Merge remote-tracking branch 'origin/master' into worktree/dsbench-patch

examples/acp-agent/tests/acp.snapshot.ts

@@ -5,10 +5,10 @@ import { defineAcpSnapshotSuite, type Scenario, type SnapshotSuiteOptions } from
 /**
  * The acp-agent example's snapshot suite: the scenario table for
  * `dsh-acp-snapshot`'s suite factory, which owns every compare/guard mechanic
- * (golden + re-persisted-log diffs, record/refresh write-back, the pinned-header
+ * (expected-output + re-persisted-log diffs, record/refresh write-back, the pinned-header
  * uniformity guard, the fixture guards). Fixtures live under `snapshots/<name>/`;
  * `pnpm run test:snapshot:record` re-records model transcripts against the real
- * API; `pnpm run test:snapshot:refresh` rewrites current replay goldens keyless.
+ * API; `pnpm run test:snapshot:refresh` rewrites current replay expected outputs keyless.
  * See the package README (packages/support/acp-snapshot) and the snapshot RFC,
  * docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md.
  */
@@ -103,6 +103,7 @@ const SCENARIOS: Scenario[] = [
     configPath: WORKSPACE_CONTEXT_CONFIG,
   },
   { name: 'cancel', hasModelTurn: true, recorded: false, overridden: true },
+  { name: 'cancel-tool-calls', hasModelTurn: true, recorded: false, overridden: true },
   { name: 'subagent-spawn', hasModelTurn: true, recorded: true },
   { name: 'subagent-multi', hasModelTurn: true, recorded: true },
   { name: 'subagent-fork', hasModelTurn: true, recorded: true },
@@ -122,6 +123,13 @@ const SCENARIOS: Scenario[] = [
     headerClass: 'advanced',
     configPath: ADVANCED_CONFIG,
   },
+  {
+    name: 'cordis-inspect-jsdoc',
+    hasModelTurn: true,
+    recorded: false,
+    headerClass: 'advanced',
+    configPath: ADVANCED_CONFIG,
+  },
   // Prompt-submit blocks are authored keylessly: they persist a rejected turn
   // and hook events without starting a model step, so their logs still compare.
   { name: 'hook-cc-promptsubmit-block', hasModelTurn: false, comparesLog: true, recorded: false },
@@ -129,7 +137,7 @@ const SCENARIOS: Scenario[] = [
   // The mid-turn seams fire during a real model turn, so each is recorded with its hook active
   // (the model's reaction to a deny/block/force-continue is part of the captured transcript).
   // SessionStart/SubagentStart are excluded because detached injection races log
-  // order; SubagentStop writes no transcript, so a golden could not prove it ran.
+  // order; SubagentStop writes no transcript, so an expected output could not prove it ran.
   // Unit tests cover those points; the hook-snapshot-matrix RFC owns the rationale.
   { name: 'hook-cc-promptsubmit-context', hasModelTurn: true, recorded: true },
   { name: 'hook-cc-pretool-deny', hasModelTurn: true, recorded: true },

examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md

@@ -44,10 +44,12 @@ declare const tools: {
     /** Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access. */
     justification?: string;
   }): Promise<string>;
-  /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. */
+  /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:"api"` or `what:"events"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */
   cordis_inspect(args: {
     /** Limit the report to one section. Omit for all sections. */
     what?: "services" | "plugins" | "tools" | "dynamic" | "api" | "events";
+    /** Exact service key or event name whose original JSDoc to include; valid only with what:"api" or what:"events". */
+    name?: string;
   }): Promise<string>;
   /** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:"api" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:"events"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:"api" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */
   cordis_mount(args: {

examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json

@@ -47,7 +47,7 @@
     },
     {
       "name": "cordis_inspect",
-      "description": "Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.",
+      "description": "Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.",
       "parameters": {
         "type": "object",
         "properties": {
@@ -62,6 +62,10 @@
               "api",
               "events"
             ]
+          },
+          "name": {
+            "type": "string",
+            "description": "Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."
           }
         }
       }

examples/acp-agent/tests/snapshots/cancel-tool-calls/input.json

@@ -0,0 +1,12 @@
+{
+  "steps": [
+    { "op": "initialize" },
+    { "op": "newSession" },
+    {
+      "op": "promptAndCancel",
+      "text": "Run two shell commands: wait for cancellation, then write skipped.txt.",
+      "afterUpdate": "tool_call",
+      "waitForToolCallUpdate": "call_skipped"
+    }
+  ]
+}

