feat(learning): add daily engineer-bot retrospective flow + bump engine to 654a31d0 - #442
Merged
Merged
Conversation
Turn on the engineer-bot learning loop for this repo, mirroring databricks-sql-python (the reference). Three parts: - engineer-bot-learning.yml (new): daily schedule (17:23 UTC) + workflow_dispatch (string since / window-hours recovery inputs). Own job sharing ./.github/actions/ bot-prelude for Python + pinned engine install, PAT-free. No setup-jfrog step: install-bot-engine self-mints its pip credential via OIDC and never reads PIP_INDEX_URL from env, so a setup-jfrog step would be redundant (the engine install is the only fetch; the learning flow runs no go build) and would leak a token-bearing PIP_INDEX_URL to the job env. actions:read added for Track B (lists engineer-bot author runs + downloads their logs via the App token). - .bot/config.yaml: add the retrospective block (log_path, branch_prefix, pr_label, plus the repo's existing prompts/retrospective_system.md as additive guidance) and close the loop with author.knowledge_log matching retrospective.log_path (.claude/knowledge/learning-log.md), so the author phase reads back what the retrospective learns. - bot-prelude: bump engine-ref d05dcb11 to 654a31d0 (engine main) so the pinned engine has the daily-cron retrospective + per-bot models. SDK/CLI (0.2.102 / 2.1.61) unchanged at that SHA, so this is a SHA-only bump. The schedule registers only once this lands on the default branch; validate before the first cron via a manual workflow_dispatch with a recent since. Co-authored-by: Isaac Signed-off-by: eric-wang-1990 <e.wang@databricks.com>
There was a problem hiding this comment.
Pull request overview
Enables the engineer-bot “daily learning / retrospective” loop for this repository by adding a scheduled + manually-dispatchable GitHub Actions workflow, wiring the retrospective configuration into .bot/config.yaml, and bumping the shared bot engine pin used by the bot prelude action.
Changes:
- Add a new scheduled (
cron) +workflow_dispatchworkflow to run the engine’s retrospective extractor and open/update a rolling learning PR. - Extend
.bot/config.yamlwithretrospective:configuration and connect it to the author phase viaauthor.knowledge_log. - Bump the pinned bot engine commit SHA in
./.github/actions/bot-prelude.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
.github/workflows/engineer-bot-learning.yml |
Introduces the daily learning workflow and execution wiring for the retrospective module. |
.bot/config.yaml |
Adds retrospective configuration and connects the learning log back into the author flow. |
.github/actions/bot-prelude/action.yml |
Updates the default engine commit SHA used by all bot workflows. |
Suppressed comments (1)
.bot/config.yaml:120
retrospective.system_promptpoints toprompts/retrospective_system.md, but this repository does not have aprompts/directory (nor aretrospective_system.mdanywhere). As written, the retrospective run is likely to fail when it tries to load the prompt, and the nearby comment claiming the file is “present in this repo” is currently incorrect.
# Omitting this block makes the retrospective a no-op. The system prompt is the
# engine's built-in base; prompts/retrospective_system.md (present in this repo) is
# appended as additive guidance.
retrospective:
system_prompt: prompts/retrospective_system.md
log_path: .claude/knowledge/learning-log.md # MUST match author.knowledge_log above
branch_prefix: ai/learning-pr-
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
![peco-review-bot[bot]](https://avatars.githubusercontent.com/in/3801177?s=60&v=4){kind=small}
There was a problem hiding this comment.
Verdict: 1 High · 1 Medium
CI/config onboarding PR. The workflow wiring is solid and faithfully mirrors the sibling bots (token minting via bot-prelude, persist-credentials:false + authenticated push remote, no setup-jfrog, single-sourced engine pin, actions: read for Track B, sane concurrency). The two real concerns are config keys pointing at files the PR says already exist but that are absent from the checkout: retrospective.system_prompt (F1, high) and the shared log_path/knowledge_log (F2, medium).
…is repo) The retrospective block pointed system_prompt at prompts/retrospective_system.md, which does not exist in this repo (only databricks-sql-kernel ships one; the sql-python reference correctly omits the key). The engine treats a set-but-missing system_prompt as a HARD ERROR, so the daily cron would fail every run. Drop the key so the flow uses the engine's built-in base prompt (engineer_prompts.RETRO_SYSTEM_PROMPT) — matching databricks-sql-python and the odbc learning PR. Also corrects the config comment, which wrongly claimed the file was "present in this repo." Caught by peco-review-bot on the sibling PRs. Co-authored-by: Isaac Signed-off-by: eric-wang-1990 <e.wang@databricks.com>
eric-wang-1990
added
the
engineer-bot
There was a problem hiding this comment.
