fix(actor): resolve provider from explicit field in v3 YAML before inferring from model #10930

Merged

hurui200320 merged 1 commit from bugfix/m3-v3-actor-provider-resolution into master 2026-04-30 02:28:35 +00:00

Conversation 4 Commits 1 Files changed 8 +132 -8

hurui200320 commented 2026-04-29 10:10:23 +00:00

Member

Copy link

Summary

Two bugs prevented built-in LLM actors from working with models that lack a / separator (e.g. claude-sonnet-4-20250514):

1. _generate_builtin_actor_yaml (actor/registry.py) was constructing the model field as {provider}/{model}, which caused 404 errors on the Anthropic API. Fixed to use the bare model identifier and lowercase the provider field to match ProviderType enum values.

2. _build_from_v3 (reactive/config_parser.py) always inferred the provider from the model string. For bare model IDs without /, this returned "custom" (invalid), causing Unknown provider type: custom. Fixed by checking for an explicit top-level provider field in the v3 YAML data per spec resolution order before falling back to inference.

As a side effect, these fixes also resolve issue #10861: agents actor run now successfully invokes the LLM for built-in actors.

Changes

• src/cleveragents/actor/registry.py: In _generate_builtin_actor_yaml, use bare model identifier and lowercase provider.
• src/cleveragents/reactive/config_parser.py: In _build_from_v3, check explicit provider field before calling infer_provider_from_model().
• features/builtin_actor_v3_yaml.feature: 3 new TDD scenarios for the registry fix.
• features/actor_v3_route_synthesis.feature: 3 new TDD scenarios for the config parser fix.
• features/steps/builtin_actor_v3_yaml_steps.py: should not contain assertion step added.
• features/steps/actor_v3_route_synthesis_steps.py: New Given steps for explicit/no-provider configs.
• features/tdd_actor_run_response.feature: Removed @tdd_expected_fail (bug #10861 fixed).

Quality Gates

• lint ✓
• typecheck ✓
• unit_tests ✓ (671 features, 15673 scenarios, 0 failures)
• integration_tests ✓ (1997/1997)
• coverage_report ✓ (97.12% ≥ 97%)

Closes #10926

## Summary Two bugs prevented built-in LLM actors from working with models that lack a `/` separator (e.g. `claude-sonnet-4-20250514`): 1. **`_generate_builtin_actor_yaml`** (`actor/registry.py`) was constructing the `model` field as `{provider}/{model}`, which caused 404 errors on the Anthropic API. Fixed to use the bare model identifier and lowercase the provider field to match `ProviderType` enum values. 2. **`_build_from_v3`** (`reactive/config_parser.py`) always inferred the provider from the model string. For bare model IDs without `/`, this returned `"custom"` (invalid), causing `Unknown provider type: custom`. Fixed by checking for an explicit top-level `provider` field in the v3 YAML data per spec resolution order before falling back to inference. As a side effect, these fixes also resolve issue #10861: `agents actor run` now successfully invokes the LLM for built-in actors. ## Changes - `src/cleveragents/actor/registry.py`: In `_generate_builtin_actor_yaml`, use bare model identifier and lowercase provider. - `src/cleveragents/reactive/config_parser.py`: In `_build_from_v3`, check explicit `provider` field before calling `infer_provider_from_model()`. - `features/builtin_actor_v3_yaml.feature`: 3 new TDD scenarios for the registry fix. - `features/actor_v3_route_synthesis.feature`: 3 new TDD scenarios for the config parser fix. - `features/steps/builtin_actor_v3_yaml_steps.py`: `should not contain` assertion step added. - `features/steps/actor_v3_route_synthesis_steps.py`: New `Given` steps for explicit/no-provider configs. - `features/tdd_actor_run_response.feature`: Removed `@tdd_expected_fail` (bug #10861 fixed). ## Quality Gates - lint ✓ - typecheck ✓ - unit_tests ✓ (671 features, 15673 scenarios, 0 failures) - integration_tests ✓ (1997/1997) - coverage_report ✓ (97.12% ≥ 97%) Closes #10926

hurui200320 added this to the v3.2.0 milestone 2026-04-29 10:10:29 +00:00

hurui200320 added the

Type

Bug

label 2026-04-29 10:10:42 +00:00

hurui200320 referenced this pull request 2026-04-29 10:11:18 +00:00

Fix v3 actor provider resolution for models without / separator #10926

hurui200320 added a new dependency 2026-04-29 10:12:14 +00:00

#10926 Fix v3 actor provider resolution for models without / separator

hurui200320 referenced this pull request 2026-04-29 10:14:40 +00:00

fix(actor): Get responses from actor-run #10900

hurui200320 commented 2026-04-29 10:17:58 +00:00

Author

Member

Copy link

Tested the branch locally, anthropic provider is working as expected with this PR.

