics.
- No format-version bump: pre-release, no persisted data, so per the format
policy there is nothing to migrate or reject (the RFC's "refresh the format
version" criterion over-reached). `version` stays 1.
- ACP fixtures + goldens re-recorded (keyless replay): dropped standalone
usage/error lines, usage folded onto assistant/message, error step on
turn/end.reason.
RFC moved proposed -> implemented with an implementation note recording the two
scope refinements.
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
Move the 18 flat packages/<name> packages into role-grouped dirs:
core/, llm/, bash/, session-persistence/, ui/, support/. Group dirs are
pure containers; each package keeps its @deepseek-ai/dsh-* name.
Collapse the per-package tsconfig paths maps (base + typecheck) into one
@deepseek-ai/dsh-* wildcard with a candidate per group, and derive the
publint list from the hierarchy. Update all depth-coupled globs/configs
(workspace, tsdown, vitest, eslint, knip, tsconfig includes/refs,
per-package tsconfigs, generators, doc-script scopes, type-equiv manifest)
and the cross-package/script relative imports in tests.
Fix doc-typecheck's workspacePaths() to parse tsconfig JSONC via the
TypeScript API instead of a regex comment-strip, which corrupted the
new wildcard `/*/` path candidates.
WIP: doc cross-links and package/RFC docs still to update.
