refactor(platform/copilot): consolidate 4 model-routing LD flags into 1 JSON flag#12917
Merged
Merged
Conversation
… 1 JSON flag
Replaces 4 string-valued LaunchDarkly flags (copilot-fast-standard-model,
copilot-fast-advanced-model, copilot-thinking-standard-model,
copilot-thinking-advanced-model) with a single JSON flag
`copilot-model-routing` keyed by `{mode: {tier: model}}`.
Same pattern as #12915 (pricing flags) and #12910 (tier-multipliers): one
flag per config domain, atomic updates, smaller LD UI surface. Per-user
targeting is preserved. Missing mode, missing tier-within-mode, non-string
cell value, non-dict payload, and LD failures all fall back to the
existing ChatConfig default — user-visible semantics don't change.
Removes the per-cell _FLAG_BY_CELL dispatch dict in model_router.py;
docstring references in copilot/config.py + copilot/sdk/service.py
updated to point at the new nested key path.
github-project-automation
Bot
moved this to 🆕 Needs initial review
in AutoGPT development kanban
majdyz
requested review from
0ubbe and
Bentlybro
and removed request for
a team
Contributor
WalkthroughConsolidates four per-cell LaunchDarkly string flags into a single JSON-valued Changes
Sequence DiagramsequenceDiagram
participant App as Application
participant Router as model_router.resolve_model()
participant LD as LaunchDarkly
participant Config as ChatConfig
App->>Router: resolve_model(user, mode, tier)
Router->>LD: get_feature_flag_value('copilot-model-routing', default=None)
LD-->>Router: payload (dict or None)
alt Valid JSON payload with string at [mode][tier]
Router->>Router: validate payload structure
Router-->>App: return model from payload
else Payload None / missing / invalid / non-string
Router->>Config: read default model field
Config-->>Router: default model
Router-->>App: return default model
else LD exception
Router->>Router: log "LD lookup failed" (with exc_info)
Router->>Config: read default model field
Config-->>Router: default model
Router-->>App: return default model
end
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes Possibly related PRs
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ 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 |
Contributor
🔍 PR Overlap DetectionThis check compares your PR against all other open PRs targeting the same branch to detect potential merge conflicts early. 🔴 Merge Conflicts DetectedThe following PRs have been tested and will have merge conflicts if merged after this PR. Consider coordinating with the authors.
🟢 Low Risk — File Overlap OnlyThese PRs touch the same files but different sections (click to expand)
Summary: 3 conflict(s), 0 medium risk, 5 low risk (out of 8 PRs with file overlap) Auto-generated on push. Ignores: |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (1)
autogpt_platform/backend/backend/copilot/model_router.py (1)
95-111: Prefer typed payload validation over nesteddictchecks.The JSON routing payload is structured data; validating it through chained
isinstance(..., dict)checks makes the shape rules harder to maintain and duplicates type logic in branches.♻️ Suggested refactor (typed payload model)
+from pydantic import BaseModel, ValidationError + +class _TierRouting(BaseModel): + standard: str | None = None + advanced: str | None = None + +class _ModelRoutingPayload(BaseModel): + fast: _TierRouting | None = None + thinking: _TierRouting | None = None + async def resolve_model( @@ - if not isinstance(payload, dict): - logger.warning( - "[model_router] copilot-model-routing expected a JSON object, got %r — " - "using config default %s for (%s, %s)", - payload, - fallback, - mode, - tier, - ) - return fallback - - mode_cell = payload.get(mode) - if not isinstance(mode_cell, dict): + try: + parsed = _ModelRoutingPayload.model_validate(payload) + except ValidationError: + logger.warning( + "[model_router] copilot-model-routing expected a valid JSON object, got %r — " + "using config default %s for (%s, %s)", + payload, + fallback, + mode, + tier, + ) return fallback - value = mode_cell.get(tier) + mode_cell = parsed.fast if mode == "fast" else parsed.thinking + if mode_cell is None: + return fallback + value = mode_cell.advanced if tier == "advanced" else mode_cell.standardAs per coding guidelines: "Use Pydantic models over dataclass/namedtuple/dict for structured data" and "Do not use duck typing — avoid hasattr/getattr/isinstance for type dispatch; use typed interfaces/unions/protocols instead".
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@autogpt_platform/backend/backend/copilot/model_router.py` around lines 95 - 111, Replace the ad-hoc nested dict/isinstance checks in model_router.py with a Pydantic model that represents the expected routing payload shape and validate payload once at the start of the function; specifically, create a Pydantic model (e.g., RoutingPayload with fields like mode: dict[str, dict[str, str]] or a nested model for mode_cell) and use it to parse/validate the incoming payload instead of checking isinstance(payload, dict), isinstance(mode_cell, dict), etc., then read the validated model (referencing payload, mode, tier, mode_cell, value) to get the string mapping and return fallback when Pydantic parsing fails or the mapping is missing/empty.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In `@autogpt_platform/backend/backend/copilot/model_router.py`:
- Around line 95-111: Replace the ad-hoc nested dict/isinstance checks in
model_router.py with a Pydantic model that represents the expected routing
payload shape and validate payload once at the start of the function;
specifically, create a Pydantic model (e.g., RoutingPayload with fields like
mode: dict[str, dict[str, str]] or a nested model for mode_cell) and use it to
parse/validate the incoming payload instead of checking isinstance(payload,
dict), isinstance(mode_cell, dict), etc., then read the validated model
(referencing payload, mode, tier, mode_cell, value) to get the string mapping
and return fallback when Pydantic parsing fails or the mapping is missing/empty.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 9fd9c21a-2426-4882-89c1-48879338cbef
📒 Files selected for processing (6)
autogpt_platform/backend/backend/copilot/config.pyautogpt_platform/backend/backend/copilot/model_router.pyautogpt_platform/backend/backend/copilot/model_router_test.pyautogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/util/feature_flag.py
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (10)
- GitHub Check: check API types
- GitHub Check: Seer Code Review
- GitHub Check: test (3.13)
- GitHub Check: test (3.11)
- GitHub Check: test (3.12)
- GitHub Check: type-check (3.11)
- GitHub Check: end-to-end tests
- GitHub Check: Check PR Status
- GitHub Check: Analyze (typescript)
- GitHub Check: Analyze (python)
🧰 Additional context used
📓 Path-based instructions (3)
autogpt_platform/backend/**/*.py
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
autogpt_platform/backend/**/*.py: Use Python 3.11 (required; managed by Poetry via pyproject.toml) for backend development
Always run 'poetry run format' (Black + isort) before linting in backend development
Always run 'poetry run lint' (ruff) after formatting in backend development
autogpt_platform/backend/**/*.py: Usepoetry run ...command for executing Python package dependencies
Use top-level imports only — avoid local/inner imports except for lazy imports of heavy optional dependencies likeopenpyxl
Use absolute imports withfrom backend.module import ...for cross-package imports; single-dot relative imports are acceptable for sibling modules within the same package; avoid double-dot relative imports
Do not use duck typing — avoidhasattr/getattr/isinstancefor type dispatch; use typed interfaces/unions/protocols instead
Use Pydantic models over dataclass/namedtuple/dict for structured data
Do not use linter suppressors — no# type: ignore,# noqa,# pyright: ignore; fix the type/code instead
Prefer list comprehensions over manual loop-and-append patterns
Use early return with guard clauses first to avoid deep nesting
Use%sfor deferred interpolation indebuglog statements for efficiency; use f-strings elsewhere for readability (e.g.,logger.debug("Processing %s items", count)vslogger.info(f"Processing {count} items"))
Sanitize error paths by usingos.path.basename()in error messages to avoid leaking directory structure
Be aware of TOCTOU (Time-Of-Check-Time-Of-Use) issues — avoid check-then-act patterns for file access and credit charging
Usetransaction=Truefor Redis pipelines to ensure atomicity on multi-step operations
Usemax(0, value)guards for computed values that should never be negative
Keep files under ~300 lines; if a file grows beyond this, split by responsibility (extract helpers, models, or a sub-module into a new file)
Keep functions under ~40 lines; extract named helpers when a function grows longer
...
