- Replace thread-based remote state sync with subprocess (sync_remote_state.py)
to prevent thread pool exhaustion hanging the API
- Fix pipeline showing 'waiting' when a real step is running alongside a gate
- Fix watcher scanner path for linux accounts mode
- Disable label-master semantic review (Step A.5 + §4.5) per user request
- Correct field names: use is_model_correct_dev for accuracy, origin_predict_dev
for model output (not cleaned_predict)
- Add prohibition against putting test set data in relabel_candidates
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix session resume: remove messages.length>1 guard so sessionStorage
ID is used as resumeSessionId on first message (prevents new session
creation when user sends "继续")
- Fix config_set tool schema: add missing `items: {}` to array type in
oneOf (Azure OpenAI strict validation rejects it otherwise)
- Metrics chart: use actual target set filename from trigger text
instead of generic "target_subset" key
- Add sub-agent skill call logging to agent_runtime.py (full
prompt/response, no truncation)
- Various metric enrichment and dedup fixes in server.py
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Wires clear_session_env_vars() into LocalCodingAgent.clear_runtime_state so the
/clear slash command now drops session-scoped env vars alongside the rest of the
ephemeral runtime state, matching commands/clear/caches.ts:127.
Core changes:
- Added claw-code/src/token_budget.py for projected prompt size, chat-framing overhead, output reserve, and soft/hard input limits.
- Wired preflight prompt-length validation and auto-compact/context collapse into claw-code/src/agent_runtime.py.
- Extended claw-code/src/compact.py so compaction reports usage back to the runtime.
- Added inspection surfaces in claw-code/src/agent_slash_commands.py and claw-code/src/main.py:
- /token-budget and /budget
- token-budget
- Hardened claw-code/src/tokenizer_runtime.py so arbitrary simple model names fall back cleanly instead of trying a slow Transformers
lookup.
- Exported the new helpers in claw-code/src/__init__.py.
Docs and tracking:
- Updated claw-code/PARITY_CHECKLIST.md to mark prompt-length validation, token-budget calculation, and auto-compact/context collapse as
done.
- Updated claw-code/README.md and claw-code/TESTING_GUIDE.md with the new commands and behavior.
Tests:
- Added claw-code/tests/test_token_budget.py.
- Updated claw-code/tests/test_agent_runtime.py, claw-code/tests/test_agent_slash_commands.py, claw-code/tests/test_main.py, and claw-code/
tests/test_agent_context_usage.py.
- Verified with:
- /data/fs201059/aa17626/miniconda3/bin/python3 -m compileall src tests
- /data/fs201059/aa17626/miniconda3/bin/python3 -m unittest -v tests.test_token_budget
tests.test_agent_runtime.AgentRuntimeTests.test_agent_rejects_prompt_before_backend_when_preflight_input_budget_is_exceeded
tests.test_agent_runtime.AgentRuntimeTests.test_agent_auto_compacts_context_before_next_model_call tests.test_agent_slash_commands
tests.test_main tests.test_compact tests.test_tokenizer_runtime tests.test_agent_context_usage
- Result: 71 tests, OK
persistent plan runtime with update_plan, plan_get, and plan_clear, plus plan-to-task sync wired through claw-code-agent/src/
agent_tools.py, claw-code-agent/src/agent_runtime.py, claw-code-agent/src/agent_context.py, claw-code-agent/src/agent_prompting.py, and claw-code-agent/src/
agent_slash_commands.py. New local plan slash commands are /plan and /planner.
wuyang6