* feat: daily docs-sync bot workflow (Kilo CLI) Adds a scheduled workflow that keeps packages/kilo-docs in sync with PRs merged to Kilo-Org/cloud and Kilo-Org/kilocode: - watermark.mjs derives the processing window from the bot's own PR body marker (self-healing, no external state; 72h fallback, 14d cap) - collect.mjs queries merged PRs via the GitHub API and applies a deterministic pre-filter (bots, chores, docs-only PRs) - triage.mjs classifies PRs in chunks of 25 with kilo run; failed chunks degrade to unclassified instead of failing the run - edit.mjs updates docs in batches of 5 PRs with kilo run, bounded per batch; failures surface as skipped entries in the PR body - verify runs the kilo-docs build + test suite; one LLM fix pass on failure; still-red becomes a draft PR - upsert-pr.mjs maintains one rolling auto-docs PR (appends while open, fresh branch after merge), with a 15-file draft cap and a machine-readable processed-through watermark Also adds docs-sync.yml to the workflow allowlist in script/check-workflows.ts. * fix: correct kilo run invocation and auth - message positional must come before flags: --file is multi-value and consumes a trailing message as a file path (File not found) - authenticate via the existing KILO_API_KEY repo secret (the kilo provider reads it natively); drop the DOCS_SYNC_KILO_CONFIG config secret requirement - fix default model IDs: gateway provider id is kilo/, not kilocode/ - include stderr tail in triage/edit failure logs * fix: handle kilo run double-printed assistant output kilo run prints the assistant message twice (streaming render + final summary), so stdout can contain the same JSON array back-to-back. Parse the largest valid trailing array instead of slicing first-to-last bracket. Verified against real chunked triage output. * fix: reviewer-pass robustness fixes - edit.mjs: unambiguous summary file path in the batch prompt and a fallback read when the agent drops the docs-sync-out/ prefix, so real edits never report as skipped - prepare-branch.mjs: use the open auto-docs PR's actual head.ref instead of assuming docs/auto-sync - upsert-pr.mjs: compute the 15-file draft cap on the cumulative PR diff (origin/main...HEAD), not just the latest commit * fix: address Kilobot review findings Security: - sanitize HTML-comment sequences out of agent-generated PR body values so a crafted value cannot forge section markers or the watermark - draft any PR whose diff touches non-content files in packages/kilo-docs (outside pages/ and lib/nav/) — build-executable changes force human review before merge - on merge conflict, keep the conflicted rolling branch untouched (preserving human commits) and continue on a fresh dated branch that links the old PR Resilience: - retry GitHub API calls on network errors and 5xx, not just 403 rate limits - isolate per-PR collect failures instead of aborting the run - trust watermark markers only on bot-authored PRs and clamp future dates loudly - validate chunk triage entries belong to their chunk before the shared dedupe - use changed_files for files_total and skip docs-only classification on truncated (300+) file lists - pipe stderr in the edit pass so failure warnings carry the real CLI error * fix: address second Kilobot review round - escape pipe characters in changeRow actions (same as skippedRow) - sanitize agent-chosen file paths before they land in draftReasons and the PR body (residual marker-forgery path via filenames) - log expected fetch misses in prepare-branch instead of silent catches * feat: keep bot-authored PRs in the docs-sync digest Release and dependency bots ship user-facing changes (e.g. JetBrains release PRs from kilo-maintainer[bot]). The auto-docs label check and docs-only path filter remain as the loop guards.
2.3 KiB
You are the Kilo Code documentation bot. You update the public product documentation in packages/kilo-docs (a Markdoc/Next.js site served at kilo.ai/docs) so it reflects recently merged PRs. You are handling one batch of PRs; the batch files and your output file are named at the end of these instructions.
Before writing anything:
- Read
packages/kilo-docs/AGENTS.mdandpackages/kilo-docs/STYLE_GUIDE.mdand follow them exactly: Markdoc custom tags, the/docsprefix in image paths, navigation files underlib/nav/, redirect rules, and the generated-screenshot policy. - Read the attached batch files: the full-details file (PR title, body, file list,
patch_excerptdiffs) and the triage file (docs-worthiness verdicts, target sections, priorities).
For each PR in the batch, in priority order:
- Find the most relevant existing docs page(s) and make minimal, precise updates in the style of the surrounding content.
- Create a new page only when no existing page fits; then add it to the matching nav file in
packages/kilo-docs/lib/nav/. - Document only behavior that is actually present in the merged diff. If the PR body or diff shows the feature is behind a flag or otherwise not user-visible yet, skip it and record why.
- If a PR turns out not to need documentation, skip it and record why. Trust evidence over the triage verdict.
Hard rules:
- Only create or modify files under
packages/kilo-docs/. Never touch code, tests, config, images, or anything outside that directory. - Never remove or rename pages. Never document unreleased behavior. Never copy internal PR discussion into the docs; write user-facing documentation.
- Do not run git commands and do not commit anything; automation handles git.
- Keep the change small and precise. Do not rewrite sections that are already accurate.
When finished, write the summary JSON file named in the batch specifics below: a JSON array with exactly one entry per batch PR, consumed by automation (this file is never committed). Use action values like updated <path>, created <path>, or skipped. Example:
[{"pr": 123, "url": "https://github.com/Kilo-Org/kilocode/pull/123", "action": "updated pages/code-with-ai/platforms/cli.md", "reason": "documented --variant flag"}, {"pr": 124, "url": "https://github.com/Kilo-Org/kilocode/pull/124", "action": "skipped", "reason": "feature behind unreleased flag"}]