Files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/util/feature_flag.pyautogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/backend/backend/copilot/config.pyautogpt_platform/backend/backend/copilot/model_router.pyautogpt_platform/backend/backend/copilot/model_router_test.py
autogpt_platform/{backend,autogpt_libs}/**/*.py
📄 CodeRabbit inference engine (AGENTS.md)
Format Python code with
poetry run format
Files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/util/feature_flag.pyautogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/backend/backend/copilot/config.pyautogpt_platform/backend/backend/copilot/model_router.pyautogpt_platform/backend/backend/copilot/model_router_test.py
autogpt_platform/backend/**/*_test.py
📄 CodeRabbit inference engine (autogpt_platform/backend/AGENTS.md)
autogpt_platform/backend/**/*_test.py: Use pytest with snapshot testing for API responses
Colocate test files with source files using*_test.pynaming convention
Mock at boundaries — mock where the symbol is used, not where it's defined; after refactoring, update mock targets to match new module paths
UseAsyncMockfromunittest.mockfor async functions in tests
When writing tests, use Test-Driven Development (TDD): write failing tests marked with@pytest.mark.xfailbefore implementation, then remove the marker once the implementation is complete
When creating snapshots in tests, usepoetry run pytest path/to/test.py --snapshot-update; always review snapshot changes withgit diffbefore committing
Files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/model_router_test.py
🧠 Learnings (23)
📓 Common learnings
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12881
File: autogpt_platform/backend/backend/copilot/sdk/service.py:0-0
Timestamp: 2026-04-22T12:26:42.571Z
Learning: In `autogpt_platform/backend/backend/copilot/sdk/service.py`, `_resolve_sdk_model_for_request`: when a per-user LaunchDarkly model value fails `_normalize_model_name` (e.g. a `moonshotai/kimi-*` slug in direct-Anthropic mode), the fallback must be tier-specific — `config.thinking_advanced_model` for advanced tier, `config.thinking_standard_model` for standard tier — NOT the generic `_resolve_sdk_model()` (which is standard-only and returns None under subscription mode). If the tier-specific config default also fails `_normalize_model_name`, re-raise the original LD error; this is a deployment-level misconfiguration that `model_validator` should have caught at startup. Established in PR `#12881` commit 637d2fef5.
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12440
File: autogpt_platform/backend/backend/copilot/workflow_import/converter.py:0-0
Timestamp: 2026-03-17T10:57:12.953Z
Learning: In Significant-Gravitas/AutoGPT PR `#12440`, `autogpt_platform/backend/backend/copilot/workflow_import/converter.py` was fully rewritten (commit 732960e2d) to no longer make direct LLM/OpenAI API calls. The converter now builds a structured text prompt for AutoPilot/CoPilot instead. There is no `response.choices` access or any direct LLM client usage in this file. Do not flag `response.choices` access or LLM client initialization patterns as issues in this file.
Learnt from: Pwuts
Repo: Significant-Gravitas/AutoGPT PR: 12740
File: autogpt_platform/frontend/src/app/api/openapi.json:0-0
Timestamp: 2026-04-13T14:19:19.341Z
Learning: Repo: Significant-Gravitas/AutoGPT — autogpt_platform
When adding new CoPilot tool response models (e.g., ScheduleListResponse, ScheduleDeletedResponse), update backend/api/features/chat/routes.py to include them in the ToolResponseUnion so the frontend’s autogenerated openapi.json dummy export (/api/chat/schema/tool-responses) exposes them for codegen. Do not hand-edit frontend/src/app/api/openapi.json.
Learnt from: Pwuts
Repo: Significant-Gravitas/AutoGPT PR: 12284
File: autogpt_platform/frontend/src/app/api/openapi.json:11897-11900
Timestamp: 2026-03-04T23:58:18.476Z
Learning: Repo: Significant-Gravitas/AutoGPT — PR `#12284`
Backend/frontend OpenAPI codegen convention: In backend/api/features/store/model.py, the StoreSubmission and StoreSubmissionAdminView models define submitted_at: datetime | None, changes_summary: str | None, and instructions: str | None with no default. This is intentional to produce “required but nullable” fields in OpenAPI (properties appear in required[] and use anyOf [type, null]). This matches Prisma’s submittedAt DateTime? and changesSummary String?. Do not flag this as a required/nullable mismatch.
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12879
File: autogpt_platform/frontend/src/app/api/openapi.json:14576-14577
Timestamp: 2026-04-22T05:58:28.595Z
Learning: Repo: Significant-Gravitas/AutoGPT — autogpt_platform
Process convention: When adding new CoPilot tool response models and updating ToolResponseUnion in backend/api/features/chat/routes.py, regenerate the frontend OpenAPI schema via `poetry run export-api-schema` (do not hand-edit autogpt_platform/frontend/src/app/api/openapi.json).
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12881
File: autogpt_platform/backend/backend/copilot/config.py:0-0
Timestamp: 2026-04-22T11:46:04.431Z
Learning: In Significant-Gravitas/AutoGPT (autogpt_platform), `anthropic/claude-sonnet-4-6` (hyphen-separated) is the project-wide convention for the Claude Sonnet 4.6 model ID, used consistently in llm.py, blocks/test, reasoning.py, _is_anthropic_model tests, and config defaults. OpenRouter accepts both `anthropic/claude-sonnet-4-6` (hyphen) and `anthropic/claude-sonnet-4.6` (dot). Do NOT flag the hyphen form as incorrect — it has been in production since the Sonnet 4.6 upgrade and is intentional.
Learnt from: ntindle
Repo: Significant-Gravitas/AutoGPT PR: 12536
File: autogpt_platform/frontend/src/app/api/openapi.json:5770-5790
Timestamp: 2026-03-24T21:25:15.983Z
Learning: Repo: Significant-Gravitas/AutoGPT — PR `#12536`
File: autogpt_platform/frontend/src/app/api/openapi.json
Learning: The OpenAPI spec file is auto-generated; per established convention, endpoints generally declare only 200/201, 401, and 422 responses. Do not suggest adding explicit 403/404 response entries for single operations unless planning a repo-wide spec update. Prefer clarifying such behaviors in endpoint descriptions/docstrings instead of altering response maps.
