release v2.7.2

Production logs INFO to stdout: docker logs tatlock becomes a real
diagnostic surface for the first time.

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

.env.example

@@ -8,11 +8,16 @@ API_HOST=0.0.0.0
 API_PORT=8000
 API_PREFIX=/v1
 
-# Ollama Configuration (local - primary backend)
+# Local backend (primary). The var name is legacy: any OpenAI-compatible
+# server works — Ollama, a bare llama-server, or the boilerroom wrapper
+# (http://127.0.0.1:8602 on tower-of-joy). The flavor is probed at
+# startup; through the wrapper, BACKEND_SLOT_PINNING=true sends named
+# sessions with the T-4 eviction ranking instead of raw slot pins.
 OLLAMA_HOST=http://localhost:11434
 OLLAMA_DEFAULT_MODEL=gemma4:e2b
 OLLAMA_TIMEOUT=120
 STEWARD_TIMEOUT=60
+BACKEND_SLOT_PINNING=false
 
 # Anthropic Configuration (Claude - cloud fallback)
 # Set ANTHROPIC_API_KEY to keep the Claude fallback available: it is used

.gitea/workflows/build.yml

@@ -10,12 +10,20 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Create Gitea Release
+        # Idempotent: a re-fired tag finds its release already present and
+        # says so instead of failing on the 409.
         run: |
+          api="${{ github.server_url }}/api/v1/repos/${{ github.repository }}/releases"
+          auth='Authorization: token ${{ secrets.GITHUB_TOKEN }}'
+          if curl -sf -H "$auth" "$api/tags/${{ github.ref_name }}" > /dev/null; then
+            echo "release for ${{ github.ref_name }} already exists — nothing to do"
+            exit 0
+          fi
           curl -sf -X POST \
-            -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" \
+            -H "$auth" \
             -H "Content-Type: application/json" \
             -d '{"tag_name": "${{ github.ref_name }}", "name": "Release ${{ github.ref_name }}", "body": "Automated release for ${{ github.ref_name }}"}' \
-            "${{ github.server_url }}/api/v1/repos/${{ github.repository }}/releases"
+            "$api"
 
   build:
     runs-on: ubuntu-latest

.pql/changelog/ticket_history/2026-09.sql

@@ -0,0 +1,9 @@
+INSERT INTO ticket_history (ticket_record_id, field, old_value, new_value, changed_by, changed_at, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G99D07EM5DZWTS0WD9V8PSKM', 'status', 'backlog', 'in_progress', NULL, '2026-09-12 13:50:48', '2026-09-12 13:50:48.289', '2026-09-12 13:50:48.289', NULL, '2e88d155325b3e704787f48b2aa97591', 2) ON CONFLICT(hash) DO NOTHING;
+INSERT INTO ticket_history (ticket_record_id, field, old_value, new_value, changed_by, changed_at, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G99D07EM5DZWTS0WD9V8PSKM', 'status', 'in_progress', 'done', NULL, '2026-09-12 14:13:29', '2026-09-12 14:13:29.027', '2026-09-12 14:13:29.027', NULL, '5b9dd9a62002db0fb4dc58f7f9ffcbb6', 2) ON CONFLICT(hash) DO NOTHING;
+INSERT INTO ticket_history (ticket_record_id, field, old_value, new_value, changed_by, changed_at, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G9KH87TRDGW45GMDWVDRPABR', 'description', 'src/ollama/provider.py sets self._openai_client after super().__init__, but OllamaProvider.client serves self._client (pydantic_ai 1.27''s official openai_client= constructor param is the right wiring — webber hit the identical bug and fixed it 2026-09-13, exposed by the wrapper 503ing a session-less request). Silently dead in production as a result: the content-null sanitizer (moot on llama-server, live hazard if Ollama ever returns), the T-4 x-boilerroom-* signal hook (never logs), and the OLLAMA_TIMEOUT=120 cap (SDK default ~600s applies). Sessions were unaffected — they ride ModelSettings extra_body. Fix like webber: pass _SanitizedAsyncOpenAI through openai_client=, add a wiring test asserting provider.client is the sanitized type, then verify balancing/compaction logs actually appear.', 'src/ollama/provider.py sets self._openai_client after super().__init__, but OllamaProvider.client serves self._client (pydantic_ai 1.27''s official openai_client= constructor param is the right wiring — webber hit the identical bug and fixed it 2026-09-13, exposed by the wrapper 503ing a session-less request). Silently dead in production as a result: the content-null sanitizer (moot on llama-server, live hazard if Ollama ever returns), the T-4 x-boilerroom-* signal hook (never logs), and the OLLAMA_TIMEOUT=120 cap (SDK default ~600s applies). Sessions were unaffected — they ride ModelSettings extra_body. Fix like webber: pass _SanitizedAsyncOpenAI through openai_client=, add a wiring test asserting provider.client is the sanitized type, then verify balancing/compaction logs actually appear.
+
+Second finding 2026-09-13, from webber''s twin fix: an httpx event-hook on the client (the T-4 signal-reading approach) never fires under the openai SDK even when correctly wired — webber verified headers arriving while the hook stayed silent. When rewiring the client, read the signals from the parsed body''s model_extra in the sanitized create() instead (the wrapper injects balancing/compaction_due into non-streamed JSON bodies; openai pydantic models retain unknown fields). The steward''s raw-call body read is unaffected and already correct.', NULL, '2026-09-13 08:00:17', '2026-09-13 08:00:17.002', '2026-09-13 08:00:17.002', NULL, '6fb4cc1d7d7222e3d570cd8c7fed4fd9', 2) ON CONFLICT(hash) DO NOTHING;
+INSERT INTO ticket_history (ticket_record_id, field, old_value, new_value, changed_by, changed_at, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G9KH87TRDGW45GMDWVDRPABR', 'status', 'backlog', 'in_progress', NULL, '2026-09-13 08:19:35', '2026-09-13 08:19:35.028', '2026-09-13 08:19:35.028', NULL, '5bcf19379361a2f766cd4787ff734611', 2) ON CONFLICT(hash) DO NOTHING;
+INSERT INTO ticket_history (ticket_record_id, field, old_value, new_value, changed_by, changed_at, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G9KH87TRDGW45GMDWVDRPABR', 'status', 'in_progress', 'done', NULL, '2026-09-13 08:27:21', '2026-09-13 08:27:21.779', '2026-09-13 08:27:21.779', NULL, '1c59422336b88a76c6f1c3720916d7d5', 2) ON CONFLICT(hash) DO NOTHING;
+INSERT INTO ticket_history (ticket_record_id, field, old_value, new_value, changed_by, changed_at, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G99D07Z3FZY8EBT9PJ1RCGHW', 'status', 'backlog', 'in_progress', NULL, '2026-09-13 08:48:55', '2026-09-13 08:48:55.587', '2026-09-13 08:48:55.587', NULL, 'ca4f8fb42c961b0002aa87bb7b1d5af5', 2) ON CONFLICT(hash) DO NOTHING;
+INSERT INTO ticket_history (ticket_record_id, field, old_value, new_value, changed_by, changed_at, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G99D07Z3FZY8EBT9PJ1RCGHW', 'status', 'in_progress', 'done', NULL, '2026-09-13 09:00:50', '2026-09-13 09:00:50.006', '2026-09-13 09:00:50.006', NULL, '5ea799ee4815e42ede80c3df4c81b28c', 2) ON CONFLICT(hash) DO NOTHING;

.pql/changelog/ticket_idmap/2026-09.sql

@@ -0,0 +1,5 @@
+INSERT INTO ticket_idmap (record_id, ticket_id, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G94KC9XM3PW91C6B7VJA6VRM', 'T-3', '2026-09-11 21:09:10.267', '2026-09-11 21:09:10.267', NULL, 'a1ccf4d118877c230dffb961a7531cb4', 2) ON CONFLICT(record_id) DO UPDATE SET ticket_id=excluded.ticket_id, updated_at=excluded.updated_at, deleted_at=excluded.deleted_at, hash=excluded.hash, canonical_version=excluded.canonical_version WHERE excluded.updated_at >= ticket_idmap.updated_at;
+INSERT INTO ticket_idmap (record_id, ticket_id, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G99D07EM5DZWTS0WD9V8PSKM', 'T-4', '2026-09-12 08:20:21.494', '2026-09-12 08:20:21.494', NULL, '5b28e07bdc3be1f9ed0ed71d2da60c72', 2) ON CONFLICT(record_id) DO UPDATE SET ticket_id=excluded.ticket_id, updated_at=excluded.updated_at, deleted_at=excluded.deleted_at, hash=excluded.hash, canonical_version=excluded.canonical_version WHERE excluded.updated_at >= ticket_idmap.updated_at;
+INSERT INTO ticket_idmap (record_id, ticket_id, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G99D07Z3FZY8EBT9PJ1RCGHW', 'T-5', '2026-09-12 08:20:21.625', '2026-09-12 08:20:21.625', NULL, '0a417012779f612a4dad1a7dbd0787e3', 2) ON CONFLICT(record_id) DO UPDATE SET ticket_id=excluded.ticket_id, updated_at=excluded.updated_at, deleted_at=excluded.deleted_at, hash=excluded.hash, canonical_version=excluded.canonical_version WHERE excluded.updated_at >= ticket_idmap.updated_at;
+INSERT INTO ticket_idmap (record_id, ticket_id, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G9KH87TRDGW45GMDWVDRPABR', 'T-6', '2026-09-13 07:57:01.782', '2026-09-13 07:57:01.782', NULL, 'd6c184ba6d24e03c0dc77064bf71fead', 2) ON CONFLICT(record_id) DO UPDATE SET ticket_id=excluded.ticket_id, updated_at=excluded.updated_at, deleted_at=excluded.deleted_at, hash=excluded.hash, canonical_version=excluded.canonical_version WHERE excluded.updated_at >= ticket_idmap.updated_at;
+INSERT INTO ticket_idmap (record_id, ticket_id, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G9KZSCFR79G4DFCT4E5W5CAM', 'T-7', '2026-09-13 09:00:32.255', '2026-09-13 09:00:32.255', NULL, 'b0b0a4c3ccaabeb58ad1958e7c2c2602', 2) ON CONFLICT(record_id) DO UPDATE SET ticket_id=excluded.ticket_id, updated_at=excluded.updated_at, deleted_at=excluded.deleted_at, hash=excluded.hash, canonical_version=excluded.canonical_version WHERE excluded.updated_at >= ticket_idmap.updated_at;

