fix(backend/copilot): handle budget-exceeded turn kill gracefully (#13398)#13432
fix(backend/copilot): handle budget-exceeded turn kill gracefully (#13398)#13432C1-BA-B1-F3 wants to merge 5 commits into
Conversation
…gnificant-Gravitas#13398) - Add pre-turn budget-viability gate in routes.py: block dispatch when remaining budget < (below viable-task threshold) instead of starting a doomed turn that dies mid-stream - Make max_budget_exhausted retryable: add to _RETRYABLE_STREAM_ERROR_CODES so the ErrorCard renders with a retry button - Improve error message: replace misleading 'wait for the next billing window' with actionable 'send a follow-up to continue, or try a smaller scope' - Fix ErrorCard context: change context='execution' to context='your request' to fix nonsensical 'when retrieving execution' phrasing - Add specific toast entry for max_budget_exhausted in frontend Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
github-project-automation
Bot
moved this to 🆕 Needs initial review
in AutoGPT development kanban
|
|
|
This PR targets the Automatically setting the base branch to |
github-actions
Bot
added
platform/frontend
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
🚧 Files skipped from review as they are similar to previous changes (2)
📜 Recent review details⏰ Context from checks skipped due to timeout. (13)
|
| Layer / File(s) | Summary |
|---|---|
Minimum viable budget contract autogpt_platform/backend/backend/copilot/budget.py, autogpt_platform/backend/backend/copilot/sdk/service.py, autogpt_platform/backend/backend/copilot/sdk/interrupted_partial_test.py, autogpt_platform/backend/backend/copilot/sdk/service_test.py |
MIN_VIABLE_TASK_BUDGET_USD is set to 1.0, _resolve_dynamic_max_budget_usd returns 0.0 below that threshold, retryable stream error codes include max_budget_exhausted and budget_below_viable, and tests cover the new boundary behavior. |
Pre-turn budget gate autogpt_platform/backend/backend/api/features/chat/routes.py |
stream_chat_post now imports get_remaining_usd_budget, checks the remaining USD budget after rate limiting, and returns HTTP 429 when it is below the threshold. |
Error copy and frontend surfacing autogpt_platform/backend/backend/copilot/sdk/response_adapter.py, autogpt_platform/frontend/src/app/(platform)/copilot/copilotStreamErrorHandlers.ts, autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsx |
error_max_budget_usd now emits updated retry guidance, max_budget_exhausted and budget_below_viable get toast mappings, and the error card context changes to your request. |
Sequence Diagram(s)
sequenceDiagram
participant User
participant stream_chat_post
participant check_rate_limit
participant get_remaining_usd_budget
User->>stream_chat_post: POST /sessions/{session_id}/stream
stream_chat_post->>check_rate_limit: validate per-window rate limit
stream_chat_post->>get_remaining_usd_budget: read remaining USD budget
alt remaining USD >= 0 and < $1.0
stream_chat_post-->>User: HTTP 429 budget too low
else remaining USD >= $1.0
stream_chat_post-->>User: continue stream dispatch
end
Estimated code review effort
🎯 3 (Moderate) | ⏱️ ~20 minutes
Possibly related PRs
- Significant-Gravitas/AutoGPT#12737: Both PRs change the SDK copilot flow in
backend/copilot/sdk/service.pyby adding new pre-dispatch control logic. - Significant-Gravitas/AutoGPT#12828: Both PRs modify the chat streaming entrypoint in
chat/routes.pyaround stream startup behavior. - Significant-Gravitas/AutoGPT#13002: This PR extends the same budget-resolution and budget-exhaustion paths introduced there.
Suggested reviewers
- 0ubbe
- kcze
- Bentlybro
Poem
I sniffed at the budget, then paused at the gate,
no doomed little hop when the funds are too late.
“Budget too low” now shines clear and bright,
with a toast and a card that feel just right.
Hop hop — I’ll try a smaller bite. 🐰
🚥 Pre-merge checks | ✅ 4 | ❌ 1
❌ Failed checks (1 warning)
| Check name | Status | Explanation | Resolution |
|---|---|---|---|
| Docstring Coverage | Docstring coverage is 33.33% which is insufficient. The required threshold is 80.00%. | Write docstrings for the functions missing them to satisfy the coverage threshold. |
✅ Passed checks (4 passed)
| Check name | Status | Explanation |
|---|---|---|
| Title check | ✅ Passed | Title clearly summarizes the main fix: handling budget-exceeded Copilot turns more gracefully. |
| Description check | ✅ Passed | The description matches the PR's budget-viability, retryable error, copy, and context fixes. |
| Linked Issues check | ✅ Passed | The changes address the linked issue's key requirements: block doomed turns, make the error retryable, fix copy/context, and improve budget-exceeded UX. |
| Out of Scope Changes check | ✅ Passed | The frontend toast and backend gates are consistent with the budget-exceeded UX fix, and no unrelated changes stand out. |
✨ Finishing Touches
🧪 Generate unit tests (beta)
- Create PR with unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.
Comment @coderabbitai help to get the list of available commands.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
autogpt_platform/backend/backend/api/features/chat/routes.py (1)
1112-1132: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winReuse the shared threshold instead of a second local constant.
_MIN_VIABLE_TASK_BUDGET_USD = 1.0duplicates_MIN_VIABLE_BUDGET_USD(just added inservice.py) under a different name. Importing the single constant prevents the two values from drifting apart and keeps the gate threshold and the service-layer copy in lockstep.♻️ Suggested change
- # Budget-viability gate: even when the user hasn't hit their - # daily/weekly cap yet, a tiny remaining budget (< $1) means - # the turn is doomed before it starts (median task cost ~$5). - # Block early and surface the rate-limit / credit-reset UI - # instead of dispatching a turn that will die mid-stream. - _MIN_VIABLE_TASK_BUDGET_USD = 1.0 remaining = await get_remaining_usd_budget( user_id=user_id, daily_cost_limit=daily_limit, weekly_cost_limit=weekly_limit, floor_usd=0.0, # faithful signal, no floor ) - if 0 <= remaining < _MIN_VIABLE_TASK_BUDGET_USD: + if 0 <= remaining < _MIN_VIABLE_BUDGET_USD:(with
_MIN_VIABLE_BUDGET_USDimported from the SDK service module)🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@autogpt_platform/backend/backend/api/features/chat/routes.py` around lines 1112 - 1132, Reuse the shared minimum viable budget constant instead of defining a second local threshold in the chat route. In the `routes.py` budget-viability gate, replace `_MIN_VIABLE_TASK_BUDGET_USD` with the existing `_MIN_VIABLE_BUDGET_USD` imported from `service.py` so the route and service layer stay in sync. Keep the `get_remaining_usd_budget` check and `HTTPException` behavior unchanged, only update the constant reference used in the `remaining < ...` comparison.Source: Coding guidelines
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@autogpt_platform/backend/backend/copilot/sdk/service.py`:
- Around line 217-224: The budget threshold is duplicated and the constant in
service.py is unused, so remove the dead _MIN_VIABLE_BUDGET_USD from the service
module and make the threshold come from a single shared source instead. Update
the pre-turn budget check in routes.py that currently uses
_MIN_VIABLE_TASK_BUDGET_USD to import the shared constant, or move the value
into a common config/module and reference it from both places. Use the symbols
_MIN_VIABLE_BUDGET_USD and _MIN_VIABLE_TASK_BUDGET_USD to locate and consolidate
the logic.