📚 Learning: 2026-04-22T12:26:42.571Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12881
File: autogpt_platform/backend/backend/copilot/sdk/service.py:0-0
Timestamp: 2026-04-22T12:26:42.571Z
Learning: In `autogpt_platform/backend/backend/copilot/sdk/service.py`, `_resolve_sdk_model_for_request`: when a per-user LaunchDarkly model value fails `_normalize_model_name` (e.g. a `moonshotai/kimi-*` slug in direct-Anthropic mode), the fallback must be tier-specific — `config.thinking_advanced_model` for advanced tier, `config.thinking_standard_model` for standard tier — NOT the generic `_resolve_sdk_model()` (which is standard-only and returns None under subscription mode). If the tier-specific config default also fails `_normalize_model_name`, re-raise the original LD error; this is a deployment-level misconfiguration that `model_validator` should have caught at startup. Established in PR `#12881` commit 637d2fef5.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/util/feature_flag.pyautogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/backend/backend/copilot/config.pyautogpt_platform/backend/backend/copilot/model_router.pyautogpt_platform/backend/backend/copilot/model_router_test.py
📚 Learning: 2026-03-17T10:57:12.953Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12440
File: autogpt_platform/backend/backend/copilot/workflow_import/converter.py:0-0
Timestamp: 2026-03-17T10:57:12.953Z
Learning: In Significant-Gravitas/AutoGPT PR `#12440`, `autogpt_platform/backend/backend/copilot/workflow_import/converter.py` was fully rewritten (commit 732960e2d) to no longer make direct LLM/OpenAI API calls. The converter now builds a structured text prompt for AutoPilot/CoPilot instead. There is no `response.choices` access or any direct LLM client usage in this file. Do not flag `response.choices` access or LLM client initialization patterns as issues in this file.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/util/feature_flag.pyautogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/backend/backend/copilot/config.pyautogpt_platform/backend/backend/copilot/model_router.pyautogpt_platform/backend/backend/copilot/model_router_test.py
📚 Learning: 2026-04-21T04:36:19.755Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12865
File: autogpt_platform/backend/backend/data/credit_subscription_test.py:1119-1122
Timestamp: 2026-04-21T04:36:19.755Z
Learning: In `autogpt_platform/backend/backend/data/credit_subscription_test.py` (and related subscription test files), test mocks for the user object returned by `get_user_by_id` should use snake_case `subscription_tier` (not camelCase `subscriptionTier`). This is because `get_user_by_id` (defined in `backend/data/user.py`) returns `backend.data.model.User` — a Pydantic application model with `subscription_tier: SubscriptionTier` — not a raw Prisma model. Production code in `backend/data/credit.py` reads `user.subscription_tier` from that Pydantic model. Do NOT flag `mock_user.subscription_tier = ...` as incorrect in these tests.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/service_test.py
📚 Learning: 2026-02-26T17:02:22.448Z
Learnt from: Pwuts
Repo: Significant-Gravitas/AutoGPT PR: 12211
File: .pre-commit-config.yaml:160-179
Timestamp: 2026-02-26T17:02:22.448Z
Learning: Keep the pre-commit hook pattern broad for autogpt_platform/backend to ensure OpenAPI schema changes are captured. Do not narrow to backend/api/ alone, since the generated schema depends on Pydantic models across multiple directories (backend/data/, backend/blocks/, backend/copilot/, backend/integrations/, backend/util/). Narrowing could miss schema changes and cause frontend type desynchronization.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/util/feature_flag.pyautogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/backend/backend/copilot/config.pyautogpt_platform/backend/backend/copilot/model_router.pyautogpt_platform/backend/backend/copilot/model_router_test.py
📚 Learning: 2026-03-04T08:04:35.881Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12273
File: autogpt_platform/backend/backend/copilot/tools/workspace_files.py:216-220
Timestamp: 2026-03-04T08:04:35.881Z
Learning: In the AutoGPT Copilot backend, ensure that SVG images are not treated as vision image types by excluding 'image/svg+xml' from INLINEABLE_MIME_TYPES and MULTIMODAL_TYPES in tool_adapter.py; the Claude API supports PNG, JPEG, GIF, and WebP for vision. SVGs (XML text) should be handled via the text path instead, not the vision path.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/backend/backend/copilot/config.pyautogpt_platform/backend/backend/copilot/model_router.pyautogpt_platform/backend/backend/copilot/model_router_test.py
📚 Learning: 2026-04-01T04:17:41.600Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12632
File: autogpt_platform/backend/backend/copilot/tools/workspace_files.py:0-0
Timestamp: 2026-04-01T04:17:41.600Z
Learning: When reviewing AutoGPT Copilot tool implementations, accept that `readOnlyHint=True` (provided via `ToolAnnotations`) may be applied unconditionally to *all* tools—even tools that have side effects (e.g., `bash_exec`, `write_workspace_file`, or other write/save operations). Do **not** flag these tools for having `readOnlyHint=True`; this is intentional to enable fully-parallel dispatch by the Anthropic SDK/CLI and has been E2E validated. Only flag `readOnlyHint` issues if they conflict with the established `ToolAnnotations` behavior (e.g., missing/incorrect propagation relative to the intended annotation mechanism).
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/backend/backend/copilot/config.pyautogpt_platform/backend/backend/copilot/model_router.pyautogpt_platform/backend/backend/copilot/model_router_test.py
📚 Learning: 2026-03-05T15:42:08.207Z
Learnt from: ntindle
Repo: Significant-Gravitas/AutoGPT PR: 12297
File: .claude/skills/backend-check/SKILL.md:14-16
Timestamp: 2026-03-05T15:42:08.207Z
Learning: In Python files under autogpt_platform/backend (recursively), rely on poetry run format to perform formatting (Black + isort) and linting (ruff). Do not run poetry run lint as a separate step after poetry run format, since format already includes linting checks.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/util/feature_flag.pyautogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/backend/backend/copilot/config.pyautogpt_platform/backend/backend/copilot/model_router.pyautogpt_platform/backend/backend/copilot/model_router_test.py
📚 Learning: 2026-03-16T16:35:40.236Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12440
File: autogpt_platform/backend/backend/api/features/workflow_import.py:54-63
Timestamp: 2026-03-16T16:35:40.236Z
Learning: Avoid using the word 'competitor' in public-facing identifiers and text. Use neutral naming for API paths, model names, function names, and UI text. Examples: rename 'CompetitorFormat' to 'SourcePlatform', 'convert_competitor_workflow' to 'convert_workflow', '/competitor-workflow' to '/workflow'. Apply this guideline to files under autogpt_platform/backend and autogpt_platform/frontend.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/util/feature_flag.pyautogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/backend/backend/copilot/config.pyautogpt_platform/backend/backend/copilot/model_router.pyautogpt_platform/backend/backend/copilot/model_router_test.py
📚 Learning: 2026-03-31T15:37:38.626Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12623
File: autogpt_platform/backend/backend/copilot/tools/agent_generator/fixer.py:37-47
Timestamp: 2026-03-31T15:37:38.626Z
Learning: When validating/constructing Anthropic API model IDs in Significant-Gravitas/AutoGPT, allow the hyphen-separated Claude Opus 4.6 model ID `claude-opus-4-6` (it corresponds to `LlmModel.CLAUDE_4_6_OPUS` in `autogpt_platform/backend/backend/blocks/llm.py`). Do NOT require the dot-separated form in Anthropic contexts. Only OpenRouter routing variants should use the dot separator (e.g., `anthropic/claude-opus-4.6`); `claude-opus-4-6` should be treated as correct when passed to Anthropic, and flagged only if it’s used in the OpenRouter path where the dot form is expected.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/util/feature_flag.pyautogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/backend/backend/copilot/config.pyautogpt_platform/backend/backend/copilot/model_router.pyautogpt_platform/backend/backend/copilot/model_router_test.py
