feat(openclaw): deterministic training status/batch command adapter#250
Closed
feat(openclaw): deterministic training status/batch command adapter#250
Conversation
Docs/comments only — no runtime behavior change. Clarifies which roles are resolved where: triage/general/code via local_model_selection.py, vision via ui_tars_bridge.py, architect_escalation as explicit policy only. Adds Resolution Surface column to all worker tables. Documents that runtime model-name strings (QwenPlan, Gemma:PatternMatch) are a tracked follow-up refactor. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…ed constants Runtime dispatch now uses role constants (role:triage, role:code, role:0102) instead of model-name strings (Gemma:PatternMatch, Qwen:Planning). QwenPlan renamed to WorkerPlan, executor methods renamed to _execute_triage_task/_execute_code_task. ROLE_GENERAL is reserved and dispatchable but not yet planner-emitted. Remaining model-name debt: workers.qwen_engine/gemma_engine are external AutonomousRefactoringOrchestrator API (separate scope). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add ScheduleEvaluator for deterministic parsing of schedule phrases (e.g. "run self research daily"), ScheduleParser for phrase-to-routine mapping, and manage_schedules.py CLI. Already wired into OpenClaw execution routes. 52 tests pass. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Drift-aware queue builder that aggregates backlog items, sorts by WSP 15 priority/scores, and detects repo drift against expected owner modules. Outputs queue JSON and status summary. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add async training adapter for OpenClaw with anchored regex matching, PatternMemory status reporting (DISABLED/UNAVAILABLE/COMPLETE/DUE/EMPTY/ERROR), and batch trigger that awaits from the async execute_query path. - training_adapter.py: try_training_command(), _training_status(), _trigger_training_batch() - openclaw_execution_routes.py: hook after schedule commands, before HoloIndex fallback - 35 tests: command matching, false-positive rejection, status states, batch outcomes, async integration Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Member
Author
|
Closing as stale/scope-drifted. Related schedule evaluator work already exists on main, and this 23-day-old OpenClaw training adapter PR likely needs a fresh implementation against current OpenClawSupervisor state if still needed. |
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
training_adapter.pywith deterministic command matching for training status, progress, batch triggerexecute_query()after schedule commands, before HoloIndex fallback_trigger_training_batch()awaits from running event loop (noasyncio.run())Test plan
pytest modules/communication/moltbot_bridge/tests/test_training_adapter.py)🤖 Generated with Claude Code