---
Nitpick comments:
In `@autogpt_platform/backend/backend/api/features/chat/routes.py`:
- Around line 1112-1132: Reuse the shared minimum viable budget constant instead
of defining a second local threshold in the chat route. In the `routes.py`
budget-viability gate, replace `_MIN_VIABLE_TASK_BUDGET_USD` with the existing
`_MIN_VIABLE_BUDGET_USD` imported from `service.py` so the route and service
layer stay in sync. Keep the `get_remaining_usd_budget` check and
`HTTPException` behavior unchanged, only update the constant reference used in
the `remaining < ...` comparison.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: a0739c67-cdb5-48c7-a3b9-7073f61f4a09
📒 Files selected for processing (5)
autogpt_platform/backend/backend/api/features/chat/routes.pyautogpt_platform/backend/backend/copilot/sdk/response_adapter.pyautogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsxautogpt_platform/frontend/src/app/(platform)/copilot/copilotStreamErrorHandlers.ts
📜 Review details
⏰ Context from checks skipped due to timeout. (13)
- GitHub Check: check API types
- GitHub Check: lint
- GitHub Check: integration_test
- GitHub Check: Analyze (python)
- GitHub Check: Analyze (typescript)
- GitHub Check: type-check (3.12)
- GitHub Check: type-check (3.13)
- GitHub Check: test (3.12)
- GitHub Check: end-to-end tests
- GitHub Check: test (3.13)
- GitHub Check: test (3.11)
- GitHub Check: type-check (3.11)
- GitHub Check: Check PR Status
🧰 Additional context used
📓 Path-based instructions (17)
autogpt_platform/frontend/**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
autogpt_platform/frontend/**/*.{ts,tsx,js,jsx}: Use Node.js 21+ with pnpm package manager for frontend development
Always run 'pnpm format' for formatting and linting code in frontend developmentFormat frontend code using
pnpm format
autogpt_platform/frontend/**/*.{ts,tsx,js,jsx}: Fully capitalize acronyms in symbols, e.g.graphID,useBackendAPI
No linter suppressors (//@ts-ignore``,// eslint-disable) — fix the actual issue
Files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsxautogpt_platform/frontend/src/app/(platform)/copilot/copilotStreamErrorHandlers.ts
autogpt_platform/frontend/**/*.{tsx,ts}
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
autogpt_platform/frontend/**/*.{tsx,ts}: Use function declarations for components and handlers (not arrow functions) in React components
Only use arrow functions for small inline lambdas (map, filter, etc.) in React components
Use PascalCase for component names and camelCase with 'use' prefix for hook names in React
Use Tailwind CSS utilities only for styling in frontend components
Use design system components from 'src/components/' (atoms, molecules, organisms) in frontend development
Never use 'src/components/legacy/' in frontend code
Only use Phosphor Icons (@phosphor-icons/react) for icons in frontend components
Use generated API hooks from '@/app/api/__generated__/endpoints/' instead of deprecated 'BackendAPI' or 'src/lib/autogpt-server-api/'
Use React Query for server state (via generated hooks) in frontend development
Default to client components ('use client') in Next.js; only use server components for SEO or extreme TTFB needs
Use '' component for rendering errors in frontend UI; use toast notifications for mutation errors; use 'Sentry.captureException()' for manual exceptions
Separate render logic from data/behavior in React components; keep comments minimal (code should be self-documenting)
Files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsxautogpt_platform/frontend/src/app/(platform)/copilot/copilotStreamErrorHandlers.ts
autogpt_platform/frontend/**/*.{ts,tsx}
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
autogpt_platform/frontend/**/*.{ts,tsx}: No barrel files or 'index.ts' re-exports in frontend code
Regenerate API hooks with 'pnpm generate:api' after backend OpenAPI spec changes in frontend development
autogpt_platform/frontend/**/*.{ts,tsx}: Use function declarations (not arrow functions) for components/handlers
Noanytypes unless the value genuinely can be anything
Keep render functions and hooks under ~50 lines; extract named helpers or sub-components when they grow longer
Files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsxautogpt_platform/frontend/src/app/(platform)/copilot/copilotStreamErrorHandlers.ts
autogpt_platform/frontend/src/**/*.{ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
autogpt_platform/frontend/src/**/*.{ts,tsx}: Use generated API hooks from@/app/api/__generated__/endpoints/following the patternuse{Method}{Version}{OperationName}, and regenerate withpnpm generate:api
Separate render logic from business logic using component.tsx + useComponent.ts + helpers.ts pattern, colocate state when possible and avoid creating large components, use sub-components in local/componentsfolder
Use function declarations for components and handlers, use arrow functions only for callbacks
Do not useuseCallbackoruseMemounless asked to optimise a given function
autogpt_platform/frontend/src/**/*.{ts,tsx}: Keep files under ~200 lines; extract sub-components or hooks into their own files when a file grows beyond this
Use generated API hooks from@/app/api/__generated__/endpoints/with patternuse{Method}{Version}{OperationName}
Always import the-Icon-suffixed alias from@phosphor-icons/react(e.g.TrashIcon,PlusIcon,SquareIcon) — bare exports are deprecated
Do not useuseCallbackoruseMemounless asked to optimize a given function
Never usesrc/components/__legacy__/*— use design system components fromsrc/components/
Files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsxautogpt_platform/frontend/src/app/(platform)/copilot/copilotStreamErrorHandlers.ts
autogpt_platform/frontend/**/*.{tsx,css}
📄 CodeRabbit inference engine (AGENTS.md)
Use Tailwind CSS only for styling, use design tokens, and use Phosphor Icons only
Files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsx
autogpt_platform/frontend/src/**/*.tsx
📄 CodeRabbit inference engine (AGENTS.md)
Component props should use
interface Props { ... }(not exported) unless the interface needs to be used outside the component
Files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsx
autogpt_platform/**/*.{ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
Never type with
any, if no types available useunknown
Files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsxautogpt_platform/frontend/src/app/(platform)/copilot/copilotStreamErrorHandlers.ts
