fix(api): synthesize mock content after bound tool results

[cursor]

Successor to #639. Same padded-none + bare-invoice stream tip, plus the second-hop tool-result hole LangChain/OpenAI SDK clients hit immediately after the first tool_calls response.

Unique vs #639 (2356202)

• Bound role=tool observations (tool_call_id matches a prior assistant tool_calls id) synthesize content / stop on mock JSON and SSE instead of emitting another lookup_balance.
• Buyer accuracy: invoice 4419 observation balance_usd=128.50 / status=open is reproduced in the answer (tests/test_tool_result_continuation_http_honesty.py).
• Unmatched tool_call_id is not treated as a result — first-hop lookup_balance still fires.
• Empty/whitespace tool_choice with tools is written back as none so HTTP omit and mock selection stay content/stop.

Buyer next action

After the first tool_calls hop, POST the tool output as role=tool with the same tool_call_id and read content / stop (or streamed content deltas). Send none or omit tool_choice when you want no tool call. Do not merge #639 in parallel — this tip already contains that stack plus the second-hop fix.

Do not merge in parallel

Prefer this over #639 / #620 / #606 / #617 for the stream-path tip. Keep KV/token #621, Responses stream #628, verify #634, omit-budget #641, and meaning-unit embeddings #643 on their own tips. Independent non-author APPROVE + Full unit/Semgrep required.

Local checks printed ok: tool-result continuation HTTP JSON+SSE, SSE tools honesty, empty-string tool_choice, chat tool_choice functions, tool_choice strip, paper/API/self-check/conventions, and related tool-message honesty files.

References

Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2023). ReAct: Synergizing reasoning and acting in language models. International Conference on Learning Representations. https://arxiv.org/abs/2210.03629

Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Hambro, E., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2023). Toolformer: Language models can teach themselves to use tools. Advances in Neural Information Processing Systems, 36. https://arxiv.org/abs/2302.04761

OpenAI. (2024). Function calling. OpenAI API documentation. https://platform.openai.com/docs/guides/function-calling

  

[cursor]

Unique slice vs #639 (2356202…d074598) is SOUND. Local tests/test_tool_result_continuation_http_honesty.py and tests/test_passthrough_sse_tools_http_honesty.py printed ok.

Buyer next action: after the first tool_calls hop, POST the tool output as role=tool with the same tool_call_id and read content / stop (or streamed content deltas). Send none when you want no first-hop tool call. Do not omit tool_choice on the first hop if you want to skip tools — omitted tool_choice stays auto and still emits lookup_balance.

What this tip uniquely locks

• Bound role=tool + matching tool_call_id synthesizes content/stop on mock JSON and SSE from the observed values. Invoice 4419 observation balance_usd=128.50 / status=open is reproduced.
• Unmatched tool_call_id is ignored and first-hop lookup_balance still fires.
• Empty/whitespace tool_choice with tools is written back as none (not popped). Writeback is correct: pop would make "" indistinguishable from a missing key, and omitted tool_choice must stay auto.
• Bound observations ending the loop before tool_choice=required is the ReAct second hop this slice adds, not a defect.

Do not merge in parallel. Prefer this over #639 / #620 / #606 / #617 for the stream-path tip. Keep KV/token #621, Responses stream #628/#648, verify #634, omit-budget #641, meaning-unit embeddings #643/#652, Responses text.format #657, and process-bootstrap #645 on their own tips.

Residual (not merge-blocking)

• CHANGELOG / docs/rest_api_design.md still say “send none or omit tool_choice when you want no tool call.” First-hop omit is auto.
• Unmatched-id test has no assistant tool_calls history. A forged call_fake beside a real assistant id should still emit lookup_balance and must not contain 128.50 (JSON and SSE).
• invoice no / invoice nr / inv#4419 still default to INV-9. That is the next bind gap, not a hole in this unique synthesizer.

Independent non-author APPROVE + Full unit / Semgrep required. Do not self-approve. Reviewer seonghobae is already requested.

  

_{Sent by Cursor Automation: Fix Issues}

[cursor]

Unique slice vs #639 remains SOUND (bound tool_call_id synthesizer + empty tool_choice writeback as none). Local honesty tests printed ok.

Prefer #682 #682 as the stream-path landing vehicle. That tip contains this synthesizer plus clerk-alias bind (invoice no. / nr / inv#4419 → INV-4419) and the forged-tool_call_id leak lock.

Buyer next action on this tip: after the first tool_calls hop, POST the tool output as role=tool with the same tool_call_id and read content / stop. Send none when you want no first-hop tool call. Do not merge this in parallel with #682 / #674 / #639.

Independent non-author APPROVE still required if this tip is taken instead. Do not self-approve. Reviewer seonghobae is already requested.

View PR

  

_{Sent by Cursor Automation: Fix Issues}

[cursor]

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.