Files

T

kami 238d353653 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>

2026-06-29 10:50:16 +00:00

2.1 KiB

Raw Blame History

apps/server

Purpose

Ktor HTTP + WebSocket server. Exposes the orchestration kernel to CLI and TUI clients, manages session lifecycle, and streams events over WebSocket.

Ownership

All sources under apps/server/src/.

Local Contracts

HTTP REST routes

GET/POST /sessions — session browse and start (POST accepts an optional intent brief, parity with the WS StartSession)
POST /sessions/{id}/resume — resume a session after restart
GET/POST /tasks — task listing and management
GET/POST /providers — provider configuration
GET/POST /workflows — workflow management
GET /health — health report (probes: event-store, llama-server, disk watermark)
GET /stats — metrics report (MetricsProjection)
GET /metrics/tool-reliability — per-model tool-call validity across the event log (ToolReliabilityInspectionService); groundwork for capability-aware routing

WebSocket protocol (`/ws`)

ServerMessage (server → client): sealed hierarchy — SessionMessage (event-derived, carries sequence + sessionSequence) and NonEventMessage (control/infra). Variants include session lifecycle, approval requests, clarification requests, narration, proposed workflows, health/metrics pushes.
ClientMessage (client → server): StartSession, ApproveToolCall, RejectToolCall, GrantApproval, AnswerClarification, SetChatMode, and others.
All protocol types are in protocol/ (Dtos.kt, ServerMessage.kt, ClientMessage.kt, ProtocolSerializer.kt).

Health monitoring

HealthMonitor runs probes on a schedule; results folded via HealthProjection into HealthState.
Adding a probe: implement HealthProbe, register in ServerModule.

Work Guidance

Follow Kotlin rules in root CLAUDE.md.
Route handlers must not contain domain logic — delegate to core services injected via ServerModule.
New WS message variants require updating both ServerMessage/ClientMessage sealed classes and ProtocolSerializer.

Verification

./gradlew :apps:server:test --rerun-tasks

Child DOX Index

No child AGENTS.md (leaf module).

2.1 KiB Raw Blame History