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.
9.7 KiB
dsh-tools
Tool registry and execution waterfall. Tool plugins register their schemas and executors; the agent loop executes calls through the tools/execute waterfall.
Service: ToolRegistry (ctx key: tools)
Public API
ctx.tools.register(definition: ToolDefinition): () => voidRegister a tool. Disposed with the calling fiber.ctx.tools.get(name: string): ToolDefinition | undefinedctx.tools.schemas(): ToolSchema[]Schemas of all registered tools (without theexecutefunctions). The shipped tools' schemas are catalogued in docs/tool-catalog/tools.md, generated by booting each tool plugin and harvesting this method (see the tool-schema-catalog RFC).ctx.tools.execute(exec: ToolExecution): Promise<ToolExecutionResult>Execute one tool call through thetools/executewaterfall.
Injected services
SystemPrompt — the registry automatically feeds its tool schemas into the system-prompt assembly via ctx.systemPrompt.tools().
Events
| Event | Mode | Purpose |
|---|---|---|
tools/execute |
waterfall | Wrap/veto tool execution (sandbox, permission, hooks, plan mode) |
tools/change |
emit | A tool was registered or unregistered |
Key types
ToolDefinition—ToolSchema+execute(args, exec): Promise<ContentBlock[] | { content: ContentBlock[]; meta? }>(the bare array is the model-facing content; the object form additionally attaches an opaque, JSON-serializablemetapresentation payload persisted on thetool/resultevent and handed back topresentResult), plus optionalpresentCall(args)/presentResult(args, result)for tool-owned UI presentation (see below).ToolExecution— one pending tool call:{ callId, name, arguments, agent?, signal? }.ToolExecutionResult— outcome:{ callId, content, isError, error? }. On failure with aHarnessError,error: { name, code }carries the structured failure class alongside the model-facing text (the loop forwards it onto thetool/resultsession event for retry/sandbox plugins and replay).ToolCallView/ToolResultView— provider-neutralcard-tagged render intents a tool returns frompresentCall/presentResultto own how a UI renders ITS calls (see "Tool-owned UI presentation").
Extension points
- Tool plugins call
ctx.tools.register()— schemas flow into the assembly automatically. - The
tools/executewaterfall is the single seam for sandbox, permission, hooks, and plan-mode plugins to wrap or veto a call. Listeners receive(exec, next): callnext()to proceed, or return a result without callingnext()to short-circuit (veto). - MCP servers: one plugin per server, discover tools, call
ctx.tools.register()with the server's schemas.
Typed tool parameter schemas
First-party plugin authors can use the defineTool() helper (exported from this package) for typed tool parameter schemas:
import { readFile } from 'node:fs/promises'
import type { Context } from 'cordis'
import { defineTool } from '@deepseek-ai/dsh-tools'
declare const ctx: Context
ctx.tools.register(defineTool({
name: 'read_file',
description: 'Read a file from disk.',
parameters: {
path: { type: 'string', required: true, description: 'Absolute file path' },
offset: { type: 'number' },
limit: { type: 'number' },
},
async execute(args, exec) {
// args is typed: { path: string; offset?: number; limit?: number }
const text = await readFile(args.path, 'utf8')
return [{ type: 'text', text }]
},
}))
The helper converts the author-facing SchemaSpec (with required: true as a per-property boolean) to standard JSON Schema for the wire format. Raw JSON-Schema tool definitions (from MCP servers) are still accepted by the registry directly.
A defineTool tool also validates the model-generated arguments against its SchemaSpec before execute runs (validateArgs). The model's JSON is untrusted — InferArgs<S> is a compile-time claim, not a runtime guarantee — so on a mismatch (missing required key, wrong primitive, bad enum member, nested violation) the tool throws a ToolArgsError (code: 'INVALID_ARGS'); the registry turns it into an isError result whose text lists the violations, which the model sees and self-corrects from. Validation mirrors the JSON Schema conversion exactly: extra keys are allowed, default is not applied, and an object/array prop without properties/items only type-checks. Raw-registered tools (MCP) are not validated by the harness — they validate their own input.
See defineTool, validateArgs, ToolArgsError, SchemaSpec, InferArgs, and schemaSpecToJsonSchema in the public API for details.
