Commit Graph

6 Commits

Author SHA1 Message Date
chiguyong be5c4e09f8 refactor(core,experts): classify except Exception + structured ReviewResult (U3)
ReviewResult dataclass (passed/degraded/feedback) replaces tuple+[DEGRADED] prefix in _review_phase_output; 3 review_result WS payloads now carry degraded field (AE3).

except Exception narrowed to specific types across 10 files (core/react, rewoo, base, orchestrator, dispatcher, plan_exec_engine + experts/orchestrator, _phase_executor, _review_gate + orchestrator/pipeline_engine). Baseline 140 -> 66 occurrences (>=50% reduction).

Fix RuntimeError regression: review-gate + compression paths now catch RuntimeError (LLM/provider internal errors) to preserve degradation semantics. Test side_effect switched to functional form to avoid StopIteration on list exhaustion.

ruff clean; 135 key + 469 experts + 163 core tests pass.
2026-06-30 18:03:58 +08:00
chiguyong 8c365486e2 fix(pipeline): address code review findings for adversarial loop
Critical:
- C1: Add verifier_timeout_seconds for independent Verifier timeout
- C2: Verifier parse failure raises RuntimeError instead of dead-loop

Major:
- M1: Inject previous_output into Worker retry context
- M2: Add Pydantic ge/le constraint on ReviewFeedback.score
- M3: Use Literal type for feedback_mode enum validation
- M4: Use Literal types for ReviewIssue severity and category
- M5: Merge error messages when escalation agent also fails

Tests: 8 new test cases added (19 total), all passing
2026-06-12 10:02:37 +08:00
chiguyong dc07c7c60a feat(pipeline): implement adversarial loop execution logic
Add Worker-Verifier adversarial loop to PipelineEngine:
- _execute_stage_with_adversarial: main loop for Worker→Verifier→retry
- _execute_agent_stage: extracted agent execution logic
- _execute_verifier: execute verifier and parse ReviewFeedback
- _build_feedback_context: build feedback context for worker retry
- _escalate: handle round exhaustion (escalate or fail)
- Route to adversarial mode when stage.verifier is configured

Support three feedback modes: structured+natural, structured, natural
2026-06-12 09:37:30 +08:00
chiguyong 31bd3b126c feat(phase8): chat adaptive enhancements, pipeline reflection, search tools upgrade
- Enhanced chat CLI with adaptive mode and session management
- Added pipeline reflection and schema extensions
- Upgraded BaiduSearch and WebSearch tools with advanced capabilities
- Expanded server routes for skills and chat
- Added session store enhancements
- New chat module and pipeline reflection support
2026-06-09 23:18:06 +08:00
chiguyong 4db637cd4f feat(pipeline): U5 state persistence with Redis hot + PG cold dual-write
Add PipelineStateMemory/Redis/PG backends, PipelineStateManager with
Redis Sorted Set hot state + PostgreSQL JSONB cold persistence.
Integrated into PipelineEngine with state persistence calls at each
step transition.
2026-06-07 17:25:52 +08:00
chiguyong 9a6d6fee4e feat: initial fischer-agentkit package with unified agent architecture
- BaseAgent with handle_task() pattern (execute template moved up)
- Protocol: TaskMessage, TaskResult, HandoffMessage, EvolutionEvent
- Tool system: FunctionTool, AgentTool, ToolRegistry with versioning
- Memory system: WorkingMemory (Redis), EpisodicMemory (pgvector), SemanticMemory (RAG adapter), MemoryRetriever (hybrid)
- Evolution engine: Reflector, PromptOptimizer (DSPy-style), StrategyTuner, ABTester, EvolutionStore
- Orchestrator: PipelineEngine (parallel DAG), PipelineLoader (YAML), HandoffManager, DynamicPipeline
- MCP: Server (FastAPI), Client (httpx), MCPTool
- Prompts: PromptTemplate, PromptSection
- Exceptions: full hierarchy including Tool, Schema, Handoff, Evolution errors
- Tests: unit tests for core, tools, protocol, evolution, pipeline
2026-06-04 22:24:06 +08:00