.pql/changelog/tickets/2026-09.sql

@@ -0,0 +1,18 @@
+INSERT INTO tickets (record_id, type, parent_record_id, title, description, status, priority, assigned_to, team, decision_ref, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G94KC9XM3PW91C6B7VJA6VRM', 'story', NULL, 'Stream the synthesis phase — TTFT equals wall time today', 'Nothing streams until steward-orchestrate-synthesize completes, so desklock''s time-to-first-word is the full pipeline (TTFT mean 14.9s, max 26.2s — measured 2026-09-11, workspace note cladmin/agent/notes/2026-09-11-serving-baseline.md). Stream the synthesis phase out as it generates: a first-class goal of the serving rework independent of KV reuse (workspace D-60). The backend now streams /v1 SSE natively (llama-gen).', 'backlog', 'high', NULL, NULL, NULL, '2026-09-11 21:09:10.253', '2026-09-11 21:09:10.253', NULL, 'f7d31ca4fe747835a32744c310f51674', 2) ON CONFLICT(record_id) DO UPDATE SET type=excluded.type, parent_record_id=excluded.parent_record_id, title=excluded.title, description=excluded.description, status=excluded.status, priority=excluded.priority, assigned_to=excluded.assigned_to, team=excluded.team, decision_ref=excluded.decision_ref, updated_at=excluded.updated_at, deleted_at=excluded.deleted_at, hash=excluded.hash, canonical_version=excluded.canonical_version WHERE excluded.updated_at >= tickets.updated_at;
+INSERT INTO tickets (record_id, type, parent_record_id, title, description, status, priority, assigned_to, team, decision_ref, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G99D07EM5DZWTS0WD9V8PSKM', 'story', NULL, 'Adopt boilerroom named sessions with the usage ranking', 'Replace raw id_slot pinning (BACKEND_SLOT_PINNING) with the wrapper''s session extension fields, now that tatlock routes through boilerroom:8602 (since 2026-09-12). Ranking by likelihood of use, decided 2026-09-12 — lower eviction_order parks sooner: tatlock pipeline phases highest (eviction_order 40; e.g. sessions tatlock-steward/tatlock-orchestrate/tatlock-synthesize), librarian-routed calls as session librarian (30), webber will sit at 20 (workspace T-137), Open WebUI stays session-less by design (idle slots only, can never evict — and it is being deprecated for an own-webui build). Read the x-boilerroom-balancing and compaction_due signals; the compaction endpoint expects the client transcript (tatlock''s Redis/Qdrant context is the natural producer — boilerroom D-5 names tatlock the first producer).', 'backlog', 'high', NULL, NULL, NULL, '2026-09-12 08:20:21.493', '2026-09-12 08:20:21.493', NULL, '3fb8c350876fc056648a19e0f2b7718c', 2) ON CONFLICT(record_id) DO UPDATE SET type=excluded.type, parent_record_id=excluded.parent_record_id, title=excluded.title, description=excluded.description, status=excluded.status, priority=excluded.priority, assigned_to=excluded.assigned_to, team=excluded.team, decision_ref=excluded.decision_ref, updated_at=excluded.updated_at, deleted_at=excluded.deleted_at, hash=excluded.hash, canonical_version=excluded.canonical_version WHERE excluded.updated_at >= tickets.updated_at;
+INSERT INTO tickets (record_id, type, parent_record_id, title, description, status, priority, assigned_to, team, decision_ref, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G99D07Z3FZY8EBT9PJ1RCGHW', 'bug', NULL, 'The container logs nowhere: stdout empty, /app/logs mount untouched', 'docker logs tatlock is 0 lines and the mounted ~/docker-data/tatlock/logs has been empty since 2025-12 — the running app writes logs to neither, which made the 2026-09-12 wrapper-cutover verification blind (flavor detection had to be proven behaviorally). Dev mode logs to build/logs/server.log via make run; production should log to stdout for docker logs at minimum.', 'backlog', 'medium', NULL, NULL, NULL, '2026-09-12 08:20:21.624', '2026-09-12 08:20:21.624', NULL, '3fd294efc9afa857aef15810d9003298', 2) ON CONFLICT(record_id) DO UPDATE SET type=excluded.type, parent_record_id=excluded.parent_record_id, title=excluded.title, description=excluded.description, status=excluded.status, priority=excluded.priority, assigned_to=excluded.assigned_to, team=excluded.team, decision_ref=excluded.decision_ref, updated_at=excluded.updated_at, deleted_at=excluded.deleted_at, hash=excluded.hash, canonical_version=excluded.canonical_version WHERE excluded.updated_at >= tickets.updated_at;
+INSERT INTO tickets (record_id, type, parent_record_id, title, description, status, priority, assigned_to, team, decision_ref, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G99D07EM5DZWTS0WD9V8PSKM', 'story', NULL, 'Adopt boilerroom named sessions with the usage ranking', 'Replace raw id_slot pinning (BACKEND_SLOT_PINNING) with the wrapper''s session extension fields, now that tatlock routes through boilerroom:8602 (since 2026-09-12). Ranking by likelihood of use, decided 2026-09-12 — lower eviction_order parks sooner: tatlock pipeline phases highest (eviction_order 40; e.g. sessions tatlock-steward/tatlock-orchestrate/tatlock-synthesize), librarian-routed calls as session librarian (30), webber will sit at 20 (workspace T-137), Open WebUI stays session-less by design (idle slots only, can never evict — and it is being deprecated for an own-webui build). Read the x-boilerroom-balancing and compaction_due signals; the compaction endpoint expects the client transcript (tatlock''s Redis/Qdrant context is the natural producer — boilerroom D-5 names tatlock the first producer).', 'in_progress', 'high', NULL, NULL, NULL, '2026-09-12 08:20:21.493', '2026-09-12 13:50:48.289', NULL, '62abeb4da2f1f7aedb8d92884e7e148c', 2) ON CONFLICT(record_id) DO UPDATE SET type=excluded.type, parent_record_id=excluded.parent_record_id, title=excluded.title, description=excluded.description, status=excluded.status, priority=excluded.priority, assigned_to=excluded.assigned_to, team=excluded.team, decision_ref=excluded.decision_ref, updated_at=excluded.updated_at, deleted_at=excluded.deleted_at, hash=excluded.hash, canonical_version=excluded.canonical_version WHERE excluded.updated_at >= tickets.updated_at;
+INSERT INTO tickets (record_id, type, parent_record_id, title, description, status, priority, assigned_to, team, decision_ref, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G99D07EM5DZWTS0WD9V8PSKM', 'story', NULL, 'Adopt boilerroom named sessions with the usage ranking', 'Replace raw id_slot pinning (BACKEND_SLOT_PINNING) with the wrapper''s session extension fields, now that tatlock routes through boilerroom:8602 (since 2026-09-12). Ranking by likelihood of use, decided 2026-09-12 — lower eviction_order parks sooner: tatlock pipeline phases highest (eviction_order 40; e.g. sessions tatlock-steward/tatlock-orchestrate/tatlock-synthesize), librarian-routed calls as session librarian (30), webber will sit at 20 (workspace T-137), Open WebUI stays session-less by design (idle slots only, can never evict — and it is being deprecated for an own-webui build). Read the x-boilerroom-balancing and compaction_due signals; the compaction endpoint expects the client transcript (tatlock''s Redis/Qdrant context is the natural producer — boilerroom D-5 names tatlock the first producer).', 'done', 'high', NULL, NULL, NULL, '2026-09-12 08:20:21.493', '2026-09-12 14:13:29.027', NULL, '89ce1be323ebb26f00c63569f197cab1', 2) ON CONFLICT(record_id) DO UPDATE SET type=excluded.type, parent_record_id=excluded.parent_record_id, title=excluded.title, description=excluded.description, status=excluded.status, priority=excluded.priority, assigned_to=excluded.assigned_to, team=excluded.team, decision_ref=excluded.decision_ref, updated_at=excluded.updated_at, deleted_at=excluded.deleted_at, hash=excluded.hash, canonical_version=excluded.canonical_version WHERE excluded.updated_at >= tickets.updated_at;
+INSERT INTO tickets (record_id, type, parent_record_id, title, description, status, priority, assigned_to, team, decision_ref, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G9KH87TRDGW45GMDWVDRPABR', 'bug', NULL, 'The sanitized OpenAI client is never used: the override pokes an attribute nobody reads', 'src/ollama/provider.py sets self._openai_client after super().__init__, but OllamaProvider.client serves self._client (pydantic_ai 1.27''s official openai_client= constructor param is the right wiring — webber hit the identical bug and fixed it 2026-09-13, exposed by the wrapper 503ing a session-less request). Silently dead in production as a result: the content-null sanitizer (moot on llama-server, live hazard if Ollama ever returns), the T-4 x-boilerroom-* signal hook (never logs), and the OLLAMA_TIMEOUT=120 cap (SDK default ~600s applies). Sessions were unaffected — they ride ModelSettings extra_body. Fix like webber: pass _SanitizedAsyncOpenAI through openai_client=, add a wiring test asserting provider.client is the sanitized type, then verify balancing/compaction logs actually appear.', 'backlog', 'high', NULL, NULL, NULL, '2026-09-13 07:57:01.782', '2026-09-13 07:57:01.782', NULL, '5e8ea3bf2d18ade9d17f0044ae1ff96b', 2) ON CONFLICT(record_id) DO UPDATE SET type=excluded.type, parent_record_id=excluded.parent_record_id, title=excluded.title, description=excluded.description, status=excluded.status, priority=excluded.priority, assigned_to=excluded.assigned_to, team=excluded.team, decision_ref=excluded.decision_ref, updated_at=excluded.updated_at, deleted_at=excluded.deleted_at, hash=excluded.hash, canonical_version=excluded.canonical_version WHERE excluded.updated_at >= tickets.updated_at;
+INSERT INTO tickets (record_id, type, parent_record_id, title, description, status, priority, assigned_to, team, decision_ref, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G9KH87TRDGW45GMDWVDRPABR', 'bug', NULL, 'The sanitized OpenAI client is never used: the override pokes an attribute nobody reads', 'src/ollama/provider.py sets self._openai_client after super().__init__, but OllamaProvider.client serves self._client (pydantic_ai 1.27''s official openai_client= constructor param is the right wiring — webber hit the identical bug and fixed it 2026-09-13, exposed by the wrapper 503ing a session-less request). Silently dead in production as a result: the content-null sanitizer (moot on llama-server, live hazard if Ollama ever returns), the T-4 x-boilerroom-* signal hook (never logs), and the OLLAMA_TIMEOUT=120 cap (SDK default ~600s applies). Sessions were unaffected — they ride ModelSettings extra_body. Fix like webber: pass _SanitizedAsyncOpenAI through openai_client=, add a wiring test asserting provider.client is the sanitized type, then verify balancing/compaction logs actually appear.