autogpt_platform/frontend/**/*.{tsx,jsx}
📄 CodeRabbit inference engine (autogpt_platform/frontend/AGENTS.md)
autogpt_platform/frontend/**/*.{tsx,jsx}: Nodark:Tailwind classes — the design system handles dark mode
Use Next.js<Link>for internal navigation — never raw<a>tags
Use Tailwind CSS only for styling with design tokens and Phosphor Icons only
Files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsx
autogpt_platform/frontend/src/**/components/**/*.{tsx,jsx}
📄 CodeRabbit inference engine (autogpt_platform/frontend/AGENTS.md)
Put sub-components in local
components/folder; component props should betype Props = { ... }(not exported) unless used outside the component
Files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsx
autogpt_platform/frontend/src/**/components/**/*.{ts,tsx}
📄 CodeRabbit inference engine (autogpt_platform/frontend/AGENTS.md)
Structure components as
ComponentName/ComponentName.tsx+useComponentName.ts+helpers.ts
Files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsx
autogpt_platform/frontend/src/**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (autogpt_platform/frontend/AGENTS.md)
Avoid index and barrel files
Files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsxautogpt_platform/frontend/src/app/(platform)/copilot/copilotStreamErrorHandlers.ts
autogpt_platform/frontend/**/*.ts
📄 CodeRabbit inference engine (AGENTS.md)
No barrel files or
index.tsre-exports in the frontend
Files:
autogpt_platform/frontend/src/app/(platform)/copilot/copilotStreamErrorHandlers.ts
autogpt_platform/frontend/src/**/*.ts
📄 CodeRabbit inference engine (AGENTS.md)
Do not type hook returns, let Typescript infer as much as possible
autogpt_platform/frontend/src/**/*.ts: Extract component logic into custom hooks grouped by concern, not by component, with each hook in its own.tsfile
Do not type hook returns; let TypeScript infer as much as possible
Files:
autogpt_platform/frontend/src/app/(platform)/copilot/copilotStreamErrorHandlers.ts
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/api/features/chat/routes.pyautogpt_platform/backend/backend/copilot/sdk/response_adapter.pyautogpt_platform/backend/backend/copilot/sdk/service.py
autogpt_platform/backend/backend/api/features/**/*.py
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
Update routes in '/backend/backend/api/features/' and add/update Pydantic models in the same directory for API development
Files:
autogpt_platform/backend/backend/api/features/chat/routes.py
autogpt_platform/{backend,autogpt_libs}/**/*.py
📄 CodeRabbit inference engine (AGENTS.md)
Format Python code with
poetry run format
Files:
autogpt_platform/backend/backend/api/features/chat/routes.pyautogpt_platform/backend/backend/copilot/sdk/response_adapter.pyautogpt_platform/backend/backend/copilot/sdk/service.py
autogpt_platform/backend/**/api/**/*.py
📄 CodeRabbit inference engine (autogpt_platform/backend/AGENTS.md)
autogpt_platform/backend/**/api/**/*.py: UseSecurity()instead ofDepends()for authentication dependencies to get proper OpenAPI security specification
Follow SSE (Server-Sent Events) protocol: usedata:lines for frontend-parsed events (must match Zod schema) and: commentlines for heartbeats/status
Files:
autogpt_platform/backend/backend/api/features/chat/routes.py
🧠 Learnings (23)
📚 Learning: 2026-02-27T10:45:49.499Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12213
File: autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunMCPTool/helpers.tsx:23-24
Timestamp: 2026-02-27T10:45:49.499Z
Learning: Prefer using generated OpenAPI types from '`@/app/api/__generated__/`' for payloads defined in openapi.json (e.g., MCPToolsDiscoveredResponse, MCPToolOutputResponse). Use inline TypeScript interfaces only for payloads that are SSE-stream-only and not exposed via OpenAPI. Apply this pattern to frontend tool components (e.g., RunMCPTool) and related areas where similar SSE/openapi-discrepancies occur; avoid re-implementing types when a generated type is available.
Applied to files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsx
📚 Learning: 2026-03-24T02:05:04.672Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12526
File: autogpt_platform/frontend/src/app/(platform)/copilot/CopilotPage.tsx:0-0
Timestamp: 2026-03-24T02:05:04.672Z
Learning: When gating React component logic on a React Query result (e.g., hooks like `useQuery` / `useGetV2GetCopilotUsage`), prefer destructuring and checking `isSuccess` (or aliasing it to a meaningful boolean like `isSuccess: hasUsage`) instead of relying on `!isLoading`. Reason: `isLoading` can be `false` in error/idle states where `data` may still be `undefined`, while `isSuccess` indicates the query completed successfully and `data` is populated.
Applied to files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsx
📚 Learning: 2026-03-24T02:23:31.305Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12526
File: autogpt_platform/frontend/src/app/(platform)/copilot/components/RateLimitResetDialog/RateLimitResetDialog.tsx:0-0
Timestamp: 2026-03-24T02:23:31.305Z
Learning: In the Copilot platform UI code, follow the established Orval hook `onError` error-handling convention: first explicitly detect/handle `ApiError`, then read `error.response?.detail` (if present) as the primary message; if not available, fall back to `error.message`; and finally fall back to a generic string message. This convention should be used for generated Orval hooks even if the custom Orval mutator already maps details into `ApiError.message`, to keep consistency across hooks/components (e.g., `useCronSchedulerDialog.ts`, `useRunGraph.ts`, and rate-limit/reset flows).
Applied to files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsxautogpt_platform/frontend/src/app/(platform)/copilot/copilotStreamErrorHandlers.ts
📚 Learning: 2026-03-31T14:04:42.444Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12623
File: autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatInput/ChatInput.tsx:172-177
Timestamp: 2026-03-31T14:04:42.444Z
Learning: In the Copilot frontend components under autogpt_platform/frontend/src/app/(platform)/copilot/, Tailwind dark mode variants (e.g., `dark:*`) are intentional and should be allowed. Do not flag `dark:` utilities in these Copilot UI components as incorrect; they are used to ensure proper contrast and correct behavior in both light and dark themes.
