skills/proffesor-for-testing__agentic-qe
1
0
Fork 0
mirror of https://github.com/proffesor-for-testing/agentic-qe.git synced 2026-09-19 08:45:47 +08:00
Code Issues Packages Projects Releases Wiki Activity
1,539 Commits 166 Branches 294 Tags
benchmarks
Commit Graph

3 Commits

Author SHA1 Message Date
Dragan Spiridonov 4a641e7ef1 fix(adr-093): post-audit sweep — CI workflow, consensus provider, MCP sampling, 12 skill evals, 9 test files 
Fifth post-audit sweep. 24 files, +66/-60.

CRITICAL (user-facing):
* .github/workflows/skill-validation.yml:422: CI eval runner
  --model claude-sonnet-4 → claude-sonnet-4-6. Previously CI would
  target a retiring model.
* src/coordination/consensus/providers/claude-provider.ts: Claude 3.x
  consensus provider modernized — type union extended with
  claude-sonnet-4-6 / claude-opus-4-7 / claude-haiku-4-5 as first
  entries, default model updated from claude-3-5-sonnet-20241022
  to claude-sonnet-4-6, availableModels list prepends new models.
  Legacy 3.x entries retained for backward compat.
* src/mcp/security/sampling-server.ts: default model
  claude-3-sonnet-20240229 (retired 2026-02-19) → claude-sonnet-4-6.

Skill evals (12 files, 6 + 6 mirrors):
* .claude/skills/ and assets/skills/ mirrors for:
  performance-testing, chaos-engineering-resilience, quality-metrics,
  localization-testing, accessibility-testing,
  n8n-trigger-testing-strategies. models_to_test list updated to
  claude-sonnet-4-6 / claude-haiku-4-5.

Test files (9):
* tests/unit/coordination/consensus/providers/claude-provider.test.ts:
  default model, test descriptions, and references updated to 4.6/4.7.
* tests/unit/routing/economic-routing.test.ts: claude-3-opus-20240229
  usage → claude-opus-4-7.
* tests/unit/learning/skill-validation-learner.test.ts: claude-3-haiku
  / claude-3.5-sonnet / claude-3-opus → new canonicals.
* tests/unit/mcp/handlers/handler-test-utils.ts: claude-3-haiku →
  claude-haiku-4-5.
* tests/integration/llm/{real-provider-integration,multi-provider}.test.ts:
  bare 'claude-sonnet-4' canonical → 'claude-sonnet-4-6'.
* tests/integration/validation/parallel-eval-runner.test.ts:
  claude-3.5-sonnet / claude-3-haiku → new canonicals.
* tests/routing/advisor/multi-model-executor.test.ts:
  CRITICAL BUG — 'claude-opus-4-6' (non-existent model ID, typo) ×2
  → 'claude-opus-4-7'. Stale test name 'anthropic/claude-opus-4
  when no provider' → '-4.7'.
* tests/unit/opencode/degradation.test.ts: CRITICAL BUG —
  modelId 'claude-opus-4-6' (typo) → 'claude-opus-4-7'.

Left intentionally untouched:
* tests/unit/coordination/consensus/providers/openrouter-provider.test.ts:
  tests that OpenRouter provider lists claude-3-haiku / claude-3.5-sonnet
  / claude-3-opus as supported. These assertions reflect actual
  OpenRouter provider data, which hasn't changed. Adding new-model
  assertions would be an enhancement, not a fix.

Verification:
* 0 tsc errors
* 174/174 tests across touched paths pass

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-17 14:26:23 +00:00
Dragan Spiridonov b055560e81 feat(adr-093): set Opus 4.7 as default ADR-092 advisor model 
Commit 5 of 6 for ADR-093 (Commit 4 skipped — no thinking-config
callers to shim; documented in the implementation plan).

* src/routing/advisor/multi-model-executor.ts: DEFAULT_ADVISOR_MODEL
  upgraded from 'anthropic/claude-opus-4' to 'anthropic/claude-opus-4.7'.
  When TinyDancerRouter sets triggerMultiModel=true (confidence < 0.80,
  or < 0.85 for security tasks), MultiModelExecutor.consult() now
  dispatches to Opus 4.7 by default via HybridRouter.chat() +
  OpenRouter provider.
* tests/routing/advisor/multi-model-executor.test.ts,
  tiny-dancer-router-advisor.test.ts: update expected provider model IDs.

SWE-bench Verified 87.6% (vs 80.8% Opus 4.6), SWE-bench Pro 64.3%
(vs 53.4%), CursorBench 70% (vs 58%). Vendor-independence preserved —
consultations still flow through HybridRouter's 7 providers per
ADR-043.

Verification:
* 0 tsc errors
* 65/65 advisor unit tests pass

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-17 12:46:42 +00:00
Dragan Spiridonov 24e30e0584 feat(advisor): implement ADR-092 provider-agnostic advisor strategy 
Multi-model routing layer with circuit breaking, PII redaction, and
domain-specific prompts for the Queen coordinator.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-13 07:40:20 +00:00