cleveragents/cleveragents-core
4
0
Fork 3
Code Issues 6.0k Pull Requests 115 Actions Packages Projects Releases Wiki Activity

#10042: Add fallback to Anthropic Haiku when OpenAI quota is exhausted #10043

Merged
HAL9000 merged 2 commits from feature/10042-openai-quota-fallback into master 2026-04-17 04:11:42 +00:00
Conversation 3 Commits 2 Files Changed 6
+401 -64
CoreRasurae commented 2026-04-16 18:17:30 +00:00
Member
Copy Link
Copy Source

Summary

Implements graceful degradation for E2E robot integration tests that hit OpenAI 429 quota limit errors.

Changes

  • Add _is_quota_error() helper to detect quota-specific API errors (429, insufficient_quota, rate_limit)
  • Modify _execute_with_llm() in StrategyActor to catch quota errors and attempt fallback to Anthropic Haiku
  • Configure fallback provider as 'anthropic/claude-3-5-haiku-20241022'
  • Add comprehensive logging for quota error detection and provider fallback
  • Add E2E test scenarios for quota fallback verification
  • Add 'Skip If No Fallback LLM Key' keyword for quota fallback tests

Impact

This ensures CI/CD pipelines can complete E2E tests even when the primary provider (OpenAI) hits quota limits, improving pipeline reliability and reducing false negatives caused by provider-specific issues.

Testing

  • All existing unit tests pass
  • All lint and type checks pass
  • New E2E test scenarios added for quota fallback verification

Related Issues

Fixes #10042

## Summary Implements graceful degradation for E2E robot integration tests that hit OpenAI 429 quota limit errors. ## Changes - Add `_is_quota_error()` helper to detect quota-specific API errors (429, insufficient_quota, rate_limit) - Modify `_execute_with_llm()` in StrategyActor to catch quota errors and attempt fallback to Anthropic Haiku - Configure fallback provider as 'anthropic/claude-3-5-haiku-20241022' - Add comprehensive logging for quota error detection and provider fallback - Add E2E test scenarios for quota fallback verification - Add 'Skip If No Fallback LLM Key' keyword for quota fallback tests ## Impact This ensures CI/CD pipelines can complete E2E tests even when the primary provider (OpenAI) hits quota limits, improving pipeline reliability and reducing false negatives caused by provider-specific issues. ## Testing - All existing unit tests pass - All lint and type checks pass - New E2E test scenarios added for quota fallback verification ## Related Issues Fixes #10042
CoreRasurae requested review from HAL9001 2026-04-16 18:18:45 +00:00
HAL9000 was assigned by CoreRasurae 2026-04-16 18:18:49 +00:00
CoreRasurae force-pushed feature/10042-openai-quota-fallback from 36428204df to 9f71f69890 2026-04-16 18:19:39 +00:00 Compare
CoreRasurae force-pushed feature/10042-openai-quota-fallback from 9f71f69890 to ac65fdb996 2026-04-16 18:22:12 +00:00 Compare
HAL9000 commented 2026-04-16 19:06:45 +00:00
Owner
Copy Link
Copy Source

@CoreRasurae — Thank you for the rapid turnaround on PR #10043. Filing the issue and submitting a fix within minutes is exactly the kind of responsiveness that keeps CI healthy.

Acknowledgment

This PR directly addresses the CI blocker identified in #10042. The approach is well-targeted:

  • _is_quota_error() helper for clean error detection
  • Fallback to anthropic/claude-3-5-haiku-20241022 on quota exhaustion
  • Comprehensive logging for observability
  • New E2E test scenarios for fallback verification

Impact

If this PR merges and CI passes, it will unblock:

  • PR #10000 (hamza.khyari — fix: clean up stale worktree branch)
  • PR #10002 (hamza.khyari — feat: plan diff using git worktree branch)
  • Any other PRs currently blocked by E2E quota failures

Next Steps

The PR has been received and is queued for automated review. Please ensure:

  1. CI passes on the current HEAD (especially the new E2E quota fallback scenarios)
  2. CHANGELOG.md includes an entry under [Unreleased] > Fixed
  3. CONTRIBUTORS.md is updated if not already present
  4. The commit footer includes ISSUES CLOSED: #10042

This will be prioritized for review given its CI blocker status.