📚 Learning: 2026-04-15T02:43:36.890Z
Learnt from: ntindle
Repo: Significant-Gravitas/AutoGPT PR: 12780
File: autogpt_platform/backend/backend/copilot/tools/workspace_files.py:0-0
Timestamp: 2026-04-15T02:43:36.890Z
Learning: When reviewing Python exception handlers, do not flag `isinstance(e, X)` checks as dead/unreachable if the caught exception `X` is a subclass of the exception type being handled. For example, if `X` (e.g., `VirusScanError`) inherits from `ValueError` (directly or via an intermediate class) and it can be raised within an `except ValueError:` block, then `isinstance(e, X)` inside that handler is reachable and should not be treated as dead code.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/util/feature_flag.pyautogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/backend/backend/copilot/config.pyautogpt_platform/backend/backend/copilot/model_router.pyautogpt_platform/backend/backend/copilot/model_router_test.py
📚 Learning: 2026-04-22T11:46:04.431Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12881
File: autogpt_platform/backend/backend/copilot/config.py:0-0
Timestamp: 2026-04-22T11:46:04.431Z
Learning: Do not flag the Claude Sonnet 4.6 model ID as incorrect when it uses the project’s established hyphenated convention: `anthropic/claude-sonnet-4-6`. This hyphen form is the intentional, production convention and should be treated as valid (including in files like llm.py, blocks tests, reasoning.py, `_is_anthropic_model` tests, and config defaults). Note that OpenRouter also accepts the dot variant `anthropic/claude-sonnet-4.6`, so either form may be tolerated, but `anthropic/claude-sonnet-4-6` should be considered the standard to match project usage.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/util/feature_flag.pyautogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/backend/backend/copilot/config.pyautogpt_platform/backend/backend/copilot/model_router.pyautogpt_platform/backend/backend/copilot/model_router_test.py
📚 Learning: 2026-04-22T11:46:12.892Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12881
File: autogpt_platform/backend/backend/copilot/baseline/service.py:322-332
Timestamp: 2026-04-22T11:46:12.892Z
Learning: In this codebase (Significant-Gravitas/AutoGPT), OpenRouter-routed Anthropic model IDs should use the hyphen-separated convention (e.g., `anthropic/claude-sonnet-4-6`, `anthropic/claude-opus-4-6`). Although OpenRouter may accept both hyphen and dot variants, treat the hyphen-separated form as the intended, correct codebase-wide convention and do not flag it as an error. Only flag the dot-separated variant (e.g., `anthropic/claude-sonnet-4.6`) as incorrect when reviewing/validating model ID strings for OpenRouter-routed Anthropic models.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/util/feature_flag.pyautogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/backend/backend/copilot/config.pyautogpt_platform/backend/backend/copilot/model_router.pyautogpt_platform/backend/backend/copilot/model_router_test.py
📚 Learning: 2026-02-04T16:49:42.490Z
Learnt from: CR
Repo: Significant-Gravitas/AutoGPT PR: 0
File: .github/copilot-instructions.md:0-0
Timestamp: 2026-02-04T16:49:42.490Z
Learning: Applies to autogpt_platform/backend/backend/api/features/**/*.py : Update routes in '/backend/backend/api/features/' and add/update Pydantic models in the same directory for API development
Applied to files:
autogpt_platform/backend/backend/util/feature_flag.pyautogpt_platform/backend/backend/copilot/config.pyautogpt_platform/backend/backend/copilot/model_router.pyautogpt_platform/backend/backend/copilot/model_router_test.py
📚 Learning: 2026-04-13T14:19:19.341Z
Learnt from: Pwuts
Repo: Significant-Gravitas/AutoGPT PR: 12740
File: autogpt_platform/frontend/src/app/api/openapi.json:0-0
Timestamp: 2026-04-13T14:19:19.341Z
Learning: Repo: Significant-Gravitas/AutoGPT — autogpt_platform
When adding new CoPilot tool response models (e.g., ScheduleListResponse, ScheduleDeletedResponse), update backend/api/features/chat/routes.py to include them in the ToolResponseUnion so the frontend’s autogenerated openapi.json dummy export (/api/chat/schema/tool-responses) exposes them for codegen. Do not hand-edit frontend/src/app/api/openapi.json.
Applied to files:
autogpt_platform/backend/backend/util/feature_flag.pyautogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/backend/backend/copilot/config.pyautogpt_platform/backend/backend/copilot/model_router.pyautogpt_platform/backend/backend/copilot/model_router_test.py
📚 Learning: 2026-04-22T05:58:28.595Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12879
File: autogpt_platform/frontend/src/app/api/openapi.json:14576-14577
Timestamp: 2026-04-22T05:58:28.595Z
Learning: Repo: Significant-Gravitas/AutoGPT — autogpt_platform
Process convention: When adding new CoPilot tool response models and updating ToolResponseUnion in backend/api/features/chat/routes.py, regenerate the frontend OpenAPI schema via `poetry run export-api-schema` (do not hand-edit autogpt_platform/frontend/src/app/api/openapi.json).
Applied to files:
autogpt_platform/backend/backend/util/feature_flag.pyautogpt_platform/backend/backend/copilot/config.pyautogpt_platform/backend/backend/copilot/model_router.pyautogpt_platform/backend/backend/copilot/model_router_test.py
📚 Learning: 2026-03-04T23:57:59.510Z
Learnt from: Pwuts
Repo: Significant-Gravitas/AutoGPT PR: 12284
File: autogpt_platform/frontend/src/app/api/openapi.json:5593-5593
Timestamp: 2026-03-04T23:57:59.510Z
Learning: In Significant-Gravitas/AutoGPT backend (FastAPI), openapi.json is autogenerated: descriptions come from route docstrings and schemas from response_model/type annotations. To prevent drift when models are renamed (e.g., AdminView variants), avoid embedding specific schema class names in route docstrings; instead describe behavior, or keep names synced via backend edits—never hand-edit frontend/src/app/api/openapi.json.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/backend/backend/copilot/config.py
📚 Learning: 2026-03-04T23:58:18.476Z
Learnt from: Pwuts
Repo: Significant-Gravitas/AutoGPT PR: 12284
File: autogpt_platform/frontend/src/app/api/openapi.json:11897-11900
Timestamp: 2026-03-04T23:58:18.476Z
Learning: Repo: Significant-Gravitas/AutoGPT — PR `#12284`
Backend/frontend OpenAPI codegen convention: In backend/api/features/store/model.py, the StoreSubmission and StoreSubmissionAdminView models define submitted_at: datetime | None, changes_summary: str | None, and instructions: str | None with no default. This is intentional to produce “required but nullable” fields in OpenAPI (properties appear in required[] and use anyOf [type, null]). This matches Prisma’s submittedAt DateTime? and changesSummary String?. Do not flag this as a required/nullable mismatch.
Applied to files:
autogpt_platform/backend/backend/copilot/config.py
📚 Learning: 2026-04-08T17:27:07.646Z
Learnt from: CR
Repo: Significant-Gravitas/AutoGPT PR: 0
File: classic/forge/CLAUDE.md:0-0
Timestamp: 2026-04-08T17:27:07.646Z
Learning: Applies to classic/forge/**/forge/llm/providers/**/*.py : Supported model names include OpenAI (GPT3, GPT3_16k, GPT4, GPT4_32k, GPT4_TURBO, GPT4_O), Anthropic (CLAUDE3_OPUS, CLAUDE3_SONNET, CLAUDE3_HAIKU, CLAUDE3_5_SONNET, CLAUDE3_5_SONNET_v2, CLAUDE3_5_HAIKU, CLAUDE4_SONNET, CLAUDE4_OPUS, CLAUDE4_5_OPUS), and Groq (LLAMA3_8B, LLAMA3_70B, MIXTRAL_8X7B)
Applied to files:
autogpt_platform/backend/backend/copilot/config.py
📚 Learning: 2026-03-31T14:05:48.405Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12623
File: autogpt_platform/frontend/src/app/api/openapi.json:12934-12940
Timestamp: 2026-03-31T14:05:48.405Z
Learning: AutoGPT OpenAPI/codegen convention: To restrict allowed string values, define the Pydantic field with typing.Literal so the auto-generated openapi.json emits an enum and FastAPI returns 422 for invalid inputs. Example: in backend/api/features/chat/routes.py, StreamChatRequest.mode uses Literal['fast','extended_thinking'] | None; the generated frontend openapi.json now shows enum ["fast","extended_thinking"] with null allowed.
