feat(tool-fs): result-time applied-hunk diffs for write/edit

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.
This commit is contained in:
Tianyi Cui
2026-07-03 17:12:00 +08:00
parent af79ceea1c
commit d8fd3225af
48 changed files with 2217 additions and 1073 deletions

View File

@@ -99,7 +99,7 @@ Tool-call presentation is **owned by each tool** (`presentCall` / `presentResult
| `ToolCallKind` mapping | S | ✅ | ✅ | ✅ | `execute`/`read`/`edit`/`other` inferred from the tool; richer mapping possible. |
| `ToolCallStatus` | S | ✅ | ✅ | ✅ | `in_progress``completed`/`failed`. |
| `content` blocks | S | ✅ | ✅ | ✅ | Text content; the description renders above the card. |
| `diff` content | S | ✅ | ✅ | ✅ | The `write`/`edit` tools declare a `diff` render intent (`presentCall``{ card: 'diff' }`); the bridge emits `{ type: 'diff', path, oldText, newText }` content blocks (call-time, args-derived — applied-hunk diffs are a follow-up). |
| `diff` content | S | ✅ | ✅ | ✅ | The `write`/`edit` tools declare a `diff` render intent: `presentCall`a call-time `{ card: 'diff' }` snippet, and `presentResult` → a result-time `{ card: 'diff' }` carrying the APPLIED hunk with surrounding context lines (one hunk per `replace_all` site), computed from the before/after file text and persisted on the `tool/result` event. The bridge emits `{ type: 'diff', path, oldText, newText }` content blocks; the result hunk supersedes the call snippet. |
| `terminal` content | S | ✅ | ✅ | ✅ | Via the Zed `_meta` terminal convention (see below), not the spec `terminal/*` sub-protocol. |
| `locations` (follow-along) | S | ✅ | ✅ | ✅ | The `read`/`write`/`edit` tools emit `{ path, line? }` file-location hints via `presentCall`. |
| `rawInput` | S | ✅ | ⚠️ | ✅ | Parsed tool args surfaced as `rawInput`. |
@@ -147,7 +147,6 @@ Ranked by how commonly the reference adapters ship them and how much UX they unl
5. **Slash commands** (`available_commands_update`).
6. **MCP passthrough** (`mcpServers` on `session/new` + `mcpCapabilities`).
7. **Richer prompt content** — image / embedded `resource` blocks (needs a multimodal model path).
8. **Applied-hunk diff rendering** — the `write`/`edit` diff cards ship (call-time, args-derived: whole `old_string``new_string`). Result-time structured-patch hunks with surrounding context (what `claude-agent-acp` derives from a PostToolUse hook) need a new result/event shape carrying the patch — a follow-up.
9. **Usage reporting** (`usage_update`) — the harness already records token usage internally (on `assistant/message`).
10. **Editor filesystem delegation** (`fs/read_text_file` / `fs/write_text_file`) — lets the agent see unsaved buffers; lower priority since the harness has direct disk access.

View File

@@ -66,7 +66,7 @@ import { assertNever, CallId } from '@deepseek-ai/dsh-llm'
import type { Agent, AgentStatus } from '@deepseek-ai/dsh-agent'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { SessionId } from '@deepseek-ai/dsh-session'
import type { SessionEvent, TodoItem, TurnEndReason } from '@deepseek-ai/dsh-session'
import type { JsonValue, SessionEvent, TodoItem, TurnEndReason } from '@deepseek-ai/dsh-session'
import type { ToolCallKind, ToolCallView, ToolRegistry, ToolResultView, TerminalResultView } from '@deepseek-ai/dsh-tools'
// Side-effect type import: declaration-merges `ctx.sessionPersistence` onto
// Context (the bridge injects it and reads `list()` for load cwd validation).
@@ -818,7 +818,7 @@ export function streamSessionEventUpdate(
return
}
case 'tool/result': {
const view = presenter.result(event.data.callId, event.data.content, event.data.isError)
const view = presenter.result(event.data.callId, event.data.content, event.data.isError, event.data.meta)
notify({ sessionId, update: toolResultUpdate(event.data.callId, view, event.data.isError, terminal) })
return
}
@@ -919,14 +919,14 @@ export class ToolPresenter {
}
/** Completed-state render intent for a `tool/result`; consumes the remembered `(name, args, card)`. */
result(callId: CallId, content: ContentBlock[], isError: boolean): ToolResultView {
result(callId: CallId, content: ContentBlock[], isError: boolean, meta?: JsonValue): ToolResultView {
const call = this.pending.get(callId)
this.pending.delete(callId)
// No remembered call (unknown/late callId) → nothing to present from; raw content.
if (call === undefined) return { card: 'generic', content }
let present: ToolResultView | undefined
try {
present = this.tools.get(call.name)?.presentResult?.(call.args, { content, isError })
present = this.tools.get(call.name)?.presentResult?.(call.args, { content, isError, ...meta !== undefined ? { meta } : {} })
} catch (error: unknown) {
// A throwing presentResult must not break streaming/replay: log + fall back.
this.onError(`acp: tool "${call.name}" presentResult threw, using raw result: ${String(error)}`)
@@ -1126,7 +1126,9 @@ function terminalExitMeta(callId: string, view: TerminalResultView): TerminalExi
* (the terminal card consumes them and `content` is OMITTED — a
* `tool_call_update.content` REPLACES the call's content collection in Zed, so
* re-sending would clobber the terminal block the call installed) and otherwise
* derives the fenced ```console fallback from `output`.
* derives the fenced ```console fallback from `output`. A `diff` result emits the
* applied-hunk `{ type: 'diff' }` content blocks, which replace the call-time
* whole-file snippet in the editor.
*/
function toolResultUpdate(callId: CallId, view: ToolResultView, isError: boolean, terminal: TerminalRendering): ToolCallSessionUpdate {
const status = isError ? 'failed' as const : 'completed' as const
@@ -1167,6 +1169,20 @@ function toolResultUpdate(callId: CallId, view: ToolResultView, isError: boolean
...view.content !== undefined ? { content: toolResultContent(view.content) } : {},
...view.title !== undefined ? { title: view.title } : {},
}
case 'diff': {
// A result-time applied-hunk diff: emit one `{ type: 'diff' }` content block
// per hunk (mirroring the call-side diff arm). `tool_call_update.content`
// REPLACES the call's content in an editor, so these hunks supersede the
// call-time whole-file snippet the pending card installed.
const content: AcpToolCallContent[] = view.diffs.map(d => ({ type: 'diff', path: d.path, oldText: d.oldText, newText: d.newText }))
return {
sessionUpdate: 'tool_call_update',
toolCallId: callId,
status,
...content.length > 0 ? { content } : {},
...view.title !== undefined ? { title: view.title } : {},
}
}
default:
return assertNever(view, 'ToolResultView.card')
}

