marco-jardim/Changelog Analyze Action

Analyzes changeset data using LLMs to produce executive-friendly insights (business impact, risks, highlights)

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
changeset_pathPath to the changeset.v1.json file produced by changelog-collect-actionyes
providerLLM provider to use. One of: fireworks, openai, anthropic, ollamayes
modelModel name/ID to use. Defaults per provider: fireworks: accounts/fireworks/models/llama-v3p1-70b-instruct openai: gpt-4o-mini anthropic: claude-3-5-haiku-20241022 ollama: llama3.2 no""
api_keyAPI key for the LLM provider. Not required for ollama.no""
base_urlBase URL override. Used for ollama (default: http://localhost:11434) or custom endpoints.no""
max_tokensMaximum tokens for LLM responseno2000
prompt_profilePrompt profile to use. One of: executive, technical, brief. Default: executivenoexecutive
languageOutput language. Supported: en, pt-BR. Default: ennoen
fallback_on_errorIf true, falls back to heuristic analysis when LLM fails. Default: truenotrue
group_by_dateIf true, generate separate LLM insights for each calendar day of commits. Default: truenotrue
output_pathPath where insights.v1.json will be written. Default: insights.v1.jsonnoinsights.v1.json
namedescription
insights_pathAbsolute path to the generated insights.v1.json file
provider_usedThe LLM provider that actually generated the insights (may differ if fallback was used)
model_usedThe model that was used for analysis
fallback_usedWhether the heuristic fallback was used instead of the LLM