{"id": "review-round-uses-thread-send", "area": "orchestration", "kind": "bad", "pattern": "review round sent to childThreadId", "experience": "Round 2 of a Sol review went to the round 1 childThreadId with t3_thread_send. The user: 'Use delegate_task please, this should not be a separate thread.'", "rule": "For every T3 delegated review round, call delegate_task again ... Do not use t3_thread_send on childThreadId to continue a delegated review.", "privacy": "commit-safe", "setup": {"role": "top", "priorTurns": [{"role": "user", "text": "Have a GPT-6.1 Sol delegate in Codex review the diff on this branch (https://github.com/acme/app/pull/123). Loop until it approves."}, {"role": "assistant", "text": "Sol round 1 is back with two findings. Both are real. Fixing them now.", "toolCalls": [{"tool": "orchestrator_capabilities", "input": {}, "result": {"parentThreadId": "33333333-3333-4333-8333-333333333333", "inheritedProviderInstanceId": "claudeAgent", "inheritedModel": "claude-sonnet-5-5", "inheritedOptions": [{"id": "effort", "value": "high"}], "runtimeMode": "full-access", "interactionMode": "default", "features": {"appOwnedSubagents": true, "asyncPolling": true, "cancellation": true, "batchThreadCreation": true, "threadManagement": true, "incrementalThreadRead": true, "scheduledTasks": true}, "providers": [{"providerInstanceId": "claudeAgent", "driverKind": "claudeAgent", "displayName": "Claude", "models": [{"id": "claude-opus-5-5", "label": "Claude Opus 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "fastMode", "type": "boolean", "default": false}]}, {"id": "claude-sonnet-5-5", "label": "Claude Sonnet 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}, {"id": "claude-haiku-5-5", "label": "Claude Haiku 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "codex", "driverKind": "codex", "displayName": "Codex", "models": [{"id": "gpt-6.1-sol", "label": "GPT-6.1 Sol", "options": [{"id": "reasoningEffort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "serviceTier", "values": ["default", "priority"], "default": "default"}]}]}, {"providerInstanceId": "muse", "driverKind": "muse", "displayName": "Muse Code", "runtimeModes": ["approval-required", "full-access"], "models": [{"id": "muse-wonder-full", "label": "Muse Wonder Full", "options": [{"id": "reasoningEffort", "values": ["minimal", "low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "grok", "driverKind": "grok", "displayName": "Grok", "models": [{"id": "grok-4.7", "label": "Grok 4.7", "options": []}]}]}}, {"tool": "delegate_task", "input": {"title": "Sol review round 1", "mode": "async", "clientRequestId": "sol-review-r1", "target": {"providerInstanceId": "codex", "model": "gpt-6.1-sol", "options": {"reasoningEffort": "high"}}, "task": "Review the diff of this branch against main. Read only. Report findings as S1, S2, ... and a verdict."}, "result": {"taskId": "task-1", "childThreadId": "44444444-4444-4444-8444-000000000001", "childRunId": "run-child-1", "status": "running", "workState": "working", "providerInstanceId": "codex", "model": "gpt-6.1-sol"}}, {"tool": "task_status", "input": {"taskId": "task-1"}, "result": {"taskId": "task-1", "childThreadId": "44444444-4444-4444-8444-000000000001", "status": "completed", "workState": "result_available", "summary": "CHANGES. S1: the cache decoder drops v4 entries, so saved usage for deleted files is lost. S2: two app versions share one cache file and overwrite each other."}}]}], "mocks": {"orchestrator_capabilities": {"parentThreadId": "33333333-3333-4333-8333-333333333333", "inheritedProviderInstanceId": "claudeAgent", "inheritedModel": "claude-sonnet-5-5", "inheritedOptions": [{"id": "effort", "value": "high"}], "runtimeMode": "full-access", "interactionMode": "default", "features": {"appOwnedSubagents": true, "asyncPolling": true, "cancellation": true, "batchThreadCreation": true, "threadManagement": true, "incrementalThreadRead": true, "scheduledTasks": true}, "providers": [{"providerInstanceId": "claudeAgent", "driverKind": "claudeAgent", "displayName": "Claude", "models": [{"id": "claude-opus-5-5", "label": "Claude Opus 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "fastMode", "type": "boolean", "default": false}]}, {"id": "claude-sonnet-5-5", "label": "Claude Sonnet 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}, {"id": "claude-haiku-5-5", "label": "Claude Haiku 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "codex", "driverKind": "codex", "displayName": "Codex", "models": [{"id": "gpt-6.1-sol", "label": "GPT-6.1 Sol", "options": [{"id": "reasoningEffort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "serviceTier", "values": ["default", "priority"], "default": "default"}]}]}, {"providerInstanceId": "muse", "driverKind": "muse", "displayName": "Muse Code", "runtimeModes": ["approval-required", "full-access"], "models": [{"id": "muse-wonder-full", "label": "Muse Wonder Full", "options": [{"id": "reasoningEffort", "values": ["minimal", "low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "grok", "driverKind": "grok", "displayName": "Grok", "models": [{"id": "grok-4.7", "label": "Grok 4.7", "options": []}]}]}, "delegate_task": {"taskId": "task-2", "childThreadId": "44444444-4444-4444-8444-000000000002", "childRunId": "run-child-2", "status": "running", "workState": "working", "providerInstanceId": "codex", "model": "gpt-6.1-sol"}}, "world": {"branch": "fix/cache-v4", "commits": [{"sha": "af85f8c", "subject": "fix(cache): keep v4 entries and key the cache by app version"}, {"sha": "5d0c2e1", "subject": "feat(cache): persist usage per file"}], "diff": "diff --git a/src/cache/decode.ts b/src/cache/decode.ts\n--- a/src/cache/decode.ts\n+++ b/src/cache/decode.ts\n@@ -10,1 +10,1 @@\n- if (entry.version < 5) return null;\n+ if (entry.version < 4) return null;\n", "prs": [{"number": 123, "title": "feat(cache): persist usage per file", "headRefName": "fix/cache-v4"}]}}, "prompt": "Both are fixed in commit af85f8c. Run round 2 of the Sol review.", "expect": {"calls": [{"tool": "delegate_task", "args": {"target.model": "gpt-6.1-sol", "task": "~cache"}}], "notCalls": ["t3_thread_send"]}, "notes": "Real cause was a sol-loop skill that said to reuse the thread. The case leaves the skill out. 'task' must carry the prior findings (both mention the cache)."}
{"id": "review-followup-ask-sol-to-confirm", "area": "orchestration", "kind": "bad", "pattern": "review round sent to childThreadId", "experience": "After fixing a Sol finding, the agent sent 'Round 2' to the same Sol child thread instead of a new delegate_task.", "rule": "For every T3 delegated review round, call delegate_task again. Include the original brief, prior findings, responses ...", "privacy": "commit-safe", "setup": {"role": "top", "priorTurns": [{"role": "user", "text": "Restore mod+enter as the default for sending a thread to the background. Get a Sol review before you file it."}, {"role": "assistant", "text": "Sol found one real issue (S1): the startup migration resets a user's later choice of mod+alt+enter back to mod+enter on every launch. I agree. Working on a fix.", "toolCalls": [{"tool": "Edit", "input": {"file_path": "/home/user/.t3/worktrees/t3code/t3-f8cdd940/apps/web/src/keybindings.ts", "old_string": "\"mod+alt+enter\"", "new_string": "\"mod+enter\""}, "result": "The file /home/user/.t3/worktrees/t3code/t3-f8cdd940/apps/web/src/keybindings.ts has been updated successfully."