feat(workflows): add dynamic until loops#36
Merged
Conversation
📝 WalkthroughWalkthroughThis PR adds workflow ChangesUntil condition feature
Executable resolution
Release version update
Estimated code review effort: 4 (Complex) | ~60 minutes Sequence Diagram(s)sequenceDiagram
participant CreateRunCommand
participant WorkflowRunner
participant ExecuteSteps
participant EvaluateUntil
participant RunJson
CreateRunCommand->>WorkflowRunner: onUntilStart / onUntilResult callbacks
WorkflowRunner->>ExecuteSteps: executeSteps(workflow.until)
loop each iteration
ExecuteSteps->>ExecuteSteps: run leaf and group steps
ExecuteSteps->>EvaluateUntil: evaluate until condition
EvaluateUntil-->>ExecuteSteps: satisfied or continue
end
ExecuteSteps->>RunJson: persist satisfiedAt
WorkflowRunner-->>CreateRunCommand: printSummary
Possibly related PRs
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@src/providers/workflow-discovery.ts`:
- Around line 376-379: The `!typeKey` guard in `getUntil` is unreachable because
`typeKeys` has already been validated to contain exactly one entry earlier in
the same flow. Remove the dead `if (!typeKey)` branch and keep the existing
`typeKeys[0]` selection and return path, using the `workflow-discovery` logic
around `typeKeys` and `typeKey` as the place to update.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: eb2b31bc-ec78-4035-87a9-303daf431dc8
📒 Files selected for processing (13)
defaults/system/workflows/review-and-fix.yamlsrc/commands/run.tssrc/domain/workflow.tssrc/providers/workflow-discovery.tssrc/services/workflow-runner.tstest/e2e/claudecode.shtest/e2e/codex.shtest/e2e/lib/workflow-until.shtest/e2e/opencode.shtest/e2e/pi.shtest/unit/commands/run.test.tstest/unit/providers/workflow-discovery.test.tstest/unit/services/workflow-runner.test.ts
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@CHANGELOG.md`:
- Line 14: Tighten the wording in the changelog sentence by replacing the phrase
“by accident” with a more concise alternative such as “unintentionally” or
“accidentally” in the note about `until: { prompt: ... }`, keeping the rest of
the explanation intact.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: 95ba64f9-f953-41cf-8e4d-f408eac26d30
📒 Files selected for processing (12)
CHANGELOG.mdREADME.mddefaults/config.jsonpackage.jsonsrc/providers/agent-runner.tssrc/providers/workflow-discovery.tssrc/services/provider-detection.tstest/unit/domain/version.test.tstest/unit/hooks/format-reminder.test.tstest/unit/services/init-service.test.tstest/unit/services/setup-session.test.tstest/unit/services/workflow-runner.test.ts
jgmontoya
force-pushed
the
feat/workflow-until
branch
from
July 8, 2026 19:36
a800189 to
17d5307
Compare
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@src/providers/agent-runner.ts`:
- Around line 11-19: The PATH lookup logic is duplicated between agent execution
and provider detection, so extract it into a shared helper and reuse it in both
places. Move the existing whichOnCurrentPath behavior from provider-detection.ts
into a common utility such as resolveOnCurrentPath or a shared which module,
then have agent-runner.ts use that helper instead of calling Bun.which inline so
both code paths stay in sync.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: f84c6349-e909-46fa-aa20-ecb1ece9815e
📒 Files selected for processing (9)
src/providers/agent-runner.tssrc/providers/workflow-discovery.tssrc/services/provider-detection.tstest/unit/hooks/format-reminder.test.tstest/unit/platform/process-runner.test.tstest/unit/services/autoresearch.test.tstest/unit/services/setup-session.test.tstest/unit/services/uninstall-service.test.tstest/unit/services/workflow-runner.test.ts
jgmontoya
force-pushed
the
feat/workflow-until
branch
from
July 9, 2026 21:49
17d5307 to
fc92625
Compare
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
test/unit/services/workflow-runner.test.ts (1)
593-614: 🎯 Functional Correctness | 🟠 Major | ⚡ Quick winSkip POSIX-only
untiltests on Windows.Three
untilintegration tests use POSIX shell commands (test -f,test "..." = "...",printf) but are not wrapped intest.skipIf(process.platform === "win32"), unlike the adjacent tests at lines 511, 694, 725, 756, and 1031. On Windows (cmd.exe), these commands don't exist, causing theuntilcondition to fail with a non-zero exit code — the workflow never satisfies, and assertions onsatisfiedAt/ callback events will fail.🔧 Proposed fix: wrap POSIX-only tests with skipIf
- test("until condition resolves current iteration step templates", async () => { + test.skipIf(process.platform === "win32")( + "until condition resolves current iteration step templates", + async () => { // ... test body unchanged ... - }); + }, + );- test("workflow loop 1 with until evaluates once and records satisfaction", async () => { + test.skipIf(process.platform === "win32")( + "workflow loop 1 with until evaluates once and records satisfaction", + async () => { // ... test body unchanged ... - }); + }, + );- test("until progress callbacks report start and result", async () => { + test.skipIf(process.platform === "win32")( + "until progress callbacks report start and result", + async () => { // ... test body unchanged ... - }); + }, + );Also applies to: 641-663, 665-692
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@test/unit/services/workflow-runner.test.ts` around lines 593 - 614, The POSIX-only `until` test in `workflow-runner.test.ts` uses shell commands that fail on Windows, so wrap this `until` case in `test.skipIf(process.platform === "win32")` like the adjacent platform-gated tests. Apply the same guard to the other affected `until` tests in the file that use `run` commands such as `test -f`, `test "..." = "..."`, and `printf`, so `runWorkflow` assertions like `metadata.satisfiedAt` only run where the commands are supported.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Outside diff comments:
In `@test/unit/services/workflow-runner.test.ts`:
- Around line 593-614: The POSIX-only `until` test in `workflow-runner.test.ts`
uses shell commands that fail on Windows, so wrap this `until` case in
`test.skipIf(process.platform === "win32")` like the adjacent platform-gated
tests. Apply the same guard to the other affected `until` tests in the file that
use `run` commands such as `test -f`, `test "..." = "..."`, and `printf`, so
`runWorkflow` assertions like `metadata.satisfiedAt` only run where the commands
are supported.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: 10fbfffc-e37d-4a7d-8361-955608822b27
📒 Files selected for processing (11)
src/platform/paths.tssrc/providers/agent-runner.tssrc/providers/workflow-discovery.tssrc/services/provider-detection.tstest/unit/hooks/format-reminder.test.tstest/unit/platform/paths.test.tstest/unit/platform/process-runner.test.tstest/unit/services/autoresearch.test.tstest/unit/services/setup-session.test.tstest/unit/services/uninstall-service.test.tstest/unit/services/workflow-runner.test.ts
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.
Summary by CodeRabbit
runsuccess or prompt verdict satisfaction.