Applied to files:
autogpt_platform/backend/backend/copilot/config.py
📚 Learning: 2026-04-23T00:07:27.117Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 0
File: :0-0
Timestamp: 2026-04-23T00:07:27.117Z
Learning: In `autogpt_platform/backend/backend/copilot/sdk/openrouter_cost.py`, the `openrouter-cost-reconcile` Langfuse event carries `cost_source` ("openrouter" for authoritative OpenRouter-resolved cost, "fallback" for rate-card fallback) and `resolved_generation_id_count` alongside the reconciled cost and token/model/provider metadata. This lets operators distinguish authoritative reconciliations from fallbacks in Langfuse. Established in PR `#12889` commit 5ce3d0388.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-04-03T11:14:16.378Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12623
File: autogpt_platform/backend/backend/copilot/transcript_builder.py:30-34
Timestamp: 2026-04-03T11:14:16.378Z
Learning: In `autogpt_platform/backend/backend/copilot/transcript_builder.py` (and its re-export shim at `sdk/transcript_builder.py`), `TranscriptEntry.parentUuid` is typed `str` (not `str | None`) and root entries use `parentUuid=""` (empty string) to match the canonical `_messages_to_transcript` JSONL format. `_parse_entry`, `append_user`, and `append_assistant` all coerce `None` to `""`. Do NOT flag `parentUuid=""` as incorrect — it is the correct root marker. This was fixed in PR `#12623`, commit b753cb7d0b.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router_test.py
📚 Learning: 2026-03-09T10:50:43.907Z
Learnt from: Bentlybro
Repo: Significant-Gravitas/AutoGPT PR: 0
File: :0-0
Timestamp: 2026-03-09T10:50:43.907Z
Learning: Repo: Significant-Gravitas/AutoGPT — File: autogpt_platform/backend/backend/blocks/llm.py
For xAI Grok models accessed via OpenRouter, the API returns `null` for `max_completion_tokens`. The convention in this codebase is to use the model's context window size as the `max_output_tokens` value in ModelMetadata. For example, Grok 3 uses 131072 (128k) and Grok 4 uses 262144 (256k). Do not flag these as incorrect max output token values.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router_test.py
🔇 Additional comments (6)
autogpt_platform/backend/backend/copilot/config.py (1)
51-53: LD routing docs look correct after flag consolidation.Line 52, Line 59, Line 68, and Line 77 now correctly reference
copilot-model-routing[mode][tier], matching the new single-JSON-flag model routing contract.Also applies to: 58-60, 67-69, 76-78
autogpt_platform/backend/backend/copilot/sdk/service_test.py (1)
616-620: Test docstring rename is accurate.Line 617-Line 620 correctly reflects the consolidated LD key path (
copilot-model-routing[thinking][standard]) with no test behavior changes.autogpt_platform/backend/backend/copilot/sdk/service.py (1)
795-799: Inline routing docs are consistent with the new JSON flag.Line 797-Line 798, Line 834-Line 838, and Line 868-Line 869 all correctly describe the
copilot-model-routing[thinking][tier]lookup semantics and subscription interaction.Also applies to: 830-839, 863-870
autogpt_platform/backend/backend/copilot/model_router.py (1)
68-127: Good consolidation to a single LD lookup with safe per-cell fallback.The resolver keeps behavior stable (user-targeted lookup + tier-specific fallback) while removing per-cell flag fan-out cleanly.
autogpt_platform/backend/backend/copilot/model_router_test.py (1)
84-317: Strong regression coverage for the JSON routing migration.These cases cover the important failure modes (shape validation, whitespace handling, LD exceptions, and single-call guard) and match the new resolver contract well.
autogpt_platform/backend/backend/util/feature_flag.py (1)
50-60: Legacy routing references successfully removed.No remaining references to removed
Flag.COPILOT_*_*_MODELenum members or old LaunchDarkly keys (copilot-{fast,thinking}-{standard,advanced}-model) found in the codebase. The consolidation toFlag.COPILOT_MODEL_ROUTINGis complete.
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## dev #12917 +/- ##
==========================================
+ Coverage 68.23% 68.24% +0.01%
==========================================
Files 1960 1960
Lines 150178 150234 +56
Branches 15621 15626 +5
==========================================
+ Hits 102473 102534 +61
+ Misses 44664 44660 -4
+ Partials 3041 3040 -1
Flags with carried forward coverage won't be shown. Click here to find out more.
🚀 New features to boost your workflow:
|
majdyz
commented
Apr 25, 2026
majdyz
commented
Apr 25, 2026
- Mirror the top-level non-dict warning down to the per-mode level: if the
operator types a string at copilot-model-routing[<mode>] instead of a
{tier: model} dict, log a warning so the typo surfaces in operator-facing
logs instead of silently dropping to ChatConfig defaults.
- Annotate `payload: object` to make the dynamic-typed return value explicit
for readers who land mid-function.
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (1)
autogpt_platform/backend/backend/copilot/model_router.py (1)
106-119: Optional: collapse the twomode_cellchecks into one block.The warning predicate (
mode in payload and not isinstance(mode_cell, dict)) and the early-return predicate (not isinstance(mode_cell, dict)) overlap — when the warning fires, the return also fires. Folding them avoids the secondisinstanceand makes the "warn-then-return" intent explicit:♻️ Proposed simplification
mode_cell = payload.get(mode) - if mode in payload and not isinstance(mode_cell, dict): - # Operator typed something at the mode level (e.g. a string) instead of - # a {tier: model} dict — surface the typo in logs. - logger.warning( - "[model_router] copilot-model-routing[%s] expected a JSON object, " - "got %r — using config default %s for tier %s", - mode, - mode_cell, - fallback, - tier, - ) if not isinstance(mode_cell, dict): + if mode in payload: + # Operator typed something at the mode level (e.g. a string) + # instead of a {tier: model} dict — surface the typo in logs. + logger.warning( + "[model_router] copilot-model-routing[%s] expected a JSON " + "object, got %r — using config default %s for tier %s", + mode, + mode_cell, + fallback, + tier, + ) return fallbackBehavior is equivalent; purely a readability nit — feel free to skip.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@autogpt_platform/backend/backend/copilot/model_router.py` around lines 106 - 119, Condense the duplicated type checks by replacing the separate warning and early-return with a single conditional around the existing mode_cell usage: after retrieving mode_cell = payload.get(mode) in model_router (the block that currently checks mode in payload and not isinstance(mode_cell, dict) then later checks not isinstance(mode_cell, dict)), use one if not isinstance(mode_cell, dict): inside it, if mode in payload: emit the existing logger.warning(...) with the same arguments (mode, mode_cell, fallback, tier), then return fallback; this preserves behavior while avoiding the repeated isinstance check and makes the warn-then-return intent explicit.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In `@autogpt_platform/backend/backend/copilot/model_router.py`:
- Around line 106-119: Condense the duplicated type checks by replacing the
separate warning and early-return with a single conditional around the existing
mode_cell usage: after retrieving mode_cell = payload.get(mode) in model_router
(the block that currently checks mode in payload and not isinstance(mode_cell,
dict) then later checks not isinstance(mode_cell, dict)), use one if not
isinstance(mode_cell, dict): inside it, if mode in payload: emit the existing
logger.warning(...) with the same arguments (mode, mode_cell, fallback, tier),
then return fallback; this preserves behavior while avoiding the repeated
isinstance check and makes the warn-then-return intent explicit.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 6e89ea45-0dee-4c1b-86f4-21911f95bc5a
📒 Files selected for processing (1)
autogpt_platform/backend/backend/copilot/model_router.py
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (10)
- GitHub Check: check API types
- GitHub Check: end-to-end tests
- GitHub Check: type-check (3.11)
- GitHub Check: test (3.11)
- GitHub Check: test (3.12)
- GitHub Check: test (3.13)
- GitHub Check: type-check (3.13)
- GitHub Check: Check PR Status
- GitHub Check: Analyze (python)
- GitHub Check: Analyze (typescript)
🧰 Additional context used
📓 Path-based instructions (2)
autogpt_platform/backend/**/*.py
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
autogpt_platform/backend/**/*.py: Use Python 3.11 (required; managed by Poetry via pyproject.toml) for backend development
Always run 'poetry run format' (Black + isort) before linting in backend development
Always run 'poetry run lint' (ruff) after formatting in backend development
autogpt_platform/backend/**/*.py: Usepoetry run ...command for executing Python package dependencies
Use top-level imports only — avoid local/inner imports except for lazy imports of heavy optional dependencies likeopenpyxl
Use absolute imports withfrom backend.module import ...for cross-package imports; single-dot relative imports are acceptable for sibling modules within the same package; avoid double-dot relative imports
Do not use duck typing — avoidhasattr/getattr/isinstancefor type dispatch; use typed interfaces/unions/protocols instead
Use Pydantic models over dataclass/namedtuple/dict for structured data
Do not use linter suppressors — no# type: ignore,# noqa,# pyright: ignore; fix the type/code instead
Prefer list comprehensions over manual loop-and-append patterns
Use early return with guard clauses first to avoid deep nesting
Use%sfor deferred interpolation indebuglog statements for efficiency; use f-strings elsewhere for readability (e.g.,logger.debug("Processing %s items", count)vslogger.info(f"Processing {count} items"))
Sanitize error paths by usingos.path.basename()in error messages to avoid leaking directory structure
Be aware of TOCTOU (Time-Of-Check-Time-Of-Use) issues — avoid check-then-act patterns for file access and credit charging
Usetransaction=Truefor Redis pipelines to ensure atomicity on multi-step operations
Usemax(0, value)guards for computed values that should never be negative
Keep files under ~300 lines; if a file grows beyond this, split by responsibility (extract helpers, models, or a sub-module into a new file)
Keep functions under ~40 lines; extract named helpers when a function grows longer
...
