aruo
e1b8d1fb2c
docs(harness): add evidence-chain, application-audit, contract-state and interview review notes; annotate guard/release core classes
2026-08-08 00:12:25 +08:00
zhuyongxin
074d1aa5a9
docs(harness): add MySQL sandbox learning note and mark tool domain complete
...
- Add MySQL sandbox note: three defense layers (semantic/connection/output),
fail-closed validation, allowlist, parameterization, cancellation, redaction
- Mark tool domain complete in roadmap; next: guard
2026-08-06 17:46:53 +08:00
zhuyongxin
f26d395650
docs(harness): annotate RAG backend core classes and add retrieval learning note
...
- Annotate LookupKnowledgeTool, KnowledgeEvidencePostProcessor, RrfFusion, KnowledgeDocumentRetriever
- Add RAG retrieval learning note: L0 navigation, multi-recall + RRF, qualityScore,
degradation, contract semantics, validation (audit + offline eval), discussion insights
2026-08-05 18:37:50 +08:00
zhuyongxin
ff0752a16c
docs(harness): annotate tool domain classes and add tool chain learning notes
...
- Annotate 43 tool domain classes (contract/projection/boundary/store/adapter/mysql)
- Add tool registration and execution chain learning note
- Add tool call chain runtime journey note (model decision to observation)
2026-08-04 18:37:17 +08:00
zhuyongxin
7844bcea40
docs(harness): annotate progress core classes and add code-level learning notes
...
- Annotate DiagnosisProgressTracker, HarnessToolInterceptor, DiagnosisProgressProjector,
DiagnosisReleaseUseCase, ToolBoundary, ToolBoundaryResult, CanonicalToolInvocation
- Add progress code learning note: interceptor gates, tracker state machine,
canonical lifecycle, execution gate, projection/release pipeline
- Update learning roadmap: progress marked as deeply learned, next is tool domain
2026-08-03 18:37:23 +08:00
wdm1802
e564863c43
docs(harness): add retry guide and learning roadmap; annotate retry core
2026-08-03 01:29:36 +08:00
wdm1802
d084202166
docs(harness): add budget flow sequence and execution control notes
2026-08-02 20:58:13 +08:00
zhuyongxin
b39a625e5b
docs(mvp): add remaining harness audit guides and engineering index
2026-07-30 19:04:59 +08:00
zhuyongxin
e9f1c48d34
docs(harness): add loop inner/outer exception handling guide
2026-07-30 18:55:43 +08:00
zhuyongxin
3a7eee8af4
docs(mvp): add harness design and progressive guides
2026-07-29 19:04:44 +08:00
zhuyongxin
584639fa2a
docs(mvp): move engineering notes under mvp/engineering
...
Relocate RAG and diagnosis decision/E2E writeups from docs/ root into
mvp/engineering so architecture, issues, and engineering narrative stay
together. Update indexes and cross-links; leave docs/learning as legacy.
2026-07-29 10:49:45 +08:00
zhuyongxin
bdac35567c
docs(issues): add ISS-017 L0 filter fallback hardening
...
Track L0 hard-filter + unfiltered retry brittleness. Keep current
behavior; prefer A+C later and defer soft-constraint redesign (D).
2026-07-29 10:48:47 +08:00
zhuyongxin
7ae9707a3b
feat(harness,rag): dual LLM audit fields, run conclusion, and hybrid quality
...
Persist provider reasoning and assistant text separately on agent_reasoning_audit
(DeepSeekAssistantMessage path), extract diagnosis_run.conclusion, enrich RAG
tool audit (step_id/query/qualityScore), gate empty mysql tools, drop devtools,
and align MVP docs after live E2E verification.
2026-07-28 19:43:13 +08:00
zhuyongxin
2f40536248
docs(mvp): document dense+BM25 hybrid knowledge retrieval
...
Add current RAG architecture covering MilvusClientV2 hybrid search,
chunk evidence identity, rebuild ops, and update the MVP architecture
index and system overview links.
2026-07-28 09:56:08 +08:00
zhuyongxin
38f781b157
feat(harness): complete protocol repair stop and archive ISS-016
...
Add repairable INVALID_PROGRESS_PROTOCOL observations, independent
PROGRESS_PROTOCOL_VIOLATED saturation, and controlled release paths.
Archive the OpenSpec change after syncing main specs and devflow.
