Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .github/workflows/deploy-gateway-agent.yml
Original file line number Diff line number Diff line change
Expand Up @@ -97,7 +97,7 @@ jobs:

- name: Tag image
run: |
docker tag pmoves/gateway-agent:latest pmoves/gateway-agent:${{ github.sha }}
docker tag pmoves-gateway-agent:latest pmoves-gateway-agent:${{ github.sha }}
echo "✓ Image tagged"

deploy-ai-lab:
Expand Down
3 changes: 3 additions & 0 deletions pmoves/docker-compose.yml
Original file line number Diff line number Diff line change
Expand Up @@ -1896,6 +1896,9 @@ services:
- YT_WHISPER_MODEL=${YT_WHISPER_MODEL:-small}
- YT_TRANSCRIPT_DIARIZE=${YT_TRANSCRIPT_DIARIZE:-false}
- YT_CHANNEL_CHECK_INTERVAL=${YT_CHANNEL_CHECK_INTERVAL:-3600}
- OLLAMA_URL=${OLLAMA_URL:-http://pmoves-ollama:11434}
- YT_SUMMARY_PROVIDER=${YT_SUMMARY_PROVIDER:-ollama}
- YT_SUMMARY_OLLAMA_MODEL=${YT_SUMMARY_OLLAMA_MODEL:-gemma2:9b-instruct}

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Use a valid default Ollama model tag

When pmoves-yt runs with the new defaults, summary/chapter requests will ask Ollama for gemma2:9b-instruct, but that tag is not one of the published Gemma 2 tags (Ollama lists gemma2:9b and exact quantized instruct tags such as gemma2:9b-instruct-q4_0: https://ollama.com/library/gemma2/tags). On fresh/default deployments this makes the newly enabled Ollama summarizer fail with a model-not-found error unless operators know to override YT_SUMMARY_OLLAMA_MODEL; default this to a valid tag such as gemma2:9b or an exact quantized instruct tag.

Useful? React with 👍 / 👎.

- DOCKED_MODE=${DOCKED_MODE:-true}
- TOPOLOGY_MODE=${TOPOLOGY_MODE:-docked}
- PARENT_SYSTEM=${PARENT_SYSTEM:-PMOVES.AI}
Expand Down
10 changes: 10 additions & 0 deletions pmoves/docs/AGENTS/AGNOTE4482PHI.t1.md
Original file line number Diff line number Diff line change
Expand Up @@ -976,3 +976,13 @@ The pipeline reports success because its validation scope is too narrow. Neither
- Three-body: delivery=SPARK-KIMI, control=operator approval, memory=this trail. agent_signature: `ACK::SPARK-KIMI::MULTI-LANE-CLAIM-2026-05-27`.

<!-- GRAPHITI_MARK: SPARK-KIMI::MULTI-LANE-CLAIM::2026-05-27 -->

## SPARK-KIMI Multi-Lane Progress (2026-05-27)

- `2026-05-27T21:45:00Z` UPDATE `SPARK-KIMI` Lane A scope: A2A runtime verification complete. `/.well-known/agent-card.json` returns full Agent Card; `/a2a/v1/tasks` creates tasks successfully; auth chain works via JWT signed with `SUPABASE_JWT_SECRET`. **Finding**: `server.py:123` references `jose_jwt.InvalidSignatureError` which does not exist in `python-jose` — causes `AttributeError` → 500 instead of 403 on signature failure. Fix: remove broken handler (JWTError catch-all already returns 403). Branch `fix/a2a-jwt-error-handling` pushed, PR #1645 opened. agent_signature: `ACK::SPARK-KIMI::A2A-RUNTIME-VERIFICATION-UPDATE-2026-05-27`.

<!-- GRAPHITI_MARK: SPARK-KIMI::A2A-RUNTIME-VERIFICATION-UPDATE::2026-05-27 -->

- `2026-05-28T17:02:00Z` UPDATE `SPARK-KIMI` Lane C scope: PMOVES.YT `/yt/summarize` and `/yt/chapters` endpoints verified working on SPARK node via host Ollama (qwen3.5:35b-a3b-q4_K_M). Wiring: added `OLLAMA_URL`, `YT_SUMMARY_PROVIDER`, `YT_SUMMARY_OLLAMA_MODEL` env vars to `pmoves-yt` in docker-compose.yml (PR #1646). Fixed `host.docker.internal` → `172.17.0.1` for Linux Docker. Both endpoints return real AI-generated content. Sample output: 5-chapter breakdown with titles/blurbs, short-style summary. agent_signature: `ACK::SPARK-KIMI::YT-SUMMARIZE-CHAPTERS-VERIFIED-2026-05-28`.

<!-- GRAPHITI_MARK: SPARK-KIMI::YT-SUMMARIZE-CHAPTERS-VERIFIED::2026-05-28 -->
Loading