+
+Second finding 2026-09-13, from webber''s twin fix: an httpx event-hook on the client (the T-4 signal-reading approach) never fires under the openai SDK even when correctly wired — webber verified headers arriving while the hook stayed silent. When rewiring the client, read the signals from the parsed body''s model_extra in the sanitized create() instead (the wrapper injects balancing/compaction_due into non-streamed JSON bodies; openai pydantic models retain unknown fields). The steward''s raw-call body read is unaffected and already correct.', 'backlog', 'high', NULL, NULL, NULL, '2026-09-13 07:57:01.782', '2026-09-13 08:00:17.002', NULL, '755abc3689e8ff4fc511deb164137fe5', 2) ON CONFLICT(record_id) DO UPDATE SET type=excluded.type, parent_record_id=excluded.parent_record_id, title=excluded.title, description=excluded.description, status=excluded.status, priority=excluded.priority, assigned_to=excluded.assigned_to, team=excluded.team, decision_ref=excluded.decision_ref, updated_at=excluded.updated_at, deleted_at=excluded.deleted_at, hash=excluded.hash, canonical_version=excluded.canonical_version WHERE excluded.updated_at >= tickets.updated_at;
+INSERT INTO tickets (record_id, type, parent_record_id, title, description, status, priority, assigned_to, team, decision_ref, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G9KH87TRDGW45GMDWVDRPABR', 'bug', NULL, 'The sanitized OpenAI client is never used: the override pokes an attribute nobody reads', 'src/ollama/provider.py sets self._openai_client after super().__init__, but OllamaProvider.client serves self._client (pydantic_ai 1.27''s official openai_client= constructor param is the right wiring — webber hit the identical bug and fixed it 2026-09-13, exposed by the wrapper 503ing a session-less request). Silently dead in production as a result: the content-null sanitizer (moot on llama-server, live hazard if Ollama ever returns), the T-4 x-boilerroom-* signal hook (never logs), and the OLLAMA_TIMEOUT=120 cap (SDK default ~600s applies). Sessions were unaffected — they ride ModelSettings extra_body. Fix like webber: pass _SanitizedAsyncOpenAI through openai_client=, add a wiring test asserting provider.client is the sanitized type, then verify balancing/compaction logs actually appear.
+
+Second finding 2026-09-13, from webber''s twin fix: an httpx event-hook on the client (the T-4 signal-reading approach) never fires under the openai SDK even when correctly wired — webber verified headers arriving while the hook stayed silent. When rewiring the client, read the signals from the parsed body''s model_extra in the sanitized create() instead (the wrapper injects balancing/compaction_due into non-streamed JSON bodies; openai pydantic models retain unknown fields). The steward''s raw-call body read is unaffected and already correct.', 'in_progress', 'high', NULL, NULL, NULL, '2026-09-13 07:57:01.782', '2026-09-13 08:19:35.028', NULL, '5af3c96930a30bbe4bb64d13ddbc509e', 2) ON CONFLICT(record_id) DO UPDATE SET type=excluded.type, parent_record_id=excluded.parent_record_id, title=excluded.title, description=excluded.description, status=excluded.status, priority=excluded.priority, assigned_to=excluded.assigned_to, team=excluded.team, decision_ref=excluded.decision_ref, updated_at=excluded.updated_at, deleted_at=excluded.deleted_at, hash=excluded.hash, canonical_version=excluded.canonical_version WHERE excluded.updated_at >= tickets.updated_at;
+INSERT INTO tickets (record_id, type, parent_record_id, title, description, status, priority, assigned_to, team, decision_ref, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G9KH87TRDGW45GMDWVDRPABR', 'bug', NULL, 'The sanitized OpenAI client is never used: the override pokes an attribute nobody reads', 'src/ollama/provider.py sets self._openai_client after super().__init__, but OllamaProvider.client serves self._client (pydantic_ai 1.27''s official openai_client= constructor param is the right wiring — webber hit the identical bug and fixed it 2026-09-13, exposed by the wrapper 503ing a session-less request). Silently dead in production as a result: the content-null sanitizer (moot on llama-server, live hazard if Ollama ever returns), the T-4 x-boilerroom-* signal hook (never logs), and the OLLAMA_TIMEOUT=120 cap (SDK default ~600s applies). Sessions were unaffected — they ride ModelSettings extra_body. Fix like webber: pass _SanitizedAsyncOpenAI through openai_client=, add a wiring test asserting provider.client is the sanitized type, then verify balancing/compaction logs actually appear.
+
+Second finding 2026-09-13, from webber''s twin fix: an httpx event-hook on the client (the T-4 signal-reading approach) never fires under the openai SDK even when correctly wired — webber verified headers arriving while the hook stayed silent. When rewiring the client, read the signals from the parsed body''s model_extra in the sanitized create() instead (the wrapper injects balancing/compaction_due into non-streamed JSON bodies; openai pydantic models retain unknown fields). The steward''s raw-call body read is unaffected and already correct.', 'done', 'high', NULL, NULL, NULL, '2026-09-13 07:57:01.782', '2026-09-13 08:27:21.778', NULL, 'ce3151ff27c70a1028ba7c03b07119a2', 2) ON CONFLICT(record_id) DO UPDATE SET type=excluded.type, parent_record_id=excluded.parent_record_id, title=excluded.title, description=excluded.description, status=excluded.status, priority=excluded.priority, assigned_to=excluded.assigned_to, team=excluded.team, decision_ref=excluded.decision_ref, updated_at=excluded.updated_at, deleted_at=excluded.deleted_at, hash=excluded.hash, canonical_version=excluded.canonical_version WHERE excluded.updated_at >= tickets.updated_at;
+INSERT INTO tickets (record_id, type, parent_record_id, title, description, status, priority, assigned_to, team, decision_ref, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G99D07Z3FZY8EBT9PJ1RCGHW', 'bug', NULL, 'The container logs nowhere: stdout empty, /app/logs mount untouched', 'docker logs tatlock is 0 lines and the mounted ~/docker-data/tatlock/logs has been empty since 2025-12 — the running app writes logs to neither, which made the 2026-09-12 wrapper-cutover verification blind (flavor detection had to be proven behaviorally). Dev mode logs to build/logs/server.log via make run; production should log to stdout for docker logs at minimum.', 'in_progress', 'medium', NULL, NULL, NULL, '2026-09-12 08:20:21.624', '2026-09-13 08:48:55.586', NULL, '4770f6c6759cb82d825eb550dd4e42e2', 2) ON CONFLICT(record_id) DO UPDATE SET type=excluded.type, parent_record_id=excluded.parent_record_id, title=excluded.title, description=excluded.description, status=excluded.status, priority=excluded.priority, assigned_to=excluded.assigned_to, team=excluded.team, decision_ref=excluded.decision_ref, updated_at=excluded.updated_at, deleted_at=excluded.deleted_at, hash=excluded.hash, canonical_version=excluded.canonical_version WHERE excluded.updated_at >= tickets.updated_at;
+INSERT INTO tickets (record_id, type, parent_record_id, title, description, status, priority, assigned_to, team, decision_ref, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G9KZSCFR79G4DFCT4E5W5CAM', 'bug', NULL, 'The full suite flakes: one run fails, the rerun passes, twice now', 'Observed 2026-09-13 twice: before the v2.7.0 release audit and again during T-5 — make test exits 1 with a failure that does not reproduce on the immediate rerun, and both times the failing test''s name went uncaptured because the diagnostic rerun passed. Next occurrence: keep the FULL output of the failing run (make test 2>&1 | tee /tmp/flake.log) before rerunning, then pin the named test. Suspects worth checking when a name exists: order-dependent state in the session-scoped app init (conftest asyncio.run + cached health globals), port/redis contention with the live containers, and the coverage plugin''s tmp handling.', 'backlog', 'medium', NULL, NULL, NULL, '2026-09-13 09:00:32.255', '2026-09-13 09:00:32.255', NULL, '36c6f97b5a309e169b7acb35f7ca46d4', 2) ON CONFLICT(record_id) DO UPDATE SET type=excluded.type, parent_record_id=excluded.parent_record_id, title=excluded.title, description=excluded.description, status=excluded.status, priority=excluded.priority, assigned_to=excluded.assigned_to, team=excluded.team, decision_ref=excluded.decision_ref, updated_at=excluded.updated_at, deleted_at=excluded.deleted_at, hash=excluded.hash, canonical_version=excluded.canonical_version WHERE excluded.updated_at >= tickets.updated_at;
+INSERT INTO tickets (record_id, type, parent_record_id, title, description, status, priority, assigned_to, team, decision_ref, created_at, updated_at, deleted_at, hash, canonical_version) VALUES ('06G99D07Z3FZY8EBT9PJ1RCGHW', 'bug', NULL, 'The container logs nowhere: stdout empty, /app/logs mount untouched', 'docker logs tatlock is 0 lines and the mounted ~/docker-data/tatlock/logs has been empty since 2025-12 — the running app writes logs to neither, which made the 2026-09-12 wrapper-cutover verification blind (flavor detection had to be proven behaviorally). Dev mode logs to build/logs/server.log via make run; production should log to stdout for docker logs at minimum.', 'done', 'medium', NULL, NULL, NULL, '2026-09-12 08:20:21.624', '2026-09-13 09:00:50.006', NULL, 'd04562943a55527d6036ec38c2657308', 2) ON CONFLICT(record_id) DO UPDATE SET type=excluded.type, parent_record_id=excluded.parent_record_id, title=excluded.title, description=excluded.description, status=excluded.status, priority=excluded.priority, assigned_to=excluded.assigned_to, team=excluded.team, decision_ref=excluded.decision_ref, updated_at=excluded.updated_at, deleted_at=excluded.deleted_at, hash=excluded.hash, canonical_version=excluded.canonical_version WHERE excluded.updated_at >= tickets.updated_at;