Verdict: 1 Low
Clean, well-documented onboarding PR that mirrors the established sibling bot workflows (reviewer/engineer). Token wiring, shell safety, trigger surface, and config placement all check out. One low-severity note: the retrospective's model is left implicit (generic anthropic endpoint + no retrospective.model in config), unlike the other bots which pin an explicit model — worth confirming the engine default is intended.
`bin/golangci-lint` set `GOBIN=$(pwd)/bin`, but $(pwd) is a Make expression, not shell — Make expands the undefined `pwd` variable to EMPTY, so GOBIN was blank and `go install` fell back to the default bin dir (GOPATH/bin, which resolves to /bin on the protected runner) → `open /bin/golangci-lint: permission denied`, failing `make tools`. This only surfaced now because `make tools` runs on the protected runner solely via the engineer-bot build prelude, and engineer-bot was triggered on this repo for the first time (the `engineer-bot` label was just applied). The bug itself predates this PR (Makefile line unchanged since 2026-07-10). Use $(CURDIR) — Make's built-in absolute cwd — so golangci-lint installs into ./bin as intended. Verified via `make -n`: GOBIN now expands to the repo path. Co-authored-by: Isaac Signed-off-by: eric-wang-1990 <e.wang@databricks.com>
eric-wang-1990
added
engineer-bot
Addresses: - #3771947885 at .bot/config.yaml:99 - #3771952784 at .bot/config.yaml:122 Signed-off-by: peco-engineer-bot[bot] <peco-engineer-bot[bot]@users.noreply.github.com>
…t form The learning workflow set MODEL_ENDPOINT to `.../serving-endpoints/anthropic/invocations`. That is NOT translated the way the old comment claimed: sdk_agent.translate_endpoint has an early-return for URLs already containing `/serving-endpoints/anthropic`, which keeps the trailing `/invocations` — so the CLI appends `/v1/messages` and calls `.../serving-endpoints/anthropic/invocations/v1/messages`, which the gateway rejects with `400 Unsupported native API path`. Proof: databricks-sql-python's learning cron (same endpoint form) has failed every scheduled run with exactly this 400. The reviewer-bot flagged it on the sibling PRs (Low), and it is the real cause. Use the concrete `.../serving-endpoints/databricks-claude-opus-4-8/invocations` form that reviewer-bot.yml / engineer-bot.yml already use successfully: translate_endpoint strips `<model>/invocations` to the `.../serving-endpoints/ anthropic` base the CLI needs. Comment corrected to explain the trap. Co-authored-by: Isaac Signed-off-by: eric-wang-1990 <e.wang@databricks.com>
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
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.
What
Turn on the engineer-bot daily learning (retrospective) loop for this repo, mirroring
databricks-sql-python(the reference implementation). Three changes:.github/workflows/engineer-bot-learning.yml(new)schedule(17:23 UTC) +workflow_dispatch. Own job on./.github/actions/bot-prelude(Python + pinned engine install, PAT-free)..bot/config.yamlretrospective:block + close the loop withauthor.knowledge_log..github/actions/bot-prelude/action.ymlengine-refd05dcb11→654a31d0.Why
The other bots (reviewer, engineer, followups) were onboarded earlier; the retrospective was deliberately deferred. This adds it. Over an adaptive look-back window the engine gathers merged PRs + engineer-bot author-run logs itself and, if it finds durable learnings, opens one rolling PR (
ai/learning-pr) appending a dated section to.claude/knowledge/learning-log.md— human-gated, never committing the canonical log directly.Notes on the wiring
setup-jfrogstep — this repo'sinstall-bot-engineself-mints its pip credential via OIDC and never readsPIP_INDEX_URLfrom env, so a setup-jfrog step would be redundant (the engine install is the only fetch — the learning flow runs nogo build) and would leak a token-bearingPIP_INDEX_URLto the job env. Mirrors the read-only reviewer-bot.yml.actions: readadded for Track B (lists engineer-bot author runs + downloads their logs via the App token). The engineer-bot App installation must also carryactions:read, or the run 403s.author.knowledge_log==retrospective.log_path(.claude/knowledge/learning-log.md) — the retrospective writes it, the author reads it back. — the retrospective writes it, the author reads it back.system_promptis omitted (this repo ships noprompts/retrospective_system.md, so the engine's base prompt is used); the learning log is created on first write.0.2.102/2.1.61) are unchanged at654a31d0. Brings the daily-cron retrospective + per-bot models.Validation
The
scheduleregisters only once this lands on the default branch. Before the first cron, validate via a manual workflow_dispatch with a recentsince— it should open/update theai/learning-pr-*PR.This pull request and its description were written by Isaac.