docs: land prior ADR + prompt updates

Commit pre-existing uncommitted working-tree changes that predate the
license/public-readiness work — NOT authored in this session, just flushed so
they're not lost: ADR-0003/0005/0009/0012 edits, the new ADR-0013
(embeddings-bypass + two-slot residency, already referenced by CLAUDE.md), and
the phase-0..3 prompt revisions + prompts/README.md.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

prompts/phase-2.md

@@ -1,33 +1,48 @@
 # phase-2.md — Ollama target client, model poller, native passthrough
 
 Re-ground: `CLAUDE.md` + ADR-0003 (API surface), 0007 (model polling), 0012
-(streaming), 0002 (unreachable = transient). Plan, get approval, implement.
+(streaming = NDJSON, not SSE), 0013 (two-slot residency + embedding bypass),
+0002 (unreachable = transient). Plan, get approval, implement.
 
 ## Objective
 
 Make foreman a working transparent front for its Ollama target — enough that
 `go-llm` can use the Mac as a target *today*, before any queue exists. (Phase 3
-will move this through the queue; here it can proxy directly.)
+will move chat through the queue; here it proxies behind a single-flight gate.)
 
 ## Tasks
 
 - `internal/ollama`: a small client to the target (`FOREMAN_OLLAMA_URL`) behind
   an interface, covering `POST /api/chat` (streaming and non-streaming),
-  `GET /api/tags`, `GET /api/ps`. Attach the outbound bearer if configured. Wrap
-  errors; classify connection failures distinctly (Phase 3 needs that signal).
+  `POST /api/embed` (+ `/api/embeddings` alias), `GET /api/tags`, `GET /api/ps`.
+  Attach the outbound bearer (`FOREMAN_OLLAMA_TOKEN`) if configured. Wrap errors;
+  classify connection failures distinctly (Phase 3 needs that signal).
+- Warm the embedder: on startup and after any reconnect-from-unreachable, issue a
+  trivial `/api/embed` to `FOREMAN_EMBED_MODEL` so it occupies a resident slot
+  (ADR-0013). The target must run `OLLAMA_MAX_LOADED_MODELS=2`; log a warning if
+  `/api/ps` ever shows only one slot under load.
 - Model poller (goroutine): poll `/api/tags` every `FOREMAN_POLL_INTERVAL`
   (default 30s) into an in-memory inventory with a mutex; track last-poll time
   and a degraded flag. On target unreachable, retain last-known inventory and set
   degraded — do not clear it. Wire degraded state into `/healthz`.
 - Passthrough handlers in `internal/server`:
   - `GET /api/tags` and `GET /api/ps` served from the poller/target.
+  - `POST /api/embed` and `POST /api/embeddings`: proxy **directly and
+    concurrently** to the target — these BYPASS the queue/worker gate entirely
+    (ADR-0013). No serialization.
   - `POST /api/chat`: validate the requested model against the inventory (one
-    re-poll on miss, then 4xx if still absent); proxy to the target. Support
-    streaming faithfully (stream the target's chunks straight through; set the
-    right content type). For now this may call the target directly — no queue.
+    re-poll on miss, then 4xx if still absent); proxy to the target. **Serialize
+    worker-model access through a single in-flight gate (a buffered channel /
+    mutex of 1)** so two concurrent chat requests never hit the worker slot at
+    once — this preserves the serial invariant *before* the full queue exists.
+    Phase 3 replaces this gate with the SQLite queue + worker loop. Stream
+    faithfully as **NDJSON** (`Content-Type: application/x-ndjson`, chunks passed
+    straight through — Ollama's native format, not SSE).
 - Tests: a stub HTTP server standing in for Ollama; assert tags/ps proxy,
-  model validation rejects unknown models, streaming passes chunks through, and
-  the poller flips degraded on target failure and recovers.
+  model validation rejects unknown models, NDJSON streaming passes chunks
+  through, **concurrent `/api/embed` calls run in parallel while `/api/chat` is
+  serialized** (assert no two chats overlap at the stub), and the poller flips
+  degraded on target failure and recovers (and re-warms the embedder).
 
 ## Definition of done