fix(nodes): propagate ExecutionError from retry mechanism instead of swallowing it #72

Merged

CoreRasurae merged 1 commit from fix/nodes-executionerror-propagation into master 2026-07-07 16:06:09 +00:00

Conversation 2 Commits 1 Files changed 6 +290 -3

CoreRasurae commented 2026-07-06 17:55:00 +00:00

Member

Copy link

Summary

Fixes a bug where ExecutionError(kind="timeout") raised by call_with_retry() when all LLM communication retries are exhausted was systematically swallowed by broad except Exception handlers in Node._execute_agent() and Node.execute(). The timeout was converted into an error string in graph state or — in the streaming path — an empty response, making the retry mechanism ineffective.

Changes

• src/cleveractors/langgraph/nodes.py: Added targeted except ExecutionError as e handlers that check e.kind == "timeout" and re-raise. Non-timeout ExecutionError instances (tool errors, etc.) continue to be caught gracefully, preserving existing behavior for non-retry errors.
• BDD tests (features/nodes_coverage_gaps.feature): Two new scenarios verify timeout propagation and non-timeout graceful handling.
• CHANGELOG.md: Added entry documenting the fix.

Related

• Closes #71
• ADR-2032: LLM Agent Communication Retry Mechanisms (defines the retry contract that was being violated)

Verification

• ✅ Lint, format, typecheck, security, deadcode: all pass
• ✅ 2742 BDD scenarios pass
• ✅ 319 Robot integration tests pass
• ✅ Coverage: 96.9% (threshold: 96.5%)

## Summary Fixes a bug where `ExecutionError(kind="timeout")` raised by `call_with_retry()` when all LLM communication retries are exhausted was systematically swallowed by broad `except Exception` handlers in `Node._execute_agent()` and `Node.execute()`. The timeout was converted into an error string in graph state or — in the streaming path — an empty response, making the retry mechanism ineffective. ## Changes - **`src/cleveractors/langgraph/nodes.py`**: Added targeted `except ExecutionError as e` handlers that check `e.kind == "timeout"` and re-raise. Non-timeout `ExecutionError` instances (tool errors, etc.) continue to be caught gracefully, preserving existing behavior for non-retry errors. - **BDD tests** (`features/nodes_coverage_gaps.feature`): Two new scenarios verify timeout propagation and non-timeout graceful handling. - **CHANGELOG.md**: Added entry documenting the fix. ## Related - Closes #71 - ADR-2032: LLM Agent Communication Retry Mechanisms (defines the retry contract that was being violated) ## Verification - ✅ Lint, format, typecheck, security, deadcode: all pass - ✅ 2742 BDD scenarios pass - ✅ 319 Robot integration tests pass - ✅ Coverage: 96.9% (threshold: 96.5%)

CoreRasurae added 1 commit 2026-07-06 17:55:00 +00:00

fix(nodes): propagate ExecutionError from retry mechanism instead of swallowing it ... bcc3b5e459

When all LLM communication retries are exhausted, call_with_retry() raises
ExecutionError(kind=\"timeout\"). Two broad except Exception handlers in
Node._execute_agent() and Node.execute() systematically caught this,
converting the timeout into an error string in graph state or — in the
streaming path — an empty response.

Added targeted except ExecutionError as e handlers that check
e.kind == \"timeout\" and re-raise. Non-timeout ExecutionError instances
(tool errors, etc.) continue to be caught and converted to error strings
for graceful graph continuation.

Two new BDD scenarios verify:
- ExecutionError(kind=\"timeout\") propagates with correct kind/reason
- Non-timeout ExecutionError is still caught gracefully

ISSUES CLOSED: #71

CoreRasurae added a new dependency 2026-07-06 17:55:51 +00:00

#71 ConnectionError retry exhaustion silently swallowed, producing empty response instead of propagating ExecutionError

CoreRasurae added the

Type

Bug

label 2026-07-06 17:57:33 +00:00

hurui200320 approved these changes 2026-07-07 05:07:06 +00:00

hurui200320 left a comment

Copy link

PR Review: !72 (Ticket #71)

Verdict: Approve

The fix correctly addresses the reported bug. ExecutionError(kind="timeout") raised when the LLM retry mechanism exhausts its budget is now propagated from both Node._execute_agent() and Node.execute() instead of being swallowed by broad except Exception handlers. The implementation is narrower than the ticket's initial "propagate all ExecutionError" sketch, but that narrower scope is intentional and safer: it preserves the existing graceful handling of non-timeout execution errors (e.g., tool parsing failures) while ensuring retry-exhaustion timeouts surface to the caller as required by ADR-2032.

