Manuel/meeting-assistant
Public Access
1
0
Fork 0
Code Issues Pull Requests 4 Actions Packages Projects Releases Wiki Activity Open in Coder

Strengthen workflow automation diagnostics

Browse Source
This commit is contained in:
codex
2026-05-27 12:55:19 +02:00
parent b114071957
commit 2422236ef7
8 changed files with 629 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+3
View File
@@ -69,6 +69,7 @@ POST /recording/start
POST /recording/stop
POST /asr/transcribe-file
POST /asr/diarize-file
POST /diagnostics/workflow/reload
POST /meetings/current/summary/run
POST /meetings/summary/retry
GET /meetings/summary/retry?summaryPath=...
@@ -214,6 +215,8 @@ Assistant context notes keep their artifact links in frontmatter and expose a li
See `docs/meeting-workflow-engine.md` for the detailed YAML format, supported variables, examples, and extension notes.
`POST /diagnostics/workflow/reload` reloads application configuration so workflow automation settings such as `Automation:RulesPath` can be changed without restarting the application. A meeting run that already captured its options keeps using those options.
`Agent` configures the Microsoft Agent Framework summary pipeline. `Key` may be set directly for local testing, but `KeyEnv` is preferred; by default the API key is read from `LITELLM_API_KEY`. After transcription has fully finished, Meeting Assistant automatically runs the summary pipeline for the meeting. `ReconnectionAttempts` and `ReconnectionDelay` control retries for transient model endpoint failures such as LiteLLM token refresh or 5xx responses. If summary generation still fails, Meeting Assistant overwrites the configured summary note with a markdown failure report containing the exception details and linked meeting artifacts.
`ContextWindowTokens`, `MaxOutputTokens`, `EnableCompaction`, and `CompactionRemainingRatio` configure summary-agent context monitoring. Meeting Assistant estimates the outgoing Responses payload size, logs the estimated token count and remaining context, and compacts the conversation when only the configured remaining ratio is left. It first attempts `POST /v1/{ResponsesCompactPath}` on the configured OpenAI-compatible endpoint. If that endpoint is unavailable or returns invalid data, it falls back to Microsoft Agent Framework compaction: collapse old tool results, summarize older message groups, preserve only the last four user turns if needed, and finally drop oldest groups until the request is back under budget.