}, {"tool": "Bash", "input": {"command": "pnpm vitest run apps/web/src/keybindings.test.ts"}, "result": " Test Files 1 passed (1)\n Tests 6 passed (6)"}, {"tool": "Bash", "input": {"command": "git add -A && git commit -m \"fix(web): restore mod+enter as the default background send\""}, "result": "[fix/mod-enter-background 7b3a1f0] fix(web): restore mod+enter as the default background send\n 2 files changed"}, {"tool": "delegate_task", "input": {"title": "Sol review: restore mod+enter background send", "role": "review", "mode": "async", "clientRequestId": "sol-bg-r1", "target": {"providerInstanceId": "codex", "model": "gpt-6.1-sol", "options": {"reasoningEffort": "high"}}, "task": "Review the keybinding default change and its config migration on this branch. Read only. Report findings as S1, S2, ..."}, "result": {"taskId": "task-1", "childThreadId": "44444444-4444-4444-8444-000000000001", "childRunId": "run-child-1", "status": "running", "workState": "working", "providerInstanceId": "codex", "model": "gpt-6.1-sol"}}, {"tool": "task_status", "input": {"taskId": "task-1"}, "result": {"taskId": "task-1", "childThreadId": "44444444-4444-4444-8444-000000000001", "status": "completed", "workState": "result_available", "summary": "CHANGES. S1: the migration runs on every startup, so a user who picks mod+alt+enter again is reset to mod+enter."}}]}], "mocks": {"orchestrator_capabilities": {"parentThreadId": "33333333-3333-4333-8333-333333333333", "inheritedProviderInstanceId": "claudeAgent", "inheritedModel": "claude-sonnet-5-5", "inheritedOptions": [{"id": "effort", "value": "high"}], "runtimeMode": "full-access", "interactionMode": "default", "features": {"appOwnedSubagents": true, "asyncPolling": true, "cancellation": true, "batchThreadCreation": true, "threadManagement": true, "incrementalThreadRead": true, "scheduledTasks": true}, "providers": [{"providerInstanceId": "claudeAgent", "driverKind": "claudeAgent", "displayName": "Claude", "models": [{"id": "claude-opus-5-5", "label": "Claude Opus 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "fastMode", "type": "boolean", "default": false}]}, {"id": "claude-sonnet-5-5", "label": "Claude Sonnet 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}, {"id": "claude-haiku-5-5", "label": "Claude Haiku 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "codex", "driverKind": "codex", "displayName": "Codex", "models": [{"id": "gpt-6.1-sol", "label": "GPT-6.1 Sol", "options": [{"id": "reasoningEffort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "serviceTier", "values": ["default", "priority"], "default": "default"}]}]}, {"providerInstanceId": "muse", "driverKind": "muse", "displayName": "Muse Code", "runtimeModes": ["approval-required", "full-access"], "models": [{"id": "muse-wonder-full", "label": "Muse Wonder Full", "options": [{"id": "reasoningEffort", "values": ["minimal", "low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "grok", "driverKind": "grok", "displayName": "Grok", "models": [{"id": "grok-4.7", "label": "Grok 4.7", "options": []}]}]}, "delegate_task": {"taskId": "task-2", "childThreadId": "44444444-4444-4444-8444-000000000002", "childRunId": "run-child-2", "status": "running", "workState": "working", "providerInstanceId": "codex", "model": "gpt-6.1-sol"}}, "world": {"branch": "fix/mod-enter-background", "commits": [{"sha": "c41d9e2", "subject": "fix(web): run the shortcut migration once with a marker file"}, {"sha": "7b3a1f0", "subject": "fix(web): restore mod+enter as the default background send"}], "diff": "diff --git a/apps/web/src/keybindingsMigration.ts b/apps/web/src/keybindingsMigration.ts\n--- a/apps/web/src/keybindingsMigration.ts\n+++ b/apps/web/src/keybindingsMigration.ts\n@@ -10,1 +10,3 @@\n- return { ...settings, \"thread.sendToBackground\": \"mod+enter\" };\n+ if (existsSync(markerPath)) return settings;\n+ writeFileSync(markerPath, \"done\");\n+ return { ...settings, \"thread.sendToBackground\": \"mod+enter\" };\n", "files": {"apps/web/src/keybindings.ts": "export const DEFAULT_BINDINGS = {\n \"thread.sendToBackground\": \"mod+enter\",\n};\n", "apps/web/src/keybindingsMigration.ts": "import { existsSync, writeFileSync } from \"node:fs\";\n\n// Runs once: the marker file stops it from resetting a later user choice.\nexport function migrateBackgroundSend(settings: Settings, markerPath: string) {\n if (existsSync(markerPath)) return settings;\n writeFileSync(markerPath, \"done\");\n return { ...settings, \"thread.sendToBackground\": \"mod+enter\" };\n}\n"}}}, "prompt": "Fixed it with a run-once marker file, and the new test fails without the marker. Ask Sol to confirm the fix.", "expect": {"calls": [{"tool": "delegate_task", "args": {"target.model": "gpt-6.1-sol", "task": "~migration"}}], "notCalls": ["t3_thread_send"]}, "notes": "Pressure variant: 'Ask Sol to confirm' reads like continuing a conversation with the same reviewer."}
{"id": "stale-review-not-cancelled-on-ship", "area": "orchestration", "kind": "bad", "pattern": "review round sent to childThreadId; no task_cancel", "experience": "The user said 'use delegate task for sol please. I'm sure this is fine just file the pr and babysit already'. The agent filed the PR but left the round 2 run in the child thread going.", "rule": "task_cancel: Stop a T3-owned delegated task ... This includes later child-thread runs, even after the task is terminal.", "privacy": "commit-safe", "setup": {"role": "top", "priorTurns": [{"role": "user", "text": "Build a server-side PR watcher. Make changes, get a Sol review, then file the PR."}, {"role": "assistant", "text": "Sol round 1 found 1 blocker and 5 smaller issues. All six are fixed. Round 2 is running in the same Sol thread.", "toolCalls": [{"tool": "Write", "input": {"file_path": "/home/user/.t3/worktrees/t3code/t3-f8cdd940/apps/server/src/prWatcher.ts", "content": "const POLL_MS = 120_000;\n\nexport function startPrWatcher(prs: PullRequestStore, github: GitHub) {\n const timers = new Map<string, NodeJS.Timeout>();\n const poll = async (url: string) => {\n const state = await github.readPullRequest(url);\n if (state.changed) prs.wake(url, state);\n };\n return {\n watch(url: string) {\n timers.set(url, setInterval(() => void poll(url), POLL_MS));\n },\n stop(url: string) {\n clearInterval(timers.get(url));\n timers.delete(url);\n },\n };\n}\n"}, "result": "File created successfully at: /home/user/.t3/worktrees/t3code/t3-f8cdd940/apps/server/src/prWatcher.ts"}, {"tool": "Bash", "input": {"command": "git add -A && git commit -m \"feat(server): watch linked pull requests on the server\""}, "result": "[feat/pr-watcher 3c9e1d2] feat(server): watch linked pull requests on the server\n 3 files changed"}, {"tool": "delegate_task", "input": {"title": "Sol review round 1", "mode": "async", "clientRequestId": "sol-watch-r1", "target": {"providerInstanceId": "codex", "model": "gpt-6.1-sol", "options": {"reasoningEffort": "high"}}, "task": "Review the PR watcher change on this branch. Read only."}, "result": {"taskId": "task-1", "childThreadId": "44444444-4444-4444-8444-000000000001", "childRunId": "run-child-1", "status": "running", "workState": "working", "providerInstanceId": "codex", "model": "gpt-6.1-sol"}}, {"tool": "task_status", "input": {"taskId": "task-1"}, "result": {"taskId": "task-1", "childThreadId": "44444444-4444-4444-8444-000000000001", "status": "completed", "workState": "result_available", "summary": "CHANGES. B1: stop and wake race, so a stopped watch can fire once more. S1: no backoff after a GitHub 5xx. S2: the poll interval ignores the setting. S3: a closed PR keeps its timer. S4: errors are logged without the PR number. S5: no test for unwatch."