Automated by CleverAgents Bot
Supervisor: Human Liaison | Agent: human-liaison-pool-supervisor
Worker: [AUTO-HUMAN-3]

@CoreRasurae — Thank you for the rapid turnaround on PR #10043. Filing the issue and submitting a fix within minutes is exactly the kind of responsiveness that keeps CI healthy. ## Acknowledgment This PR directly addresses the CI blocker identified in #10042. The approach is well-targeted: - `_is_quota_error()` helper for clean error detection - Fallback to `anthropic/claude-3-5-haiku-20241022` on quota exhaustion - Comprehensive logging for observability - New E2E test scenarios for fallback verification ## Impact If this PR merges and CI passes, it will unblock: - PR #10000 (hamza.khyari — fix: clean up stale worktree branch) - PR #10002 (hamza.khyari — feat: plan diff using git worktree branch) - Any other PRs currently blocked by E2E quota failures ## Next Steps The PR has been received and is queued for automated review. Please ensure: 1. CI passes on the current HEAD (especially the new E2E quota fallback scenarios) 2. `CHANGELOG.md` includes an entry under `[Unreleased] > Fixed` 3. `CONTRIBUTORS.md` is updated if not already present 4. The commit footer includes `ISSUES CLOSED: #10042` This will be prioritized for review given its CI blocker status. --- **Automated by CleverAgents Bot** Supervisor: Human Liaison | Agent: human-liaison-pool-supervisor Worker: [AUTO-HUMAN-3]
HAL9000 added the
State
In Review
Type
Bug
MoSCoW
Must have
Priority
CI Blocker
 labels 2026-04-16 19:12:24 +00:00
CoreRasurae force-pushed feature/10042-openai-quota-fallback from ac65fdb996 to f99fd631ea 2026-04-16 19:58:16 +00:00 Compare
CoreRasurae force-pushed feature/10042-openai-quota-fallback from 6f669efd91 to 361afdfe8d 2026-04-16 20:52:34 +00:00 Compare
brent.edwards reviewed 2026-04-16 22:07:58 +00:00
src/cleveragents/application/services/strategy_actor.py Outdated
@@ -498,3 +523,3 @@
# Retry loop for transient LLM failures
content = self._invoke_llm_with_retry(llm, messages, plan_id)
try:
brent.edwards commented 2026-04-16 22:07:58 +00:00
Member
Copy Link
Copy Source

Hi Luis (or the bot) --

This changes the code from only using llm to the following:

  • Try using llm
  • If there is a quota error:
    • Create a fallback LLM
    • Try the fallback LLM

There are two obvious ways to improve the code:

  1. fallback_llm doesn't need to be recreated every time. It's fine to create it as a global variable.
  2. Losing quota will not change rapidly. Every time that you send a message through this function, you'll first get a quota error -- then try the other LLM. It would be faster in general if:

2.1 Set the llm variable to the fallback provider, fallback model.
2.2 If it's been, say, 5 minutes since the last time that the quota has been checked, set llm to the old llm and see whether it's been solved.

Hi Luis (or the bot) -- This changes the code from only using `llm` to the following: - Try using llm - If there is a quota error: - - Create a fallback LLM - - Try the fallback LLM There are two obvious ways to improve the code: 1. `fallback_llm` doesn't need to be recreated every time. It's fine to create it as a global variable. 2. Losing quota will not change rapidly. Every time that you send a message through this function, you'll first get a quota error -- then try the other LLM. It would be faster in general if: 2.1 Set the `llm` variable to the fallback provider, fallback model. 2.2 If it's been, say, 5 minutes since the last time that the quota has been checked, set `llm` to the old llm and see whether it's been solved.
CoreRasurae force-pushed feature/10042-openai-quota-fallback from 5ff0c0c4bb to 8703ddc4d2 2026-04-16 22:35:08 +00:00 Compare
brent.edwards approved these changes 2026-04-16 22:43:50 +00:00
brent.edwards left a comment
Member
Copy Link
Copy Source

I approve; thank you for listening to my suggested change.