Tool-owned UI presentation
A tool owns how ITS calls render in a UI (an editor's tool-call card, a CLI log line) — a UI plugin must NOT special-case tool names. A ToolDefinition may declare two optional, pure, display-only methods that return a card-tagged render intent (a discriminated union — a tool declares its card kind once and a UI bridge switches on card):
presentCall(args): ToolCallView | undefined— the PENDING state, one of:{ card: 'generic', title, kind?, rawInput?, content?, locations? }— the default card: a human-readabletitle, an optionalkind(read/edit/execute/… for icon/treatment, defaultother), an optionalrawInput(the salient input to show in a detail view — e.g. a background task id, NOT the whole args object), optionalcontent(extra UI content blocks), and optionallocations({ path, line? }[]— files this call reads/modifies, so a capable UI can follow along; the ACP bridge forwards them astool_call.locations).{ card: 'terminal', title, description?, cwd? }— a shell command: a capable UI renders a terminal card (thetitleis the command,descriptionrenders above it,cwdheads it); an incapable UI falls back to a generic execute card.{ card: 'diff', title, diffs, locations? }— a file create/modify: a capable UI renders an inline diff card fromdiffs({ path, oldText, newText }[];oldText: nullfor a new file). Used bywrite/edit.
presentResult(args, result): ToolResultView | undefined— the COMPLETED state, given the sameargsand the{ content, isError, meta? }result, one of:{ card: 'generic', title?, content? }— an optional replacementtitleand reformattedcontent.{ card: 'terminal', title?, output?, exitCode?, signal? }— a terminal run's capturedoutputand exit status. A capable UI shows an exit-status pill; an incapable UI gets a fenced```consolefallback the BRIDGE derives fromoutput(the tool does not encode the fences).{ card: 'diff', title?, diffs }— a completed file mutation as an inline diff.diffsisFileDiff[]— the APPLIED hunks with surrounding context (one entry per changed site), computed from the before/after file content, distinct from the call-time whole-snippetdiff. Used bywrite/edit; atool_call_update.contentreplaces the call's content, so this supersedes the pending snippet.
Returning undefined (or omitting a method) tells a UI to fall back to a generic presentation (title = tool name, raw args as input, raw result content). Both methods must be pure and side-effect-free: a UI may call them during live streaming AND during a session-log replay, so they depend only on their arguments. result.meta is the tool's own optional presentation payload (JsonValue), attached by execute (see below) and persisted on the tool/result event, so a presentResult reading it stays replay-deterministic (the same meta is read back from the log). With defineTool, args is the typed InferArgs<S> shape; the helper soft-validates before calling (a malformed/older logged arg shape yields undefined rather than throwing, since display must never crash a replay). The views are provider-neutral — the ACP bridge (dsh-acp) maps each card to ACP tool_call/tool_call_update wire fields (a diff card to a { type: 'diff' } content block, a terminal card to the _meta terminal convention), and relativizes a file card's title against the session cwd. See the render-intent-union RFC (docs/rfc/implemented/architecture/2026-07-02-tool-render-intent-union.md) and the applied-hunk-diffs RFC (docs/rfc/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.md); dsh-tool-bash (terminal) and dsh-tool-fs (diff/generic) are the reference implementations.
import { defineTool } from '@deepseek-ai/dsh-tools'
const bash = defineTool({
name: 'bash',
description: 'Run a shell command.',
parameters: {
command: { type: 'string', required: true, description: 'The command to run.' },
description: { type: 'string', required: true, description: 'One-line summary shown in the UI.' },
},
async execute(args) {
return [{ type: 'text', text: `ran: ${args.command}` }]
},
// A terminal card: the command is the title, the description renders above it.
presentCall: args => ({ card: 'terminal', title: args.command, description: args.description }),
// A terminal result: the raw output + exit; the bridge derives the fenced fallback.
presentResult: (_args, result) => {
const block = result.content.length === 1 ? result.content[0] : undefined
if (block === undefined || block.type !== 'text') return undefined
return { card: 'terminal', output: block.text }
},
})
What is NOT here (TODO)
- Tool shapes review — when real tools land (e.g. a concurrency-safety hint for parallel execution); phase 1 executes tool calls sequentially.
- Parallel execution — the loop currently iterates tool calls sequentially.