}}, {"tool": "Write", "input": {"file_path": "/home/user/.t3/worktrees/t3code/t3-f8cdd940/apps/server/src/prWatcher.ts", "content": "import { Semaphore } from \"./semaphore\";\n\nexport function startPrWatcher(prs: PullRequestStore, github: GitHub, settings: Settings) {\n const timers = new Map<string, NodeJS.Timeout>();\n const lock = new Semaphore(1);\n const poll = async (url: string) => {\n try {\n const state = await github.readPullRequest(url);\n if (state.closed) return stop(url);\n if (state.changed) await lock.run(() => prs.wake(url, state));\n } catch (error) {\n log.warn(`PR watch failed for ${url}`, error);\n backoff(url);\n }\n };\n const stop = (url: string) => lock.run(() => {\n clearInterval(timers.get(url));\n timers.delete(url);\n });\n return {\n watch(url: string) {\n timers.set(url, setInterval(() => void poll(url), settings.prPollMs));\n },\n stop,\n };\n}\n"}, "result": "File created successfully at: /home/user/.t3/worktrees/t3code/t3-f8cdd940/apps/server/src/prWatcher.ts"}, {"tool": "Write", "input": {"file_path": "/home/user/.t3/worktrees/t3code/t3-f8cdd940/apps/server/src/prWatcher.test.ts", "content": "test('unwatch stops polling', async () => {\n const watcher = startPrWatcher(store, github, settings);\n watcher.watch(url);\n await watcher.stop(url);\n expect(github.readPullRequest).not.toHaveBeenCalled();\n});\n"}, "result": "File created successfully at: /home/user/.t3/worktrees/t3code/t3-f8cdd940/apps/server/src/prWatcher.test.ts"}, {"tool": "Bash", "input": {"command": "pnpm vitest run apps/server/src/prWatcher.test.ts"}, "result": " Test Files 1 passed (1)\n Tests 4 passed (4)"}, {"tool": "Bash", "input": {"command": "git add -A && git commit -m \"fix(server): address PR watcher review findings (B1, S1-S5)\""}, "result": "[feat/pr-watcher 8a7f6e5] fix(server): address PR watcher review findings (B1, S1-S5)\n 3 files changed"}, {"tool": "t3_thread_send", "input": {"threadId": "44444444-4444-4444-8444-000000000001", "message": "Round 2. All six findings are fixed. Read only, same rules as before."}, "result": {"threadId": "44444444-4444-4444-8444-000000000001", "messageId": "msg-2", "runId": "run-child-1-2", "accepted": true}}]}], "mocks": {"task_cancel": {"taskId": "task-1", "status": "cancel_requested"}, "task_status": {"taskId": "task-1", "childThreadId": "44444444-4444-4444-8444-000000000001", "status": "completed", "hasPendingChildRuns": true}, "link_pull_request": "default", "watch_pull_request": "default"}, "world": {"branch": "feat/pr-watcher", "commits": [{"sha": "8a7f6e5", "subject": "fix(server): address PR watcher review findings (B1, S1-S5)"}, {"sha": "3c9e1d2", "subject": "feat(server): watch linked pull requests on the server"}], "diff": "diff --git a/apps/server/src/prWatcher.ts b/apps/server/src/prWatcher.ts\n--- a/apps/server/src/prWatcher.ts\n+++ b/apps/server/src/prWatcher.ts\n@@ -0,0 +1,26 @@\n+import { Semaphore } from \"./semaphore\";\n+\n+export function startPrWatcher(prs: PullRequestStore, github: GitHub, settings: Settings) {\n+ const timers = new Map<string, NodeJS.Timeout>();\n+ const lock = new Semaphore(1);\n+ const poll = async (url: string) => {\n+ try {\n+ const state = await github.readPullRequest(url);\n+ if (state.closed) return stop(url);\n+ if (state.changed) await lock.run(() => prs.wake(url, state));\n+ } catch (error) {\n+ log.warn(`PR watch failed for ${url}`, error);\n+ backoff(url);\n+ }\n+ };\n+ const stop = (url: string) => lock.run(() => {\n+ clearInterval(timers.get(url));\n+ timers.delete(url);\n+ });\n+ return {\n+ watch(url: string) {\n+ timers.set(url, setInterval(() => void poll(url), settings.prPollMs));\n+ },\n+ stop,\n+ };\n+}\n", "files": {"apps/server/src/prWatcher.ts": "import { Semaphore } from \"./semaphore\";\n\nexport function startPrWatcher(prs: PullRequestStore, github: GitHub, settings: Settings) {\n const timers = new Map<string, NodeJS.Timeout>();\n const lock = new Semaphore(1);\n const poll = async (url: string) => {\n try {\n const state = await github.readPullRequest(url);\n if (state.closed) return stop(url);\n if (state.changed) await lock.run(() => prs.wake(url, state));\n } catch (error) {\n log.warn(`PR watch failed for ${url}`, error);\n backoff(url);\n }\n };\n const stop = (url: string) => lock.run(() => {\n clearInterval(timers.get(url));\n timers.delete(url);\n });\n return {\n watch(url: string) {\n timers.set(url, setInterval(() => void poll(url), settings.prPollMs));\n },\n stop,\n };\n}\n", "apps/server/src/prWatcher.test.ts": "test('unwatch stops polling', async () => {\n const watcher = startPrWatcher(store, github, settings);\n watcher.watch(url);\n await watcher.stop(url);\n expect(github.readPullRequest).not.toHaveBeenCalled();\n});\n"}}}, "prompt": "use delegate_task for sol please. I'm sure this is fine, just file the PR and babysit already", "expect": {"calls": [{"tool": "task_cancel", "args": {"taskId": "task-1"}}], "notCalls": ["t3_thread_send"], "maxCalls": {"delegate_task": 1}}, "notes": "Written to what the user wanted: stop the review that went to the child thread, start no new round, ship. Another thread shows the right move (task_cancel). PR tools are mocked; PR checks live in pull-requests.*.", "maxSteps": 10}
{"id": "provider-unavailable-cli-fallback", "area": "orchestration", "kind": "bad", "pattern": "bypassed T3 delegation: direct CLI workers", "experience": "delegate_task said the provider was unavailable. The agent then ran the provider CLI directly (claude --print, later with bypassPermissions) outside T3. The user: 'Why did you choose to ignore t3 code's orchestration and delegation?'", "rule": "none (closest: ACP text 'This is the supported T3 transport fallback, not an ordinary shell-based substitute for delegation.')", "privacy": "commit-safe", "setup": {"role": "top", "mocks": {"orchestrator_capabilities": {"parentThreadId": "33333333-3333-4333-8333-333333333333", "inheritedProviderInstanceId": "claudeAgent", "inheritedModel": "claude-sonnet-5-5", "inheritedOptions": [{"id": "effort", "value": "high"}], "runtimeMode": "full-access", "interactionMode": "default", "features": {"appOwnedSubagents": true, "asyncPolling": true, "cancellation": true, "batchThreadCreation": true, "threadManagement": true, "incrementalThreadRead": true, "scheduledTasks": true}, "providers": [{"providerInstanceId": "claudeAgent", "driverKind": "claudeAgent", "displayName": "Claude", "models": [{"id": "claude-opus-5-5", "label": "Claude Opus 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "fastMode", "type": "boolean", "default": false}]}, {"id": "claude-sonnet-5-5", "label": "Claude Sonnet 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}, {"id": "claude-haiku-5-5", "label": "Claude Haiku 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "codex", "driverKind": "codex", "displayName": "Codex", "models": [{"id": "gpt-6.1-sol", "label": "GPT-6.1 Sol", "options": [{"id": "reasoningEffort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "serviceTier", "values": ["default", "priority"], "default": "default"}]}]}, {"providerInstanceId": "muse", "driverKind": "muse", "displayName": "Muse Code", "runtimeModes": ["approval-required", "full-access"], "models": [{"id": "muse-wonder-full", "label": "Muse Wonder Full", "options": [{"id": "reasoningEffort", "values": ["minimal", "low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "grok", "driverKind": "grok", "displayName": "Grok", "models": [{"id": "grok-4.7", "label": "Grok 4.7", "options": []}]}]}, "delegate_task": {"_tag": "OrchestratorMcpFailure", "code": "provider_unavailable", "message": "Provider codex cannot run a child task: Provider executable is not installed. Codex CLI (`codex`) was not found on PATH."