 Tested the branch locally, anthropic provider is working as expected with this PR.

image.png

26 KiB

hurui200320 2026-04-29 10:18:05 +00:00

• added the
  Priority
  Critical
  MoSCoW
  Must have
  labels
• requested reviews from HAL9000, HAL9001

HAL9000 was assigned by hurui200320 2026-04-29 10:18:19 +00:00

HAL9001 was assigned by hurui200320 2026-04-29 10:18:20 +00:00

hurui200320 force-pushed bugfix/m3-v3-actor-provider-resolution from 96467032df to 920083f636 2026-04-29 10:18:56 +00:00 Compare

hurui200320 force-pushed bugfix/m3-v3-actor-provider-resolution from 920083f636 to 3157f25bf1 2026-04-29 10:56:59 +00:00 Compare

hurui200320 force-pushed bugfix/m3-v3-actor-provider-resolution from 3157f25bf1 to 0526ea4c5c 2026-04-29 11:00:57 +00:00 Compare

hurui200320 commented 2026-04-29 12:13:20 +00:00

Author

Member

Copy link

@HAL9000 please review this PR

@HAL9000 please review this PR

HAL9000 approved these changes 2026-04-29 18:16:30 +00:00

HAL9000 left a comment

Copy link

Review Summary

PR #10930 — fix(actor): resolve provider from explicit field in v3 YAML before inferring from model
Closes: #10926 (and side-effect fix for #10861)

Issues Addressed

All acceptance criteria from issue #10926 have been met:

• _build_from_v3 checks for explicit provider field before inferring from model
• _generate_builtin_actor_yaml generates model as bare identifier (no provider prefix)
• _generate_builtin_actor_yaml generates provider in lowercase
• Existing actors with / in the model string continue to work via inference fallback
• All existing tests pass (671 features, 15,673 scenarios, 0 failures)

Spec Alignment

The provider resolution fix in _build_from_v3 correctly implements the spec resolution order (line 21412): CLI override → top-level provider/model keys → provider_type/model_id aliases → v2-extracted values. The explicit top-level provider field is now checked as step 2 before falling back to infer_provider_from_model().

10-Category Review

1. Correctness ✅ — Both bug fixes are precisely targeted. The bare-model fix prevents 404s on Anthropic API; the explicit-provider fix prevents the Unknown provider type: custom crash for models without /.

2. Specification Alignment ✅ — Follows the provider/model resolution order defined in docs/specification.md at line 21412. The ActorConfigSchema.provider field (line 747) is respected as the spec requires.

3. Test Quality ✅ — 6 well-named TDD scenarios (3 per component), covering: explicit provider without slash, inference from slash-containing model, and no-provider fallback to custom. The TDD regression test for #10861 had @tdd_expected_fail removed. Coverage at 97.12% meets the ≥97% gate.

4. Type Safety ✅ — All signatures annotated; isinstance(explicit_provider, str) type guard used; no # type: ignore present.

5. Readability ✅ — Clear variable names (explicit_provider), descriptive scenario titles, comments referencing spec lines and issue numbers.

6. Performance ✅ — No changes to algorithmic complexity; only a single dict lookup added.

7. Security ✅ — No new attack surface; no secrets/tokens introduced.

8. Code Style ✅ — SOLID principles followed; small focused changes; all files well under 500 lines; follows ruff conventions.

9. Documentation ✅ — Inline comments explain the spec-alignment (# m11: Resolve provider per spec resolution order). PR body is comprehensive.

10. Commit and PR Quality ✅ — PR description matches issue metadata; correct milestone (v3.2.0, milestone m3); one Type/Bug label; CI green across all 14 checks.

Non-Blocking Suggestions

• The docstring in features/steps/tdd_actor_run_response_steps.py still says "The @tdd_expected_fail tag inverts the result so CI passes while the bug exists." Consider adding a note that the tag was removed after the fix, for future maintainers.

Verdict: APPROVED

All acceptance criteria met, all CI gates passing (lint, typecheck, security, unit_tests, integration_tests, coverage at 97.12%), code is correct and spec-aligned. Changes are minimal, well-tested, and focused.