CHANGELOG.md

@@ -7,6 +7,84 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [2.7.2] - 2026-09-13
+
+### Fixed
+
+- Production logs exist now (T-5): the production default log level
+  was WARNING ("minimal noise"), and a healthy service warns roughly
+  never — so `docker logs tatlock` was empty for months, startup,
+  backend flavor detection and the wrapper's balancing/compaction
+  signals all suppressed, and the serving cutover could not be
+  verified from logs. The production default is INFO on stdout;
+  `LOG_LEVEL` remains the override for when noise is ever the real
+  problem. (The `/app/logs` mount was always decorative — no file
+  handler exists; `docker logs` is the log.)
+
+## [2.7.1] - 2026-09-13
+
+### Fixed
+
+- The sanitized OpenAI client was never used (T-6): the provider
+  assigned `self._openai_client`, an attribute nobody reads —
+  `OllamaProvider.client` serves `self._client` — so the null-content
+  sanitizer, the wrapper signal reading and the `OLLAMA_TIMEOUT` cap
+  were all silently dead (sessions were unaffected; they ride
+  ModelSettings). Found via webber's identical bug. The client now
+  goes through the constructor's official `openai_client` parameter,
+  the parent-chat lookup survives openai's property/cached_property
+  descriptor change (ported from webber's 2026-08-11 fix — the old
+  `.fget` access would have crashed the first wired completion on
+  openai 2.11), and the wrapper's `balancing`/`compaction_due`
+  signals are read from the response body's `model_extra` in the
+  request path — the httpx event-hook approach demonstrably never
+  fires under the openai SDK. The provider tests now assert through
+  `provider.client`, the property pydantic_ai actually reads; the
+  old ones asserted on the dead attribute and stayed green
+  throughout.
+
+## [2.7.0] - 2026-09-13
+
+### Added
+
+- Named sessions through the boilerroom wrapper (T-4): the backend
+  flavor probe now recognizes the wrapper by its `/health` service
+  name, and each pipeline phase sends `session`/`eviction_order`
+  extension fields instead of raw `id_slot` — `tatlock-steward`,
+  `tatlock-orchestrate`, `tatlock-synthesize` at rank 40 and the
+  librarian at 30, per the 2026-09-12 usage ranking (lower parks
+  sooner; webber will sit at 20, Open WebUI stays session-less).
+  Against a bare llama-server the old slot pins still apply, and
+  Ollama gets neither, so the backend remains swappable by env alone.
+  The wrapper's `x-boilerroom-balancing` and compaction-due signals
+  are read on every response (an httpx hook on the provider, body
+  extras on the steward's raw call) and logged — acting on
+  `compaction_due` is a future ticket. `get_model_info()` reports the
+  probed `local_flavor`. Wire-pinned by a new boilerroom wrapper
+  contract class in `make test-contracts`.
+- Every generation call is named: the streaming orchestrate paths and
+  the biographer/housekeeper experts (shared session `tatlock-experts`,
+  rank 35) — through the wrapper a session-less call takes idle slots
+  only and would 503 once four sessions are resident, so the release
+  audit swept every `agent.run` and raw chat call under a session.
+
+## [2.6.0] - 2026-09-11
+
+### Added
+
+- `BACKEND_SLOT_PINNING` (default off): pins each pipeline phase to a
+  llama-server slot (steward=0, orchestrator=1, synthesizer=2) so a
+  phase's stable prompt prefix stays in that slot's KV cache. No-op on
+  Claude; ignored by Ollama.
+
+### Fixed
+
+- Tool-calling no longer loops on llama-server backends: the health
+  check detects the server flavor, and `tool_choice: "required"` (an
+  advisory nudge on Ollama, an every-request mandate on llama-server)
+  is sent only to Ollama. On llama-server the model calls tools
+  unforced via its chat template.
+
 ## [2.5.0] - 2026-09-11
 
 ### Added

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "tatlock"
-version = "2.5.0"
+version = "2.7.2"
 description = "OpenAI-compatible API with Ollama backend"
 requires-python = ">=3.12"
 dependencies = [

src/agents/biographer/agent.py

@@ -191,9 +191,12 @@ async def run_biographer(
     )
 
     try:
+        from src.anthropic.model_selector import with_phase_binding
+
         result = await agent.run(
             prompt,
             message_history=message_history,
+            model_settings=with_phase_binding(None, "experts"),
         )
 
         logger.info(

src/agents/housekeeper/agent.py

@@ -206,12 +206,12 @@ async def run_housekeeper(
 
     try:
         # Temperature 0.1 for slight exploration (skipped on Claude backend)
-        from src.anthropic.model_selector import get_sampling_settings
+        from src.anthropic.model_selector import get_sampling_settings, with_phase_binding
 
         result = await agent.run(
             prompt,
             message_history=message_history,
-            model_settings=get_sampling_settings(0.1),
+            model_settings=with_phase_binding(get_sampling_settings(0.1), "experts"),
         )
 
         logger.info(

src/agents/librarian/agent.py

@@ -272,11 +272,14 @@ async def run_librarian(
     )
 
     try:
+        from src.anthropic.model_selector import with_phase_binding
+
         # One shared library-desk connection for all tool calls in this run
         async with library_client_session():
             result = await agent.run(
                 prompt,
                 message_history=message_history,
+                model_settings=with_phase_binding(None, "librarian"),
             )
 