I approve; thank you for listening to my suggested change.
CoreRasurae force-pushed feature/10042-openai-quota-fallback from 8703ddc4d2 to 5beadc1301 2026-04-16 23:00:06 +00:00 Compare
HAL9000 force-pushed feature/10042-openai-quota-fallback from 53dfda239b to 2fc57f1f07 2026-04-17 02:59:16 +00:00 Compare
HAL9000 force-pushed feature/10042-openai-quota-fallback from 2fc57f1f07 to 51472c0b37 2026-04-17 03:56:37 +00:00 Compare
HAL9000 scheduled this pull request to auto merge when all checks succeed 2026-04-17 03:56:54 +00:00
HAL9000 merged commit 51472c0b37 into master 2026-04-17 04:11:42 +00:00
Sign in to join this conversation.
Reviewers
No Reviewers
HAL9001
brent.edwards
Labels
Clear labels
auto/needs-reevaluation
Controller deferred this PR; awaiting Phase 6+ scope-evaluator or operator re-enablement.
 controller-managed
Auto-agents controller manages this PR/issue (see tools/controller/deploy/RUNBOOK.md). Remove this label to abandon controller management.
 overdue
auto/blocked-by-deps
PR blocked by an open issue dependency. Operator must close the dep (or remove the dependency link) before the merge driver can act. Auto-cleared by merge_drive when no open deps remain.
 auto/ci-timeout
Most recent merge cycle hit CI timeout. Driver excludes this PR while last merge_cycle row is < 30 min old; label persists thereafter as visible history.
 auto/claimed-implementer
Currently being processed by an implementer worker.
 auto/claimed-merge
Currently being processed by the merge driver.
 auto/claimed-reviewer
Currently being processed by a reviewer worker.
 auto/driver-down
Merge driver heartbeat stale; pipeline halted. Closed automatically on next clean tick.
 auto/invariant-violation
Detected master commit violating the strict merge invariant. Tracked as an issue (not a PR label); kept here for label completeness.
 auto/last-attempt-tier-0
In-cycle escalation: most recent attempt ran at the Tier 0 slot (`tier-0`). Slot's model defined in .opencode/models/tiers.yaml.
 auto/last-attempt-tier-1
In-cycle escalation: most recent attempt ran at the Tier 1 slot (`tier-1`). Slot's model defined in .opencode/models/tiers.yaml.
 auto/last-attempt-tier-2
In-cycle escalation: most recent attempt ran at the Tier 2 slot (`tier-2`). Slot's model defined in .opencode/models/tiers.yaml. Gated behind IMPLEMENTER_ESCALATION_TIER2_ENABLED.
 auto/last-attempt-tier-min
In-cycle escalation: most recent attempt ran at the Tier -1 slot (`tier-min`). Slot's model defined in .opencode/models/tiers.yaml. Suffix is ``-min`` (not ``--1``) so the Forgejo UI reads naturally.
 Automation Tracking
Tracking issues used by the AI Automation system for agents to communicate and report.
 auto/needs-conflict-resolution
Rebase conflict needs LLM conflict-resolver.
 auto/needs-implementer
Failing CI needs implementer attention.
 auto/postmortem
Documenting a driver incident or rollback.
 auto/ready-to-merge
Reviewer has APPROVED this PR and no later REQUEST_CHANGES is outstanding. The merge driver requires this label to even consider a PR for merging. Set by the reviewer worker on APPROVE; cleared on REQUEST_CHANGES.
 auto/restart-throttled
Train repeatedly lost master-tempo races. Driver excludes via merge_cycle until cooldown elapses; label persists as visible history.
 auto/revert
Revert PR backing out an invariant violation. Fast-tracked through the merge driver.
 auto/sentinel
Sentinel PR duplicated from upstream into a personal fork by tools/duplicate_prs_to_fork.py for pipeline testing. Lives only in the fork; the canonical pipeline never sees it.
 auto/stale-inactivity
No implementer activity for N days. Flagged for human review. Auto-cleared on next push to head branch.
 auto/unstable
Repeatedly fails on current master (>= 3 ci-fail-on-rebased-sha releases in 12 h). Excluded from driver until human triage.
 Blocked
A ticket in a blocked state and unable to complete until some other task is completed first.
Bounty
$100
A bounty of $100 for any open-source contributor who provides a MR that solves this issue
Bounty
$1000
A bounty of $1000 for any open-source contributor who provides a MR that solves this issue
Bounty
$10000
A bounty of $10000 for any open-source contributor who provides a MR that solves this issue
Bounty
$20
A bounty of $20 for any open-source contributor who provides a MR that solves this issue
Bounty
$2000
A bounty of $2000 for any open-source contributor who provides a MR that solves this issue
Bounty
$250
A bounty of $250 for any open-source contributor who provides a MR that solves this issue
Bounty
$50
A bounty of $50 for any open-source contributor who provides a MR that solves this issue
Bounty
$500
A bounty of $500 for any open-source contributor who provides a MR that solves this issue
Bounty
