docs(sprint): close #299, #300, #260; #305/#261 status calls

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

docs/sprints/2026-07-23.md

@@ -156,12 +156,34 @@ every flat alias still pointed at npm, so a Kotlin run's auto-gate would have ru
     own class, and routing dead-ends carry `gate="stage"` while every other path carries its real gate,
     so `"$gate:$signature"` can't collapse them. Locked in with a regression test rather than a rewrite.
 
-**Goal 3 remaining:** #299 + #300 (provider-death path). #308 partly pre-empted by `ac460156` — a shell
-timeout is now recoverable and coaches `nohup &` detach, so there is no background-process registry to
-build unless a real gate needs one.
+- **#299 ✅** (commit `c5289420`). `route()` now splits the two cases the old code conflated: a
+  capability **nobody was ever configured with** still fails fast, but a capability that *is*
+  configured whose candidates are all currently unhealthy gets a bounded wait (3 × 2s, each round
+  re-checking `refreshedHealth` rather than the TTL cache) before `NoEligibleProvider`. A crash-plus-
+  restart no longer collapses a retryable failure into a session kill.
+- **#300 ✅** (commit `bf362527`). Made health *gating* instead of reactive: new
+  `InferenceRouter.reportFailure(providerId, reason)` (default no-op) writes `Unavailable` straight
+  into the health cache, bypassing `healthCheck()`/TTL, and `SessionOrchestrator.kt:454` calls it from
+  the inference catch when `isConnectionLevelFailure(e)`. The next `route()` sees the drop
+  immediately instead of ~18s later. Recovery needs no extra path — TTL expiry or #299's bounded-wait
+  re-check picks the provider back up.
 
-**Goal 2 remaining:** #261 (impl decomposition), plus status calls on #260 and #305 — both have landed
-commits (`516af1ca`; `5df35879`/`8806de16`/`12775d56`/`f5aaa255`) but neither ticket is closed.
+**Goal 3 remaining:** none. #308 partly pre-empted by `ac460156` — a shell timeout is now recoverable
+and coaches `nohup &` detach, so there is no background-process registry to build unless a real gate
+needs one.
+
+**Goal 2 status calls — 2026-07-27.**
+- **#260 ✅** (commit `516af1ca`). Both halves are in the prompts: `discovery.md` requires inspecting
+  the whole decision surface and batching *all* operator-only questions after inspection (no
+  stop-at-first-uncertainty), and `analyst_freestyle.md` makes the `dod` artifact the handoff contract
+  — atomic, yes/no-checkable criteria, plus one criterion carrying the named task into the impl plan
+  and one per material failure path. #3 (architect re-plans on better input) fell out for free.
+- **#305 stays open.** Store 1 (Observations) shipped (`5df35879` et al) and is real, but Stores 2
+  (fix lifecycle) and 3 (plan-shapes + discovery warm-start read path) are unbuilt — and Store 3 is
+  exactly what Goal 2's exit criterion ("discovery carries accreted knowledge from a prior run")
+  names. Not closable; carries past this sprint.
+- **#261 blocked by #267, correctly.** Its own body defers it until the simpler pipeline is proven on
+  a clean end-to-end run — which is the #267 acceptance run. Do #267 first.
 
 ---