feat(research): sin-code research — autonomous research-report generation (#384) - #401
Closed
Delqhi wants to merge 1 commit into
Closed
feat(research): sin-code research — autonomous research-report generation (#384)#401Delqhi wants to merge 1 commit into
Delqhi wants to merge 1 commit into
Conversation
…#384) Adds the search -> fetch -> synthesize pipeline as a goal template that the autonomy daemon (v3.5.0) can drive end-to-end. The new 'sin-code research <topic>' subcommand enqueues a goal with a Definition-of-Done contract; every successful pipeline run lands a citation-grounded Markdown report under .sin-code/reports/<slug>.md. Stack: - cmd/sin-code/internal/autonomy/research_report.go ResearchReport, Source, Searcher/Fetcher/LLM interfaces, Generator pipeline + byte-stable Validate. Pluggable StaticSearcher/StaticLLM for hermetic tests. HTTPFetcher wired to stdlib net/http with a hard byte cap. - cmd/sin-code/research_cmd.go cobra subcommand with --priority, --retries, --sources, --fetch-bytes, --out-dir, --dry-run, --json, --frontmatter, --criteria. Enqueues the goal via Queue.AddWithContract. - internal/permission_defaults.go research__run -> ask (M4); research__dry_run / list / show -> allow. research__* catch-all -> ask to keep headless modes gated. - main.go NewResearchCmd() registered as the 43rd subcommand (v3.23.0). Tests (cmd/sin-code/internal/autonomy/research_report_test.go): - TestResearchReportGeneration: 3-source happy path, Body + Sources. - TestResearchReportSlug: 7 inputs incl. truncation + determinism. - TestResearchReportMarkdown: Body isValid via Validate() rejects whitespace + header-less + nil. - TestResearchReportWiringGuards: nil gen, nil LLM, empty topic, LLM + searcher error, empty sources. - TestResearchReportDedupRank: dedup URL + longest-snippet upgrade. - TestResearchReportFrontmatter: deterministic 2026-06-18 timestamp. go build ./cmd/sin-code/internal/autonomy -> OK go test -race -count=1 ./cmd/sin-code/internal/autonomy -> PASS (all 6 + regression suite)
Contributor
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Collaborator
Author
|
Superseded by #408 — the research-report feature was cherry-picked cleanly onto a branch that also repairs the main build drift caused by parallel-agent WIP. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Autonomous report via websearch + fetch + LLM synthesis. 6 tests race-clean.