🤖 feat: add actor-critic mode loop and source-aware rendering#2471
🤖 feat: add actor-critic mode loop and source-aware rendering#2471ammar-agent wants to merge 13 commits intomainfrom
Conversation
|
@codex review |
|
@codex review Addressed the failing integration check by switching the new critic UI test from a |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: f91158db9a
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
|
@codex review Addressed queue-priority feedback:
|
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 70929b8143
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
|
@codex review Aligned
|
|
@codex review Addressed the edit-precedence thread:
|
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 78e85797d2
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
|
@codex review Addressed the critic-resume thread:
|
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 84fd2e8d31
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
|
@codex review Addressed both new threads:
|
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 03461a1949
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
|
@codex review Addressed the /done parity thread:
|
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: edb08de807
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
|
@codex review Addressed both latest threads:
|
|
Codex Review: Didn't find any major issues. Breezy! ℹ️ About Codex in GitHubCodex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback". |
Implement actor-critic mode across command parsing, send options, backend stream orchestration, and UI rendering. - Add /critic toggle command and workspace-scoped critic prompt persistence. - Add backend actor↔critic automatic turn loop with strict /done termination and critic-only tool disable policy. - Persist actor/critic message source metadata and transform request history for critic role-flip + actor feedback. - Render critic reasoning/assistant output with dedicated source badges and styling. - Expand mock router/player plumbing and add comprehensive UI coverage for looping, /done semantics, context recovery, and interrupt behavior. Validation: - make static-check - bun test ./tests/ui/critic/criticMode.test.ts - bun test ./src/browser/utils/slashCommands/parser.test.ts ./src/browser/utils/slashCommands/suggestions.test.ts ./src/browser/utils/messages/sendOptions.test.ts --- _Generated with `mux` • Model: `openai:gpt-5.3-codex` • Thinking: `xhigh` • Cost: `$19.73`_ <!-- mux-attribution: model=openai:gpt-5.3-codex thinking=xhigh costs=19.73 -->
The integration CI suite runs tests with Jest, not bun:test. Replace the bun:test import in the new critic-mode UI suite so the file uses the same Jest global pattern as other `tests/ui/*.test.ts` files. Validation: - env TEST_INTEGRATION=1 bun x jest --maxWorkers=100% --silent tests/ui/critic/criticMode.test.ts - make static-check --- _Generated with `mux` • Model: `openai:gpt-5.3-codex` • Thinking: `xhigh` • Cost: `$19.73`_ <!-- mux-attribution: model=openai:gpt-5.3-codex thinking=xhigh costs=19.73 -->
When a user sends a follow-up during a critic-streaming turn, the queued message should be processed before the actor-critic loop starts another automatic continuation turn. - Stop actor-critic auto-continuation when queued user input exists at stream end. - Clear critic loop state in that branch so the queued user turn can own continuation semantics. - Add a UI integration test that queues user input during critic streaming and asserts the queued turn executes before auto-continuation. Validation: - bun test ./tests/ui/critic/criticMode.test.ts - env TEST_INTEGRATION=1 bun x jest --maxWorkers=100% --silent tests/ui/critic/criticMode.test.ts - make static-check --- _Generated with `mux` • Model: `openai:gpt-5.3-codex` • Thinking: `xhigh` • Cost: `$19.73`_ <!-- mux-attribution: model=openai:gpt-5.3-codex thinking=xhigh costs=19.73 -->
Reduce the mocked critic stream length in the new queue-priority scenario so CI workers can still queue input during streaming without timing out waiting for the critic turn to finish. Validation: - bun test ./tests/ui/critic/criticMode.test.ts - env TEST_INTEGRATION=1 bun x jest --maxWorkers=100% --silent tests/ui/critic/criticMode.test.ts - make static-check --- _Generated with `mux` • Model: `openai:gpt-5.3-codex` • Thinking: `xhigh` • Cost: `$19.73`_ <!-- mux-attribution: model=openai:gpt-5.3-codex thinking=xhigh costs=19.73 -->
ammar-agent
force-pushed
the
critic-mode-pgfx
branch
from
f0d18fd to
00357fb
Compare
In critic mode, the main text input now serves as the critic prompt input. Removes the separate inline critic prompt field and its wrapper row. - Textarea placeholder changes to "Critic instructions..." when critic mode is on - Sending in critic mode uses the message text as the critic prompt (persisted for resumability and override in send options) - Badge kept as a simple standalone indicator - Removed unused setCriticPromptFromUi/findCriticPromptInput test helpers - Updated 3 tests to reflect new UX model (TDD approach) Generated with `mux` · anthropic:claude-opus-4-6 · xhigh · $20.56
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 5c87e16b99
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
Command prefixes (e.g. /haiku) were included in the critic prompt because we used messageText (raw input) instead of actualMessageText (parsed send payload). Now the critic evaluates against the same text the actor sees.
|
@codex review Fixed: critic prompt now uses |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 3b9d36c3e2
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
When a critic turn is interrupted and resumed, the frontend only sets isCriticTurn/criticEnabled. The tool-disable policy and critic system instructions (including /done contract and user critic prompt) were missing, allowing unintended tool execution on resumed critic turns. Now streamWithHistory ensures critic guardrails are applied whenever isCriticTurn is true, using criticLoopState (preserved across aborts) to recover the original actor instructions and critic prompt.
|
@codex review Addressed: critic guardrails (tool-disable policy, critic system instructions, |
|
Codex Review: Didn't find any major issues. Keep them coming! ℹ️ About Codex in GitHubCodex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback". |
1 participant
Summary
Adds an actor-critic mode loop where a critic LLM automatically reviews each actor turn and provides feedback until it signals
/done. The main text input becomes the critic prompt in critic mode — no separate inline input field.Background
Actor-critic is a workflow pattern where a "critic" LLM evaluates the "actor" LLM's output after each turn, providing iterative feedback. This enables autonomous self-improvement loops where the actor refines its work based on critic feedback until the critic is satisfied.
Implementation
Critic mode UX
/criticslash command toggles critic mode per workspace (persisted in localStorage)Actor-critic loop orchestration (
agentSession.ts)criticEnabled, a critic turn auto-firesbuildCriticRequestHistory), disables all tools, and injects critic-specific system instructions/doneto stop the loopCritic message building (
criticMessageBuilder.ts)buildCriticRequestHistory— role-flips actor ↔ user messages for critic perspectivebuildActorRequestHistoryWithCriticFeedback— transforms critic feedback into user-role messages for actor context, filtering out partial and/donemessagesisCriticDoneResponse— detects/donesentinel, allowing reasoning parts but checking only visible textbuildCriticAdditionalInstructions— assembles critic system prompt from base instructions + user critic promptSource-aware rendering
metadata.messageSource = "actor" | "critic"data-message-sourceattribute on assistant/reasoning message DOM elementsmessageSourcethreaded through stream events (stream-start,reasoning-delta,stream-end)Resilience
shouldResumeAsCriticTurninspects latest partial message metadataValidation
/donesemantics, role-flip, reasoning persistence, context-exceeded recovery, model parity, queue priority, interrupt, disabled baselineisCriticDoneResponseandbuildActorRequestHistoryWithCriticFeedbackmake static-checkpassesGenerated with
mux• Model:anthropic:claude-opus-4-6• Thinking:xhigh• Cost:$20.56