docs(roadmap): M2 Client HTTP loop done + live-proven; NPC conversation next

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

docs/roadmap.md

@@ -47,8 +47,8 @@ The milestones are ordered to reach the POC's one question as early as possible,
 - ✅ **Narrator / Ollama pipeline (server)** — the shared server-side model-call pipeline (Ollama httpx client, role→model routing config, prompt loader + canon-log digest renderer, §10 call logging, single-retry → typed 502) wired through `/dm/narrate`. Non-streaming. Both phases landed: **(1) pipeline foundation** (`config`/`routing`/`prompts`/`ollama_client`/`call_log`), **(2) Narrator online** (authored `narrator.md` body + `narrate` service + gated live smoke). Server returns raw prose; the client extracts tags. **The other four roles become thin drop-ins on this pipeline.** Live wire proven against qwen3.5; 49 tests. Merged to `dev` (`ddc00d4`). *§2: text · depends on the contract.*
 
 ### M2 — Prove aliveness ◀ *(the POC's one question)*
-- ▶ **Client HTTP loop** — client posts its canon log to `/dm/narrate`, displays the prose, harvests `[FACT]` via its `TagExtractor` into its own log, and shows the degraded-DM authored fallback (§13) on any non-200. First end-to-end vertical slice: **state → HTTP → model → prose → screen → fact-harvest.** The first moment a human sees generated prose in the running game. *§2: state (client owns the loop, consumes text) · depends on M1 + the client engine · goal: put the Narrator on screen.*
-- ○ **Bounded NPC conversation** — `/npc/speak` with persona + `knowledge[]` + `available_moves[]`; client validates and applies moves, silently drops the invalid, keeps the prose (§6). Drops onto the *proven* client loop — adds move-tag validation on top of a display+harvest pipeline that already works. **The core experiment: this is the surface §17 is really asking about.** *§2: both (text = the NPC's voice · state = the validated moves) · depends on the client loop · goal: answer the one question.*
+- ✅ **Client HTTP loop** — client posts its canon log to `/dm/narrate`, displays the prose, harvests `[FACT]` via its `TagExtractor` into its own log, and shows the degraded-DM authored fallback (§13) on any non-200. First end-to-end vertical slice: **state → HTTP → model → prose → screen → fact-harvest.** Pure `DmService` core behind an injectable transport seam; throwaway harness scene for the first on-screen prose. **Live-proven** against qwen3.5 through Docker (grounded scene prose, no numbers per §7). 67/67 client tests; merged to `dev` (`b949cd2`). Surfaced + fixed two Docker-dev gaps in M1 (prompts not packaged, no container→host-Ollama route) — M1's live proof had been venv-on-host only. *§2: state (client owns the loop, consumes text) · goal: put the Narrator on screen.*
+- ▶ **Bounded NPC conversation** — `/npc/speak` with persona + `knowledge[]` + `available_moves[]`; client validates and applies moves, silently drops the invalid, keeps the prose (§6). Drops onto the *proven* client loop — adds move-tag validation on top of a display+harvest pipeline that already works. **The core experiment: this is the surface §17 is really asking about.** *§2: both (text = the NPC's voice · state = the validated moves) · depends on the client loop · goal: answer the one question.*
 - ○ **Streaming** (§14) — server streams Ollama → client; latency reads as *the DM is speaking* rather than *the game is frozen*, hiding the ~2s call. **Gated on aliveness:** landed only after the dialogue experiment above says the prose is worth polishing. Additive to `ollama_client` (shaped for it) + an SSE/chunked response + the client stream consumer. *§2: text · depends on the client loop · goal: polish, not proof.*
 
 ### M3 — Make it a game *(the playable ~30-min slice — dungeon first, per the sequencing call)*