Files:
autogpt_platform/backend/backend/copilot/model_router.py
autogpt_platform/{backend,autogpt_libs}/**/*.py
📄 CodeRabbit inference engine (AGENTS.md)
Format Python code with
poetry run format
Files:
autogpt_platform/backend/backend/copilot/model_router.py
🧠 Learnings (20)
📓 Common learnings
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12881
File: autogpt_platform/backend/backend/copilot/sdk/service.py:0-0
Timestamp: 2026-04-22T12:26:42.571Z
Learning: In `autogpt_platform/backend/backend/copilot/sdk/service.py`, `_resolve_sdk_model_for_request`: when a per-user LaunchDarkly model value fails `_normalize_model_name` (e.g. a `moonshotai/kimi-*` slug in direct-Anthropic mode), the fallback must be tier-specific — `config.thinking_advanced_model` for advanced tier, `config.thinking_standard_model` for standard tier — NOT the generic `_resolve_sdk_model()` (which is standard-only and returns None under subscription mode). If the tier-specific config default also fails `_normalize_model_name`, re-raise the original LD error; this is a deployment-level misconfiguration that `model_validator` should have caught at startup. Established in PR `#12881` commit 637d2fef5.
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12440
File: autogpt_platform/backend/backend/copilot/workflow_import/converter.py:0-0
Timestamp: 2026-03-17T10:57:12.953Z
Learning: In Significant-Gravitas/AutoGPT PR `#12440`, `autogpt_platform/backend/backend/copilot/workflow_import/converter.py` was fully rewritten (commit 732960e2d) to no longer make direct LLM/OpenAI API calls. The converter now builds a structured text prompt for AutoPilot/CoPilot instead. There is no `response.choices` access or any direct LLM client usage in this file. Do not flag `response.choices` access or LLM client initialization patterns as issues in this file.
Learnt from: Pwuts
Repo: Significant-Gravitas/AutoGPT PR: 12284
File: autogpt_platform/frontend/src/app/api/openapi.json:11897-11900
Timestamp: 2026-03-04T23:58:18.476Z
Learning: Repo: Significant-Gravitas/AutoGPT — PR `#12284`
Backend/frontend OpenAPI codegen convention: In backend/api/features/store/model.py, the StoreSubmission and StoreSubmissionAdminView models define submitted_at: datetime | None, changes_summary: str | None, and instructions: str | None with no default. This is intentional to produce “required but nullable” fields in OpenAPI (properties appear in required[] and use anyOf [type, null]). This matches Prisma’s submittedAt DateTime? and changesSummary String?. Do not flag this as a required/nullable mismatch.
Learnt from: Pwuts
Repo: Significant-Gravitas/AutoGPT PR: 12740
File: autogpt_platform/frontend/src/app/api/openapi.json:0-0
Timestamp: 2026-04-13T14:19:19.341Z
Learning: Repo: Significant-Gravitas/AutoGPT — autogpt_platform
When adding new CoPilot tool response models (e.g., ScheduleListResponse, ScheduleDeletedResponse), update backend/api/features/chat/routes.py to include them in the ToolResponseUnion so the frontend’s autogenerated openapi.json dummy export (/api/chat/schema/tool-responses) exposes them for codegen. Do not hand-edit frontend/src/app/api/openapi.json.
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12879
File: autogpt_platform/frontend/src/app/api/openapi.json:14576-14577
Timestamp: 2026-04-22T05:58:28.595Z
Learning: Repo: Significant-Gravitas/AutoGPT — autogpt_platform
Process convention: When adding new CoPilot tool response models and updating ToolResponseUnion in backend/api/features/chat/routes.py, regenerate the frontend OpenAPI schema via `poetry run export-api-schema` (do not hand-edit autogpt_platform/frontend/src/app/api/openapi.json).
Learnt from: ntindle
Repo: Significant-Gravitas/AutoGPT PR: 12536
File: autogpt_platform/frontend/src/app/api/openapi.json:5770-5790
Timestamp: 2026-03-24T21:25:15.983Z
Learning: Repo: Significant-Gravitas/AutoGPT — PR `#12536`
File: autogpt_platform/frontend/src/app/api/openapi.json
Learning: The OpenAPI spec file is auto-generated; per established convention, endpoints generally declare only 200/201, 401, and 422 responses. Do not suggest adding explicit 403/404 response entries for single operations unless planning a repo-wide spec update. Prefer clarifying such behaviors in endpoint descriptions/docstrings instead of altering response maps.
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12622
File: autogpt_platform/backend/backend/copilot/tools/agent_search.py:223-236
Timestamp: 2026-03-31T14:22:29.127Z
Learning: When reviewing code under autogpt_platform/backend/backend/copilot/tools/, the `AgentInfo.graph` field (in agent_search.py / models.py) uses `Graph | None` (the typed `backend.data.graph.Graph` Pydantic model), NOT `dict[str, Any]`. The enrichment function `_enrich_agents_with_graph` calls `graph_db().get_graph(graph_id, version=None, user_id=user_id)` directly rather than going through `get_agent_as_json()` / `graph_to_json()`. This was updated in PR `#12622` (commit 22d05bc).
Learnt from: ntindle
Repo: Significant-Gravitas/AutoGPT PR: 12536
File: autogpt_platform/frontend/src/app/api/openapi.json:5732-5752
Timestamp: 2026-03-24T21:27:22.326Z
Learning: Repo: Significant-Gravitas/AutoGPT — Preference: Do not add explicit 403/404 entries to FastAPI route decorators for admin endpoints just to influence OpenAPI. Keep openapi.json autogenerated and use route docstrings to document admin-only (403) and not-found (404) behavior; rely on tests for enforcement. File context: autogpt_platform/backend/backend/api/features/admin/store_admin_routes.py. PR `#12536`.
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12773
File: autogpt_platform/backend/backend/copilot/pending_messages.py:52-64
Timestamp: 2026-04-14T14:36:25.545Z
Learning: In `autogpt_platform/backend/backend/copilot` (PR `#12773`, commit d7bced0c6): when draining pending messages into `session.messages`, each message's text is sanitized via `strip_user_context_tags` before persistence to prevent user-controlled `<user_context>` injection from bypassing the trusted server-side context prefix. Additionally, if `upsert_chat_session` fails after draining, the drained `PendingMessage` objects are requeued back to Redis to avoid silent message loss. Do NOT flag the drain-then-requeue pattern as redundant — it is the intentional failure-resilience strategy for the pending buffer.
