Commit graph

3 commits

Author SHA1 Message Date
Claude
a12de32a34
feat(ws5): add memory/handbook injection seams for context-provider pattern
- retriever: add save_memory() writing to _box-drafts/ review queue, add
  memory_dir param to retrieve() for isolated test routing
- handbook: new load_handbook_conventions() with safe no-op contract (returns
  "" when dir absent/empty/unreadable, never raises)
- clarifier_llm: add context_provider=None seam to ClaudeClarifier and
  build_claude_clarifier_callables(); failure in provider is silent
- planner: add context_provider=None seam to build_plan_prompt() and plan_node()
- coordinator: thread context_provider through default_plan_node_factory(),
  only pass kwarg when non-None to preserve stub-monkeypatching in tests
- tests: 19 new WS5 tests covering all seams (1063 total, all passing)
2026-06-23 01:08:34 +00:00
035c6e57e5 fix(agent-team): clear 3 non-blocking SAST mediums on main
clarifier_llm: sha1 -> sha256 for the non-security cache-discriminator (CWE-327 false positive). github_adapter + github_intake: inline nosemgrep on the urlopen lines (dynamic-urllib-use-detected) — the URL is built from a fixed https GitHub API base, dynamic part is the path only, no SSRF/file:// surface (extends the existing noqa:S310 trusted-host judgment to semgrep). Scanner now reports 0 mediums on the agent-team scope.
2026-06-18 14:16:31 -04:00
270ce93b2a feat(agent-team): bind P1 clarifier to real Claude via subscription-OAuth invoker
Adds the billing-seam invoker (claude_agent_sdk subscription-OAuth, deferred import, API/Bedrock paths) and the Claude-backed clarifier callables (ConfidenceAssessor/QuestionGenerator, one call/turn memoized on (thread_id,len,content-hash), fail-safe to 0.0 so garbage never clears the 98% human gate).
2026-06-18 12:56:42 -04:00