ed/manual_slop
Private
Public Access
0
0
Fork 0
Code Activity

docs(mcp_client+ai_client): correct tool counts (15->18, 45->46)

Browse Source 
- Total tool count: 45 -> 46 (per src/models.py:AGENT_TOOL_NAMES)
- Python AST tools: 15 -> 18 (3 structural mutators added:
  py_remove_def, py_add_def, py_move_def, py_region_wrap)
- py_get_symbol_info is fictional; replaced with the 4 actual
  structural mutator tools
- Cross-link from guide_ai_client.md updated
This commit is contained in:
Edward R. Gonzalez
2026-06-10 20:02:01 -04:00
parent 07c1ed4928
commit 2e12b266e4
2 changed files with 12 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/guide_ai_client.md
+1 -1
View File
@@ -425,7 +425,7 @@ Gated by env var (e.g., `RUN_REAL_AI_TESTS=1`). Hits the real API. Not in defaul
- **[guide_architecture.md](guide_architecture.md#ai-client-multi-provider-architecture)** — Threading model and provider dispatch
- **[guide_mma.md](guide_mma.md#tier-3-worker-lifecycle-run_worker_lifecycle)** — How Tier 3 workers use ai_client
- **[guide_mcp_client.md](guide_mcp_client.md)** — The 45 tools that ai_client can invoke
- **[guide_mcp_client.md](guide_mcp_client.md)** — The 46 tools that ai_client can invoke (canonical list in `models.AGENT_TOOL_NAMES`)
- **[guide_rag.md](guide_rag.md)** — RAG engine integration via `rag_engine` parameter
- **[guide_state_lifecycle.md](guide_state_lifecycle.md)** — The per-provider history globals (`_anthropic_history`, etc.) are managed here; their locking and reset behavior is documented
- **[guide_context_aggregation.md](guide_context_aggregation.md)** — The `aggregate.py` pipeline that produces the markdown the AI client sends