Applied to files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsx
📚 Learning: 2026-04-01T18:54:16.035Z
Learnt from: Bentlybro
Repo: Significant-Gravitas/AutoGPT PR: 12633
File: autogpt_platform/frontend/src/app/(platform)/library/components/AgentFilterMenu/AgentFilterMenu.tsx:3-10
Timestamp: 2026-04-01T18:54:16.035Z
Learning: In the frontend, the legacy Select component at `@/components/__legacy__/ui/select` is an intentional, codebase-wide visual-consistency pattern. During code reviews, do not flag or block PRs merely for continuing to use this legacy Select. If a migration to the newer design-system Select is desired, bundle it into a single dedicated cleanup/migration PR that updates all Select usages together (e.g., avoid piecemeal replacements).
Applied to files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsxautogpt_platform/frontend/src/app/(platform)/copilot/copilotStreamErrorHandlers.ts
📚 Learning: 2026-04-07T09:24:16.582Z
Learnt from: 0ubbe
Repo: Significant-Gravitas/AutoGPT PR: 12686
File: autogpt_platform/frontend/src/app/(no-navbar)/onboarding/steps/__tests__/PainPointsStep.test.tsx:1-19
Timestamp: 2026-04-07T09:24:16.582Z
Learning: In Significant-Gravitas/AutoGPT’s `autogpt_platform/frontend` (Vite + `vitejs/plugin-react` with the automatic JSX transform), do not flag usages of React types/components (e.g., `React.ReactNode`) in `.ts`/`.tsx` files as missing `React` imports. Since the React namespace is made available by the project’s TS/Vite setup, an explicit `import React from 'react'` or `import type { ReactNode } ...` is not required; only treat it as missing if typechecking (e.g., `pnpm types`) would actually fail.
Applied to files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsxautogpt_platform/frontend/src/app/(platform)/copilot/copilotStreamErrorHandlers.ts
📚 Learning: 2026-04-02T05:43:49.128Z
Learnt from: 0ubbe
Repo: Significant-Gravitas/AutoGPT PR: 12640
File: autogpt_platform/frontend/src/app/(no-navbar)/onboarding/steps/WelcomeStep.tsx:13-13
Timestamp: 2026-04-02T05:43:49.128Z
Learning: Do not flag `import { Question } from "phosphor-icons/react"` as an invalid import. `Question` is a valid named export from `phosphor-icons/react` (as reflected in the package’s generated `.d.ts` files and re-exports via `dist/index.d.ts`), so it should be treated as a supported named export during code reviews.
Applied to files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsxautogpt_platform/frontend/src/app/(platform)/copilot/copilotStreamErrorHandlers.ts
📚 Learning: 2026-04-13T13:11:07.445Z
Learnt from: 0ubbe
Repo: Significant-Gravitas/AutoGPT PR: 12764
File: autogpt_platform/frontend/src/app/(platform)/library/components/SitrepItem/SitrepItem.tsx:143-145
Timestamp: 2026-04-13T13:11:07.445Z
Learning: In `autogpt_platform/frontend`, do not flag direct interpolation of `executionID` UUID strings into URL query parameters (e.g., `activeItem=${executionID}` in JSX/Next links). If the value is a UUID string matching `[0-9a-f-]`, it contains no reserved URL characters, so additional `encodeURIComponent` or Next.js object-based `href` encoding is unnecessary. Only treat it as an encoding issue if the query-param value is not guaranteed to be UUID-formatted (i.e., may include characters outside `[0-9a-f-]`).
Applied to files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsx
📚 Learning: 2026-04-15T22:49:06.896Z
Learnt from: ntindle
Repo: Significant-Gravitas/AutoGPT PR: 11235
File: autogpt_platform/frontend/src/app/(platform)/admin/diagnostics/components/ExecutionsTable.tsx:0-0
Timestamp: 2026-04-15T22:49:06.896Z
Learning: In the AutoGPT frontend (React Query + toast/ErrorCard patterns), do not require `Sentry.captureException` in React Query mutation `catch` blocks. React Query handles error propagation for mutation paths, so follow the established pattern: show toast notifications for mutation errors and use `ErrorCard` for render/fetch errors. Only add `Sentry.captureException` for truly manual/unexpected exception paths that are outside React Query’s control (e.g., standalone async utilities or event handlers not wired through React Query).
Applied to files:
autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsx
📚 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/api/features/chat/routes.pyautogpt_platform/backend/backend/copilot/sdk/response_adapter.pyautogpt_platform/backend/backend/copilot/sdk/service.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/api/features/chat/routes.pyautogpt_platform/backend/backend/copilot/sdk/response_adapter.pyautogpt_platform/backend/backend/copilot/sdk/service.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/api/features/chat/routes.pyautogpt_platform/backend/backend/copilot/sdk/response_adapter.pyautogpt_platform/backend/backend/copilot/sdk/service.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/api/features/chat/routes.pyautogpt_platform/backend/backend/copilot/sdk/response_adapter.pyautogpt_platform/backend/backend/copilot/sdk/service.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/api/features/chat/routes.pyautogpt_platform/backend/backend/copilot/sdk/response_adapter.pyautogpt_platform/backend/backend/copilot/sdk/service.py
📚 Learning: 2026-05-23T05:29:43.085Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 13200
File: autogpt_platform/backend/backend/executor/scheduler.py:590-593
Timestamp: 2026-05-23T05:29:43.085Z
Learning: When reviewing Python code that uses Pydantic discriminated/tagged unions (e.g., `Annotated[Union[...], Field(discriminator="kind")]`), recognize that using `isinstance(x, SomeVariantInfo)` to narrow the union is an intentional and correct runtime guard and should also enable static type narrowing in tools like Pyright. Do not recommend replacing such `isinstance`-based narrowing with `cast(...)` when the check already proves the variant at runtime.
Applied to files:
autogpt_platform/backend/backend/api/features/chat/routes.pyautogpt_platform/backend/backend/copilot/sdk/response_adapter.pyautogpt_platform/backend/backend/copilot/sdk/service.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/api/features/chat/routes.pyautogpt_platform/backend/backend/copilot/sdk/response_adapter.pyautogpt_platform/backend/backend/copilot/sdk/service.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/api/features/chat/routes.pyautogpt_platform/backend/backend/copilot/sdk/response_adapter.pyautogpt_platform/backend/backend/copilot/sdk/service.py
📚 Learning: 2026-05-07T18:48:14.242Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 13040
File: autogpt_platform/backend/backend/blocks/llm.py:0-0
Timestamp: 2026-05-07T18:48:14.242Z
Learning: In this repository, isort may split imports from the same module into separate blocks when some imports are aliased (e.g., `from module import X as Y`) and others are not. Preserve the two-block layout when it results from isort (such as keeping `from openai.types.chat import ChatCompletion as OpenAIChatCompletion` separate from non-aliased imports from `openai.types.chat`). Do not treat that split as a style issue during review; merging them into a single block can fail CI with `Imports are incorrectly sorted and/or formatted`.
