Merge remote-tracking branch 'origin/master' into pr-265

# Conflicts: # docs/config-catalog.md # docs/cordis-catalog/services.md # docs/rfc/INDEX.md # examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl # examples/acp-agent/tests/snapshots/skill-load/session.jsonl # examples/acp-agent/tests/snapshots/text-turn/session.jsonl # examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl # examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl # packages/core/agent-loop/README.md # packages/core/agent-loop/src/loop.ts # packages/core/tools/README.md # packages/core/tools/src/index.ts # packages/core/tools/src/schema.ts # packages/ui/acp/src/index.ts # packages/ui/stdio-agent/README.md
2026-07-14 20:49:54 +08:00
parent 5ab8f2e328 fb126e164a
commit 77be4b891b
715 changed files with 21094 additions and 14133 deletions
@@ -11,15 +11,9 @@ import * as ToolFs from '@deepseek-ai/dsh-tool-fs'
 import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'

 /**
- * Shared harness for the fs-tools with-key e2e: a minimal real agent stack (the
- * DeepSeek adapter + the real fs provider + the read-before-write/edit policy +
- * the model-facing read/write/edit tools). Lives outside the *.e2e.ts pattern so
- * importing it never re-registers another file's tests.
- *
- * `fsCwd` is the local backend's default base; a per-session cwd (set via a
- * session header) overrides it, but this harness creates agents without a
- * session cwd, so the provider default IS the workspace. `persona` is the
- * deployment persona (the system-prompt plugin's per-context config).
+ * Build the real fs-tool stack for with-key e2e tests. Agents have no session
+ * cwd, so `fsCwd` is their workspace; `persona` configures the deployment prompt.
+ * This helper lives outside the e2e glob so imports do not register tests.
 */
 export async function fsHarness(fsCwd: string, persona = ''): Promise<Context> {
  const ctx = new Context()
@@ -1,16 +1,8 @@
 /**
- * Integration tests: the real local backend (`dsh-fs-local`) plus the model
- * tools (`dsh-tool-fs`) as the executor, exercised through `ctx.tools.execute()`
- * so nothing bypasses the tool registry. Two deployments:
- *
- *  - DEFAULT — with the real `dsh-fs-policy` policy gate plugin: read-before-
- *    write/edit, version-guarded mutation, FS_NOT_OBSERVED for unread edits.
- *  - BARE — WITHOUT the policy plugin: every `fs/*` waterfall falls through to
- *    its undefined default, so write/edit are unconditional. This proves the
- *    tool carries no dependency on the policy plugin.
- *
- * These verify the WORLD — files are read back from disk and asserted
- * byte-for-byte — not the tool's self-report.
+ * End-to-end tool-registry tests against the real local backend. The policy deployment verifies
+ * observed-state and guarded mutation; the bare deployment proves unconditional tools have no
+ * policy-service dependency. Assertions read files back byte-for-byte rather than trusting tool
+ * messages.
 */

 import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
@@ -28,9 +20,7 @@ import * as ToolFs from '@deepseek-ai/dsh-tool-fs'
 let dir: string
 let ctx: Context
 let fiber: Awaited<ReturnType<Context['plugin']>>
-// A stable session object stands in for an agent session (the file-state
-// owner). It carries a `header` (no `cwd`) so `sessionCwd(exec)` resolves to
-// `undefined` and the backend falls back to its configured cwd (= `dir`).
+// No header cwd: sessionCwd returns undefined and the provider's configured test dir applies.
 const session = { header: {} }

 let callCounter = 0
@@ -290,13 +280,9 @@ describe('bare provider (no dsh-fs-policy)', () => {
  })
 })

-// --------------------------------------------------------------------------
-// Per-session cwd: a relative file_path resolves against the CALLING session's
-// workspace (`exec.agent.session.header.cwd`), NOT the backend's config.cwd —
-// so an ACP editor's per-session dir wins, matching dsh-tool-bash. The regression
-// this guards: before the seam fix the tool passed no cwd, so a relative write
-// landed in config.cwd instead of the session dir.
-// --------------------------------------------------------------------------
+// Per-session cwd: a relative file_path resolves against the calling session's workspace
+// (`exec.agent.session.header.cwd`), not the backend's config.cwd — so an ACP editor's
+// per-session dir wins, matching dsh-tool-bash.
 describe('per-session cwd', () => {
  let sessionDir: string
  beforeEach(async () => {
@@ -428,9 +414,8 @@ describe('signal, concurrency, and the fs/observed contract', () => {
  })

  it('a throwing fs/observed listener surfaces as isError, but the mutation already hit disk', async () => {
-    // fs/observed is a plain ctx.emit AFTER the write succeeded; a throwing
-    // listener cannot roll the write back — it only turns the tool result into
-    // isError. The file must still carry the written bytes.
+    // fs/observed is a plain ctx.emit after the write succeeded; a throwing listener cannot
+    // roll the write back — it only turns the tool result into isError.
    ctx.on('fs/observed', () => { throw new Error('recording bug') })
    const result = await callOwned('write', { file_path: 'w.txt', content: 'durable' })
    expect(result.isError).toBe(true)
@@ -1,11 +1,6 @@
 /**
- * Consumer-surface tests for the filesystem tools as the EXECUTOR. They run the
- * REAL `@deepseek-ai/dsh-fs-policy` gate plugin (the genuine policy
- * collaborator, per the prefer-the-real-implementation rule) over a fake
- * `ctx.fs` provider, so they verify schemas, argument validation, result
- * formatting, FsError→isError propagation, and that each tool dispatches the
- * `fs/*` waterfalls + records observed-state through the gate (read authorizes a
- * later edit) — not just that it moved bytes.
+ * Consumer-surface tests over a fake provider and the real policy collaborator: schemas,
+ * validation, formatting, typed errors, intent dispatch, and observation-driven authorization.
 */

 import { describe, expect, it, vi } from 'vitest'
@@ -419,9 +414,8 @@ describe('tool-owned presentation (pure presentCall)', () => {
 })

 describe('result-time contextual diff (meta + presentResult)', () => {
-  // An edit records the applied contextual hunk on `tool/result` meta, and the
-  // tool's presentResult narrows it back into a `diff` result card the bridge
-  // renders. Drive execute end-to-end so the meta is the REAL computed hunk.
+  // An edit records the applied contextual hunk on `tool/result` meta, and the tool's
+  // presentResult narrows it back into a `diff` result card the bridge renders.
  const withContext = 'a\nb\nc\nOLD\nd\ne\nf\n'

  it('edit: execute attaches the applied hunk as meta { diffs }', async () => {
@@ -462,10 +456,9 @@ describe('result-time contextual diff (meta + presentResult)', () => {
  })

  it('write CREATE: no before-version → no meta, but presentResult still renders a whole-file diff card', async () => {
-    // A create has no prior content (no `meta`), yet the completed card must be a
-    // `diff` — an ACP tool_call_update.content REPLACES the call's content, so a
-    // non-diff result would clobber the pending new-file diff. The whole-file diff
-    // is derived from the args (oldText:null), replay-safe.
+    // A create has no prior content (no `meta`), yet the completed card must be a `diff` — an
+    // ACP tool_call_update.content REPLACES the call's content, so a non-diff result would
+    // clobber the pending new-file diff.
    const { ctx } = await setup()
    const session = { header: {} }
    const result = await call(ctx, 'write', { file_path: 'new.txt', content: 'fresh\n' }, { session })