2026-07-27 19:10:07 +08:00
aruo
edb6153fd6
docs(issue): mark iss-015 partially implemented
2026-07-27 10:22:09 +08:00
aruo
d0452184ee
feat(harness): add information gain stop and audit
2026-07-27 01:03:34 +08:00
zhuyongxin
e47f2dead0
docs(mvp): align architecture and audit table design
2026-07-23 20:16:29 +08:00
zhuyongxin
49180abccf
docs(issue): archive legacy issues and add iss-015
2026-07-23 19:54:01 +08:00
zhuyongxin
529f4ff43b
docs(demo): add successful diagnosis request
2026-07-23 19:06:37 +08:00
zhuyongxin
8300435a63
docs(issue): add iss-014 handoff
2026-07-23 18:03:14 +08:00
zhuyongxin
e20249c5d9
feat(harness): improve trace fallback and reasoning audit
2026-07-23 17:52:01 +08:00
zhuyongxin
8fbc443f76
docs(issue): close iss-014 stage status
2026-07-22 18:08:29 +08:00
zhuyongxin
8ee7cc0b70
refactor(harness): remove legacy agent architecture
2026-07-22 18:02:01 +08:00
zhuyongxin
bc36248cd8
feat(chat): cut over to single SSE endpoint
2026-07-22 10:01:12 +08:00
zhuyongxin
f8809cb7dd
feat(harness): add chat application use case
2026-07-22 00:57:39 +08:00
zhuyongxin
ee0949d464
feat(harness): add evidence and semantic guards
2026-07-21 23:50:51 +08:00
zhuyongxin
2362665519
feat(harness): add single diagnosis react agent
2026-07-21 22:29:49 +08:00
zhuyongxin
85029d96a7
feat(harness): add readonly mysql tool
2026-07-21 21:24:42 +08:00
zhuyongxin
0dbdd7d8d3
feat(harness): add canonical tool invocation boundary
2026-07-21 19:36:25 +08:00
zhuyongxin
6b74990f86
feat(harness): add run context and retry core
2026-07-21 18:36:19 +08:00
zhuyongxin
4274f3350b
feat(harness): freeze aci tool contracts
2026-07-21 18:01:18 +08:00
zhuyongxin
58c39107c5
refactor(harness): freeze single-agent contracts
2026-07-21 17:33:25 +08:00
zhuyongxin
30d3296043
docs(mvp): archive session run trace issue
2026-07-11 16:46:20 +08:00
zhuyongxin
f9df94377b
feat(trace): finish run-aware demo verification
2026-07-10 21:37:43 +08:00
zhuyongxin
d928a1968a
feat(trace): bind feedback to runs
2026-07-10 20:29:56 +08:00
zhuyongxin
26d5529280
feat(trace): isolate chat runs
2026-07-10 19:02:04 +08:00
zhuyongxin
52bf0302c6
feat(trace): add session run isolation schema
2026-07-10 17:47:56 +08:00
zhuyongxin
841437fa06
docs(mvp): organize mvp documentation
2026-07-09 13:40:08 +08:00
zhuyongxin
9c9a0024d4
feat(demo): add interview quality audit
2026-07-09 11:18:49 +08:00
aruo
db0f229285
feat(eval): add evidence pipeline acceptance closure
2026-07-09 00:47:48 +08:00
aruo
a77c947cd4
docs(architecture): align evidence pipeline design
2026-07-08 23:53:21 +08:00
aruo
9a84b3de34
feat(agent): support no-evidence references
2026-07-08 23:30:00 +08:00
aruo
7b8c75e571
feat(agent): harden verifier evidence references
2026-07-08 16:12:56 +08:00
aruo
a08672b31e
feat(eval): add executor audit closure checks
2026-07-08 10:21:39 +08:00
aruo
39c0c5f8be
docs(mvp): clarify executor v2 implementation issue
2026-07-08 02:43:12 +08:00
aruo
1b31e78be5
feat(agent): add verifier claim checks
2026-07-08 02:33:02 +08:00
aruo
c5e496e715
feat(agent): add executor gatekeeper hook
2026-07-08 02:01:49 +08:00
aruo
050cbc8fee
feat(agent): add executor evidence v2 contract
2026-07-08 01:37:15 +08:00
zhuyongxin
04eb50e2b4
feat(agent): add executor evidence output contract
2026-07-07 19:02:02 +08:00
aruo