feat(qa): remote NIM provider + headless-QA robustness

Enable autonomous QA through a remote OpenAI-compatible provider (NVIDIA NIM)
and harden the tool/approval path so unattended multi-stage runs complete.

- inference: add openai_compat provider (Bearer chat-completions for NIM/OpenAI),
  dispatched by provider type "nim"/"openai"; key via api_key/api_key_env.
- server: bind configured [server] host/port instead of a hardcoded 8080;
  POST /sessions accepts an optional `intent` (WS parity) for intent-driven workflows.
- kernel: thread the bound operator profile's approval_mode into per-tool gating so
  auto/yolo enable unattended approval (engine still consulted; policy/plane-2 BLOCK
  stays terminal); on a recoverable tool failure feed the tool's arg-schema back into
  context so the model self-corrects instead of repeating a malformed call.
- tools: split deletion out of file_write into a separate, explicitly-named file_delete
  tool — a model can no longer delete a file by getting a write-mode parameter wrong.
- server: add GET /metrics/tool-reliability — per-model tool-call validity from the
  event log (measurement groundwork for capability-aware routing).
- docs: update AGENTS.md across kernel, tools, server, inference.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
2026-06-29 10:50:16 +00:00
parent d26f20c316
commit 238d353653
27 changed files with 924 additions and 268 deletions
+2 -1
View File
@@ -16,6 +16,7 @@ Adapter for `core:tools`. Depends on `core:tools`, `core:events`, `core:approval
- Web search and web fetch results are environment observations; they must be recorded as events by callers to preserve replay determinism (invariant #9).
- `ToolConfig` is the only configuration surface; pass via `InfrastructureModule.createToolExecutor()`.
- `buildTools()` extension on `ToolConfig` assembles the full tool list; add new tools there, not in the registry directly.
- Filesystem mutation is split by intent: `file_write` only writes (`{path, content}`), `file_edit` edits, and `file_delete` only deletes (`{path}`) — deletion is a separately-named capability so a model can never delete by getting a write-mode parameter wrong. `file_delete` shares `file_write`'s path jail and `fileWrite.enabled` toggle and carries `ToolCapability.FILE_WRITE`.
## Work Guidance
@@ -30,4 +31,4 @@ Standard adapter rules apply (see parent `AGENTS.md`). Network calls (web tools)
## Child DOX Index
- `filesystem/` — filesystem read/write/list tools implementing `core:tools` contracts; no separate AGENTS.md (sub-leaf, covered by this doc)
- `filesystem/` — filesystem tools implementing `core:tools` contracts: `FileReadTool`, `FileWriteTool` (write-only), `FileDeleteTool`, `FileEditTool`, list; no separate AGENTS.md (sub-leaf, covered by this doc)