$5000
A bounty of $5000 for any open-source contributor who provides a MR that solves this issue
Bounty
$750
A bounty of $750 for any open-source contributor who provides a MR that solves this issue
MoSCoW
Could have
Could have feature in order to satisfy the epic/legendary.
MoSCoW
Must have
Must have feature in order to satisfy the epic/legendary.
MoSCoW
Should have
Should have feature in order to satisfy the epic/legendary.
Needs Feedback
There are questions in the ticket that can not be completed until the project owner provides clarity.
Points
1
1 man-hours worth of work for an expert with no learning curve.
Points
13
13 man-hours worth of work for an expert with no learning curve.
Points
2
2 man-hours worth of work for an expert with no learning curve.
Points
21
21 man-hours worth of work for an expert with no learning curve.
Points
3
3 man-hours worth of work for an expert with no learning curve.
Points
34
34 man-hours worth of work for an expert with no learning curve.
Points
5
5 man-hours worth of work for an expert with no learning curve.
Points
55
55 man-hours worth of work for an expert with no learning curve.
Points
8
8 man-hours worth of work for an expert with no learning curve.
Points
88
88 man-hours worth of work for an expert with no learning curve.
Priority
Backlog
This ticket has backlogged priority and is not to be worked on yet
Priority
CI Blocker
Critical priority issue that blocks CI/CD pipeline and prevents PR merges
Priority
Critical
The priority is critical
Priority
High
The priority is high
Priority
Low
The priority is low
Priority
Medium
The priority is medium
Signed-off: Owner
When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.
 Signed-off: Scrum Master
When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.
 Signed-off: Tech Lead
When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.
 Spike
A ticket for learning a tool or technology that is needed to be able to do future planning and design.
State
Completed
The ticket has been fully implemented, completed, and merged with the source code. This label should only be applied once a ticket is closed.
State
Duplicate
A ticket that represents the same content as an existing ticket.
State
In Progress
A ticket that is actively being developed.
State
In Review
A ticket that has had some code completed to implement but is waiting to pass peer review and is not yet merged in.
State
Paused
This ticket's work started but wasn't finished. It's on hold (likely in a feature branch) and will be resumed later, either due to a blocker or a delay.
State
Unverified
All new tickets start in this state. A developer may set it to show the ticket is unverified. This means we haven't agreed to work on it. It will either move to a verified state or be closed as wontdo.
State
Verified
The issue has been verified by a developer as legitimate. It will be worked on and verified tickets are now considered part of the backlog.
State
Wont Do
This ticket has been decided it wont be done. This may mean the bug has been determined to not be real (cant verify) or the feature is one we have decided we dont want to adopt.
Type
Automation
Any edits or discussion about the AI automated coding system.
Type
Bug
Something that doesnt work as intended.
Type
Discussion
Anytime a ticket represents a discussion about a subject and doesnt fall into one of the other categories.
Type
Documentation
An error or improvement needed in the documentation.
Type
Epic
Any first tier epic. That is, an epic which contains only issues as children and will not have sub-epics.
Type
Feature
Some new functionality not present.
Type
Legendary
A type of Epic which will contain other Epics.
Type
Refactor
A code change that restructures existing code without changing its external behavior.
Type
Support
Someone needs help using the project.
Type
Task
A generic task that doesnt fit into the other type categories.
Type
Testing
Work exclusively focusing on fixing or expanding testing.
No Label
MoSCoW
Must have
Priority
CI Blocker
State
In Review
Type
Bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
aditya (Aditya Chhabra) aleenaumair (Aleena Umair) brent.edwards (Brent Edwards) CoreRasurae (Luis Mendes) drew (Drew Morris) eugen.thaci (Eugen Thaci) freemo (Jeffrey Phillips Freeman) HAL9000 (HAL 9000) HAL9001 (HAL9001) hamza.khyari (Hamza Khyari) hurui200320 (Rui Hu) justin.morris khird (Kyle Hird) org.cleveragents
No Assignees HAL9000
3 Participants
Notifications
Due Date
No due date set.
Blocks
#10042 [CI BLOCKER] Add fallback to Anthropic Haiku when OpenAI E2E tests hit quota limits
cleveragents/cleveragents-core
Reference: cleveragents/cleveragents-core#10043
Delete Branch "feature/10042-openai-quota-fallback"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?