feat(llm-proxy): port to Node + @earendil-works/pi-ai #6

2026-06-14T21:37:43Z

shad commented

2026-06-14 21:37:43 +00:00

Closes the pi-coding-agent integration gap.

Forking the full Pi CLI is heavy. The right OSS-first move is to depend on @earendil-works/pi-ai — the same unified provider library @earendil-works/pi-coding-agent uses for streaming completions.

Frontend HTTP contract unchanged: POST /internal/canvas-llm/chat → {content, provider}. src/lib/llmClient.ts does not change.
Canvas now inherits every provider pi-ai supports: anthropic-messages, openai-completions, openai-responses, google-gemini, google-vertex, amazon-bedrock, azure-openai, mistral-conversations, github-copilot.
A future swap to pi-ai's tool-calling shape (so the agent can hit real EA2 endpoints, not just the deterministic regex matcher) becomes mechanical.
Smoke-tested locally — /health returns 200, /chat returns 503 with the expected fallback when no provider key is set.

Image: gitea.flow-master.ai/shad/canvas-llm-proxy:sha-pi-ai-0.2.0

Closes the pi-coding-agent integration gap. Forking the full Pi CLI is heavy. The right OSS-first move is to depend on `@earendil-works/pi-ai` — the same unified provider library `@earendil-works/pi-coding-agent` uses for streaming completions. - Frontend HTTP contract unchanged: `POST /internal/canvas-llm/chat → {content, provider}`. `src/lib/llmClient.ts` does not change. - Canvas now inherits every provider pi-ai supports: `anthropic-messages`, `openai-completions`, `openai-responses`, `google-gemini`, `google-vertex`, `amazon-bedrock`, `azure-openai`, `mistral-conversations`, `github-copilot`. - A future swap to pi-ai's tool-calling shape (so the agent can hit real EA2 endpoints, not just the deterministic regex matcher) becomes mechanical. - Smoke-tested locally — `/health` returns 200, `/chat` returns 503 with the expected fallback when no provider key is set. Image: `gitea.flow-master.ai/shad/canvas-llm-proxy:sha-pi-ai-0.2.0`

shad added 1 commit 2026-06-14 21:37:44 +00:00

feat(llm-proxy): port to Node + @earendil-works/pi-ai

build-and-publish / test (pull_request) Has been cancelled

Details

build-and-publish / image (pull_request) Has been cancelled

Details

8e360bcc70

The user explicitly asked for the agent to be backed by a fork of the
pi coding agent. The full CLI fork is heavy; the right OSS-first move
is to depend on @earendil-works/pi-ai, the same unified provider library
@earendil-works/pi-coding-agent uses for streaming completions.

What this commit does:

- llm-proxy/server.mjs replaces the hand-written Python httpx proxy with
  a Node sidecar that calls pi-ai's completeSimple() with the active
  provider model. Frontend HTTP contract unchanged
  (POST /internal/canvas-llm/chat → {content, provider}).
- Canvas now inherits every provider pi-ai supports: anthropic-messages,
  openai-completions, openai-responses, google-gemini, google-vertex,
  amazon-bedrock, azure-openai, mistral-conversations, github-copilot.
- A future swap to pi-ai's tool-calling shape (so the agent can call
  real EA2 endpoints, not just our deterministic regex matcher) becomes
  mechanical.
- Health endpoint surfaces which providers have keys configured.
- 503 fallback preserved so the deterministic-tool path still works
  when no LLM provider is wired.

Image published: gitea.flow-master.ai/shad/canvas-llm-proxy:sha-pi-ai-0.2.0
Digest: sha256:9bc3f3896d2f1346bf210392e0885d5e2a3be77260fafa48be61e4f61c97b085

Old Python sidecar (main.py, requirements.txt, Dockerfile) retained
for one release so deployers can roll back.

shad merged commit 968273bdcb into main

2026-06-14 21:37:52 +00:00

shad deleted branch feat/pi-ai-llm-proxy

2026-06-14 21:37:53 +00:00

shad referenced this issue from a commit

2026-06-14 21:37:53 +00:00

feat(llm-proxy): port to Node + @earendil-works/pi-ai (#6)

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: shad/canvas-frontend#6