Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12356
File: autogpt_platform/backend/backend/copilot/constants.py:9-12
Timestamp: 2026-03-10T08:39:22.025Z
Learning: In Significant-Gravitas/AutoGPT PR `#12356`, the `COPILOT_SYNTHETIC_ID_PREFIX = "copilot-"` check in `create_auto_approval_record` (human_review.py) is intentional and safe. The `graph_exec_id` passed to this function comes from server-side `PendingHumanReview` DB records (not from user input); the API only accepts `node_exec_id` from users. Synthetic `copilot-*` IDs are only ever created server-side in `run_block.py`. The prefix skip avoids a DB lookup for a `AgentGraphExecution` record that legitimately does not exist for CoPilot sessions, while `user_id` scoping is enforced at the auth layer and on the resulting auto-approval record.

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: 2026-04-22T05:58:31.684Z
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: 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: 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: 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.

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.

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.

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.

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.

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.

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.

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.

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`.

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.

Learnt from: ntindle
Repo: Significant-Gravitas/AutoGPT PR: 11796
File: autogpt_platform/backend/backend/blocks/video/concat.py:3-4
Timestamp: 2026-02-05T04:11:00.596Z
Learning: In autogpt_platform/backend/backend/blocks/**/*.py, when creating a new block, generate a UUID once with uuid.uuid4() and hard-code the resulting string as the block's id parameter. Do not call uuid.uuid4() at runtime; IDs must be constant across all imports and runs to ensure stability.

Learnt from: Abhi1992002
Repo: Significant-Gravitas/AutoGPT PR: 12417
File: autogpt_platform/backend/backend/blocks/agent_mail/pods.py:62-74
Timestamp: 2026-03-16T16:32:21.686Z
Learning: In autogpt_platform/backend/backend/blocks/, the Block base class execute() already wraps run() in a try/except to convert uncaught exceptions into BlockExecutionError/BlockUnknownError. Do not add per-block try/except in individual block run() methods, as this is not the established pattern (e.g., Gmail, Slack, Todoist blocks omit it). Only use explicit try/except within blocks that need to distinguish between success and error yield paths inside a generator (e.g., attachment blocks). This guidance applies to all Python files under autogpt_platform/backend/backend/blocks/ and similar block implementations; avoid duplicating error handling in run() unless a block requires generator-based branching.

Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12893
File: autogpt_platform/backend/backend/blocks/ayrshare/post_to_tiktok.py:24-24
Timestamp: 2026-04-23T12:55:26.122Z
Learning: Cost billing via the cost(*costs) decorator is applied at input-evaluation time (before a block’s run() executes). Therefore, mutating input_data inside run() will not change billing. When a block’s billing depends on a field plus URL/sniff-derived signals, treat the explicitly declared billing field (e.g., is_video) as the only billing source—set it correctly before run() (or in the code path that occurs before the decorator evaluates input_data). This should be checked for all blocks under autogpt_platform/backend/backend/blocks/ so billing signals are not mistakenly assumed to update during run().

Learnt from: Abhi1992002
Repo: Significant-Gravitas/AutoGPT PR: 12417
File: autogpt_platform/backend/backend/blocks/agent_mail/threads.py:80-102
Timestamp: 2026-03-16T16:30:11.452Z
Learning: In autogpt_platform/backend/backend/blocks/ (and related blocks under autogpt_platform/backend/backend/blocks/), do not add try/except blocks around a block's run() method for standard error propagation. The block executor framework (backend/executor/manager.py) catches uncaught exceptions from run() and emits them on the 'error' output. Only add explicit try/except blocks when you need to control partial outputs in failure cases (e.g., certain outputs must not be yielded on error, as in attachment blocks). This is the standard pattern across the codebase; apply it broadly to blocks' run() implementations.

Learnt from: Abhi1992002
Repo: Significant-Gravitas/AutoGPT PR: 12417
File: autogpt_platform/backend/backend/blocks/agent_mail/pods.py:62-74
Timestamp: 2026-03-16T16:30:23.196Z
Learning: In any Python file under autogpt_platform/backend/backend/blocks, do not add a try/except around run() solely for standard error handling. The block framework’s _execute() in _base.py already catches unhandled exceptions and re-raises as BlockExecutionError or BlockUnknownError. If you yield ("error", message), _execute() raises BlockExecutionError immediately, so the error port will not propagate downstream. Reserve explicit try/except for scenarios where you must control partial output (e.g., attachment blocks that must skip yielding content_base64 on failure).

Learnt from: Abhi1992002
Repo: Significant-Gravitas/AutoGPT PR: 12417
File: autogpt_platform/backend/backend/blocks/agent_mail/threads.py:80-102
Timestamp: 2026-03-16T16:30:11.452Z
Learning: Do not wrap synchronous AgentMail SDK calls with asyncio.to_thread() in blocks under autogpt_platform/backend/backend/blocks (and across the codebase). The block executor runs node execution in dedicated threads via asyncio.run_coroutine_threadsafe (see manager.py around lines ~745-752 and ~1079). The existing pattern avoids using asyncio.to_thread for SDK calls inside async run() methods, so maintain that approach and do not add to_thread usage in these code paths.

