fix(ci): stop blanket-stripping OpenRouter rows on evidence_only alone

CHANGELOG.md

@@ -23,6 +23,37 @@ this file. The format follows Keep a Changelog, and versioned releases follow
 Semantic Versioning where the repository publishes a release.
 
 ## [Unreleased]
+- `scripts/ci/contextual_orchestrator_review_launcher.py`'s `_routable_discovered_models()`
+  no longer blanket-strips every OpenRouter row on `evidence_only` alone.
+  `contextual-orchestrator`'s OpenRouter `ProviderModelSource` currently
+  hardcodes `evidence_only=True` for every discovered model unconditionally
+  (a confirmed bug, being fixed upstream separately), which was excluding
+  100% of OpenRouter discovery rows here before
+  `zdr_policy.is_zdr_model()`'s purpose-built, per-route OpenRouter ZDR-feed
+  check ever got a chance to evaluate them -- making that already-correct
+  mechanism dead code for OpenRouter specifically. OpenRouter rows are now
+  exempt from this exclusion; a genuinely non-servable OpenRouter row is
+  still excluded by the existing, provider-agnostic chat-capability check
+  every other provider's rows already go through. `_routable_discovered_models()`
+  also now excludes a `spend_admitted=False` row the same way it excludes
+  `evidence_only=True`, so a credit-exhausted priced OpenRouter row cannot
+  reach `orchestrator/auto`'s served catalog.
+- **Fix a stale `test_strix_quick_gate.sh` assertion left broken by the `#1630`
+  scheduler-cadence lengthening.** `pr-review-merge-scheduler.yml`'s repository-local
+  heartbeat was changed from a half-hourly `cron: "*/30 * * * *"` to an hourly
+  `cron: "30 * * * *"` (see `docs/doctoring/actions-queue-saturation-hourly-sweep.md`),
+  and the Python regression `tests/test_actions_queue_saturation_scheduler_cadence.py`
+  was updated to match at the time — but the parallel bash contract in
+  `scripts/ci/test_strix_quick_gate.sh` still asserted the literal old string, so
+  every PR whose required `exact-head-path-policy` check ran this script against a
+  current `main` checkout failed on an assertion the workflow file itself could no
+  longer satisfy, regardless of the PR's own diff. Updated the assertion to the
+  current cron string and corrected an adjacent stale "15-minute organization sweep
+  / 30-minute scheduled scan" description to the current hourly/hourly cadence.
+  Verified: `bash scripts/ci/test_strix_quick_gate.sh` now passes against unmodified
+  `main` (confirmed failing before this fix, on the same clean clone); full suite
+  unaffected (2600+ passed, 100% coverage, 100% docstrings) since this is a
+  bash-only assertion string with no Python-side counterpart to update.
 - **Consolidate the two genuinely duplicate quality-CI callers behind one reusable
   `workflow_call` gate; leave the other six alone.** An audit of the 8
   `.github/workflows/*-quality-ci.yml` bootstrap-templated files found only one pair —