View File

@@ -618,6 +618,92 @@ describe('diff-card mapping', () => {
})
})
describe('result-time diff card (REAL fs edit tool → tool_call_update diff blocks)', () => {
// Drive the SHIPPING fs edit tool through the bridge: the pending tool/call
// installs the call-time snippet, then the tool/result carries the tool's
// computed applied-hunk `meta`, which presentResult narrows into a `diff`
// result card the bridge forwards as `{ type: 'diff' }` content blocks. Uses
// the REAL tool (not a stand-in) per the anti-mock convention, mirroring the
// call-side diff test above.
async function fsCtx(): Promise<Context> {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(FsLocal)
await ctx.plugin(ToolFs)
return ctx
}
function updatesWith(presenter: ToolPresenter, ...events: SessionEvent[]): SessionNotification['update'][] {
const out: SessionNotification['update'][] = []
for (const event of events) streamSessionEventUpdate(SessionId('s1'), event, n => out.push(n.update), presenter)
return out
}
it('forwards the applied-hunk meta onto the wire as tool_call_update diff content', async () => {
const ctx = await fsCtx()
const presenter = new ToolPresenter(ctx.tools)
const args = JSON.stringify({ file_path: 'src/b.ts', old_string: 'OLD', new_string: 'NEW' })
// The applied hunk the tool would compute and persist on the result meta.
const meta = { diffs: [{ path: 'src/b.ts', oldText: 'a\nOLD\nb', newText: 'a\nNEW\nb' }] }
const [, resultUpdate] = updatesWith(
presenter,
evt('tool/call', { turn: 1, step: 1, callId: CallId('e1'), name: 'edit', arguments: args }),
evt('tool/result', { turn: 1, step: 1, callId: CallId('e1'), content: [{ type: 'text', text: 'ok' }], isError: false, meta }),
)
expect(resultUpdate).toEqual({
sessionUpdate: 'tool_call_update',
toolCallId: 'e1',
status: 'completed',
title: 'Edit src/b.ts',
content: [{ type: 'diff', path: 'src/b.ts', oldText: 'a\nOLD\nb', newText: 'a\nNEW\nb' }],
})
await ctx.fiber.dispose()
})
it('an error result carries NO diff card (falls back to raw content)', async () => {
const ctx = await fsCtx()
const presenter = new ToolPresenter(ctx.tools)
const args = JSON.stringify({ file_path: 'src/b.ts', old_string: 'OLD', new_string: 'NEW' })
const [, resultUpdate] = updatesWith(
presenter,
evt('tool/call', { turn: 1, step: 1, callId: CallId('e1'), name: 'edit', arguments: args }),
evt('tool/result', { turn: 1, step: 1, callId: CallId('e1'), content: [{ type: 'text', text: 'Error: boom' }], isError: true }),
)
expect(resultUpdate).toMatchObject({ sessionUpdate: 'tool_call_update', status: 'failed' })
expect(resultUpdate).not.toHaveProperty('content', expect.arrayContaining([expect.objectContaining({ type: 'diff' })]))
await ctx.fiber.dispose()
})
it('a diff result with an EMPTY diffs array and no title omits both keys (nothing to send)', () => {
// A synthetic tool whose presentResult yields a `diff` card with no hunks and
// no title — the shipping fs tools never emit this (edit always has a hunk; an
// empty write returns undefined), so a stand-in is the only way to exercise
// the empty-content AND absent-title branches of the result-side diff arm.
const emptyDiffTool: ToolDefinition = {
name: 'writer',
description: 'writes a file',
parameters: {},
execute: async () => [],
presentCall: () => ({ card: 'diff', title: 'Write x', diffs: [{ path: 'x', oldText: null, newText: 'y' }] }),
presentResult: () => ({ card: 'diff', diffs: [] }),
}
const presenter = new ToolPresenter(registryOf(emptyDiffTool))
const [, resultUpdate] = updatesWith(
presenter,
evt('tool/call', { turn: 1, step: 1, callId: CallId('w1'), name: 'writer', arguments: '{}' }),
evt('tool/result', { turn: 1, step: 1, callId: CallId('w1'), content: [{ type: 'text', text: 'ok' }], isError: false }),
)
expect(resultUpdate).toEqual({
sessionUpdate: 'tool_call_update',
toolCallId: 'w1',
status: 'completed',
})
expect(resultUpdate).not.toHaveProperty('content')
expect(resultUpdate).not.toHaveProperty('title')
})
})
describe('relative-path display titles (bridge relativizes the title against the session cwd)', () => {
// The bridge relativizes a file card's TITLE against the session workspace cwd
// (mirroring the reference adapter's toDisplayPath), while leaving locations/