Applied to files:
autogpt_platform/backend/backend/api/features/chat/routes.pyautogpt_platform/backend/backend/copilot/sdk/response_adapter.pyautogpt_platform/backend/backend/copilot/sdk/service.py
📚 Learning: 2026-05-26T14:24:34.866Z
Learnt from: Abhi1992002
Repo: Significant-Gravitas/AutoGPT PR: 13217
File: autogpt_platform/backend/backend/api/features/search/service.py:137-137
Timestamp: 2026-05-26T14:24:34.866Z
Learning: In the Significant-Gravitas/AutoGPT backend, treat `user_id` (an opaque UUID used only for correlation/tracing) as non-PII. Do not flag direct logging of `user_id` in `logger.warning`/`logger.info` statements as a PII exposure issue, as the established convention is to log `user_id` for tracing while reserving PII for fields like email or display name.
Applied to files:
autogpt_platform/backend/backend/api/features/chat/routes.pyautogpt_platform/backend/backend/copilot/sdk/response_adapter.pyautogpt_platform/backend/backend/copilot/sdk/service.py
📚 Learning: 2026-06-11T19:39:10.493Z
Learnt from: ntindle
Repo: Significant-Gravitas/AutoGPT PR: 13337
File: autogpt_platform/backend/backend/copilot/graphiti/reranker.py:0-0
Timestamp: 2026-06-11T19:39:10.493Z
Learning: In the Significant-Gravitas/AutoGPT Python backend, when calling the OpenAI Python client `chat.completions.create`, construct the `messages` payload using the concrete typed-dict variants from `openai.types.chat` (e.g., `ChatCompletionSystemMessageParam`, `ChatCompletionUserMessageParam`, etc.) rather than trying to instantiate `ChatCompletionMessageParam` directly. `ChatCompletionMessageParam` is a `Union` alias and is not constructible, so `ChatCompletionMessageParam(role=..., content=...)` should fail type checking. Build each message element with the appropriate concrete typed dict and then annotate the resulting list as `list[ChatCompletionMessageParam]` (e.g., `messages: list[ChatCompletionMessageParam] = [ChatCompletionSystemMessageParam(...), ...]`).
Applied to files:
autogpt_platform/backend/backend/api/features/chat/routes.pyautogpt_platform/backend/backend/copilot/sdk/response_adapter.pyautogpt_platform/backend/backend/copilot/sdk/service.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/response_adapter.pyautogpt_platform/backend/backend/copilot/sdk/service.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/response_adapter.pyautogpt_platform/backend/backend/copilot/sdk/service.py
📚 Learning: 2026-06-06T12:22:37.648Z
Learnt from: anvyle
Repo: Significant-Gravitas/AutoGPT PR: 13302
File: autogpt_platform/backend/backend/copilot/tools/agent_search.py:579-583
Timestamp: 2026-06-06T12:22:37.648Z
Learning: When writing LLM-facing instruction strings that trigger tool calls in this AutoGPT codebase, use the exact registered tool name `view_agent_output` (as defined in `backend/copilot/tools/agent_output.py` via its `name` property and exported via `TOOL_REGISTRY`). Do not reference the bare name `agent_output`, since it is not a valid tool name and will cause tool invocation to fail.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/response_adapter.pyautogpt_platform/backend/backend/copilot/sdk/service.py
🔇 Additional comments (5)
autogpt_platform/backend/backend/copilot/sdk/service.py (1)
1019-1019: LGTM!autogpt_platform/backend/backend/copilot/sdk/response_adapter.py (1)
602-618: LGTM!autogpt_platform/frontend/src/app/(platform)/copilot/copilotStreamErrorHandlers.ts (1)
64-68: LGTM!autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/components/MessagePartRenderer.tsx (1)
170-177: LGTM!autogpt_platform/backend/backend/api/features/chat/routes.py (1)
1118-1132: 🩺 Stability & AvailabilityConfirm valid: the floor collision concern is addressed by the call order.
The
floor_usd=0.0parameter is correctly used here. The precedingcheck_rate_limitcall on lines 1106–1110 is the primary guard that raisesRateLimitUnavailable(HTTP 503) on Redis brown-out. If that call succeeds (does not raise), Redis is available, andget_remaining_usd_budgetwill return the actual calculated budget rather than the floor. Thus, a Redis outage is intercepted before reaching lines 1124–1132, ensuring a 429 is only raised for a genuine low-budget state, not a service degradation.
Codecov Report❌ Patch coverage is ❌ Your patch check has failed because the patch coverage (68.00%) is below the target coverage (80.00%). You can increase the patch coverage or adjust the target coverage. Additional details and impacted files@@ Coverage Diff @@
## dev #13432 +/- ##
==========================================
+ Coverage 74.31% 74.66% +0.34%
==========================================
Files 2528 2538 +10
Lines 191018 192328 +1310
Branches 18851 18944 +93
==========================================
+ Hits 141959 143599 +1640
+ Misses 44974 44593 -381
- Partials 4085 4136 +51
Flags with carried forward coverage won't be shown. Click here to find out more.
🚀 New features to boost your workflow:
|
Add a pre-dispatch budget viability gate that prevents doomed turns from being dispatched when the user's remaining daily/weekly budget is below a viable threshold. Previously, _resolve_dynamic_max_budget_usd would floor the budget at $0.50 even when the user's actual remaining budget was tiny (e.g. $0.10). The turn would start with $0.50 budget but die mid-stream when it exceeded the budget, producing a confusing 'budget exceeded' ErrorCard with a 'doomed dispatch' UX. Now: - Add _MIN_VIABLE_BUDGET_USD = $1.0 constant (minimum viable budget) - _resolve_dynamic_max_budget_usd returns 0.0 when remaining is below this threshold, signaling the turn is doomed - stream_chat_completion_sdk checks for 0.0 and yields a retryable rate-limit error (budget_below_viable) instead of dispatching - Add budget_below_viable to _RETRYABLE_STREAM_ERROR_CODES - Update tests to cover the new behavior
There was a problem hiding this comment.
Actionable comments posted: 3
🧹 Nitpick comments (1)
autogpt_platform/backend/backend/copilot/sdk/service.py (1)
4145-4175: 🚀 Performance & Scalability | 🔵 Trivial | 💤 Low valueConsider gating before the expensive setup; also de-duplicate the message string.