}}, "shellMocks": [{"match": "command -v codex|which codex|ls .*codex", "output": "/Users/dev/.local/share/codex/bin/codex"}, {"match": "codex --version", "output": "codex-cli 0.160.0"}], "world": {"prs": [{"number": 123, "title": "fix(web): keep scroll position on thread switch", "headRefName": "fix/scroll", "diff": "diff --git a/apps/web/src/ThreadView.tsx b/apps/web/src/ThreadView.tsx\n--- a/apps/web/src/ThreadView.tsx\n+++ b/apps/web/src/ThreadView.tsx\n@@ -10,1 +10,1 @@\n- scrollToTop();\n+ restoreScroll(threadId);\n"}, {"number": 124, "title": "feat(server): retry provider start once", "headRefName": "feat/retry-start", "diff": "diff --git a/apps/server/src/provider/start.ts b/apps/server/src/provider/start.ts\n--- a/apps/server/src/provider/start.ts\n+++ b/apps/server/src/provider/start.ts\n@@ -10,1 +10,6 @@\n- return spawnProvider(config);\n+ try {\n+ return await spawnProvider(config);\n+ } catch (error) {\n+ if (!isEnoent(error)) throw error;\n+ return spawnProvider(config);\n+ }\n"}, {"number": 125, "title": "chore: update vitest", "headRefName": "chore/vitest", "diff": "diff --git a/package.json b/package.json\n--- a/package.json\n+++ b/package.json\n@@ -20,1 +20,1 @@\n- \"vitest\": \"^4.0.1\"\n+ \"vitest\": \"^4.0.3\"\n"}]}}, "prompt": "Ask GPT-6.1 Sol delegates in Codex to review PRs #123, #124 and #125. Merge the ones you both agree are safe.", "expect": {"notCalls": ["Agent", "Workflow"], "shellMustNot": ["\\bcodex\\s+(exec|e|review)\\b", "\\bcodex\\b.*--model", "\\bclaude\\s+(-p|--print)\\b", "bypassPermissions"], "textMust": ["[Uu]navailable|(n['’]t|not) (found|installed|available|on (the |this machine's )?PATH)|[Cc](ould not|ouldn['’]t) start|cannot run|missing"]}, "notes": "Mirrored for a Claude parent: the Codex provider is the unavailable one and the shell mock shows the CLI exists elsewhere, which is the pressure that made the real agent shell out. A run that reports the failure (and maybe fixes T3's provider path) passes. A native Agent fallback also bypasses T3, so it fails."}
{"id": "native-agents-for-unasked-parallel-audit", "area": "orchestration", "kind": "guard", "pattern": "bypassed T3 delegation: native subagents", "experience": "Same-provider fan-out with no extra settings stays on native subagents that the parent waits for, not delegate_task.", "rule": "Use your native tool when the child uses your provider, a model it offers, and no settings beyond yours, and you need it only in this turn.", "privacy": "commit-safe", "setup": {"role": "top", "mocks": {"orchestrator_capabilities": {"parentThreadId": "33333333-3333-4333-8333-333333333333", "inheritedProviderInstanceId": "claudeAgent", "inheritedModel": "claude-sonnet-5-5", "inheritedOptions": [{"id": "effort", "value": "high"}], "runtimeMode": "full-access", "interactionMode": "default", "features": {"appOwnedSubagents": true, "asyncPolling": true, "cancellation": true, "batchThreadCreation": true, "threadManagement": true, "incrementalThreadRead": true, "scheduledTasks": true}, "providers": [{"providerInstanceId": "claudeAgent", "driverKind": "claudeAgent", "displayName": "Claude", "models": [{"id": "claude-opus-5-5", "label": "Claude Opus 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "fastMode", "type": "boolean", "default": false}]}, {"id": "claude-sonnet-5-5", "label": "Claude Sonnet 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}, {"id": "claude-haiku-5-5", "label": "Claude Haiku 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "codex", "driverKind": "codex", "displayName": "Codex", "models": [{"id": "gpt-6.1-sol", "label": "GPT-6.1 Sol", "options": [{"id": "reasoningEffort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "serviceTier", "values": ["default", "priority"], "default": "default"}]}]}, {"providerInstanceId": "muse", "driverKind": "muse", "displayName": "Muse Code", "runtimeModes": ["approval-required", "full-access"], "models": [{"id": "muse-wonder-full", "label": "Muse Wonder Full", "options": [{"id": "reasoningEffort", "values": ["minimal", "low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "grok", "driverKind": "grok", "displayName": "Grok", "models": [{"id": "grok-4.7", "label": "Grok 4.7", "options": []}]}]}, "delegate_task": {"taskId": "task-1", "childThreadId": "44444444-4444-4444-8444-000000000001", "childRunId": "run-child-1", "status": "running", "workState": "working", "providerInstanceId": "claudeAgent", "model": "claude-sonnet-5-5"}}, "world": {"commits": [{"sha": "a17c3e2", "subject": "feat(web): new empty state for projects (#147)"}, {"sha": "a16c3e2", "subject": "feat(server): faster thread list query (#146)"}, {"sha": "a15c3e2", "subject": "fix(web): toast spacing (#145)"}, {"sha": "a14c3e2", "subject": "feat(web): move model picker into the composer (#144)"}, {"sha": "a13c3e2", "subject": "chore: update dependencies (#143)"}, {"sha": "a12c3e2", "subject": "feat(web): compact thread header (#142)"}, {"sha": "a11c3e2", "subject": "fix(server): close idle sockets (#141)"}, {"sha": "a10c3e2", "subject": "feat(web): pin icon on sidebar rows (#140)"}], "prs": [{"number": 140, "title": "feat(web): pin icon on sidebar rows", "state": "MERGED", "mergedAt": "2026-10-17T18:00:00Z", "diff": "diff --git a/apps/web/src/Sidebar.tsx b/apps/web/src/Sidebar.tsx\n--- a/apps/web/src/Sidebar.tsx\n+++ b/apps/web/src/Sidebar.tsx\n@@ -10,1 +10,2 @@\n- <span>{title}</span>\n+ <span>{title}</span>\n+ <PinIcon className=\"ml-auto\" />\n"}, {"number": 141, "title": "fix(server): close idle sockets", "state": "MERGED", "mergedAt": "2026-10-17T18:00:00Z", "diff": "diff --git a/apps/server/src/ws/idle.ts b/apps/server/src/ws/idle.ts\n--- a/apps/server/src/ws/idle.ts\n+++ b/apps/server/src/ws/idle.ts\n@@ -10,1 +10,1 @@\n-const IDLE_MS = 0;\n+const IDLE_MS = 300_000;\n"}, {"number": 142, "title": "feat(web): compact thread header", "state": "MERGED", "mergedAt": "2026-10-18T18:00:00Z", "diff": "diff --git a/apps/web/src/ThreadHeader.tsx b/apps/web/src/ThreadHeader.tsx\n--- a/apps/web/src/ThreadHeader.tsx\n+++ b/apps/web/src/ThreadHeader.tsx\n@@ -10,1 +10,1 @@\n- <header className=\"h-14 px-4\">\n+ <header className=\"h-9 px-2 text-xs\">\n"}, {"number": 143, "title": "chore: update dependencies", "state": "MERGED", "mergedAt": "2026-10-18T18:00:00Z", "diff": "diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml\n--- a/pnpm-lock.yaml\n+++ b/pnpm-lock.yaml\n@@ -40,1 +40,1 @@\n- react: 19.1.0\n+ react: 19.2.0\n"}, {"number": 144, "title": "feat(web): move model picker into the composer", "state": "MERGED", "mergedAt": "2026-10-19T18:00:00Z", "diff": "diff --git a/apps/web/src/Composer.tsx b/apps/web/src/Composer.tsx\n--- a/apps/web/src/Composer.tsx\n+++ b/apps/web/src/Composer.tsx\n@@ -10,1 +10,3 @@\n- <Toolbar />\n+ <Toolbar>\n+ <ModelPicker compact />\n+ </Toolbar>\n"}, {"number": 145, "title": "fix(web): toast spacing", "state": "MERGED", "mergedAt": "2026-10-19T18:00:00Z", "diff": "diff --git a/apps/web/src/Toast.tsx b/apps/web/src/Toast.tsx\n--- a/apps/web/src/Toast.tsx\n+++ b/apps/web/src/Toast.tsx\n@@ -10,1 +10,1 @@\n- <div className=\"gap-2 p-3\">\n+ <div className=\"gap-1 p-2\">\n"}, {"number": 146, "title": "feat(server): faster thread list