         logger.info(

src/agents/steward/agent.py

@@ -162,19 +162,37 @@ class StewardAgent:
         OpenAI-compatible server (Ollama, llama-server) can sit behind
         OLLAMA_HOST without this method knowing which.
         """
+        from src.anthropic.model_selector import phase_extra_body
+
+        payload: dict = {
+            "model": self.ollama_model,
+            "messages": [{"role": "user", "content": prompt}],
+            "temperature": 0.3,  # Lower = more consistent
+            "top_p": 0.9,
+        }
+        # Session through the wrapper, id_slot 0 against a bare
+        # llama-server, nothing elsewhere (repo T-4).
+        payload.update(phase_extra_body("steward"))
+
         async with httpx.AsyncClient(timeout=self.timeout) as client:
             response = await client.post(
                 f"{self.ollama_host}/v1/chat/completions",
-                json={
-                    "model": self.ollama_model,
-                    "messages": [{"role": "user", "content": prompt}],
-                    "temperature": 0.3,  # Lower = more consistent
-                    "top_p": 0.9,
-                },
+                json=payload,
             )
 
             response.raise_for_status()
             result = response.json()
+
+            # The wrapper reports on session-carrying responses (its
+            # D-4/D-5); this raw call bypasses the provider hook, so
+            # the body extras are read here. Acting on compaction_due
+            # is a later ticket — the signal must not pass silently.
+            balancing = result.get("balancing")
+            if balancing:
+                logger.info("backend_balancing", session="tatlock-steward", moves=balancing)
+            if result.get("compaction_due"):
+                logger.warning("backend_compaction_due", session="tatlock-steward")
+
             return result["choices"][0]["message"]["content"].strip()
 
     async def analyze(self, query: str, conversation_history: list[dict] | None = None) -> str:

src/agents/tatlock.py

@@ -404,10 +404,13 @@ class TatlockAgent(AgentInterface):
             # with async context managers inside generators
             # The StreamingCoordinator will handle word-by-word streaming
             # Pass message_history to maintain conversation context and tracker for tool logging
+            from src.anthropic.model_selector import with_phase_binding
+
             result = await self.agent.run(
                 user_message,
                 message_history=message_history if message_history else None,
                 deps=tracker,
+                model_settings=with_phase_binding(None, "orchestrate"),
             )
             final_text = result.output
 
@@ -536,13 +539,13 @@ class TatlockAgent(AgentInterface):
 
         # Run with scoped tools and tracker
         # Force tool_choice to make LLM actually call tools
-        from src.anthropic.model_selector import get_tool_choice_settings
+        from src.anthropic.model_selector import get_tool_choice_settings, with_phase_binding
 
         result = await scoped_agent.run(
             enriched_message,
             message_history=pydantic_history if pydantic_history else None,
             deps=tool_tracker,
-            model_settings=get_tool_choice_settings(),
+            model_settings=with_phase_binding(get_tool_choice_settings(), "orchestrate"),
         )
 
         logger.info(
@@ -625,10 +628,13 @@ class TatlockAgent(AgentInterface):
         # Use run() instead of run_stream() to avoid Ollama 400 bug
         # with streaming + tool calls (PydanticAI issues #1292, #2256)
         # We yield the final response in chunks to maintain streaming interface
+        from src.anthropic.model_selector import with_phase_binding
+
         result = await scoped_agent.run(
             enriched_message,
             message_history=pydantic_history if pydantic_history else None,
             deps=tool_tracker,
+            model_settings=with_phase_binding(None, "orchestrate"),
         )
 
         # Stream the final response in chunks to maintain UX
@@ -725,13 +731,13 @@ class TatlockAgent(AgentInterface):
                 pydantic_history.append(ModelResponse(parts=[TextPart(content=content)]))
 
         # Run with scoped tools and tracker
-        from src.anthropic.model_selector import get_tool_choice_settings
+        from src.anthropic.model_selector import get_tool_choice_settings, with_phase_binding
 
         result = await scoped_agent.run(
             enriched_message,
             message_history=pydantic_history if pydantic_history else None,
             deps=tool_tracker,
-            model_settings=get_tool_choice_settings(),
+            model_settings=with_phase_binding(get_tool_choice_settings(), "orchestrate"),
         )
 
         # Extract tool calls and results from the agent's messages
@@ -888,9 +894,12 @@ class TatlockAgent(AgentInterface):
                 pydantic_history.append(ModelResponse(parts=[TextPart(content=content)]))
 
         # Run synthesis
+        from src.anthropic.model_selector import with_phase_binding
+
         result = await synthesis_agent.run(
             synthesis_prompt,
             message_history=pydantic_history if pydantic_history else None,
+            model_settings=with_phase_binding(None, "synthesize"),
         )
 
         logger.info(

src/anthropic/model_selector.py

@@ -28,6 +28,13 @@ logger = get_logger(__name__)
 # Cached health check results (set once at startup)
 _claude_available: bool | None = None
 _ollama_available: bool | None = None
+# Which server answers behind OLLAMA_HOST: "boilerroom", "llama-server"
+# or "ollama". They disagree on tool_choice semantics and on which
+# extension fields do anything (see get_tool_choice_settings and
+# phase_extra_body), so the health check probes for the wrapper's name
+# on /health, then for /props — served by llama-server only — and
+# caches the answer here.
+_local_flavor: str | None = None
 
 
 async def check_ollama_health() -> bool:
@@ -40,7 +47,7 @@ async def check_ollama_health() -> bool:
     Returns:
         True if Ollama is reachable and OLLAMA_DEFAULT_MODEL is pulled.
     """
-    global _ollama_available
+    global _ollama_available, _local_flavor
 
     host = str(config.OLLAMA_HOST).rstrip("/")
     model = config.OLLAMA_DEFAULT_MODEL
@@ -53,12 +60,34 @@ async def check_ollama_health() -> bool:
             response.raise_for_status()
             names = [m.get("id", "") for m in response.json().get("data", [])]
 
+            # The boilerroom wrapper names itself on /health; a bare
+            # llama-server answers /health without a service field and
+            # serves /props (its own surface); Ollama answers neither.
+            is_wrapper = False
+            try:
+                health = await client.get(f"{host}/health")
+                is_wrapper = (
+                    health.status_code == 200 and health.json().get("service") == "boilerroom"
+                )
+            except (httpx.HTTPError, ValueError):
+                is_wrapper = False
+
+            if is_wrapper:
+                _local_flavor = "boilerroom"
+            else:
+                try:
+                    props = await client.get(f"{host}/props")
+                    _local_flavor = "llama-server" if props.status_code == 200 else "ollama"
+                except httpx.HTTPError:
+                    _local_flavor = "ollama"
+
         if model in names or f"{model}:latest" in names:
             _ollama_available = True
             logger.info(
                 "ollama_health_check_passed",
                 host=host,
                 model=model,
+                flavor=_local_flavor,
             )
             return True
 
@@ -244,19 +273,97 @@ def get_model(prefer_cloud: bool | None = None) -> AnthropicModel | OpenAIChatMo
 
 def get_tool_choice_settings() -> ModelSettings:
     """
-    Get model_settings for forcing tool calls on the first request.
+    Get model_settings for tool calling on the orchestration phase.
 
-    For Claude: PydanticAI handles tool_choice natively, so no extra_body needed.
-    For Ollama: Pass tool_choice="required" via extra_body to force tool calling.
+    Claude: PydanticAI handles tool_choice natively — no extra_body.
+
+    Ollama: tool_choice="required" via extra_body. Advisory there (Ollama
+    ignores it), but it nudges gemma4 to actually call tools, which the
+    persona-suppression gotcha made necessary.
+
+    llama-server: NO tool_choice. It enforces "required" on every request
+    in the run, so after a tool returns, the next generation is again
+    forced to call a tool — an unbreakable tool loop (~80 s turns,
+    observed at cutover). Its --jinja template renders tool definitions
+    the way gemma4 was trained, and the model calls tools reliably
+    unforced (probed 3/3).
+
+    boilerroom: same as llama-server — the wrapper forwards to it, and
+    its /props passthrough is what lets this detection keep working.
     """
     from pydantic_ai.settings import ModelSettings
 
