Commit Graph
6 Commits
Author SHA1 Message Date
Melvin StroblandClaude Opus 5.5 0d8c02a9ef Speech calls keep one connection per server, opened when listening starts
transcribe and speak share an httpx client per speech server with a 300 s
keep-alive, and run on the engine's loop. stt warms it with GET /v1/models
when an utterance opens, so a reply's first sentence finds the connection
open: a new one over a lossy link cost up to a second (openpanel V4).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ljdk7nDaguh9Uhi3zhcSjn
2026-10-19 22:06:08 +02:00
Melvin StroblandClaude Opus 5.5 a12bc5a2ee tts speaks MP3: a seventh of WAV's bytes over a slow link to the server
A sentence's length for `append` comes from the Xing header LAME writes into
the first frame. The cache key carries the format, so no WAV is reused.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ljdk7nDaguh9Uhi3zhcSjn
2026-10-19 21:55:17 +02:00
Melvin StroblandClaude Opus 5.5 200509c1bd Voice nodes (openpanel V4): stt, tts, wren reply/unhandled, socket publish
- `stt`: one realtime transcription session per utterance on the speech
  server's url, opened at `listening` true or the first chunk, committed at
  false; a whole clip goes to /v1/audio/transcriptions. Returns at once and
  publishes `partial` and `text` when the server answers.
- `tts`: one /v1/audio/speech call per sentence, cached by voice and text in
  node state; a reference is marked `append` while earlier ones still play.
- wren: `reply` says what was applied, `unhandled` carries the prompt when
  nothing was. The install hint names the git pin (PyPI's `wren` is another
  package).
- ai/client: transcribe, speak and transcribe_stream beside stream_completion.
- A device socket publishes scalar `in` ports as {"type": "publish"} text,
  in order with its binary frames.
- Pipeline.publish walks only what its values reach: a node downstream of a
  consumer that published nothing no longer runs again (wren re-acted on
  every microphone chunk).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ljdk7nDaguh9Uhi3zhcSjn
2026-10-19 21:34:02 +02:00
stroblmeandClaude Opus 5.5 58b92da8b0 Assistant streams its answer token by token
ai/client.py streams the completion and puts the chunks back together
(Assembler), covering OpenAI's piecewise tool-call arguments, Ollama's whole
calls, OpenRouter's comment lines, unnumbered calls and in-stream errors.
The turn emits a delta event per piece and a message per round as before,
and the chat grows the last answer as deltas arrive.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WgBfkm4rCmtd1T4vHWjEPx
2026-10-15 17:37:56 +02:00
stroblmeandClaude Opus 5.5 9bd622a5b5 Assistant answers render as markdown
react-markdown, lazy-loaded with the first answer (37 kB gzip chunk, main
bundle unchanged). No raw HTML, images dropped, links open in a new tab.
The system prompt asks for lists, inline code and fenced code blocks.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WgBfkm4rCmtd1T4vHWjEPx
2026-10-15 17:18:12 +02:00
stroblmeandClaude Fable 5.1 cc4091166e Add the assistant: a chat that drives the MCP tools in-process
Docs / docs (push) Successful in 42s
Playwright Tests / test-playwright (1, 2) (push) Failing after 2m42s
Playwright Tests / test-playwright (2, 2) (push) Failing after 10s
pre-commit / pre-commit (push) Failing after 2m33s
Test Backend / test-backend (push) Failing after 2m48s
Compose Smoke Test / test-compose (push) Failing after 9s
Playwright Tests / merge-reports (push) Failing after 2m17s
A provider set under Settings (OpenAI-compatible; key encrypted in
flow-data/ai.json) turns on an Assistant panel in the sidebar. Each turn runs
the FastMCP tools in-process as the person chatting, streams the rounds over
SSE and keeps one transcript per user. The panel floats on any screen and
shares the editor's lane: a settings panel keeps the top half, the chat the
bottom. The MCP client is now built once, for the endpoint and the chat.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-16 23:28:23 +02:00