v0.17.3: bug-fix maintenance pass — ingest origin exemption, FK safety, auto-search reset, deterministic ingest, WAL, config centralization, dead-code removal

- /api/ingest exempt from origin check for CLI/Bearer clients
- recreate deleted conversations on bogus conversation_id (chat + search)
- augmented auto-search emits reset:true; frontend clears first-pass text
- image uploads stored as placeholders, never text-ingested
- check_fact_conflicts requires shared subject keywords
- deterministic ingest point ids (md5 chunk hash)
- get_load() no longer crashes when rocm-smi yields no VRAM lines
- SQLite WAL + busy_timeout; timing-safe API key compares
- supervise fire-and-forget auto-ingest tasks; log missing logprobs
- centralize EMBED_URL/EMBED_MODEL/QDRANT_URL/NODE_NAME in config
- remove dead triage.py, select_node tests, is_state_changing, stray artifacts
- add regression tests + autouse global-reset conftest

ai.md

@@ -35,15 +35,15 @@ Every router has a dedicated test file:
 | `test_search_url_sanitization.py` | `search.py` URL sanitizer |
 | `test_cluster.py` | `cluster.py` — registration, deregistration, pong, events, coordinator query |
 | `test_cluster_heartbeat.py` | `cluster.py` — heartbeat handler, known/unknown node |
-| `test_model_swap.py` | `cluster.py` + `triage.py` — request_model_swap, handle_model_ready/failed, select_node swap triggering |
+| `test_model_swap.py` | `cluster.py` — request_model_swap, handle_model_ready/failed |
 | `test_node_agent.py` | `node_agent/agent.py` — registration, ping/pong, model swap |
 | `test_image.py` | Image generation — cluster handlers, router proxy, node agent ComfyUI integration, hardware probe, capability detection |
-| `test_triage.py` | `triage.py` — classify_query, select_node, get_inference_url |
 | `test_settings_allowlist.py` | `routers/settings.py` — allowlisted key enforcement |
 | `test_skills_framework.py` | `routers/skills.py` — list, toggle, unknown skill, prompt injection |
 | `test_ip_allowlist.py` | IP allowlist helper + middleware |
 | `test_rate_and_payload_guardrails.py` | Rate limits + payload size enforcement |
 | `test_error_envelopes.py` | Global exception handler + stream error incidents |
+| `test_fixes_regression.py` | Origin-exempt ingest, bogus conversation_id FK, auto-search reset, image uploads, conflict false-positives, deterministic ingest ids, get_load VRAM parsing, version pin |
 | `test_upload.py` | `routers/upload.py` — upload, delete, link, by-conversation, attachment_count integration |
 
 Modules that call `httpx.AsyncClient` (chat, completions, models, search_route, upload, ingest, model_pull)
@@ -69,7 +69,6 @@ Refactored from single-file (`app.py`) into modules under project root:
 | `gpu.py` | GPU stats — `rocm-smi` (AMD/Linux) or `system_profiler` (Apple Silicon/macOS) |
 | `crypto.py` | AES-256-GCM encrypt/decrypt + key management (stored as `heartbeat_interval_ms` in settings) |
 | `model_pull.py` | Startup model availability check + Ollama pull API |
-| `triage.py` | Phi-4-mini-based query classification + cluster node selection |
 | `cluster.py` | Cluster node registry, event log, coordinator election, ping/pong, model swap handlers, image generation request/response |
 | `amqp.py` | AMQP connection manager — connect, disconnect, publish, subscribe, auto-reconnect |
 | `node_agent/` | Standalone worker agent — AMQP client for registration, ping/pong, model swap, image generation |
@@ -84,7 +83,7 @@ Refactored from single-file (`app.py`) into modules under project root:
 
 ### Key flows
 
-1. **`/api/chat`** → `process_remember_command()` intercepts "remember that..." / "forget about..." first → optional `upload_context_id` fetches document text from SQLite → `build_system_prompt()` (profile + FTS5 memory + Qdrant RAG + preset + skills + uploaded doc) → triage classifies query (general/code/search/rag) → `select_node()` picks best worker → stream from chosen node with `logprobs: true` → if perplexity > 15.0 OR `REFUSAL_PATTERNS` match, re-query with SearXNG results
+1. **`/api/chat`** → `process_remember_command()` intercepts "remember that..." / "forget about..." first → optional `upload_context_id` fetches document text from SQLite → `build_system_prompt()` (profile + FTS5 memory + Qdrant RAG + preset + skills + uploaded doc) → stream from `LLAMA_SERVER_BASE` with `logprobs: true` → if perplexity > 15.0 OR `REFUSAL_PATTERNS` match, re-query with SearXNG results
 2. **`/api/search`** → bypasses perplexity/refusal, queries SearXNG directly → summarizes via llama-server
 3. **`/v1/chat/completions`** → OpenAI-compatible for Continue.dev/IDE integration; FIM requests proxied without persistence
 4. **`/api/upload`** → multipart file upload, PDF/text extraction, `mode=(context|ingest|both)`, stores SQLite context (1hr expiry) + Qdrant upsert
@@ -118,7 +117,6 @@ All services are available bare-metal or as containers in `docker compose up`.
 | Service | Required | Port | Docker service name |
 |---------|----------|------|---------------------|
 | llama-server (coordinator) | Yes | 8081 + RPC :50052 (worker GPU) | `llama-server` |
-| Phi-4-mini (triage) | No | 8083 | — |
 | SearXNG | No | 8888 | `searxng` |
 | RabbitMQ (coordinator) | No | 5672 — AMQP broker | `rabbitmq` |
 | wttr.in | No | weather shortcut | — |