Conversation
Remove the dedicated self-dev subsystem from stable paths and replace it with minimal Clio repo-awareness prompt behavior. Simplify dispatch, middleware, worker spec validation, tool profiles, and eval metrics while preserving ordinary coding-agent behavior outside the Clio source tree. Document and verify the mini/AgenticQwen real-target harness path.
Make allowedTools required and remove the supervised field from worker specs and runtime. Extract dispatch lifecycle resolution into resolveLifecycle and add DispatchLifecycleStage. Simplify middleware rule handling to yield empty runtime rule lists. Count only successful, non-timed-out verifier commands as validation evidence. Add appendSubmittedUserTurn and update tests accordingly.
Resolve local model family, thinking surface, request payload, and response parsing through one provider-domain capability layer. Wire GPT-OSS Harmony, on/off local reasoning models, advisory budget models, UI display paths, and worker dispatch through the resolved effective capability state. Cover Harmony payload/parsing and dashboard/footer/settings/thinking consistency with focused tests.
Remove top-level anyOf requirements from the read, write, and edit tool parameter schemas so the OpenAI Codex Responses API accepts the tool catalog. Keep the path/file_path requirement enforced in the tool runtime and update the existing registry expectation to match that runtime error.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
validate_frontend, TUI active-run cancel/queue behavior, local model capability/Harmony handling, docs refresh, and safety/evidence/eval/memory/components updates.Verification
npm run typechecknpm run lintnpm run test(1317 passed)npm run buildnpm run test:e2e(70 passed)git diff --checknpm audit --json(0 vulnerabilities)npm run prepublishOnlynpm pack --dry-runclio doctorclio targets --jsonSmoke Receipts
clio-release-print-ok3i15lg67h1be,clio-release-json-ok3i0v4kje2odh, targetmini, modelAgenticQwen-30B-A3B-i1-Q4_K_M, exit 0, zero tool calls28udh8artd65, targetopenai-codex, modelgpt-5.4-mini, exit 0, zero tool callsNot Run