Merge origin/master into parallel-tool-call

packages/core/agent-loop/README.md

@@ -61,7 +61,7 @@ Everything that goes beyond "call the model, run the tools, repeat" belongs to p
 - Hooks and policy: the relevant `agent/*` checkpoints plus the guarded `tools/pre-execute` → `tools/execute` → `tools/post-execute` → `tools/result` pipeline; exact signatures and modes live in the [generated event catalog](../../../docs/cordis-catalog/events.md)
 - Compaction: `agent/pre-step`
 - Sandbox, permission, plan mode: `tools/pre-execute` for extensible deny/ask, `tools.guard()` for monotonic owner policy, `tools/post-execute` for result decisions, and `tools/result` for final observation
-- Sub-agents: implemented outside the loop as `ctx.subagents` providers; in-process providers use `ctx.agents.create()` and owned `AgentHandle` teardown, while child streaming/progress and background/poll collection remain deferred.
+- Sub-agents: implemented outside the loop as `ctx.subagents` providers; in-process providers use `ctx.agents.create()` and owned `AgentHandle` teardown, while generic [`ctx.tasks`](../../tasks/tasks/) plus [`dsh-tool-subagent`](../../subagent/tool-subagent/) own background collection.
 - Persistence: `session/event` + `session/flush`
 - UI: `session/event` (assistant token stream, boundaries, tool activity) + `agent/*` control events (`agent/status`, `agent/created`/`agent/disposed`)
 

packages/core/agent-loop/package.json

@@ -28,7 +28,7 @@
     "@deepseek-ai/dsh-session-persistence": "^0.0.1",
     "@deepseek-ai/dsh-system-prompt": "^0.0.1",
     "@deepseek-ai/dsh-tools": "^0.0.1",
-    "cordis": "^4.0.0-rc.6"
+    "cordis": "^4.0.0-rc.7"
   },
   "dependencies": {
     "schemastery": "^3.18.0"
@@ -43,6 +43,6 @@
     "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^",
     "@deepseek-ai/dsh-system-prompt": "workspace:^",
     "@deepseek-ai/dsh-tools": "workspace:^",
-    "cordis": "^4.0.0-rc.6"
+    "cordis": "^4.0.0-rc.7"
   }
 }

packages/core/agent-loop/src/tool-calls.ts

@@ -282,10 +282,8 @@ function appendToolResult(
 ): void {
   session.append('tool/result', {
     turn, step,
-    // The correlation id MUST be the loop's authoritative call.id (the
-    // model-transcript id deriveMessages turns into toolCallId), NOT
-    // result.callId — a post-execute listener returning a mismatched id would
-    // otherwise orphan the call↔result pairing in the next model request.
+    // Correlation stays with the loop's authoritative model-transcript call id;
+    // registry results deliberately do not duplicate it.
     callId: block.id,
     content: result.content,
     isError: result.isError,

packages/core/agent-loop/tests/contract-regressions.spec.ts

@@ -1045,8 +1045,7 @@ describe('tool result call identity', () => {
 
     // A post-execute listener transforms the result (accept-with-replacement).
     // The loop must still record the tool/result under the model's authoritative
-    // call.id (the loop ignores result.callId — which the registry always sets to
-    // exec.callId anyway — and uses call.id, the model-transcript id).
+    // call.id, which is the immutable identity carried by the execution input.
     ctx.on('tools/post-execute', (exec, _result) => {
       expect(exec.callId).toBe(CallId('c1')) // the loop passed the real id in
       return Promise.resolve({ kind: 'accept', content: [{ type: 'text', text: 'ok' }] })
@@ -1056,8 +1055,7 @@ describe('tool result call identity', () => {
     send(agent, 'use tool')
     await waitForIdle(ctx, agent)
 
-    // The logged tool/result.callId is the originating call.id, NOT the
-    // listener's wrong id.
+    // The logged tool/result.callId is the originating call.id.
     const resultEvent = [...agent.session.events].find(e => e.type === 'tool/result')
     expect(resultEvent?.type).toBe('tool/result')
     if (resultEvent?.type === 'tool/result') {