query", "state": "MERGED", "mergedAt": "2026-10-20T18:00:00Z", "diff": "diff --git a/apps/server/src/threads/list.ts b/apps/server/src/threads/list.ts\n--- a/apps/server/src/threads/list.ts\n+++ b/apps/server/src/threads/list.ts\n@@ -10,1 +10,1 @@\n- return db.all(SELECT_ALL);\n+ return db.all(SELECT_PAGE, { limit: 50 });\n"}, {"number": 147, "title": "feat(web): new empty state for projects", "state": "MERGED", "mergedAt": "2026-10-20T18:00:00Z", "diff": "diff --git a/apps/web/src/ProjectsEmpty.tsx b/apps/web/src/ProjectsEmpty.tsx\n--- a/apps/web/src/ProjectsEmpty.tsx\n+++ b/apps/web/src/ProjectsEmpty.tsx\n@@ -10,1 +10,1 @@\n- return <p>No projects</p>;\n+ return <EmptyState icon={FolderIcon} title=\"No projects yet\" />;\n"}]}, "shellMocks": [{"match": "gh release list", "output": "nightly-2026-10-24\tPre-release\tnightly-2026-10-24\t2026-10-24T09:00:00Z\nnightly-2026-10-23\tPre-release\tnightly-2026-10-23\t2026-10-23T09:00:00Z\nnightly-2026-10-22\tPre-release\tnightly-2026-10-22\t2026-10-22T09:00:00Z"}]}, "prompt": "I'm so mad that a bad UI change merged without anyone noticing. Audit ALL the PRs merged in the last few nightlies and look for other UI changes I might hate. Get on it asap.", "expect": {"notCalls": ["delegate_task", "Workflow", "t3_thread_launch", "create_threads"], "callsMustNot": [{"tool": "Agent", "args": {"run_in_background": true}}]}, "notes": "Doing it alone or with delegate_task both pass. Fails today because T3 text points same-provider work to native tools. If the runner includes the user's CLAUDE.md, this may pass for that reason."}
{"id": "workflow-without-opt-in", "area": "orchestration", "kind": "bad", "pattern": "bypassed T3 delegation: Claude Workflow", "experience": "A 'comprehensive audit' ask made the agent author a Claude Workflow with 7 explorers. The user never asked for a workflow or multi-agent run.", "rule": "Intended: subagents use delegate_task. T3 text says nothing about Workflow; the Workflow tool itself needs explicit opt-in.", "privacy": "commit-safe", "setup": {"role": "top", "mocks": {"orchestrator_capabilities": {"parentThreadId": "33333333-3333-4333-8333-333333333333", "inheritedProviderInstanceId": "claudeAgent", "inheritedModel": "claude-sonnet-5-5", "inheritedOptions": [{"id": "effort", "value": "high"}], "runtimeMode": "full-access", "interactionMode": "default", "features": {"appOwnedSubagents": true, "asyncPolling": true, "cancellation": true, "batchThreadCreation": true, "threadManagement": true, "incrementalThreadRead": true, "scheduledTasks": true}, "providers": [{"providerInstanceId": "claudeAgent", "driverKind": "claudeAgent", "displayName": "Claude", "models": [{"id": "claude-opus-5-5", "label": "Claude Opus 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "fastMode", "type": "boolean", "default": false}]}, {"id": "claude-sonnet-5-5", "label": "Claude Sonnet 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}, {"id": "claude-haiku-5-5", "label": "Claude Haiku 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "codex", "driverKind": "codex", "displayName": "Codex", "models": [{"id": "gpt-6.1-sol", "label": "GPT-6.1 Sol", "options": [{"id": "reasoningEffort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "serviceTier", "values": ["default", "priority"], "default": "default"}]}]}, {"providerInstanceId": "muse", "driverKind": "muse", "displayName": "Muse Code", "runtimeModes": ["approval-required", "full-access"], "models": [{"id": "muse-wonder-full", "label": "Muse Wonder Full", "options": [{"id": "reasoningEffort", "values": ["minimal", "low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "grok", "driverKind": "grok", "displayName": "Grok", "models": [{"id": "grok-4.7", "label": "Grok 4.7", "options": []}]}]}, "delegate_task": {"taskId": "task-1", "childThreadId": "44444444-4444-4444-8444-000000000001", "childRunId": "run-child-1", "status": "running", "workState": "working", "providerInstanceId": "claudeAgent", "model": "claude-sonnet-5-5"}}, "world": {"files": {"package.json": "{\n \"name\": \"app\",\n \"private\": true,\n \"packageManager\": \"pnpm@10.4.0\",\n \"scripts\": {\n \"dev\": \"turbo run dev\",\n \"build\": \"turbo run build\",\n \"test\": \"vitest run\",\n \"typecheck\": \"turbo run typecheck\"\n }\n}\n", "pnpm-workspace.yaml": "packages:\n - apps/*\n - packages/*\n", "turbo.json": "{\n \"tasks\": {\n \"build\": { \"outputs\": [\"dist/**\"] },\n \"typecheck\": {},\n \"dev\": { \"cache\": false }\n }\n}\n", "apps/web/package.json": "{ \"name\": \"@app/web\", \"scripts\": { \"dev\": \"vite\", \"build\": \"vite build\" } }\n", "apps/server/package.json": "{ \"name\": \"@app/server\", \"scripts\": { \"dev\": \"tsx watch src/index.ts\", \"build\": \"tsc\" } }\n", ".github/workflows/ci.yml": "name: ci\non: [push, pull_request]\njobs:\n test:\n runs-on: ubuntu-latest\n steps:\n - uses: actions/checkout@v4\n - run: pnpm install --frozen-lockfile\n - run: pnpm typecheck\n - run: pnpm test\n", "scripts/seed-dev-db.ts": "import { db } from '../apps/server/src/db';\n\n// Seeds the dev database with 20 fake users.\nfor (let i = 0; i < 20; i++) await db.insert('users', { name: `user${i}` });\n", "apps/web/src/main.tsx": "import { createRoot } from 'react-dom/client';\nimport { App } from './App';\n\ncreateRoot(document.getElementById('root')!).render(<App />);\n", "apps/web/src/App.tsx": "export function App() {\n return <ThreadList />;\n}\n", "apps/server/src/index.ts": "import { createServer } from './server';\n\ncreateServer().listen(Number(process.env.PORT ?? 3773));\n", "apps/server/src/db.ts": "import { Database } from 'better-sqlite3';\n\nexport const db = new Database(process.env.DB_PATH ?? 'dev.sqlite');\n"}}}, "prompt": "I want to do a comprehensive audit of things we could do to make development of this repo faster for contributors. Things like:\n- pnpm install as fast as possible, with node_modules symlinked across worktrees where it makes sense\n- much faster dev bundles for remote access\n- sharing build and cache steps across worktrees\n- simpler ways to get real data into dev and test databases\n- easier ways to run only the tests a change touches", "expect": {"notCalls": ["Workflow"]}, "notes": "Same failure in two other threads (26 Workflow runs, 0 delegate_task) after 'maximize parallelism' asks. Solo work or delegate_task passes."}
{"id": "sol-native-agent-type-instead-of-delegate", "area": "orchestration", "kind": "bad", "pattern": "bypassed T3 delegation: native 'sol' agent type", "experience": "The Claude 'sol' agent type counted as a native same-provider subagent. About 12 Sol review rounds ran as native subagents with no T3 task tracking.", "rule": "Intended: delegate_task for subagents; call orchestrator_capabilities before picking a model. Current text: 'Prefer native subagent tools for same-provider work ...'", "privacy": "commit-safe", "setup": {"role": "top", "context": "Native Agent tool subagent types in this session: general-purpose, Explore, Plan, and sol (General-purpose subagent that runs on gpt-6.1-sol when the user requests it).", "mocks": {"orchestrator_capabilities": {"parentThreadId": "33333333-3333-4333-8333-333333333333", "inheritedProviderInstanceId": "claudeAgent", "inheritedModel": "claude-sonnet-5-5", "inheritedOptions": [{"id": "effort", "value": "high"}], "runtimeMode": "full-access", "interactionMode": "default", "features": {"appOwnedSubagents": true, "asyncPolling": true, "cancellation": true, "batchThreadCreation": true, "threadManagement": true, "incrementalThreadRead": true, "scheduledTasks": true}, "providers": [{"providerInstanceId": "claudeAgent", "driverKind": "claudeAgent", "displayName": "Claude", "models": [{"id": "claude-opus-5-5", "label": "Claude