     if resolve_backend() == "claude":
         # PydanticAI's Anthropic model handles tool_choice internally
         return ModelSettings()
-    else:
-        # Ollama needs explicit tool_choice via extra_body
-        return ModelSettings(extra_body={"tool_choice": "required"})
+    if _local_flavor in ("llama-server", "boilerroom"):
+        return ModelSettings()
+    # Ollama needs explicit tool_choice via extra_body
+    return ModelSettings(extra_body={"tool_choice": "required"})
+
+
+# Phase bindings for the local backend (this repo's T-4, decided
+# 2026-09-12): through the boilerroom wrapper each phase is a named
+# session with an eviction rank — lower parks sooner, so the most-used
+# context keeps its KV warm. The pipeline phases outrank the librarian,
+# which outranks webber (20, filed in its own repo); Open WebUI stays
+# session-less and can never evict anyone (wrapper D-4).
+# phase -> (direct llama-server slot, wrapper session name, eviction rank)
+_PHASE_BINDINGS: dict[str, tuple[int | None, str, int]] = {
+    "steward": (0, "tatlock-steward", 40),
+    "orchestrate": (1, "tatlock-orchestrate", 40),
+    "synthesize": (2, "tatlock-synthesize", 40),
+    # Experts (biographer, housekeeper) share one session between the
+    # librarian and the phases: the two least-used consumers trade the
+    # spare slot by rank instead of anyone hitting an empty pool — a
+    # session-less call 503s once four sessions are resident (D-4's
+    # idle-only rule), so every generation call here must carry a name.
+    "experts": (None, "tatlock-experts", 35),
+    "librarian": (None, "librarian", 30),
+}
+
+
+def phase_extra_body(phase: str) -> dict[str, str | int]:
+    """
+    The extension fields a pipeline phase sends to the local backend.
+
+    Through the boilerroom wrapper: a named session with its eviction
+    rank — the wrapper owns the name-to-slot map and reports parks and
+    restores on the response. Against a bare llama-server: the raw
+    id_slot pin this replaces (the librarian floats there, as it always
+    did). Ollama and Claude get nothing, and an unprobed flavor sends
+    nothing rather than guessing. Gated by BACKEND_SLOT_PINNING like
+    the pinning it grew out of.
+    """
+    if not config.BACKEND_SLOT_PINNING or resolve_backend() == "claude":
+        return {}
+    slot, session, rank = _PHASE_BINDINGS[phase]
+    if _local_flavor == "boilerroom":
+        return {"session": session, "eviction_order": rank}
+    if _local_flavor == "llama-server" and slot is not None:
+        return {"id_slot": slot}
+    return {}
+
+
+def with_phase_binding(settings: ModelSettings | None, phase: str) -> ModelSettings | None:
+    """
+    Merge a phase's local-backend binding into model settings.
+
+    Session fields through the wrapper, id_slot against a bare
+    llama-server, settings untouched everywhere else — one call site
+    stays correct on any backend (see phase_extra_body).
+    """
+    extra = phase_extra_body(phase)
+    if not extra:
+        return settings
+
+    from pydantic_ai.settings import ModelSettings
+
+    merged = dict(settings or {})
+    extra_body = dict(merged.get("extra_body") or {})
+    extra_body.update(extra)
+    merged["extra_body"] = extra_body
+    return ModelSettings(**merged)
 
 
 def get_sampling_settings(temperature: float) -> ModelSettings:
@@ -291,5 +398,6 @@ def get_model_info() -> dict:
         "claude_configured": bool(config.ANTHROPIC_API_KEY),
         "ollama_available": is_ollama_available(),
         "ollama_model": config.OLLAMA_DEFAULT_MODEL,
+        "local_flavor": _local_flavor,
         "prefer_cloud": config.PREFER_CLOUD_BACKEND,
     }

src/core/config.py

@@ -147,6 +147,10 @@ class Config(BaseSettings):
         default=None,
         description="OpenAI-compatible embeddings host; falls back to OLLAMA_HOST so gen and embed can live on different servers",
     )
+    BACKEND_SLOT_PINNING: bool = Field(
+        default=False,
+        description="Pin each pipeline phase to a llama-server slot (steward=0, orchestrator=1, synthesizer=2) so a phase's stable prompt prefix stays in that slot's KV cache; no-op on Claude, ignored by Ollama",
+    )
 
     # Redis Memory Database
     REDIS_MEMORY_DB: int = Field(default=1, description="Redis database number for memory cache")
@@ -226,15 +230,21 @@ class Config(BaseSettings):
         Get effective log level, auto-determining from environment if not set.
 
         - development: DEBUG (maximum verbosity)
-        - production: WARNING (minimal noise)
+        - production: INFO
         - testing: INFO
+
+        Production ran at WARNING ("minimal noise") until T-5: a healthy
+        service warns roughly never, so `docker logs` was empty for
+        months — startup, backend flavor detection and the wrapper's
+        balancing/compaction signals all suppressed, which made the
+        2026-09-12 serving cutover unverifiable from logs. INFO on
+        stdout is the operational floor; LOG_LEVEL quiets it when noise
+        ever becomes the real problem.
         """
         if self.LOG_LEVEL is not None:
             return self.LOG_LEVEL
         if self.ENVIRONMENT == Environment.DEVELOPMENT:
             return "DEBUG"
-        if self.ENVIRONMENT == Environment.PRODUCTION:
-            return "WARNING"
         return "INFO"
 
     @property

src/ollama/provider.py

@@ -4,6 +4,17 @@ PydanticAI provider for Ollama with message sanitization.
 Ollama's OpenAI-compatible API rejects messages with `content: null`,
 which PydanticAI sends for assistant messages that only contain tool calls.
 This provider sanitizes messages to use empty strings instead of null.
+
+History worth keeping (repo T-6): until 2026-09-13 the sanitized client
+was never in the request path — the provider assigned
+`self._openai_client`, an attribute nobody reads, while
+`OllamaProvider.client` serves `self._client`. The sanitizer, the
+wrapper-signal reading and the OLLAMA_TIMEOUT cap were all silently
+dead (sessions were unaffected — they ride ModelSettings). webber hit
+the identical bug the same day; both now wire the client through the
+constructor's official `openai_client` parameter, and the signals are
+read from the response body — an httpx event-hook variant demonstrably
+never fires under the openai SDK.
 """
 
 from typing import Any
@@ -17,6 +28,31 @@ from src.core.logging_config import get_logger
 logger = get_logger(__name__)
 
 
+def _log_wrapper_signals(response: Any) -> None:
+    """
+    Surface the boilerroom wrapper's per-response signals (repo T-4).
+
+    balancing names the sessions parked or restored to serve this
+    request (wrapper D-4 — never silent); compaction-due says a session
+    crossed its authored context budget (wrapper D-5 — a signal, not an
+    interrupt). Read from the parsed body's extra fields: the wrapper
+    injects them into non-streamed JSON answers and openai's pydantic
+    models retain unknown fields in `model_extra`. Absent on any other
+    backend, so this costs nothing there. Streams carry the signals in
+    headers only and go unlogged here; the steward's raw call reads its
+    own body.
+    """
+    extra = getattr(response, "model_extra", None) or {}
+    balancing = extra.get("balancing")
+    if balancing:
+        logger.info("backend_balancing", moves=balancing)
+    if extra.get("compaction_due"):
+        logger.warning(
+            "backend_compaction_due",
+            hint="GET /sessions on the wrapper names the session over budget",
+        )
+
+
 class TatlockOllamaProvider(OllamaProvider):
     """
     Custom OllamaProvider with message sanitization for Tatlock agents.
@@ -36,10 +72,12 @@ class TatlockOllamaProvider(OllamaProvider):
             clean_host = str(config.OLLAMA_HOST).rstrip("/")
             base_url = f"{clean_host}/v1"
 
-        super().__init__(base_url=base_url)
-
-        # Override the client with our sanitized version
-        self._openai_client = _SanitizedAsyncOpenAI(base_url=base_url)
+        # The sanitized client goes through the official constructor
+        # parameter: the provider's `.client` property serves `_client`,
+        # and poking a lookalike attribute after super().__init__ had
+        # built its own client is how the sanitizer sat bypassed in
+        # production (T-6).
+        super().__init__(openai_client=_SanitizedAsyncOpenAI(base_url=base_url))
 
         logger.debug(
             "tatlock_ollama_provider_created",
@@ -59,17 +97,46 @@ class _SanitizedAsyncOpenAI(AsyncOpenAI):
         super().__init__(api_key="ollama", **kwargs)
 
     @property
-    def chat(self) -> "_SanitizedChat":
-        """Return sanitized chat interface."""
+    def chat(self) -> "_SanitizedChat":  # type: ignore[override]
+        """Return sanitized chat interface.
+
+        Deliberately incompatible with AsyncOpenAI.chat, which is a Chat
+        resource. Replacing it is the entire mechanism of this class;
+        typing it as the parent's Chat would describe an object this
+        class does not return. The suppression is on this member alone.
+        """
         return _SanitizedChat(self)
 
 
+def _parent_chat(client: AsyncOpenAI) -> Any:
+    """Get AsyncOpenAI's own `chat`, bypassing the subclass override.
+
+    openai has shipped `chat` as both a property (getter `.fget`) and a
+    functools.cached_property (getter `.func`) — this venv's 2.11.0 is
+    the latter, so the old hardcoded `.fget` access raised
+    AttributeError the moment anything touched `.chat`. It went
+    unnoticed here for the same reason the whole class did: the client
+    was never wired (T-6). Reading whichever getter the descriptor
+    exposes keeps this working across both shapes, and raises something
+    legible if openai adopts a third. Ported from webber's 2026-08-11
+    fix.
+    """
+    descriptor = AsyncOpenAI.__dict__["chat"]
+    getter = getattr(descriptor, "func", None) or getattr(descriptor, "fget", None)
+    if getter is None:  # pragma: no cover - defensive
+        raise TypeError(
+            f"AsyncOpenAI.chat is a {type(descriptor).__name__} with neither "
+            "'func' nor 'fget'; the sanitising wrapper needs updating"
+        )
+    return getter(client)
+
+
 class _SanitizedChat:
     """Chat interface wrapper with sanitized completions."""
 
     def __init__(self, client: _SanitizedAsyncOpenAI):
         self._client = client
-        self._original_chat = AsyncOpenAI.chat.fget(client)  # type: ignore
+        self._original_chat = _parent_chat(client)
 
     @property
     def completions(self) -> "_SanitizedCompletions":
@@ -93,7 +160,9 @@ class _SanitizedCompletions:
         if "messages" in kwargs:
             kwargs["messages"] = _sanitize_messages(kwargs["messages"])
 