📚 Learning: 2026-04-22T12:26:42.571Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12881
File: autogpt_platform/backend/backend/copilot/sdk/service.py:0-0
Timestamp: 2026-04-22T12:26:42.571Z
Learning: In `autogpt_platform/backend/backend/copilot/sdk/service.py`, `_resolve_sdk_model_for_request`: when a per-user LaunchDarkly model value fails `_normalize_model_name` (e.g. a `moonshotai/kimi-*` slug in direct-Anthropic mode), the fallback must be tier-specific — `config.thinking_advanced_model` for advanced tier, `config.thinking_standard_model` for standard tier — NOT the generic `_resolve_sdk_model()` (which is standard-only and returns None under subscription mode). If the tier-specific config default also fails `_normalize_model_name`, re-raise the original LD error; this is a deployment-level misconfiguration that `model_validator` should have caught at startup. Established in PR `#12881` commit 637d2fef5.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-03-17T10:57:12.953Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12440
File: autogpt_platform/backend/backend/copilot/workflow_import/converter.py:0-0
Timestamp: 2026-03-17T10:57:12.953Z
Learning: In Significant-Gravitas/AutoGPT PR `#12440`, `autogpt_platform/backend/backend/copilot/workflow_import/converter.py` was fully rewritten (commit 732960e2d) to no longer make direct LLM/OpenAI API calls. The converter now builds a structured text prompt for AutoPilot/CoPilot instead. There is no `response.choices` access or any direct LLM client usage in this file. Do not flag `response.choices` access or LLM client initialization patterns as issues in this file.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-04-23T00:07:27.117Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 0
File: :0-0
Timestamp: 2026-04-23T00:07:27.117Z
Learning: In `autogpt_platform/backend/backend/copilot/sdk/openrouter_cost.py`, the `openrouter-cost-reconcile` Langfuse event carries `cost_source` ("openrouter" for authoritative OpenRouter-resolved cost, "fallback" for rate-card fallback) and `resolved_generation_id_count` alongside the reconciled cost and token/model/provider metadata. This lets operators distinguish authoritative reconciliations from fallbacks in Langfuse. Established in PR `#12889` commit 5ce3d0388.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-03-31T14:22:29.127Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12622
File: autogpt_platform/backend/backend/copilot/tools/agent_search.py:223-236
Timestamp: 2026-03-31T14:22:29.127Z
Learning: When reviewing code under autogpt_platform/backend/backend/copilot/tools/, the `AgentInfo.graph` field (in agent_search.py / models.py) uses `Graph | None` (the typed `backend.data.graph.Graph` Pydantic model), NOT `dict[str, Any]`. The enrichment function `_enrich_agents_with_graph` calls `graph_db().get_graph(graph_id, version=None, user_id=user_id)` directly rather than going through `get_agent_as_json()` / `graph_to_json()`. This was updated in PR `#12622` (commit 22d05bc).
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-03-31T15:37:38.626Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12623
File: autogpt_platform/backend/backend/copilot/tools/agent_generator/fixer.py:37-47
Timestamp: 2026-03-31T15:37:38.626Z
Learning: When validating/constructing Anthropic API model IDs in Significant-Gravitas/AutoGPT, allow the hyphen-separated Claude Opus 4.6 model ID `claude-opus-4-6` (it corresponds to `LlmModel.CLAUDE_4_6_OPUS` in `autogpt_platform/backend/backend/blocks/llm.py`). Do NOT require the dot-separated form in Anthropic contexts. Only OpenRouter routing variants should use the dot separator (e.g., `anthropic/claude-opus-4.6`); `claude-opus-4-6` should be treated as correct when passed to Anthropic, and flagged only if it’s used in the OpenRouter path where the dot form is expected.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-04-02T13:16:03.050Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12649
File: .gitleaks.toml:34-35
Timestamp: 2026-04-02T13:16:03.050Z
Learning: In Significant-Gravitas/AutoGPT, the `.gitleaks.toml` allowlist regex `Llama-\d.*Instruct` is intentionally narrow. Only `Llama-X-...-Instruct-FP8` style model name enum values in `autogpt_platform/backend/backend/blocks/llm.py` actually trigger gitleaks' `generic-api-key` rule due to high entropy in the FP8-quantization suffix. Lowercase variants (e.g., `llama-3.3-70b-versatile`) and Mistral model names do not reach gitleaks' entropy/pattern thresholds, so broadening the pattern is unnecessary. Do not flag this allowlist as too narrow.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-03-09T10:50:43.907Z
Learnt from: Bentlybro
Repo: Significant-Gravitas/AutoGPT PR: 0
File: :0-0
Timestamp: 2026-03-09T10:50:43.907Z
Learning: Repo: Significant-Gravitas/AutoGPT — File: autogpt_platform/backend/backend/blocks/llm.py
For xAI Grok models accessed via OpenRouter, the API returns `null` for `max_completion_tokens`. The convention in this codebase is to use the model's context window size as the `max_output_tokens` value in ModelMetadata. For example, Grok 3 uses 131072 (128k) and Grok 4 uses 262144 (256k). Do not flag these as incorrect max output token values.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-03-24T21:27:22.326Z
Learnt from: ntindle
Repo: Significant-Gravitas/AutoGPT PR: 12536
File: autogpt_platform/frontend/src/app/api/openapi.json:5732-5752
Timestamp: 2026-03-24T21:27:22.326Z
Learning: Repo: Significant-Gravitas/AutoGPT — Preference: Do not add explicit 403/404 entries to FastAPI route decorators for admin endpoints just to influence OpenAPI. Keep openapi.json autogenerated and use route docstrings to document admin-only (403) and not-found (404) behavior; rely on tests for enforcement. File context: autogpt_platform/backend/backend/api/features/admin/store_admin_routes.py. PR `#12536`.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-03-17T06:48:26.471Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12445
File: autogpt_platform/backend/backend/copilot/sdk/service.py:1071-1072
Timestamp: 2026-03-17T06:48:26.471Z
Learning: In Significant-Gravitas/AutoGPT (autogpt_platform), the AI SDK enforces `z.strictObject({type, errorText})` on SSE `StreamError` responses, so additional fields like `retryable: bool` cannot be added to `StreamError` or serialized via `to_sse()`. Instead, retry signaling for transient Anthropic API errors is done via the `COPILOT_RETRYABLE_ERROR_PREFIX` constant prepended to persisted session messages (in `ChatMessage.content`). The frontend detects retryable errors by checking `markerType === "retryable_error"` from `parseSpecialMarkers()` — no SSE schema changes and no string matching on error text. This pattern was established in PR `#12445`, commit 64d82797b.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-03-24T21:25:15.983Z
Learnt from: ntindle
Repo: Significant-Gravitas/AutoGPT PR: 12536
File: autogpt_platform/frontend/src/app/api/openapi.json:5770-5790
Timestamp: 2026-03-24T21:25:15.983Z
Learning: Repo: Significant-Gravitas/AutoGPT — PR `#12536`
File: autogpt_platform/frontend/src/app/api/openapi.json
Learning: The OpenAPI spec file is auto-generated; per established convention, endpoints generally declare only 200/201, 401, and 422 responses. Do not suggest adding explicit 403/404 response entries for single operations unless planning a repo-wide spec update. Prefer clarifying such behaviors in endpoint descriptions/docstrings instead of altering response maps.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-04-22T05:58:28.595Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12879
File: autogpt_platform/frontend/src/app/api/openapi.json:14576-14577
Timestamp: 2026-04-22T05:58:28.595Z
Learning: Repo: Significant-Gravitas/AutoGPT — autogpt_platform
Process convention: When adding new CoPilot tool response models and updating ToolResponseUnion in backend/api/features/chat/routes.py, regenerate the frontend OpenAPI schema via `poetry run export-api-schema` (do not hand-edit autogpt_platform/frontend/src/app/api/openapi.json).