examples/acp-agent/tests/snapshots/cancel-tool-calls/replay.override.json

@@ -0,0 +1,15 @@
+[
+  {
+    "kind": "chunks",
+    "chunks": [
+      { "type": "block-start", "index": 0, "blockType": "tool-call" },
+      { "type": "tool-call-delta", "index": 0, "id": "call_wait", "name": "bash", "argumentsDelta": "{\"command\":\"node -e \\\"setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}" },
+      { "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_wait", "name": "bash", "arguments": "{\"command\":\"node -e \\\"setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}" } },
+      { "type": "block-start", "index": 1, "blockType": "tool-call" },
+      { "type": "tool-call-delta", "index": 1, "id": "call_skipped", "name": "bash", "argumentsDelta": "{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}" },
+      { "type": "block-end", "index": 1, "block": { "type": "tool-call", "id": "call_skipped", "name": "bash", "arguments": "{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}" } },
+      { "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 10 } },
+      { "type": "finish", "reason": { "kind": "tool-calls" } }
+    ]
+  }
+]

examples/acp-agent/tests/snapshots/cancel-tool-calls/session.jsonl

@@ -0,0 +1,20 @@
+{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}"}
+{"type":"turn/start","seq":0,"time":1784437195072,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
+{"type":"user/message","seq":1,"time":1784437195072,"data":{"content":[{"type":"text","text":"Run two shell commands: wait for cancellation, then write skipped.txt."}],"source":{"kind":"user"}},"surfaceOp":"append"}
+{"type":"step/start","seq":2,"time":1784437195076,"data":{"turn":1,"step":1}}
+{"type":"request/header","seq":3,"time":1784437195076,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
+{"type":"assistant/chunk","seq":4,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
+{"type":"assistant/chunk","seq":5,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_wait","name":"bash","argumentsDelta":"{\"command\":\"node -e \\\"setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}"}}}
+{"type":"assistant/chunk","seq":6,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_wait","name":"bash","arguments":"{\"command\":\"node -e \\\"setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}"}}}}
+{"type":"assistant/chunk","seq":7,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
+{"type":"assistant/chunk","seq":8,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_skipped","name":"bash","argumentsDelta":"{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}"}}}
+{"type":"assistant/chunk","seq":9,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_skipped","name":"bash","arguments":"{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}"}}}}
+{"type":"assistant/chunk","seq":10,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":10}}}}
+{"type":"assistant/chunk","seq":11,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
+{"type":"assistant/message","seq":12,"time":1784437195078,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_wait","name":"bash","arguments":"{\"command\":\"node -e \\\"setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}"},{"type":"tool-call","id":"call_skipped","name":"bash","arguments":"{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":10}},"sourceEventSeqs":[4,5,6,7,8,9,10,11],"surfaceOp":"append"}
+{"type":"tool/call","seq":13,"time":1784437195078,"data":{"turn":1,"step":1,"callId":"call_wait","name":"bash","arguments":"{\"command\":\"node -e \\\"setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}"}}
+{"type":"tool/result","seq":14,"time":1784437195089,"data":{"turn":1,"step":1,"callId":"call_wait","content":[{"type":"text","text":"Error: command aborted"}],"isError":true},"sourceEventSeqs":[13],"surfaceOp":"append"}
+{"type":"tool/call","seq":15,"time":1784437195089,"data":{"turn":1,"step":1,"callId":"call_skipped","name":"bash","arguments":"{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}"}}
+{"type":"tool/result","seq":16,"time":1784437195089,"data":{"turn":1,"step":1,"callId":"call_skipped","content":[{"type":"text","text":"Error: tool call skipped because the step was aborted before execution"}],"isError":true,"error":{"name":"AbortError","code":"ABORTED"}},"sourceEventSeqs":[15],"surfaceOp":"append"}
+{"type":"step/end","seq":17,"time":1784437195090,"data":{"turn":1,"step":1}}
+{"type":"turn/end","seq":18,"time":1784437195090,"data":{"turn":1,"reason":{"kind":"aborted","reason":"session/cancel"}}}

examples/acp-agent/tests/snapshots/cancel-tool-calls/stdout.expected.jsonl

@@ -0,0 +1,7 @@
+{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
+{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_wait","title":"node -e \"setInterval(() => {}, 1000)\"","kind":"execute","status":"in_progress","rawInput":"node -e \"setInterval(() => {}, 1000)\"","content":[{"type":"content","content":{"type":"text","text":"Wait until cancellation"}}]}}}
+{"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_wait","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\nError: command aborted\n```"}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_skipped","title":"printf skipped > skipped.txt","kind":"execute","status":"in_progress","rawInput":"printf skipped > skipped.txt","content":[{"type":"content","content":{"type":"text","text":"Write skipped marker"}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_skipped","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\nError: tool call skipped because the step was aborted before execution\n```"}}]}}}

examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/input.json

@@ -0,0 +1,7 @@
+{
+  "steps": [
+    { "op": "initialize" },
+    { "op": "newSession" },
+    { "op": "prompt", "text": "Inspect the exact tools service API and tools/pre-execute event with cordis_inspect, then reply with exactly CORDIS_INSPECT_JSDOC_OK." }
+  ]
+}

examples/headless-agent/tests/headless.snapshot.ts

@@ -13,7 +13,7 @@ import { describe, expect, it } from 'vitest'
 const snapshotsDir = join(dirname(fileURLToPath(import.meta.url)), 'snapshots')
 const scenarioDir = join(snapshotsDir, 'advanced-toolchain')
 const sessionFixture = join(scenarioDir, 'session.jsonl')
-const streamGolden = join(scenarioDir, 'stream-json.golden.jsonl')
+const streamExpected = join(scenarioDir, 'stream-json.expected.jsonl')
 const configPath = fileURLToPath(new URL('../advanced.cordis.snapshot.yml', import.meta.url))
 const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url))
 const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
@@ -134,7 +134,7 @@ describe('headless stream-json snapshots', () => {
 
     expect(result.stderr).toBe('')
     const normalized = normalizeHeadlessStream(result.stdout, runCwd)
-    if (refreshing) await writeFile(streamGolden, normalized)
-    expect(normalized).toBe(await readFile(streamGolden, 'utf8'))
+    if (refreshing) await writeFile(streamExpected, normalized)
+    expect(normalized).toBe(await readFile(streamExpected, 'utf8'))
   }, LOADER_SMOKE_TEST_TIMEOUT_MS)
 })

examples/repl-agent/cordis.yml

@@ -51,8 +51,8 @@
 - id: token-meter
   name: '@deepseek-ai/dsh-token-meter'
 
-# Summarize an older range when measured history approaches the context window.
-# Service-wide policy provides the ordinary threshold and retained-tail defaults.
+# Summarize an older range after measured pressure or a canonical provider overflow.
+# Service-wide policy provides pressure, retention, and one overflow-retry default.
 - id: compact-basic
   name: '@deepseek-ai/dsh-compact-basic'
 

examples/tui-agent/README.md

@@ -20,4 +20,4 @@ Run `pnpm run demo:code-mode tui` for the sibling Code Mode overlay.
 
 ## Snapshot tests
 
-`tests/snapshots/<scenario>/session.jsonl` supplies recorded user prompts and model chunks; sibling child logs drive subagents and workflows. The keyless suite executes those scripts through the real loop and tool implementations, then compares readable terminal cell/style goldens. Use `pnpm run test:snapshot:refresh` for presentation-only changes and `pnpm run test:snapshot:record` with a DeepSeek key when a recorded model journey changes. The implemented [TUI snapshot RFC](../../docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md) owns the scenario matrix and the split between recorded journeys, transient package snapshots, and PTY coverage.
+`tests/snapshots/<scenario>/session.jsonl` supplies recorded user prompts and model chunks; sibling child logs drive subagents and workflows. The keyless suite executes those scripts through the real loop and tool implementations, then compares readable expected terminal cell/style output. Use `pnpm run test:snapshot:refresh` for presentation-only changes and `pnpm run test:snapshot:record` with a DeepSeek key when a recorded model journey changes. The implemented [TUI snapshot RFC](../../docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md) owns the scenario matrix and the split between recorded journeys, transient package snapshots, and PTY coverage.

examples/tui-agent/tests/tui.snapshot.ts

@@ -296,7 +296,7 @@ describe('TUI recorded-session terminal snapshots', () => {
     it(scenario.name, async () => {
       observedScenarios.add(scenario.name)
       const result = await runScenario(scenario)
-      const terminalFile = join(scenarioDir(scenario), 'terminal.golden.txt')
+      const terminalFile = join(scenarioDir(scenario), 'terminal.expected.txt')
       if (MODE === 'record' || MODE === 'refresh') {
         await mkdir(scenarioDir(scenario), { recursive: true })
         await writeFile(terminalFile, result.terminal)
@@ -317,7 +317,7 @@ afterAll(async () => {
   for (const scenario of SCENARIOS) {
     const expected = [
       'session.jsonl',
-      'terminal.golden.txt',
+      'terminal.expected.txt',
       ...scenario.seedWorkspace === true ? ['workspace'] : [],
       ...Array.from({ length: scenario.childSessions ?? 0 }, (_, index) => `session.${index + 1}.jsonl`),
     ].sort()