No critical or major correctness issues were found. I also checked the PR and ticket comment threads; there are no existing reviewer comments or author responses that would remove items from scope.

Critical Issues

None.

Major Issues

None.

Minor Issues

None.

Nits

None.

Summary

The PR adds a targeted except ExecutionError as e clause in front of the existing broad except Exception handlers in Node.execute() and Node._execute_agent(). When e.kind == "timeout", the exception is re-raised so it can propagate through PureLangGraph._execute_from_node() (whose existing handler at pure_graph.py:983 already expects limit-enforcement errors to surface) and up to the router with the correct HTTP mapping. Non-timeout ExecutionError instances continue down the original graceful path and are converted to error strings in graph state.

The logic is sound:

• The retry mechanism in call_with_retry() raises ExecutionError(kind="timeout", reason="...") per ADR-2032 D-7.
• LLMAgent.process_message() already preserves kind/reason when re-raising an inner ExecutionError, so the timeout identity survives the agent layer.
• The new handlers sit in the correct exception-precedence order (ExecutionError before Exception) and the current_graph_name ContextVar is still reset in the finally block on the timeout path.
• The BDD scenarios added verify both the propagation path and the preservation of graceful handling for non-timeout errors.

The only behavior change worth being aware of is that non-timeout ExecutionError no longer reaches the node-level retry_policy loop in Node.execute(). In practice this is correct behavior—execution-limit/failure errors should not be retried like transient exceptions—but it is a subtle narrowing of the retry_policy contract. No current node type appears to rely on the old behavior. Overall, the change is minimal, focused, and fixes the reported regression without introducing new risks.

## PR Review: !72 (Ticket #71) ### Verdict: Approve The fix correctly addresses the reported bug. `ExecutionError(kind="timeout")` raised when the LLM retry mechanism exhausts its budget is now propagated from both `Node._execute_agent()` and `Node.execute()` instead of being swallowed by broad `except Exception` handlers. The implementation is narrower than the ticket's initial "propagate all `ExecutionError`" sketch, but that narrower scope is intentional and safer: it preserves the existing graceful handling of non-timeout execution errors (e.g., tool parsing failures) while ensuring retry-exhaustion timeouts surface to the caller as required by ADR-2032. No critical or major correctness issues were found. I also checked the PR and ticket comment threads; there are no existing reviewer comments or author responses that would remove items from scope. ### Critical Issues None. ### Major Issues None. ### Minor Issues None. ### Nits None. ### Summary The PR adds a targeted `except ExecutionError as e` clause in front of the existing broad `except Exception` handlers in `Node.execute()` and `Node._execute_agent()`. When `e.kind == "timeout"`, the exception is re-raised so it can propagate through `PureLangGraph._execute_from_node()` (whose existing handler at `pure_graph.py:983` already expects limit-enforcement errors to surface) and up to the router with the correct HTTP mapping. Non-timeout `ExecutionError` instances continue down the original graceful path and are converted to error strings in graph state. The logic is sound: - The retry mechanism in `call_with_retry()` raises `ExecutionError(kind="timeout", reason="...")` per ADR-2032 D-7. - `LLMAgent.process_message()` already preserves `kind`/`reason` when re-raising an inner `ExecutionError`, so the timeout identity survives the agent layer. - The new handlers sit in the correct exception-precedence order (`ExecutionError` before `Exception`) and the `current_graph_name` ContextVar is still reset in the `finally` block on the timeout path. - The BDD scenarios added verify both the propagation path and the preservation of graceful handling for non-timeout errors. The only behavior change worth being aware of is that non-timeout `ExecutionError` no longer reaches the node-level `retry_policy` loop in `Node.execute()`. In practice this is correct behavior—execution-limit/failure errors should not be retried like transient exceptions—but it is a subtle narrowing of the `retry_policy` contract. No current node type appears to rely on the old behavior. Overall, the change is minimal, focused, and fixes the reported regression without introducing new risks.

CoreRasurae force-pushed fix/nodes-executionerror-propagation from bcc3b5e459 to b29ee0996e 2026-07-07 09:55:04 +00:00 Compare

CoreRasurae added 1 commit 2026-07-07 12:02:54 +00:00

fix(retry,llm): handle provider APIConnectionError as retryable transient failure ... d0f18ec2e7

Extend _is_http_comms_error() in retry.py to recognize provider SDK
connection errors (APIConnectionError, APITimeoutError) by class name,
so they are retried with exponential backoff instead of propagating
immediately.

