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

@@ -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/