fix(api): pop blank Responses instructions before passthrough - #649
Closed
cursor[bot] wants to merge 14 commits into
Closed
fix(api): pop blank Responses instructions before passthrough#649cursor[bot] wants to merge 14 commits into
cursor[bot] wants to merge 14 commits into
Conversation
…closed otherwise Chat history: message-level audio and legacy function_call are null/empty omit no-ops; non-empty fail closed with named errors (including tools passthrough). Tip substrate from #577 assistant refusal/annotations honesty. Local full unit: 940 passed.
…ed otherwise OpenAI fine-tune style message weight is not applied on this gateway. Accept null/0/1 as honest no-ops; reject other types and values with invalid_message_weight. Tip substrate from #578. Local full unit: 943 passed.
…ion role Reject unsupported message keys with named unknown_message_fields (not silent strip or tools-passthrough smuggle). Reject legacy function role with invalid_message_role migration to tool. Tip substrate from #579. Local full unit: 947 passed.
OpenAI partial-assistant prefix flag is not applied on this gateway. null/false are honest no-ops; true and non-booleans fail closed with invalid_message_prefix. Tip substrate from #580. Local full unit: 950 passed.
…therwise Named invalid_max_tool_calls on /v1/chat/completions instead of opaque unknown_fields. Aligns with Responses max_tool_calls honesty; gateway has no multi-step tool loop.
…losed otherwise Legacy /v1/completions treated max_tool_calls as unknown_fields. Accept the key for named invalid_max_tool_calls (null/empty/whitespace omit-equivalent), matching chat/Responses honesty so SDKs get a clear migration path.
SDK clients often send include_usage/include_obfuscation as JSON null. Drop null flag values before validation so null (and null+false mixes) match omit / all-false no-ops on chat, Completions, and Responses. True flags remain fail-closed with invalid_stream_options.
…or Responses parallel true SDK optional defaults often send function.strict and json_schema.strict as null — treat as omit rather than type errors. Align Responses parallel_tool_calls=true with chat by requiring a non-empty tools array.
SDK optional defaults often send description and parameters as JSON null. Treat null as omit rather than type errors; non-null non-string/object values remain fail-closed with invalid_tools.
OpenAI-style tool descriptions are at most 1024 characters. Over-long descriptions fail closed with named invalid_tools so SDKs never believe a truncated description was accepted.
SDK optional participant name blanks ("" / whitespace) are omit-equivalent
like JSON null. Non-string, over-long, and invalid charset names remain
fail-closed with invalid_message_name.
…ll as omit SDK optional defaults often send top_logprobs as "" and tool_calls function.arguments as JSON null. Empty/whitespace top_logprobs matches null/0 omit on chat and Completions; null arguments normalizes to empty JSON-text string. Non-zero top_logprobs and non-string arguments stay fail-closed.
SDK optional defaults often send instructions as empty or blank. Match JSON null omit-equivalent behavior so blank instructions do not fail closed as invalid_instructions; non-string and oversized remain rejected.
SDK null/empty/whitespace instructions are now omit-real: the key is removed so /v1/responses does not forward a blank system prompt. HTTP tests lock the mock echo, and the OpenAPI/docs contract tells callers to send a non-empty string when they want instructions. Co-authored-by: Seongho Bae <seonghobae@users.noreply.github.com>
3 tasks
seonghobae
marked this pull request as ready for review
August 16, 2026 16:33
seonghobae
enabled auto-merge (squash)
August 16, 2026 16:33
Author
|
Bugbot is not enabled for your account, so this pull request was not reviewed. Enable Bugbot in the Cursor dashboard to get automatic reviews on future PRs. |
This was referenced Aug 16, 2026
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
Author
There was a problem hiding this comment.
Unique tip 85617de is SOUND. Do not merge this stack onto main.
#635 accepted blank instructions with HTTP 200 and still forwarded "instructions": " " upstream. This tip closes that gap:
_validate_responses_instructionspops JSONnull/ empty / whitespace (including NBSP) from the samebodythatproxy_completioncopies (minus orchestration-only keys)._mock_rawechoesinstructions, so HTTP tests can lock absence for blanks and equality for a real prompt.- OpenAPI
create_model_response,docs/rest_api_design.md, andCHANGELOG.mdtell callers what to send next.
Local scripts printed ok: test_responses_instructions_reasoning_http_honesty.py, test_sdk_null_object_optional_noop_http_honesty.py, test_openai_passthrough.py, test_api_contract.py, test_product_planning_contract.py, test_self_check.py, test_paper_contracts.py, test_conventions.py.
Merge path (buyer / reviewer)
- Review this commit only (
85617de). The PR vsmainis the 150-file honesty stack — do not merge that ontomain. - Prefer this tip over
#635. Independent non-author APPROVE is required (this automation cannot self-approve acursor[bot]PR). - After parent unique tips land, cherry-pick or rebase
85617de. Then point SDKs at/v1/responses: leaveinstructionsunset, or sendnull/""/ whitespace — the gateway deletes the key. Send a non-empty string when you need a system prompt.invalid_instructionsmeans fix the type or shorten the value; do not retry the same blank payload.
Residual (non-blocking)
- OpenAPI
/v1/responsesonly documentsmodel/input/instructions. Other accepted Responses fields still live in the handler, not the stub schema. test_http_responses_accepts_instructions_omittedlocks HTTP 200 only; blank-value cases already lock echo absence.- Checks were still queued at review time. Queued OpenCode / Strix / Noema is not a unique-tip defect.
- CodeRabbit CLI 0.7.3 is installed here;
coderabbit auth login --agenttimed out (no interactive user). This is not a CodeRabbit result.
Do not open a third instructions-omit PR. Extend #649 only if this slice regresses.
Sent by Cursor Automation: Fix Issues
9 tasks
This was referenced Aug 16, 2026
auto-merge was automatically disabled
August 16, 2026 18:21
Pull request was closed
Contributor
|
Superseded by tip substrate ≥ #691 (cumulative OpenAI/gateway honesty band + auto-merge tip). Closing to free product-gate runners (Full unit + Semgrep). |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Unique tip on #635 (
95346e7). #635 accepts SDK blankinstructionswith HTTP 200 but still forwards"instructions": " "upstream. This tip makes omit real:_validate_responses_instructionspops null/empty/whitespace (including NBSP) from the request body before/v1/responsespassthrough.echoincludesinstructionsso HTTP tests lock absence for blanks and equality for a real prompt.create_model_response,docs/rest_api_design.md, andCHANGELOG.mdtell callers: send a non-empty string when you want a system prompt; do not retry a blank payload.Review this commit only
85617de— do not merge this 143-file honesty stack ontomain. Parent unique tip is #635 / #626.Test plan
python3 tests/test_responses_instructions_reasoning_http_honesty.pypython3 tests/test_sdk_null_object_optional_noop_http_honesty.pypython3 tests/test_openai_passthrough.pypython3 tests/test_api_contract.pypython3 tests/test_product_planning_contract.pypython3 tests/test_self_check.pypython3 tests/test_paper_contracts.pypython3 tests/test_conventions.pyexercise_request_bodyfor blank/null/non-stringinstructionsBuyer next action
Point SDKs at
/v1/responses. Leaveinstructionsunset, or sendnull/""/ whitespace — the gateway deletes the key. If you need a system prompt, send a non-empty string.invalid_instructionsmeans fix the type or shorten the value.