Add safety net in process_message() to wrap non-retried connection
errors as ExecutionError(kind='timeout') for correct propagation
through the node layer (issue #71).

Also apply non-blocking review suggestion: change the guard in
_execute_agent() and execute() from 'e.kind == "timeout"' to
'if e.kind' — matching the ExecutionError contract where non-empty
kind means limit breach (depth, model_calls, tool_calls, timeout,
cost).

CoreRasurae commented 2026-07-07 12:03:05 +00:00

Author

Member

Copy link

Updated with two additional commits:

1. d0f18ec — Applied the non-blocking review suggestion: changed e.kind == "timeout" to if e.kind in both _execute_agent() and execute() to future-proof against any limit enforcement moving into the agent/node layer (depth, model_calls, tool_calls, cost).

2. d0f18ec (same commit) — Extended _is_http_comms_error() in retry.py to detect provider SDK connection errors (APIConnectionError, APITimeoutError) by class name. Added safety net in process_message() to wrap non-retried connection errors as ExecutionError(kind="timeout"). The user log output (APIConnectionError: Connection error.) showed that the original fix did not handle these because provider SDK exception types are not subclasses of httpx.HTTPError.

**Updated with two additional commits:** 1. `d0f18ec` — Applied the non-blocking review suggestion: changed `e.kind == "timeout"` to `if e.kind` in both `_execute_agent()` and `execute()` to future-proof against any limit enforcement moving into the agent/node layer (depth, model_calls, tool_calls, cost). 2. `d0f18ec` (same commit) — Extended `_is_http_comms_error()` in retry.py to detect provider SDK connection errors (`APIConnectionError`, `APITimeoutError`) by class name. Added safety net in `process_message()` to wrap non-retried connection errors as `ExecutionError(kind="timeout")`. The user log output (`APIConnectionError: Connection error.`) showed that the original fix did not handle these because provider SDK exception types are not subclasses of `httpx.HTTPError`.

CoreRasurae force-pushed fix/nodes-executionerror-propagation from d0f18ec2e7 to ceb577e405 2026-07-07 12:48:24 +00:00 Compare

CoreRasurae merged commit ceb577e405 into master 2026-07-07 16:06:09 +00:00

CoreRasurae deleted branch fix/nodes-executionerror-propagation 2026-07-07 16:06:09 +00:00

Sign in to join this conversation.

Reviewers

No reviewers

hurui200320

Labels

Clear labels

  

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 labels

auto/blocked-by-deps

auto/ci-timeout

auto/claimed-implementer

auto/claimed-merge

auto/claimed-reviewer

auto/driver-down

auto/invariant-violation

auto/last-attempt-tier-0

auto/last-attempt-tier-1

auto/last-attempt-tier-2

auto/last-attempt-tier-min

Automation Tracking

auto/needs-conflict-resolution

auto/needs-implementer

auto/postmortem

auto/ready-to-merge

auto/restart-throttled

auto/revert

auto/sentinel

auto/stale-inactivity

auto/unstable

Blocked

Bounty

$100

Bounty

$1000

Bounty

$10000

Bounty

$20

Bounty

$2000

Bounty

$250

Bounty

$50

Bounty

$500

Bounty

$5000

Bounty

$750

MoSCoW

Could have

MoSCoW

Must have

MoSCoW

Should have

Needs Feedback

Points

1

Points

13

Points

2

Points

21

Points

3

Points

34

Points

5

Points

55

Points

8

Points

88

Priority

Backlog

Priority

CI Blocker

Priority

Critical

Priority

High

Priority

Low

Priority

Medium

Signed-off: Owner

Signed-off: Scrum Master

Signed-off: Tech Lead

Spike

State

Completed

State

Duplicate

State

In Progress

State

In Review

State

Paused

State

Unverified

State

Verified

State

Wont Do

Type

Automation

Type

Bug

Type

Discussion

Type

Documentation

Type

Epic

Type

Feature

Type

Legendary

Type

Refactor

Type

Support

Type

Task

Type

Testing

Milestone

Clear milestone

No items

No milestone

Projects

Clear projects

No items

No project

Assignees

Clear assignees

No assignees

2 participants

Notifications

Subscribe

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Blocks

#71 ConnectionError retry exhaustion silently swallowed, producing empty response instead of propagating ExecutionError

cleveragents/cleveractors-core

Reference

cleveragents/cleveractors-core!72

No description provided.