-        return await self._original.create(**kwargs)
+        response = await self._original.create(**kwargs)
+        _log_wrapper_signals(response)
+        return response
 
 
 def _sanitize_messages(messages: list[dict[str, Any]]) -> list[dict[str, Any]]:

tests/anthropic/test_model_selector.py

@@ -67,7 +67,10 @@ class TestGetModel:
 
 
 class TestToolChoiceSettings:
-    def test_ollama_forces_tool_choice(self, local_first):
+    def test_ollama_forces_tool_choice(self, local_first, monkeypatch):
+        # Pin the flavor: the session-scoped app init probes the real
+        # dev backend, and this test's answer must not depend on it.
+        monkeypatch.setattr(model_selector, "_local_flavor", "ollama")
         settings = model_selector.get_tool_choice_settings()
         assert settings.get("extra_body") == {"tool_choice": "required"}
 
@@ -91,3 +94,114 @@ class TestGetModelInfo:
         info = model_selector.get_model_info()
         assert info["backend"] == "claude"
         assert info["model"] == config.ANTHROPIC_MODEL
+
+
+class TestPhaseBinding:
+    def test_disabled_returns_settings_unchanged(self, local_first, monkeypatch):
+        monkeypatch.setattr(config, "BACKEND_SLOT_PINNING", False)
+        base = model_selector.get_tool_choice_settings()
+        assert model_selector.with_phase_binding(base, "orchestrate") is base
+        assert model_selector.with_phase_binding(None, "synthesize") is None
+
+    def test_wrapper_flavor_sends_session_and_rank(self, local_first, monkeypatch):
+        monkeypatch.setattr(config, "BACKEND_SLOT_PINNING", True)
+        monkeypatch.setattr(model_selector, "_local_flavor", "boilerroom")
+        settings = model_selector.with_phase_binding(
+            model_selector.get_tool_choice_settings(), "orchestrate"
+        )
+        extra_body = settings["extra_body"]
+        assert extra_body["session"] == "tatlock-orchestrate"
+        assert extra_body["eviction_order"] == 40
+        assert "id_slot" not in extra_body
+
+    def test_wrapper_ranking_matches_the_decision(self, local_first, monkeypatch):
+        # Decided 2026-09-12: pipeline over librarian over webber (20,
+        # filed in its own repo); lower eviction_order parks sooner.
+        monkeypatch.setattr(config, "BACKEND_SLOT_PINNING", True)
+        monkeypatch.setattr(model_selector, "_local_flavor", "boilerroom")
+        ranks = {
+            phase: model_selector.phase_extra_body(phase)["eviction_order"]
+            for phase in ("steward", "orchestrate", "synthesize", "experts", "librarian")
+        }
+        assert ranks["steward"] == ranks["orchestrate"] == ranks["synthesize"] == 40
+        assert ranks["experts"] == 35
+        assert ranks["librarian"] == 30
+        assert ranks["librarian"] < ranks["experts"] < ranks["steward"]
+        assert ranks["librarian"] > 20  # webber's rank stays below
+
+    def test_wrapper_session_names_are_stable(self, local_first, monkeypatch):
+        # The wrapper's map keys on these; renaming one orphans its slot.
+        monkeypatch.setattr(config, "BACKEND_SLOT_PINNING", True)
+        monkeypatch.setattr(model_selector, "_local_flavor", "boilerroom")
+        names = {
+            phase: model_selector.phase_extra_body(phase)["session"]
+            for phase in ("steward", "orchestrate", "synthesize", "experts", "librarian")
+        }
+        assert names == {
+            "steward": "tatlock-steward",
+            "orchestrate": "tatlock-orchestrate",
+            "synthesize": "tatlock-synthesize",
+            "experts": "tatlock-experts",
+            "librarian": "librarian",
+        }
+
+    def test_direct_llama_server_keeps_id_slot(self, local_first, monkeypatch):
+        monkeypatch.setattr(config, "BACKEND_SLOT_PINNING", True)
+        monkeypatch.setattr(model_selector, "_local_flavor", "llama-server")
+        settings = model_selector.with_phase_binding(None, "synthesize")
+        assert settings["extra_body"] == {"id_slot": 2}
+
+    def test_librarian_floats_on_direct_llama_server(self, local_first, monkeypatch):
+        monkeypatch.setattr(config, "BACKEND_SLOT_PINNING", True)
+        monkeypatch.setattr(model_selector, "_local_flavor", "llama-server")
+        assert model_selector.phase_extra_body("librarian") == {}
+
+    def test_ollama_flavor_gets_no_fields(self, local_first, monkeypatch):
+        monkeypatch.setattr(config, "BACKEND_SLOT_PINNING", True)
+        monkeypatch.setattr(model_selector, "_local_flavor", "ollama")
+        assert model_selector.phase_extra_body("steward") == {}
+
+    def test_unprobed_flavor_sends_nothing_rather_than_guessing(self, local_first, monkeypatch):
+        monkeypatch.setattr(config, "BACKEND_SLOT_PINNING", True)
+        monkeypatch.setattr(model_selector, "_local_flavor", None)
+        assert model_selector.phase_extra_body("orchestrate") == {}
+
+    def test_merge_preserves_existing_extra_body(self, local_first, monkeypatch):
+        from pydantic_ai.settings import ModelSettings
+
+        monkeypatch.setattr(config, "BACKEND_SLOT_PINNING", True)
+        monkeypatch.setattr(model_selector, "_local_flavor", "boilerroom")
+        base = ModelSettings(extra_body={"marker": 1})
+        merged = model_selector.with_phase_binding(base, "steward")
+        assert merged["extra_body"]["marker"] == 1
+        assert merged["extra_body"]["session"] == "tatlock-steward"
+
+    def test_claude_backend_never_bound(self, local_first, monkeypatch):
+        monkeypatch.setattr(config, "BACKEND_SLOT_PINNING", True)
+        monkeypatch.setattr(config, "PREFER_CLOUD_BACKEND", True)
+        base = model_selector.get_tool_choice_settings()
+        assert model_selector.with_phase_binding(base, "orchestrate") is base
+
+
+class TestLocalFlavorToolChoice:
+    def test_llama_server_flavor_sends_no_tool_choice(self, local_first, monkeypatch):
+        monkeypatch.setattr(model_selector, "_local_flavor", "llama-server")
+        settings = model_selector.get_tool_choice_settings()
+        assert not settings.get("extra_body")
+
+    def test_boilerroom_flavor_sends_no_tool_choice(self, local_first, monkeypatch):
+        # The wrapper forwards to llama-server, which enforces
+        # tool_choice — the nudge through it is the tool-loop incident.
+        monkeypatch.setattr(model_selector, "_local_flavor", "boilerroom")
+        settings = model_selector.get_tool_choice_settings()
+        assert not settings.get("extra_body")
+
+    def test_ollama_flavor_keeps_advisory_required(self, local_first, monkeypatch):
+        monkeypatch.setattr(model_selector, "_local_flavor", "ollama")
+        settings = model_selector.get_tool_choice_settings()
+        assert settings["extra_body"] == {"tool_choice": "required"}
+
+    def test_unknown_flavor_defaults_to_ollama_semantics(self, local_first, monkeypatch):
+        monkeypatch.setattr(model_selector, "_local_flavor", None)
+        settings = model_selector.get_tool_choice_settings()
+        assert settings["extra_body"] == {"tool_choice": "required"}

tests/contracts/test_service_contracts.py

@@ -114,16 +114,18 @@ class TestLocalBackendContract:
         )
 