## Review Summary **PR #10930** — fix(actor): resolve provider from explicit field in v3 YAML before inferring from model **Closes:** #10926 (and side-effect fix for #10861) ### Issues Addressed All acceptance criteria from issue #10926 have been met: - [x] `_build_from_v3` checks for explicit `provider` field before inferring from model - [x] `_generate_builtin_actor_yaml` generates `model` as bare identifier (no provider prefix) - [x] `_generate_builtin_actor_yaml` generates `provider` in lowercase - [x] Existing actors with `/` in the model string continue to work via inference fallback - [x] All existing tests pass (671 features, 15,673 scenarios, 0 failures) ### Spec Alignment The provider resolution fix in `_build_from_v3` correctly implements the spec resolution order (line 21412): CLI override → top-level `provider`/`model` keys → `provider_type`/`model_id` aliases → v2-extracted values. The explicit top-level `provider` field is now checked as step 2 before falling back to `infer_provider_from_model()`. ### 10-Category Review 1. **Correctness** ✅ — Both bug fixes are precisely targeted. The bare-model fix prevents 404s on Anthropic API; the explicit-provider fix prevents the `Unknown provider type: custom` crash for models without `/`. 2. **Specification Alignment** ✅ — Follows the provider/model resolution order defined in docs/specification.md at line 21412. The `ActorConfigSchema.provider` field (line 747) is respected as the spec requires. 3. **Test Quality** ✅ — 6 well-named TDD scenarios (3 per component), covering: explicit provider without slash, inference from slash-containing model, and no-provider fallback to `custom`. The TDD regression test for #10861 had `@tdd_expected_fail` removed. Coverage at 97.12% meets the ≥97% gate. 4. **Type Safety** ✅ — All signatures annotated; `isinstance(explicit_provider, str)` type guard used; no `# type: ignore` present. 5. **Readability** ✅ — Clear variable names (`explicit_provider`), descriptive scenario titles, comments referencing spec lines and issue numbers. 6. **Performance** ✅ — No changes to algorithmic complexity; only a single dict lookup added. 7. **Security** ✅ — No new attack surface; no secrets/tokens introduced. 8. **Code Style** ✅ — SOLID principles followed; small focused changes; all files well under 500 lines; follows ruff conventions. 9. **Documentation** ✅ — Inline comments explain the spec-alignment (`# m11: Resolve provider per spec resolution order`). PR body is comprehensive. 10. **Commit and PR Quality** ✅ — PR description matches issue metadata; correct milestone (v3.2.0, milestone m3); one `Type/Bug` label; CI green across all 14 checks. ### Non-Blocking Suggestions - The docstring in `features/steps/tdd_actor_run_response_steps.py` still says "The @tdd_expected_fail tag inverts the result so CI passes while the bug exists." Consider adding a note that the tag was removed after the fix, for future maintainers. ### Verdict: APPROVED All acceptance criteria met, all CI gates passing (lint, typecheck, security, unit_tests, integration_tests, coverage at 97.12%), code is correct and spec-aligned. Changes are minimal, well-tested, and focused.

HAL9000 commented 2026-04-29 18:16:37 +00:00

Owner

Copy link

Review completed: APPROVED ✅

All acceptance criteria met. Changes are correctly targeted, spec-aligned, and well-tested. Full review summary posted on the PR.

---

Automated by CleverAgents Bot
Supervisor: PR Review | Agent: pr-review-worker

Review completed: **APPROVED** ✅ All acceptance criteria met. Changes are correctly targeted, spec-aligned, and well-tested. Full review summary posted on the PR. --- Automated by CleverAgents Bot Supervisor: PR Review | Agent: pr-review-worker

hurui200320 scheduled this pull request to auto merge when all checks succeed 2026-04-30 02:04:56 +00:00

hurui200320 force-pushed bugfix/m3-v3-actor-provider-resolution from 0526ea4c5c to caf146e132 2026-04-30 02:05:15 +00:00 Compare

hurui200320 merged commit caf146e132 into master 2026-04-30 02:28:35 +00:00

hurui200320 deleted branch bugfix/m3-v3-actor-provider-resolution 2026-04-30 02:28:36 +00:00

hurui200320 referenced this pull request 2026-04-30 13:22:41 +00:00

agents actor run does not work. #10861

Sign in to join this conversation.

Reviewers

No reviewers

HAL9001

HAL9000

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.

  

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/needs-reevaluation

controller-managed

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

v3.2.0

Projects

Clear projects

No items

No project

Assignees

Clear assignees

No assignees

HAL9001

HAL9000

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

#10926 Fix v3 actor provider resolution for models without / separator

cleveragents/cleveragents-core

Reference

cleveragents/cleveragents-core!10930

No description provided.