The viability gate runs only after the E2B sandbox spin-up, system-prompt build, and CLI session restore (
asyncio.gatherat Lines 4004-4019). For the auto-continue recursive path (which bypasses the routes.py 429 gate), that work is wasted before rejection. Moving the gate to just after lock acquisition would avoid it. Also, the rejection copy is duplicated verbatim between_append_error_markerand theStreamError; extract it so the persisted marker and the streamed error can't drift.♻️ De-duplicate the message
+ _budget_msg = ( + "Your remaining budget is too low to start a new turn. " + "Please wait for your budget to reset, or upgrade your plan." + ) resolved_budget = await _resolve_dynamic_max_budget_usd(user_id) if resolved_budget == 0.0: logger.info( "%s Remaining budget below viable threshold ($%.2f); " "rejecting turn with rate-limit error", log_prefix, _MIN_VIABLE_BUDGET_USD, ) - _append_error_marker( - session, - "Your remaining budget is too low to start a new turn. " - "Please wait for your budget to reset, or upgrade your plan.", - retryable=True, - ) - yield StreamError( - errorText=( - "Your remaining budget is too low to start a new turn. " - "Please wait for your budget to reset, or upgrade your plan." - ), - code="budget_below_viable", - ) + _append_error_marker(session, _budget_msg, retryable=True) + yield StreamError(errorText=_budget_msg, code="budget_below_viable") yield StreamFinish() return🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@autogpt_platform/backend/backend/copilot/sdk/service.py` around lines 4145 - 4175, Move the pre-dispatch budget viability gate in the service flow so it runs immediately after lock acquisition, before the expensive sandbox/session setup and recursive auto-continue path work. In the same `service.py` flow around `_resolve_dynamic_max_budget_usd`, extract the rejection copy into a single shared message constant/string and reuse it for both `_append_error_marker` and the `StreamError` so the persisted marker and streamed error stay identical.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@autogpt_platform/backend/backend/copilot/sdk/service_test.py`:
- Around line 1897-1917: The test for _resolve_dynamic_max_budget_usd is
asserting the wrong outcome when remaining budget is at the viable threshold;
update test_clamps_to_floor_when_remaining_is_at_viable to expect the returned
remaining value instead of _MAX_BUDGET_USD_FLOOR. Use the existing patched
get_remaining_usd_budget and get_global_rate_limits setup to align the assertion
with the resolver’s max(floor, remaining) behavior when the viability guard does
not trigger.
In `@autogpt_platform/backend/backend/copilot/sdk/service.py`:
- Around line 265-272: The budget calculation in the remaining-cap logic still
clamps with _MAX_BUDGET_USD_FLOOR even though the earlier threshold check in the
same function already returns 0.0 for any viable-but-too-small remaining value.
Update the return path in the budget helper that uses _MIN_VIABLE_BUDGET_USD and
static_cap so it simply returns the minimum of static_cap and remaining, and
remove the now-unreachable floor clamp.
- Around line 1028-1030: The frontend toast mapping is missing a dedicated
handler for the `budget_below_viable` error code, so add it to
`copilotStreamErrorHandlers.ts` alongside the other stream error entries. Update
the mapping used by the copilot stream error handling logic so
`budget_below_viable` resolves to the intended “wait for budget to reset”
guidance instead of falling back to the generic message. Use the existing
handler structure and the `budget_below_viable` symbol from `service.py` as the
reference for the new entry.
---
Nitpick comments:
In `@autogpt_platform/backend/backend/copilot/sdk/service.py`:
- Around line 4145-4175: Move the pre-dispatch budget viability gate in the
service flow so it runs immediately after lock acquisition, before the expensive
sandbox/session setup and recursive auto-continue path work. In the same
`service.py` flow around `_resolve_dynamic_max_budget_usd`, extract the
rejection copy into a single shared message constant/string and reuse it for
both `_append_error_marker` and the `StreamError` so the persisted marker and
streamed error stay identical.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 1293556d-519c-42b3-8eca-78c27a0f8777
📒 Files selected for processing (3)
autogpt_platform/backend/backend/copilot/sdk/interrupted_partial_test.pyautogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/backend/backend/copilot/sdk/service_test.py
📜 Review details
⏰ Context from checks skipped due to timeout. (6)
- GitHub Check: integration_test
- GitHub Check: end-to-end tests
- GitHub Check: test (3.12)
- GitHub Check: test (3.13)
- GitHub Check: test (3.11)
- GitHub Check: Check PR Status
🧰 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/interrupted_partial_test.pyautogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.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/interrupted_partial_test.pyautogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.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/interrupted_partial_test.pyautogpt_platform/backend/backend/copilot/sdk/service_test.py
🧠 Learnings (14)
📚 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/interrupted_partial_test.pyautogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.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/interrupted_partial_test.pyautogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.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/interrupted_partial_test.pyautogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.py
📚 Learning: 2026-06-06T12:22:37.648Z
Learnt from: anvyle
Repo: Significant-Gravitas/AutoGPT PR: 13302
File: autogpt_platform/backend/backend/copilot/tools/agent_search.py:579-583
Timestamp: 2026-06-06T12:22:37.648Z
Learning: When writing LLM-facing instruction strings that trigger tool calls in this AutoGPT codebase, use the exact registered tool name `view_agent_output` (as defined in `backend/copilot/tools/agent_output.py` via its `name` property and exported via `TOOL_REGISTRY`). Do not reference the bare name `agent_output`, since it is not a valid tool name and will cause tool invocation to fail.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/interrupted_partial_test.pyautogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.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/interrupted_partial_test.pyautogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.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/interrupted_partial_test.pyautogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.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/interrupted_partial_test.pyautogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.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/interrupted_partial_test.pyautogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.py
📚 Learning: 2026-05-23T05:29:43.085Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 13200
File: autogpt_platform/backend/backend/executor/scheduler.py:590-593
Timestamp: 2026-05-23T05:29:43.085Z
