Skip to content

ci(spec-sync): raise AI turn cap + exploration tools #103

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yzld2002 merged 3 commits into from
Jul 8, 2026
Merged

ci(spec-sync): raise AI turn cap + exploration tools #103

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d1e909b
ci(spec-sync): raise AI turn cap and give the agent exploration tools
yzld2002 Jul 8, 2026
1aa69e9
ci(spec-sync): resolve prompt git-diff contradiction; bump job timeou…
yzld2002 Jul 8, 2026
caf7a3e
Potential fix for pull request finding
yzld2002 Jul 8, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 16 additions & 9 deletions .github/workflows/spec-sync.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ jobs:
# secrets and would just produce noisy failing runs.
if: github.repository == 'landing-ai/ade-python'
runs-on: ubuntu-latest
timeout-minutes: 30
timeout-minutes: 60 # headroom for the AI wiring step (up to --max-turns 250) plus rye sync
env:
V1_SPEC_URL: https://api.va.staging.landing.ai/v1/ade/openapi.json # staging drives the loop
SYNC_BRANCH: spec-sync/v1 # fixed branch: reruns update one PR in place, never a pile of them
Expand Down Expand Up @@ -110,16 +110,23 @@ jobs:
github_token: ${{ secrets.SPEC_SYNC_TOKEN }}
prompt: |
The previous commit updated specs/v1-ade.json and regenerated reference models in
specs/_generated/v1_models.py. Edit the SDK to match the spec diff: add or adjust
resource classes, method signatures, param TypedDicts, response models, tests, api.md,
and README examples, mirroring the conventions in
src/landingai_ade/resources/parse_jobs.py. Then run `./scripts/format`.
specs/_generated/v1_models.py. Wire the SDK to match the spec diff.

First inspect the mechanical commit diff (`git diff HEAD~1..HEAD`) and read
src/landingai_ade/resources/parse_jobs.py — mirror its structure exactly for any
new resource (sync + async classes, the raw/streaming response wrappers, param
TypedDicts under src/landingai_ade/types/, response models, and registration in
src/landingai_ade/resources/__init__.py and the client). Add tests under
tests/api_resources/ and update api.md and the README examples. Then run
`./scripts/format` and `./scripts/lint` and fix anything they report.

Rules: PURELY ADDITIVE — never modify or remove an existing public signature (the
surface-lock CI job will fail the PR). Do NOT run git or push; a later workflow step
commits and pushes your edits.
surface-lock CI job will fail the PR). `git diff` (read-only, to inspect the change)
is fine; do NOT stage, commit, push, or run any other git command — a later workflow
step commits and pushes your edits.
claude_args: |
--max-turns 40
--allowedTools "Edit,Write,Read,Bash(rye *),Bash(./scripts/*)"
--max-turns 250
--allowedTools "Edit,Write,Read,Glob,Grep,Bash(rye *),Bash(./scripts/*),Bash(git diff:*)"
Comment thread
yzld2002 marked this conversation as resolved.
Comment on lines +128 to +129

# Deterministic: commit whatever the AI edited and push to the sync branch. This guarantees
# the AI changes actually reach the PR (the action's automation mode does not push), and it
Expand Down