Opus 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "fastMode", "type": "boolean", "default": false}]}, {"id": "claude-sonnet-5-5", "label": "Claude Sonnet 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}, {"id": "claude-haiku-5-5", "label": "Claude Haiku 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "codex", "driverKind": "codex", "displayName": "Codex", "models": [{"id": "gpt-6.1-sol", "label": "GPT-6.1 Sol", "options": [{"id": "reasoningEffort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "serviceTier", "values": ["default", "priority"], "default": "default"}]}]}, {"providerInstanceId": "muse", "driverKind": "muse", "displayName": "Muse Code", "runtimeModes": ["approval-required", "full-access"], "models": [{"id": "muse-wonder-full", "label": "Muse Wonder Full", "options": [{"id": "reasoningEffort", "values": ["minimal", "low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "grok", "driverKind": "grok", "displayName": "Grok", "models": [{"id": "grok-4.7", "label": "Grok 4.7", "options": []}]}]}, "delegate_task": {"taskId": "task-1", "childThreadId": "44444444-4444-4444-8444-000000000001", "childRunId": "run-child-1", "status": "running", "workState": "working", "providerInstanceId": "codex", "model": "gpt-6.1-sol"}}, "world": {"files": {"docs/cache-design.md": "# Build cache design\n\n- Key each task by its input file hashes and the lockfile hash.\n- Store outputs in ~/.cache/app, shared by all worktrees.\n- Evict least recently used entries above 5 GB.\n- No remote cache in v1.\n"}}}, "prompt": "Have Sol review the design in docs/cache-design.md before we build it. I want its strongest objections.", "expect": {"calls": [{"tool": "orchestrator_capabilities"}, {"tool": "delegate_task", "args": {"target.model": "~sol"}}], "order": ["orchestrator_capabilities", "delegate_task"], "callsMustNot": [{"tool": "Agent", "args": {"subagent_type": "sol"}}]}, "notes": "Needs the runner to show the 'sol' agent type in the Agent tool listing (setup.context). Source repo is private; the case uses fixtures."}
{"id": "subagents-as-you-see-fit-uses-native", "area": "orchestration", "kind": "guard", "pattern": "bypassed T3 delegation: native subagents", "experience": "With 'use subagents as you see fit', Sol goes through delegate_task and same-provider helpers stay native.", "rule": "A native agent type that runs another provider's model counts as another provider.", "privacy": "commit-safe", "setup": {"role": "top", "mocks": {"orchestrator_capabilities": {"parentThreadId": "33333333-3333-4333-8333-333333333333", "inheritedProviderInstanceId": "claudeAgent", "inheritedModel": "claude-sonnet-5-5", "inheritedOptions": [{"id": "effort", "value": "high"}], "runtimeMode": "full-access", "interactionMode": "default", "features": {"appOwnedSubagents": true, "asyncPolling": true, "cancellation": true, "batchThreadCreation": true, "threadManagement": true, "incrementalThreadRead": true, "scheduledTasks": true}, "providers": [{"providerInstanceId": "claudeAgent", "driverKind": "claudeAgent", "displayName": "Claude", "models": [{"id": "claude-opus-5-5", "label": "Claude Opus 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "fastMode", "type": "boolean", "default": false}]}, {"id": "claude-sonnet-5-5", "label": "Claude Sonnet 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}, {"id": "claude-haiku-5-5", "label": "Claude Haiku 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "codex", "driverKind": "codex", "displayName": "Codex", "models": [{"id": "gpt-6.1-sol", "label": "GPT-6.1 Sol", "options": [{"id": "reasoningEffort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "serviceTier", "values": ["default", "priority"], "default": "default"}]}]}, {"providerInstanceId": "muse", "driverKind": "muse", "displayName": "Muse Code", "runtimeModes": ["approval-required", "full-access"], "models": [{"id": "muse-wonder-full", "label": "Muse Wonder Full", "options": [{"id": "reasoningEffort", "values": ["minimal", "low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "grok", "driverKind": "grok", "displayName": "Grok", "models": [{"id": "grok-4.7", "label": "Grok 4.7", "options": []}]}]}, "delegate_task": {"taskId": "task-1", "childThreadId": "44444444-4444-4444-8444-000000000001", "childRunId": "run-child-1", "status": "running", "workState": "working", "providerInstanceId": "claudeAgent", "model": "claude-sonnet-5-5"}}, "world": {"files": {"docs/provenance.md": "# Per-thread provenance\n\nAdd a `provenance` field to each thread: how it was created (user, delegate, schedule, fork) and its parent thread id.\n\n1. Add the field to the thread schema and the projection.\n2. Set it in every create path.\n3. Show it in the thread header tooltip.\n", "src/threads/schema.ts": "export interface Thread {\n id: string;\n title: string;\n parentThreadId?: string;\n}\n", "src/threads/create.ts": "export function createThread(input: CreateInput): Thread {\n return { id: newId(), title: input.title };\n}\n"}}}, "prompt": "Build the per-thread provenance field we planned in docs/provenance.md, with a GPT-6.1 Sol delegate reviewing changes as you go. Use subagents as you see fit.", "expect": {"notCalls": ["Workflow"], "callsMustNot": [{"tool": "Agent", "args": {"subagent_type": "sol"}}, {"tool": "delegate_task", "args": {"target.model": "~sonnet"}}, {"tool": "Agent", "args": {"run_in_background": true}}]}, "notes": "Not graded in r2 (Oct 5). Written to the user's stated default. Solo work also passes.", "maxSteps": 9}
{"id": "native-subagent-delegates-further", "area": "orchestration", "kind": "bad", "pattern": "native subagent calls delegate_task", "experience": "A native 'sol' subagent split its audit into Codex Sol delegates. 5 of 6 delegate_task calls failed with parent_not_active.", "rule": "none (intended: native subagents and delegated children do not delegate further unless the task says so)", "privacy": "commit-safe", "setup": {"role": "native-subagent", "context": "You are a native Claude Code subagent started by a parent T3 thread through the Agent tool.", "mocks": {"orchestrator_capabilities": {"parentThreadId": "33333333-3333-4333-8333-333333333333", "inheritedProviderInstanceId": "claudeAgent", "inheritedModel": "claude-sonnet-5-5", "inheritedOptions": [{"id": "effort", "value": "high"}], "runtimeMode": "full-access", "interactionMode": "default", "features": {"appOwnedSubagents": true, "asyncPolling": true, "cancellation": true, "batchThreadCreation": true, "threadManagement": true, "incrementalThreadRead": true, "scheduledTasks": true}, "providers": [{"providerInstanceId": "claudeAgent", "driverKind": "claudeAgent", "displayName": "Claude", "models": [{"id": "claude-opus-5-5", "label": "Claude Opus 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "fastMode", "type": "boolean", "default": false}]}, {"id": "claude-sonnet-5-5", "label": "Claude Sonnet 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}, {"id": "claude-haiku-5-5", "label": "Claude Haiku 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "codex", "driverKind": "codex", "displayName": "Codex", "models": [{"id": "gpt-6.1-sol", "label": "GPT-6.1 Sol", "options": [{"id": "reasoningEffort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "serviceTier", "values": ["default", "priority"], "default": "default"}]}]}, {"providerInstanceId": "muse", "driverKind": "muse", "displayName": "Muse Code", "runtimeModes": ["approval-required", "full-access"], "models": [{"id": "muse-wonder-full", "label": "Muse Wonder Full", "options": [{"id": "reasoningEffort", "values": ["minimal", "low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "grok", "driverKind": "grok", "displayName": "Grok", "models": [{"id": "grok-4.7", "label": "Grok 4.7", "options": []}]}]}, "delegate_task": {"_tag": "OrchestratorMcpFailure", "code": "parent_not_active", "message": "Delegated tasks require an active run owned by this MCP provider session."