Learning: When reviewing Python code that uses Pydantic discriminated/tagged unions (e.g., `Annotated[Union[...], Field(discriminator="kind")]`), recognize that using `isinstance(x, SomeVariantInfo)` to narrow the union is an intentional and correct runtime guard and should also enable static type narrowing in tools like Pyright. Do not recommend replacing such `isinstance`-based narrowing with `cast(...)` when the check already proves the variant at runtime.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/interrupted_partial_test.pyautogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.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/interrupted_partial_test.pyautogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.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/interrupted_partial_test.pyautogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.py
📚 Learning: 2026-05-07T18:48:14.242Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 13040
File: autogpt_platform/backend/backend/blocks/llm.py:0-0
Timestamp: 2026-05-07T18:48:14.242Z
Learning: In this repository, isort may split imports from the same module into separate blocks when some imports are aliased (e.g., `from module import X as Y`) and others are not. Preserve the two-block layout when it results from isort (such as keeping `from openai.types.chat import ChatCompletion as OpenAIChatCompletion` separate from non-aliased imports from `openai.types.chat`). Do not treat that split as a style issue during review; merging them into a single block can fail CI with `Imports are incorrectly sorted and/or formatted`.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/interrupted_partial_test.pyautogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.py
📚 Learning: 2026-05-26T14:24:34.866Z
Learnt from: Abhi1992002
Repo: Significant-Gravitas/AutoGPT PR: 13217
File: autogpt_platform/backend/backend/api/features/search/service.py:137-137
Timestamp: 2026-05-26T14:24:34.866Z
Learning: In the Significant-Gravitas/AutoGPT backend, treat `user_id` (an opaque UUID used only for correlation/tracing) as non-PII. Do not flag direct logging of `user_id` in `logger.warning`/`logger.info` statements as a PII exposure issue, as the established convention is to log `user_id` for tracing while reserving PII for fields like email or display name.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/interrupted_partial_test.pyautogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.py
📚 Learning: 2026-06-11T19:39:10.493Z
Learnt from: ntindle
Repo: Significant-Gravitas/AutoGPT PR: 13337
File: autogpt_platform/backend/backend/copilot/graphiti/reranker.py:0-0
Timestamp: 2026-06-11T19:39:10.493Z
Learning: In the Significant-Gravitas/AutoGPT Python backend, when calling the OpenAI Python client `chat.completions.create`, construct the `messages` payload using the concrete typed-dict variants from `openai.types.chat` (e.g., `ChatCompletionSystemMessageParam`, `ChatCompletionUserMessageParam`, etc.) rather than trying to instantiate `ChatCompletionMessageParam` directly. `ChatCompletionMessageParam` is a `Union` alias and is not constructible, so `ChatCompletionMessageParam(role=..., content=...)` should fail type checking. Build each message element with the appropriate concrete typed dict and then annotate the resulting list as `list[ChatCompletionMessageParam]` (e.g., `messages: list[ChatCompletionMessageParam] = [ChatCompletionSystemMessageParam(...), ...]`).
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/interrupted_partial_test.pyautogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.py
🔇 Additional comments (3)
autogpt_platform/backend/backend/copilot/sdk/service.py (1)
4198-4198: LGTM!autogpt_platform/backend/backend/copilot/sdk/interrupted_partial_test.py (1)
344-345: LGTM!autogpt_platform/backend/backend/copilot/sdk/service_test.py (1)
1876-1895: LGTM!
|
/review |
1. Fix test assertion in service_test.py: test_clamps_to_floor_when_remaining_is_at_viable was asserting result == _MAX_BUDGET_USD_FLOOR (0.5) but with remaining=1.0 and _MIN_VIABLE_BUDGET_USD=1.0, the viable gate does NOT fire and the resolver returns min(static_cap, remaining) = 1.0. 2. Remove unreachable _MAX_BUDGET_USD_FLOOR clamping in service.py: with _MIN_VIABLE_BUDGET_USD=1.0, any remaining < 1.0 returns 0.0 at the viable gate, so the floor (0.5) is always exceeded by the time we reach the return statement. 3. Add budget_below_viable to frontend toast map in copilotStreamErrorHandlers.ts: the backend emits this error code but the frontend was falling back to the generic 'AutoPilot ran into a problem' message instead of the intended guidance.
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
autogpt_platform/backend/backend/copilot/sdk/service.py (1)
4128-4158: 🗄️ Data Integrity & Integration | 🟠 Major | ⚡ Quick winSkip Graphiti ingestion for budget-rejected turns.
This new early return happens before
pre_attempt_msg_countis set by the retry loop, but thefinallyblock can still enqueue Graphiti ingestion usingsession.messages[pre_attempt_msg_count:]. Forbudget_below_viable, that can persist stale history or the retryable budget error marker as assistant output.Proposed fix
graphiti_enabled = False + skip_graphiti_ingest = False pre_attempt_msg_count = 0if resolved_budget == 0.0: + skip_graphiti_ingest = True logger.info(- if graphiti_enabled and user_id and message and is_user_message: + if ( + graphiti_enabled + and not skip_graphiti_ingest + and user_id + and message + and is_user_message + ):🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@autogpt_platform/backend/backend/copilot/sdk/service.py` around lines 4128 - 4158, The early budget rejection in the pre-dispatch gate can still fall through to the cleanup path that enqueues Graphiti ingestion using session.messages[pre_attempt_msg_count:], even though pre_attempt_msg_count was never set for this branch. Update the control flow around the retry loop and its finally block so budget_below_viable turns are excluded from Graphiti ingestion entirely, and make sure the budget error marker added by _append_error_marker is not treated as assistant content for ingestion.
🧹 Nitpick comments (1)
autogpt_platform/backend/backend/copilot/sdk/service.py (1)
122-122: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winUse an absolute import for the shared budget constant.
from ..budgetviolates the backend import rule that avoids double-dot relative imports.Proposed fix
-from ..budget import MIN_VIABLE_TASK_BUDGET_USD +from backend.copilot.budget import MIN_VIABLE_TASK_BUDGET_USDAs per coding guidelines, “Use absolute imports with
from 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.”🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@autogpt_platform/backend/backend/copilot/sdk/service.py` at line 122, The import in the shared budget constant is using a double-dot relative path, which violates the backend import rule. Update the import in the service module to use an absolute backend import for MIN_VIABLE_TASK_BUDGET_USD instead of a parent-relative import, keeping the reference in service.py consistent with the project’s cross-package import style.Source: Coding guidelines
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Outside diff comments:
In `@autogpt_platform/backend/backend/copilot/sdk/service.py`:
- Around line 4128-4158: The early budget rejection in the pre-dispatch gate can
still fall through to the cleanup path that enqueues Graphiti ingestion using
session.messages[pre_attempt_msg_count:], even though pre_attempt_msg_count was
never set for this branch. Update the control flow around the retry loop and its
finally block so budget_below_viable turns are excluded from Graphiti ingestion
entirely, and make sure the budget error marker added by _append_error_marker is
not treated as assistant content for ingestion.