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-02-26T17:02:22.448Z
Learnt from: Pwuts
Repo: Significant-Gravitas/AutoGPT PR: 12211
File: .pre-commit-config.yaml:160-179
Timestamp: 2026-02-26T17:02:22.448Z
Learning: Keep the pre-commit hook pattern broad for autogpt_platform/backend to ensure OpenAPI schema changes are captured. Do not narrow to backend/api/ alone, since the generated schema depends on Pydantic models across multiple directories (backend/data/, backend/blocks/, backend/copilot/, backend/integrations/, backend/util/). Narrowing could miss schema changes and cause frontend type desynchronization.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-03-04T08:04:35.881Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12273
File: autogpt_platform/backend/backend/copilot/tools/workspace_files.py:216-220
Timestamp: 2026-03-04T08:04:35.881Z
Learning: In the AutoGPT Copilot backend, ensure that SVG images are not treated as vision image types by excluding 'image/svg+xml' from INLINEABLE_MIME_TYPES and MULTIMODAL_TYPES in tool_adapter.py; the Claude API supports PNG, JPEG, GIF, and WebP for vision. SVGs (XML text) should be handled via the text path instead, not the vision path.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-04-01T04:17:41.600Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12632
File: autogpt_platform/backend/backend/copilot/tools/workspace_files.py:0-0
Timestamp: 2026-04-01T04:17:41.600Z
Learning: When reviewing AutoGPT Copilot tool implementations, accept that `readOnlyHint=True` (provided via `ToolAnnotations`) may be applied unconditionally to *all* tools—even tools that have side effects (e.g., `bash_exec`, `write_workspace_file`, or other write/save operations). Do **not** flag these tools for having `readOnlyHint=True`; this is intentional to enable fully-parallel dispatch by the Anthropic SDK/CLI and has been E2E validated. Only flag `readOnlyHint` issues if they conflict with the established `ToolAnnotations` behavior (e.g., missing/incorrect propagation relative to the intended annotation mechanism).
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-03-05T15:42:08.207Z
Learnt from: ntindle
Repo: Significant-Gravitas/AutoGPT PR: 12297
File: .claude/skills/backend-check/SKILL.md:14-16
Timestamp: 2026-03-05T15:42:08.207Z
Learning: In Python files under autogpt_platform/backend (recursively), rely on poetry run format to perform formatting (Black + isort) and linting (ruff). Do not run poetry run lint as a separate step after poetry run format, since format already includes linting checks.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-03-16T16:35:40.236Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12440
File: autogpt_platform/backend/backend/api/features/workflow_import.py:54-63
Timestamp: 2026-03-16T16:35:40.236Z
Learning: Avoid using the word 'competitor' in public-facing identifiers and text. Use neutral naming for API paths, model names, function names, and UI text. Examples: rename 'CompetitorFormat' to 'SourcePlatform', 'convert_competitor_workflow' to 'convert_workflow', '/competitor-workflow' to '/workflow'. Apply this guideline to files under autogpt_platform/backend and autogpt_platform/frontend.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-04-15T02:43:36.890Z
Learnt from: ntindle
Repo: Significant-Gravitas/AutoGPT PR: 12780
File: autogpt_platform/backend/backend/copilot/tools/workspace_files.py:0-0
Timestamp: 2026-04-15T02:43:36.890Z
Learning: When reviewing Python exception handlers, do not flag `isinstance(e, X)` checks as dead/unreachable if the caught exception `X` is a subclass of the exception type being handled. For example, if `X` (e.g., `VirusScanError`) inherits from `ValueError` (directly or via an intermediate class) and it can be raised within an `except ValueError:` block, then `isinstance(e, X)` inside that handler is reachable and should not be treated as dead code.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-04-22T11:46:04.431Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12881
File: autogpt_platform/backend/backend/copilot/config.py:0-0
Timestamp: 2026-04-22T11:46:04.431Z
Learning: Do not flag the Claude Sonnet 4.6 model ID as incorrect when it uses the project’s established hyphenated convention: `anthropic/claude-sonnet-4-6`. This hyphen form is the intentional, production convention and should be treated as valid (including in files like llm.py, blocks tests, reasoning.py, `_is_anthropic_model` tests, and config defaults). Note that OpenRouter also accepts the dot variant `anthropic/claude-sonnet-4.6`, so either form may be tolerated, but `anthropic/claude-sonnet-4-6` should be considered the standard to match project usage.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
📚 Learning: 2026-04-22T11:46:12.892Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12881
File: autogpt_platform/backend/backend/copilot/baseline/service.py:322-332
Timestamp: 2026-04-22T11:46:12.892Z
Learning: In this codebase (Significant-Gravitas/AutoGPT), OpenRouter-routed Anthropic model IDs should use the hyphen-separated convention (e.g., `anthropic/claude-sonnet-4-6`, `anthropic/claude-opus-4-6`). Although OpenRouter may accept both hyphen and dot variants, treat the hyphen-separated form as the intended, correct codebase-wide convention and do not flag it as an error. Only flag the dot-separated variant (e.g., `anthropic/claude-sonnet-4.6`) as incorrect when reviewing/validating model ID strings for OpenRouter-routed Anthropic models.
Applied to files:
autogpt_platform/backend/backend/copilot/model_router.py
🔇 Additional comments (1)
autogpt_platform/backend/backend/copilot/model_router.py (1)
59-138: LGTM — clean consolidation with sensible fallback hierarchy.The validation ladder is well-structured:
- Missing user / LD failure → silent fallback (LD failure logs warning).
- Payload
None→ silent fallback (legitimate "not configured" state).- Payload non-dict / mode cell non-dict / tier value non-string-or-empty → warning + fallback (operator misconfiguration).
The asymmetry between silent-on-missing and loud-on-malformed correctly distinguishes "flag not set" from "flag set incorrectly", which is exactly what an operator wants from logs. Per-user LD targeting is preserved, and trimming the config default at line 73 keeps the comparison/return surface consistent with the trimmed payload values at line 123.
github-project-automation
Bot
moved this from 🆕 Needs initial review
to ✅ Done
in AutoGPT development kanban
7 tasks
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.
What
Replaces 4 string-valued LaunchDarkly flags with a single JSON-valued flag for copilot model routing:
copilot-fast-standard-modelcopilot-fast-advanced-modelcopilot-thinking-standard-modelcopilot-thinking-advanced-modelNew:
copilot-model-routing(JSON), keyed{mode: {tier: model}}:{ "fast": { "standard": "anthropic/claude-sonnet-4-6", "advanced": "anthropic/claude-opus-4-6" }, "thinking": { "standard": "moonshotai/kimi-k2.6", "advanced": "anthropic/claude-opus-4-6" } }Why
Same pattern as the sibling consolidation in #12915 (pricing / cost-limits flags) and the merged #12910 (tier-multipliers):
How
backend/util/feature_flag.py: drop the fourCOPILOT_*_MODELenum values, addCOPILOT_MODEL_ROUTING.backend/copilot/model_router.py: rewriteresolve_modelto fetch the JSON flag once per call and walkpayload[mode][tier]. Missing mode, missing tier-within-mode, non-string cell value, non-dict payload, or LD failure all fall back to the correspondingChatConfigdefault (same user-visible semantics as before)._FLAG_BY_CELLremoved entirely;_config_default/ModelMode/ModelTierunchanged.copilot/config.py+copilot/sdk/service.pyupdated to point at the new nested key path; one docstring inservice_test.pylikewise.Operator action required BEFORE merging
This PR removes 4 LD flags and introduces 1 replacement.
In LaunchDarkly, create
copilot-model-routing(type: JSON, server-side only). Default variation = union of the current four string flags, shaped as:{ "fast": { "standard": "<current copilot-fast-standard-model>", "advanced": "<current copilot-fast-advanced-model>" }, "thinking": { "standard": "<current copilot-thinking-standard-model>", "advanced": "<current copilot-thinking-advanced-model>" } }Omit any cell that's currently unset (its
ChatConfigdefault will be used).Merge this PR.
After deploy + smoke, delete the four legacy flags:
copilot-fast-standard-modelcopilot-fast-advanced-modelcopilot-thinking-standard-modelcopilot-thinking-advanced-modelTesting
backend/copilot/model_router_test.pyrewritten — 27 tests pass:Nonepayload → fallback for every cell.exc_info.user_id=None→ skip LD entirely.backend/copilot/sdk/service_test.py: 61 tests still pass (it mocks_resolve_thinking_model_for_user, so the inner flag change is transparent).black --check/ruff check/isort --checkall clean.Sibling
Checklist