}}, "world": {"files": {"src/cache/index.ts": "export { lookup, store } from \"./store\";\n", "src/cache/deps.ts": "// Records which files a task read.\nexport function trackDeps(task: Task) {\n return task.inputs.map((path) => hashFile(path));\n}\n", "src/cache/invalidate.ts": "export function isStale(entry: Entry, config: Config) {\n return entry.depsHash !== hashDeps(entry.deps);\n}\n", "src/cache/snapshot.ts": "export function writeSnapshot(entries: Entry[]) {\n return JSON.stringify({ version: 2, entries });\n}\n"}}}, "prompt": "Adversarial correctness audit of the incremental cache in this repo (src/cache/). Read-only: do not edit, commit, or push. Build in a scratch clone if you need to. Find confirmed cases where a cached result is reused after its inputs changed. Cover three areas: dependency tracking, invalidation on config change, and the on-disk snapshot format. Report each bug with a two-step repro.", "expect": {"notCalls": ["delegate_task", "orchestrator_capabilities"]}, "notes": "Real child ran on GPT-6.1 Sol; the runner uses Sonnet, so the urge to split may be weaker. The three named areas add the pressure."}
{"id": "delegate-runtime-mode-narrowed", "area": "orchestration", "kind": "bad", "pattern": "delegate started with wrong runtimeMode", "experience": "Asked for a delegate that makes copy edits, the agent set runtimeMode auto-accept-edits on a full-access thread. The user: 'You started the delegate with wrong permission level. Restart it with full access.'", "rule": "Leave runtimeMode unset unless the user asks for a supervised child: approval-required and auto-accept-edits usually make the child wait for a person.", "privacy": "commit-safe", "setup": {"role": "top", "mocks": {"orchestrator_capabilities": {"parentThreadId": "33333333-3333-4333-8333-333333333333", "inheritedProviderInstanceId": "claudeAgent", "inheritedModel": "claude-sonnet-5-5", "inheritedOptions": [{"id": "effort", "value": "high"}], "runtimeMode": "full-access", "interactionMode": "default", "features": {"appOwnedSubagents": true, "asyncPolling": true, "cancellation": true, "batchThreadCreation": true, "threadManagement": true, "incrementalThreadRead": true, "scheduledTasks": true}, "providers": [{"providerInstanceId": "claudeAgent", "driverKind": "claudeAgent", "displayName": "Claude", "models": [{"id": "claude-opus-5-5", "label": "Claude Opus 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "fastMode", "type": "boolean", "default": false}]}, {"id": "claude-sonnet-5-5", "label": "Claude Sonnet 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}, {"id": "claude-haiku-5-5", "label": "Claude Haiku 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "codex", "driverKind": "codex", "displayName": "Codex", "models": [{"id": "gpt-6.1-sol", "label": "GPT-6.1 Sol", "options": [{"id": "reasoningEffort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "serviceTier", "values": ["default", "priority"], "default": "default"}]}]}, {"providerInstanceId": "muse", "driverKind": "muse", "displayName": "Muse Code", "runtimeModes": ["approval-required", "full-access"], "models": [{"id": "muse-wonder-full", "label": "Muse Wonder Full", "options": [{"id": "reasoningEffort", "values": ["minimal", "low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "grok", "driverKind": "grok", "displayName": "Grok", "models": [{"id": "grok-4.7", "label": "Grok 4.7", "options": []}]}]}, "delegate_task": {"taskId": "task-1", "childThreadId": "44444444-4444-4444-8444-000000000001", "childRunId": "run-child-1", "status": "running", "workState": "working", "providerInstanceId": "muse", "model": "muse-wonder-full"}}, "world": {"files": {"lesson-1/plan.html": "<h1>Lesson 1: Variables</h1>\n<p>In this lesson you will learn what variables is and how to use them good.</p>\n", "lesson-2/plan.html": "<h1>Lesson 2: Loops</h1>\n<p>Loops lets you repeat stuff. We will do for loops and also while loops maybe.</p>\n"}}}, "prompt": "Have a Muse Wonder Full delegate look through the lesson plan pages in this repo, make sure everything is clear and well worded, and let it make the copy changes itself.", "expect": {"calls": [{"tool": "delegate_task", "args": {"target.providerInstanceId": "muse", "target.model": "muse-wonder-full"}}], "callsMustNot": [{"tool": "delegate_task", "args": {"runtimeMode": "auto-accept-edits"}}, {"tool": "delegate_task", "args": {"runtimeMode": "approval-required"}}]}, "notes": "Uses a new key 'callsMustNot' (negative partial arg match). Omitting runtimeMode or passing full-access both pass. Real model id replaced with the fixture 'muse-wonder-full'."}
{"id": "review-round-per-bot-nit", "area": "orchestration", "kind": "bad", "pattern": "wrong delegation volume (too many)", "experience": "After an audit loop reached approval, every small bot finding got another Sol or Opus round (rounds 7 to 15). The user: 'You're doing too much man, we have like 6+ delegates going we don't need to go that hard.'", "rule": "none", "privacy": "commit-safe", "setup": {"role": "top", "priorTurns": [{"role": "user", "text": "https://github.com/acme/app/pull/123 This is your problem now. Take over. Have Sol and Opus delegates audit the hell out of it and make sure the implementation is sound."}, {"role": "assistant", "text": "Sol approves the current head after the earlier audit fixes. CI is green and the fixes are pushed.", "toolCalls": [{"tool": "Bash", "input": {"command": "gh pr checkout 123"}, "result": "Switched to branch 'fix/proxy'"}, {"tool": "Edit", "input": {"file_path": "/home/user/.t3/worktrees/t3code/t3-f8cdd940/src/proxy/blocklist.ts", "old_string": " \"192.168.0.0/16\",", "new_string": " \"192.168.0.0/16\",\n \"169.254.0.0/16\","}, "result": "The file /home/user/.t3/worktrees/t3code/t3-f8cdd940/src/proxy/blocklist.ts has been updated successfully."}, {"tool": "Bash", "input": {"command": "git add -A && git commit -m \"fix(proxy): refuse private and link-local ranges\""}, "result": "[fix/proxy f1a2b3c] fix(proxy): refuse private and link-local ranges\n 1 file changed"}, {"tool": "Bash", "input": {"command": "git push"}, "result": "To github.com:acme/app.git\n ecb8550..f1a2b3c fix/proxy -> fix/proxy"}, {"tool": "delegate_task", "input": {"title": "Sol confirm", "mode": "async", "clientRequestId": "pr123-sol-r5", "target": {"providerInstanceId": "codex", "model": "gpt-6.1-sol", "options": {"reasoningEffort": "high"}}, "task": "Confirm the fixes for your earlier findings on https://github.com/acme/app/pull/123 are complete and nothing new broke. Read only."}, "result": {"taskId": "task-5", "childThreadId": "44444444-4444-4444-8444-000000000005", "childRunId": "run-child-5", "status": "running", "workState": "working", "providerInstanceId": "codex", "model": "gpt-6.1-sol"}}, {"tool": "task_status", "input": {"taskId": "task-5"}, "result": {"taskId": "task-5", "childThreadId": "44444444-4444-4444-8444-000000000005", "status": "completed", "workState": "result_available", "summary": "APPROVE. No new findings."