---
Nitpick comments:
In `@autogpt_platform/backend/backend/copilot/sdk/service.py`:
- Line 122: The import in the shared budget constant is using a double-dot
relative path, which violates the backend import rule. Update the import in the
service module to use an absolute backend import for MIN_VIABLE_TASK_BUDGET_USD
instead of a parent-relative import, keeping the reference in service.py
consistent with the project’s cross-package import style.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 365dceb9-4376-4a86-81e1-fd3cf05fc6d2
📒 Files selected for processing (5)
autogpt_platform/backend/backend/api/features/chat/routes.pyautogpt_platform/backend/backend/copilot/budget.pyautogpt_platform/backend/backend/copilot/sdk/service.pyautogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/frontend/src/app/(platform)/copilot/copilotStreamErrorHandlers.ts
✅ Files skipped from review due to trivial changes (1)
- autogpt_platform/backend/backend/copilot/budget.py
🚧 Files skipped from review as they are similar to previous changes (2)
- autogpt_platform/frontend/src/app/(platform)/copilot/copilotStreamErrorHandlers.ts
- autogpt_platform/backend/backend/api/features/chat/routes.py
📜 Review details
⏰ Context from checks skipped due to timeout. (16)
- GitHub Check: check API types
- GitHub Check: lint
- GitHub Check: integration_test
- GitHub Check: test (3.13)
- GitHub Check: test (3.11)
- GitHub Check: test (3.12)
- GitHub Check: lint
- GitHub Check: type-check (3.11)
- GitHub Check: type-check (3.12)
- GitHub Check: type-check (3.13)
- GitHub Check: lint
- GitHub Check: types
- GitHub Check: Analyze (typescript)
- GitHub Check: Analyze (python)
- GitHub Check: end-to-end tests
- GitHub Check: Check PR Status
🧰 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/copilot/sdk/service.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/copilot/sdk/service.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.py
🧠 Learnings (14)
📚 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/copilot/sdk/service.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.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.py
📚 Learning: 2026-06-06T12:22:37.648Z
Learnt from: anvyle
Repo: Significant-Gravitas/AutoGPT PR: 13302
File: autogpt_platform/backend/backend/copilot/tools/agent_search.py:579-583
Timestamp: 2026-06-06T12:22:37.648Z
Learning: When writing LLM-facing instruction strings that trigger tool calls in this AutoGPT codebase, use the exact registered tool name `view_agent_output` (as defined in `backend/copilot/tools/agent_output.py` via its `name` property and exported via `TOOL_REGISTRY`). Do not reference the bare name `agent_output`, since it is not a valid tool name and will cause tool invocation to fail.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.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/copilot/sdk/service.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/copilot/sdk/service.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/copilot/sdk/service.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/copilot/sdk/service.py
📚 Learning: 2026-05-23T05:29:43.085Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 13200
File: autogpt_platform/backend/backend/executor/scheduler.py:590-593
Timestamp: 2026-05-23T05:29:43.085Z
Learning: When reviewing Python code that uses Pydantic discriminated/tagged unions (e.g., `Annotated[Union[...], Field(discriminator="kind")]`), recognize that using `isinstance(x, SomeVariantInfo)` to narrow the union is an intentional and correct runtime guard and should also enable static type narrowing in tools like Pyright. Do not recommend replacing such `isinstance`-based narrowing with `cast(...)` when the check already proves the variant at runtime.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.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/copilot/sdk/service.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/copilot/sdk/service.py
📚 Learning: 2026-05-07T18:48:14.242Z
Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 13040
File: autogpt_platform/backend/backend/blocks/llm.py:0-0
Timestamp: 2026-05-07T18:48:14.242Z
Learning: In this repository, isort may split imports from the same module into separate blocks when some imports are aliased (e.g., `from module import X as Y`) and others are not. Preserve the two-block layout when it results from isort (such as keeping `from openai.types.chat import ChatCompletion as OpenAIChatCompletion` separate from non-aliased imports from `openai.types.chat`). Do not treat that split as a style issue during review; merging them into a single block can fail CI with `Imports are incorrectly sorted and/or formatted`.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.py
📚 Learning: 2026-05-26T14:24:34.866Z
Learnt from: Abhi1992002
Repo: Significant-Gravitas/AutoGPT PR: 13217
File: autogpt_platform/backend/backend/api/features/search/service.py:137-137
Timestamp: 2026-05-26T14:24:34.866Z
Learning: In the Significant-Gravitas/AutoGPT backend, treat `user_id` (an opaque UUID used only for correlation/tracing) as non-PII. Do not flag direct logging of `user_id` in `logger.warning`/`logger.info` statements as a PII exposure issue, as the established convention is to log `user_id` for tracing while reserving PII for fields like email or display name.
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.py
📚 Learning: 2026-06-11T19:39:10.493Z
Learnt from: ntindle
Repo: Significant-Gravitas/AutoGPT PR: 13337
File: autogpt_platform/backend/backend/copilot/graphiti/reranker.py:0-0
Timestamp: 2026-06-11T19:39:10.493Z
Learning: In the Significant-Gravitas/AutoGPT Python backend, when calling the OpenAI Python client `chat.completions.create`, construct the `messages` payload using the concrete typed-dict variants from `openai.types.chat` (e.g., `ChatCompletionSystemMessageParam`, `ChatCompletionUserMessageParam`, etc.) rather than trying to instantiate `ChatCompletionMessageParam` directly. `ChatCompletionMessageParam` is a `Union` alias and is not constructible, so `ChatCompletionMessageParam(role=..., content=...)` should fail type checking. Build each message element with the appropriate concrete typed dict and then annotate the resulting list as `list[ChatCompletionMessageParam]` (e.g., `messages: list[ChatCompletionMessageParam] = [ChatCompletionSystemMessageParam(...), ...]`).
Applied to files:
autogpt_platform/backend/backend/copilot/sdk/service_test.pyautogpt_platform/backend/backend/copilot/sdk/service.py
🔇 Additional comments (2)
autogpt_platform/backend/backend/copilot/sdk/service.py (1)
212-255: LGTM!Also applies to: 1012-1012, 4181-4181
autogpt_platform/backend/backend/copilot/sdk/service_test.py (1)
18-19: LGTM!Also applies to: 1875-1917
- Reorder imports in routes.py (isort --profile black) - Format service.py with black (blank line, frozenset formatting)
3 participants
Fixes #13398
Summary
Budget-exceeded turns were dying mid-stream with a non-retryable ErrorCard and misleading copy. This PR fixes all 4 root causes identified in the issue.
Changes
1. Pre-turn budget-viability gate (routes.py)
2. Make max_budget_exhausted retryable (service.py)
3. Improve error message (response_adapter.py)
4. Fix ErrorCard context (MessagePartRenderer.tsx)
5. Add specific toast for max_budget_exhausted (copilotStreamErrorHandlers.ts)