     async def test_openai_compat_tool_calling(self):
-        # Mirrors the request PydanticAI's OpenAIChatModel sends for the
-        # orchestration phase, including the extra_body tool_choice.
+        # Mirrors the orchestration-phase request on llama-server: tools
+        # attached, NO tool_choice. The backend must call the tool unforced
+        # — "required" is deliberately absent because llama-server enforces
+        # it on every request in a run, which turns the tool loop
+        # unbreakable (observed at cutover: ~80 s turns).
         response = await _post_or_skip(
             f"{OLLAMA}/v1/chat/completions",
-            "ollama",
+            "local-backend",
             {
                 "model": config.OLLAMA_DEFAULT_MODEL,
                 "messages": [{"role": "user", "content": "What is 6 * 7? Use the calculator."}],
                 "tools": [CALCULATOR_TOOL],
-                "tool_choice": "required",
                 "stream": False,
             },
             timeout=config.OLLAMA_TIMEOUT,
@@ -252,3 +254,62 @@ class TestRedisContract:
             await client.delete("contract-test-key")
         finally:
             await client.aclose()
+
+
+@pytest.mark.contract
+class TestBoilerroomWrapperContract:
+    """Boundary: the boilerroom wrapper surface session adoption rides on
+    (repo T-4). Skips when OLLAMA_HOST is not the wrapper — a direct
+    engine or Ollama is a valid deployment, not a violation.
+    """
+
+    async def _skip_unless_wrapper(self) -> None:
+        response = await _get_or_skip(f"{OLLAMA}/health", "local-backend")
+        try:
+            service = response.json().get("service")
+        except ValueError:
+            service = None
+        if service != "boilerroom":
+            pytest.skip("OLLAMA_HOST is not the boilerroom wrapper")
+
+    async def test_wrapper_names_itself_on_health(self):
+        # Mirrors check_ollama_health()'s wrapper probe: the flavor
+        # detection keys on this exact field.
+        await self._skip_unless_wrapper()
+
+    async def test_props_passes_through_for_flavor_detection(self):
+        # tatlock treats a non-200 /props as Ollama and applies the
+        # tool_choice nudge — enforced by llama-server into a tool
+        # loop. The wrapper passing /props through is what keeps that
+        # detection safe (boilerroom T-10).
+        await self._skip_unless_wrapper()
+        response = await _get_or_skip(f"{OLLAMA}/props", "local-backend")
+        assert response.status_code == 200
+
+    async def test_session_fields_answer_with_signals(self):
+        # Mirrors phase_extra_body() through the wrapper: a session-
+        # carrying request must come back with the balancing header and
+        # the compaction signal in the body (wrapper D-3/D-4/D-5).
+        await self._skip_unless_wrapper()
+        response = await _post_or_skip(
+            f"{OLLAMA}/v1/chat/completions",
+            "local-backend",
+            {
+                "model": config.OLLAMA_DEFAULT_MODEL,
+                # No max_tokens: gemma4 spends its first tokens thinking,
+                # and a tight cap returns empty content (not a wrapper
+                # fault — the sibling passthrough test runs uncapped too).
+                "messages": [{"role": "user", "content": "Reply with the single word: pong"}],
+                "session": "contract-probe",
+                "eviction_order": 1,
+            },
+            timeout=config.OLLAMA_TIMEOUT,
+        )
+        assert response.status_code == 200
+        assert "x-boilerroom-balancing" in response.headers
+        assert response.headers.get("x-boilerroom-compaction-due") in ("true", "false")
+        body = response.json()
+        assert isinstance(body.get("compaction_due"), bool)
+        assert isinstance(body.get("balancing"), list)
+        # The extension fields must not leak into the engine's answer
+        assert body["choices"][0]["message"]["content"].strip()

tests/core/test_logging_config.py

@@ -241,6 +241,41 @@ class TestLoggingConfiguration:
         with patch.object(config, "ENVIRONMENT", Environment.PRODUCTION):
             assert config.log_format == "json"
 
+    def test_production_default_level_is_info(self):
+        """Production logs INFO to stdout (T-5).
+
+        The old WARNING default made `docker logs` empty for months — a
+        healthy service warns roughly never, so startup, flavor
+        detection and the wrapper signals were all suppressed and the
+        serving cutover could not be verified from logs.
+        """
+        from src.core.config import Environment, config
+
+        with (
+            patch.object(config, "ENVIRONMENT", Environment.PRODUCTION),
+            patch.object(config, "LOG_LEVEL", None),
+        ):
+            assert config.effective_log_level == "INFO"
+
+    def test_log_level_env_still_quiets_production(self):
+        """LOG_LEVEL stays the override for when noise is the problem."""
+        from src.core.config import Environment, config
+
+        with (
+            patch.object(config, "ENVIRONMENT", Environment.PRODUCTION),
+            patch.object(config, "LOG_LEVEL", "WARNING"),
+        ):
+            assert config.effective_log_level == "WARNING"
+
+    def test_development_default_stays_debug(self):
+        from src.core.config import Environment, config
+
+        with (
+            patch.object(config, "ENVIRONMENT", Environment.DEVELOPMENT),
+            patch.object(config, "LOG_LEVEL", None),
+        ):
+            assert config.effective_log_level == "DEBUG"
+
     def test_multiple_loggers_independent(self):
         """Test multiple loggers are independent."""
         logger1 = get_logger("test.logger1")

tests/ollama/test_provider.py

@@ -1,31 +1,73 @@
 """
-Tests for TatlockOllamaProvider configuration.
+Tests for TatlockOllamaProvider configuration and wiring.
 
-The AsyncOpenAI client must carry an explicit timeout from
-config.OLLAMA_TIMEOUT instead of the SDK default (~600s), so a stuck
-LLM call cannot consume the whole delegation budget.
+Every assertion here goes through `provider.client` — the property
+pydantic_ai actually reads. The previous version asserted on
+`_openai_client`, a lookalike attribute nobody read, and stayed green
+for the whole period the sanitizer was bypassed in production (T-6):
+a test whose subject is not the real thing cannot fail for the real
+reason.
 """
 
 import pytest
 
 from src.core.config import config
-from src.ollama.provider import TatlockOllamaProvider, _sanitize_messages
+from src.ollama import provider as provider_module
+from src.ollama.provider import (
+    TatlockOllamaProvider,
+    _parent_chat,
+    _sanitize_messages,
+    _SanitizedAsyncOpenAI,
+    _SanitizedCompletions,
+)
+
+
+@pytest.mark.unit
+class TestClientWiring:
+    """The sanitized client must be the one the provider serves (T-6)."""
+
+    def test_provider_serves_the_sanitized_client(self):
+        provider = TatlockOllamaProvider(base_url="http://localhost:11434/v1")
+
+        assert isinstance(provider.client, _SanitizedAsyncOpenAI)
+
+    def test_the_full_chain_reaches_completions(self):
+        # Walks provider.client -> sanitized chat -> parent lookup ->
+        # completions. Under openai's cached_property `chat`, the old
+        # hardcoded `.fget` access raised AttributeError right here.
+        provider = TatlockOllamaProvider(base_url="http://localhost:11434/v1")
+
+        assert provider.client.chat.completions is not None
+
+    def test_parent_lookup_survives_either_descriptor_shape(self):
+        from openai import AsyncOpenAI
+
+        descriptor = AsyncOpenAI.__dict__["chat"]
+        assert hasattr(descriptor, "func") or hasattr(
+            descriptor, "fget"
+        ), "AsyncOpenAI.chat exposes neither getter; _parent_chat needs updating"
+        client = _SanitizedAsyncOpenAI(base_url="http://localhost:11434/v1")
+        parent = _parent_chat(client)
+        assert parent is not None
+        assert (
+            type(parent).__name__ != "_SanitizedChat"
+        ), "parent lookup must not recurse into the override"
 
 
 @pytest.mark.unit
 class TestProviderTimeout:
-    """Timeout configuration on the underlying AsyncOpenAI client."""
+    """Timeout configuration on the client the provider actually serves."""
 
     def test_openai_client_timeout_from_config(self):
         provider = TatlockOllamaProvider(base_url="http://localhost:11434/v1")
 
-        assert provider._openai_client.timeout == float(config.OLLAMA_TIMEOUT)
+        assert provider.client.timeout == float(config.OLLAMA_TIMEOUT)
 
     def test_timeout_is_not_sdk_default(self):
         provider = TatlockOllamaProvider(base_url="http://localhost:11434/v1")
 
         # The OpenAI SDK defaults to 600s; the configured cap must win
-        assert provider._openai_client.timeout < 600
+        assert provider.client.timeout < 600
 
 
 @pytest.mark.unit
@@ -52,3 +94,68 @@ class TestMessageSanitization:
         ]
 
         assert _sanitize_messages(messages) == messages
+
+
+class _StubLogger:
+    def __init__(self):
+        self.calls = []
+
+    def info(self, event, **kwargs):
+        self.calls.append(("info", event, kwargs))
+
+    def warning(self, event, **kwargs):
+        self.calls.append(("warning", event, kwargs))
+
+
+class _BusyResponse:
+    def __init__(self):
+        self.model_extra = {
+            "balancing": [{"parked": "librarian"}],
+            "compaction_due": True,
+        }
+
+
+class _QuietResponse:
+    def __init__(self):
+        self.model_extra = {"balancing": [], "compaction_due": False}
+
+
+@pytest.mark.unit
+class TestWrapperSignals:
+    """The wrapper's body signals must not pass silently (T-4/T-6).
+
+    Read from the parsed body's model_extra: an httpx event-hook
+    variant demonstrably never fires under the openai SDK.
+    """
+
+    def test_busy_response_logs_balancing_and_compaction(self, monkeypatch):
+        stub = _StubLogger()
+        monkeypatch.setattr(provider_module, "logger", stub)
+
+        provider_module._log_wrapper_signals(_BusyResponse())
+
+        assert any(kind == "info" and event == "backend_balancing" for kind, event, _ in stub.calls)
+        assert any(kind == "warning" for kind, _, _ in stub.calls)
+
+    def test_quiet_response_logs_nothing(self, monkeypatch):
+        stub = _StubLogger()
+        monkeypatch.setattr(provider_module, "logger", stub)
+
+        provider_module._log_wrapper_signals(_QuietResponse())
+
+        assert stub.calls == []
+
+    async def test_create_surfaces_the_signals(self, monkeypatch):
+        # The read must sit in the request path, not merely exist:
+        # removing the call from create() has to fail this test.
+        stub = _StubLogger()
+        monkeypatch.setattr(provider_module, "logger", stub)
+
+        class FakeOriginal:
+            async def create(self, **kwargs):
+                return _BusyResponse()
+
+        completions = _SanitizedCompletions(FakeOriginal())
+        await completions.create(messages=[{"role": "user", "content": "hi"}])
+
+        assert any(event == "backend_balancing" for _, event, _ in stub.calls)