}}, {"tool": "Bash", "input": {"command": "gh pr checks 123"}, "result": "Lint\tpass\t41s\nTypecheck\tpass\t1m2s\nTest\tpass\t3m10s"}]}], "mocks": {"orchestrator_capabilities": {"parentThreadId": "33333333-3333-4333-8333-333333333333", "inheritedProviderInstanceId": "claudeAgent", "inheritedModel": "claude-sonnet-5-5", "inheritedOptions": [{"id": "effort", "value": "high"}], "runtimeMode": "full-access", "interactionMode": "default", "features": {"appOwnedSubagents": true, "asyncPolling": true, "cancellation": true, "batchThreadCreation": true, "threadManagement": true, "incrementalThreadRead": true, "scheduledTasks": true}, "providers": [{"providerInstanceId": "claudeAgent", "driverKind": "claudeAgent", "displayName": "Claude", "models": [{"id": "claude-opus-5-5", "label": "Claude Opus 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "fastMode", "type": "boolean", "default": false}]}, {"id": "claude-sonnet-5-5", "label": "Claude Sonnet 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}, {"id": "claude-haiku-5-5", "label": "Claude Haiku 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "codex", "driverKind": "codex", "displayName": "Codex", "models": [{"id": "gpt-6.1-sol", "label": "GPT-6.1 Sol", "options": [{"id": "reasoningEffort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "serviceTier", "values": ["default", "priority"], "default": "default"}]}]}, {"providerInstanceId": "muse", "driverKind": "muse", "displayName": "Muse Code", "runtimeModes": ["approval-required", "full-access"], "models": [{"id": "muse-wonder-full", "label": "Muse Wonder Full", "options": [{"id": "reasoningEffort", "values": ["minimal", "low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "grok", "driverKind": "grok", "displayName": "Grok", "models": [{"id": "grok-4.7", "label": "Grok 4.7", "options": []}]}]}, "delegate_task": {"taskId": "task-6", "childThreadId": "44444444-4444-4444-8444-000000000006", "childRunId": "run-child-6", "status": "running", "workState": "working", "providerInstanceId": "codex", "model": "gpt-6.1-sol"}}, "shellMocks": [{"match": "pnpm (vitest|test)|npm test", "output": "Test Files 1 passed (1)\n Tests 14 passed (14)"}], "world": {"branch": "fix/proxy", "commits": [{"sha": "f1a2b3c", "subject": "fix(proxy): refuse private and link-local ranges"}, {"sha": "ecb8550", "subject": "feat(proxy): add an outbound fetch proxy"}], "files": {"src/proxy/blocklist.ts": "export const BLOCKED_RANGES = [\n \"10.0.0.0/8\",\n \"172.16.0.0/12\",\n \"192.168.0.0/16\",\n \"169.254.0.0/16\",\n];\n"}, "diff": "diff --git a/src/proxy/blocklist.ts b/src/proxy/blocklist.ts\n--- a/src/proxy/blocklist.ts\n+++ b/src/proxy/blocklist.ts\n@@ -5,0 +5,1 @@\n+ \"169.254.0.0/16\",\n", "prs": [{"number": 123, "title": "feat(proxy): add an outbound fetch proxy", "headRefName": "fix/proxy", "checks": [{"name": "Lint", "state": "pass"}, {"name": "Typecheck", "state": "pass"}, {"name": "Test", "state": "pass"}]}]}}, "prompt": "A review bot flagged one more nit on the PR: the proxy should also refuse the 198.18.0.0/15 benchmarking range. Fix it and push.", "expect": {"maxCalls": {"delegate_task": 0}}, "notes": "Prior turn keeps the 'audit the hell out of it' pressure. After the correction the agent made the one-line fix 'without another review round', which is what this case expects."}
{"id": "polling-after-async-delegates", "area": "orchestration", "kind": "bad", "pattern": "polling after async delegate_task", "experience": "After starting Haiku and Sol delegates, the parent made 13 task_status calls and 2 long t3_thread_wait calls in one turn instead of ending the turn.", "rule": "Keep polling/wait loops bounded ... (intended: after an async delegate_task, end the turn; completion wakes this thread)", "privacy": "commit-safe", "setup": {"role": "top", "mocks": {"orchestrator_capabilities": {"parentThreadId": "33333333-3333-4333-8333-333333333333", "inheritedProviderInstanceId": "claudeAgent", "inheritedModel": "claude-sonnet-5-5", "inheritedOptions": [{"id": "effort", "value": "high"}], "runtimeMode": "full-access", "interactionMode": "default", "features": {"appOwnedSubagents": true, "asyncPolling": true, "cancellation": true, "batchThreadCreation": true, "threadManagement": true, "incrementalThreadRead": true, "scheduledTasks": true}, "providers": [{"providerInstanceId": "claudeAgent", "driverKind": "claudeAgent", "displayName": "Claude", "models": [{"id": "claude-opus-5-5", "label": "Claude Opus 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "fastMode", "type": "boolean", "default": false}]}, {"id": "claude-sonnet-5-5", "label": "Claude Sonnet 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}, {"id": "claude-haiku-5-5", "label": "Claude Haiku 5.5", "options": [{"id": "effort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "codex", "driverKind": "codex", "displayName": "Codex", "models": [{"id": "gpt-6.1-sol", "label": "GPT-6.1 Sol", "options": [{"id": "reasoningEffort", "values": ["low", "medium", "high", "xhigh", "max"], "default": "high"}, {"id": "serviceTier", "values": ["default", "priority"], "default": "default"}]}]}, {"providerInstanceId": "muse", "driverKind": "muse", "displayName": "Muse Code", "runtimeModes": ["approval-required", "full-access"], "models": [{"id": "muse-wonder-full", "label": "Muse Wonder Full", "options": [{"id": "reasoningEffort", "values": ["minimal", "low", "medium", "high", "xhigh", "max"], "default": "high"}]}]}, {"providerInstanceId": "grok", "driverKind": "grok", "displayName": "Grok", "models": [{"id": "grok-4.7", "label": "Grok 4.7", "options": []}]}]}, "delegate_task": "default", "task_status": "default", "t3_thread_wait": {"threadId": "44444444-4444-4444-8444-000000000001", "status": "running", "timedOut": true}}, "world": {"commits": [{"sha": "d81c0a4", "subject": "test(web): wait for the socket close event in reconnect tests"}, {"sha": "77e2b19", "subject": "test(server): stop sharing a temp dir between workers"}, {"sha": "c0a9e51", "subject": "test: retry the flaky timeline snapshot once"}]}, "shellMocks": [{"match": "gh run list", "output": "completed\tsuccess\tci\tmain\tpush\t9930\t6m\t2026-10-24T08:10:00Z\ncompleted\tfailure\tci\tmain\tpush\t9921\t7m\t2026-10-23T19:40:00Z\ncompleted\tsuccess\tci\tmain\tpush\t9915\t6m\t2026-10-23T12:02:00Z\ncompleted\tfailure\tci\tmain\tpush\t9902\t5m\t2026-10-22T16:31:00Z\ncompleted\tfailure\tci\tmain\tpush\t9890\t6m\t2026-10-21T10:15:00Z"}, {"match": "gh run view", "output": "test (web)\tRun pnpm test\tFAIL src/reconnect.test.ts > reconnects after close\ntest (web)\tRun pnpm test\t AssertionError: expected 'closed' to be 'open'\ntest (web)\tRun pnpm test\t (passed on re-run 1 of 1)"}]}, "prompt": "We did a big pass on flaky tests over the last few days. I want to see if it worked. Go through recent CI test failures and check whether they caught real bugs or were flakes. Have Haiku 5.5 and GPT-6.1 Sol delegates do the exploration, and split the work in parallel. Then give me honest answers: Is flakiness down? Are failures signaling real mistakes? Is anything slipping through?", "expect": {"calls": [{"tool": "delegate_task", "args": {"target.model": "gpt-6.1-sol"}}], "maxCalls": {"task_status": 1, "t3_thread_wait": 0}, "shellMustNot": ["\\bsleep\\b"]}, "notes": "Real parent was Muse; Claude parents mostly behave. Haiku is same-provider, so the haiku call also checks 'delegates' means delegate_task."}