Learnt from: kcze
Repo: Significant-Gravitas/AutoGPT PR: 13135
File: autogpt_platform/backend/backend/blocks/generic_webhook/_webhook.py:0-0
Timestamp: 2026-05-17T06:58:54.665Z
Learning: In `autogpt_platform/backend/backend/blocks/generic_webhook/_webhook.py`, when `GenericWebhooksManager._configured_secret()` finds multiple distinct `secret_token` values across attached `triggered_nodes` and `triggered_presets`, the intended behavior is to log a warning (not fail closed / raise HTTP 403). This is because a webhook is scoped per `(user_id, graph_id)`, so multiple `GenericWebhookTriggerBlock` instances in the same graph share one webhook endpoint and may legitimately have different tokens configured by the user. Failing closed would lock users out of their own webhook, which is worse UX than logging the conflict. The first token found wins.

Learnt from: Pwuts
Repo: Significant-Gravitas/AutoGPT PR: 12206
File: autogpt_platform/backend/backend/api/external/v2/runs.py:130-145
Timestamp: 2026-06-03T14:22:14.714Z
Learning: In Significant-Gravitas/AutoGPT (autogpt_platform), `add_exception_handlers(app)` from `autogpt_platform/backend/backend/api/utils/exceptions.py` is registered on every API app instance, including `v2_app`. It automatically maps `NotFoundError` and `PrismaRecordNotFoundError` to HTTP 404. Therefore, v2 external API route handlers (e.g., in `autogpt_platform/backend/backend/api/external/v2/runs.py`) do NOT need explicit try/except blocks to catch `NotFoundError` from downstream helpers like `execution_utils.stop_graph_execution`; the top-level handler translates those to 404 without leaking a 500. Do NOT flag missing per-endpoint NotFoundError handling as a bug in v2 external API routes.

Learnt from: ntindle
Repo: Significant-Gravitas/AutoGPT PR: 11185
File: autogpt_platform/backend/backend/blocks/exa/webhook_blocks.py:133-161
Timestamp: 2025-11-03T17:41:48.242Z
Learning: The ExaWebsetWebhookBlock in autogpt_platform/backend/backend/blocks/exa/webhook_blocks.py is currently disabled (disabled=True in __init__) and not active in production.

Learnt from: 0ubbe
Repo: Significant-Gravitas/AutoGPT PR: 12960
File: autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunAgent/components/AgentDetailsCard/__tests__/helpers.test.ts:3-3
Timestamp: 2026-04-30T14:10:26.644Z
Learning: In `autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunAgent/components/AgentDetailsCard/__tests__/helpers.test.ts`, the import path change from `./helpers` to `../helpers` was purely a file relocation into a `__tests__/` subdirectory — the helper module's contract did not change. `buildInputSchema({})` correctly returns `null` (empty properties check), `extractDefaults` correctly falls back to `examples[0]`, and `isFormValid(schema, formData)` has the correct argument order. Do not flag these assertions as mismatched after the path adjustment.

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/blocks/**/*.py : Write tests alongside block implementation when adding new blocks in backend

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/**/test/**/*.py : Use snapshot testing with '--snapshot-update' flag in backend tests when output changes; always review with 'git diff'

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.

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).

Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12279
File: autogpt_platform/backend/backend/copilot/tools/base.py:184-188
Timestamp: 2026-03-04T12:19:39.243Z
Learning: In autogpt_platform/backend/backend/copilot/tools/, ensure that anonymous users always pass user_id=None to tool execution methods. The anon_ prefix (e.g., anon_123) is used only for PostHog/analytics distinct_id and must not be used as an actual user_id. Use a simple truthiness check on user_id (e.g., if user_id: ... else: ... or a dedicated is_authenticated flag) to distinguish anonymous from authenticated users, and review all tool execution call sites within this directory to prevent accidentally forwarding an anon_ user_id to tools.

Learnt from: majdyz
Repo: Significant-Gravitas/AutoGPT PR: 12622
File: autogpt_platform/backend/backend/copilot/tools/agent_search.py:223-236
Timestamp: 2026-03-31T14:22:26.566Z
Learning: In files under autogpt_platform/backend/backend/copilot/tools/, ensure agent graph enrichment uses the typed Pydantic model `backend.data.graph.Graph` for `AgentInfo.graph` (i.e., `Graph | None`), not `dict[str, Any]`. When enriching with graph data (e.g., `_enrich_agents_with_graph`), prefer calling `graph_db().get_graph(graph_id, version=None, user_id=user_id)` directly to retrieve the typed `Graph` object rather than routing through JSON conversions like `get_agent_as_json()` / `graph_to_json()`.

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/blocks/**/*.py : Inherit from 'Block' base class with input/output schemas when adding new blocks in backend

Learnt from: CR
Repo: Significant-Gravitas/AutoGPT PR: 0
File: autogpt_platform/CLAUDE.md:0-0
Timestamp: 2026-04-08T17:26:12.102Z
Learning: Agents must validate inputs before processing