Expose accumulated streamed function-call args in SDK surfaces
Expose fully accumulated streamed function-call arguments across streaming, live sessions, and chat history.
go-genai-streamed-function-args
Normalized profile
What this task asks for
Expose fully accumulated streamed function-call arguments across streaming, live sessions, and chat history. Streamed function calls that arrive through partial argument fragments should be usable through the public SDK surfaces without requiring callers to reconstruct the final JSON arguments themselves. For each streamed response, both public access paths for reading function calls must expose `Args` as the accumulated JSON object built from every `partialArgs` fragment seen so far for that in-progress call. Any existing `args` object sent with a streamed function call remains part of the accumulated result. When a later fragment targets the same path and the earlier fragment had `willContinue=true`, the later fragment must append to the existing string value in arrival order. `nullValue` becomes JSON null. A later send must replay that stored turn as a normal completed function-call turn. If streamed fragments for one call require incompatible shapes at the same JSON path, the streaming operation must return an error instead of silently overwriting data.
Intent
- feature implementation
Work surfaces
- parser
- library API
Technology
- Go GenAI
- JSON
Expected artifacts
- repository patch
What makes it difficult
- reverse engineering from incomplete or indirect evidence
- strict behavioral compatibility or exact-output validation
Published evidence
Model × harness outcomes
Counts are tied to these exact configurations. Harnesses are not treated as equivalent across benchmarks.
- Models
- 13
- Configurations
- 41
- Trials
- 164
Showing 41 of 41 configurations
| Model | Harness | Effort | Result | Passes |
|---|---|---|---|---|
| claude-fable-5vertex_ai | mini-swe-agentpublished configuration | low | Mixed | 3/4 |
| claude-fable-5vertex_ai | mini-swe-agentpublished configuration | medium | Mixed | 3/4 |
| claude-fable-5vertex_ai | mini-swe-agentpublished configuration | high | Mixed | 3/4 |
| claude-fable-5vertex_ai | mini-swe-agentpublished configuration | xhigh | All passed | 4/4 |
| claude-fable-5vertex_ai | mini-swe-agentpublished configuration | max | Mixed | 3/4 |
| claude-opus-4-8anthropic | mini-swe-agentpublished configuration | low | No passes | 0/4 |
| claude-opus-4-8anthropic | mini-swe-agentpublished configuration | medium | Mixed | 3/4 |
| claude-opus-4-8anthropic | mini-swe-agentpublished configuration | high | Mixed | 3/4 |
| claude-opus-4-8anthropic | mini-swe-agentpublished configuration | xhigh | All passed | 4/4 |
| claude-opus-4-8anthropic | mini-swe-agentpublished configuration | max | All passed | 4/4 |
| claude-sonnet-4-6anthropic | mini-swe-agentpublished configuration | high | No passes | 0/4 |
| claude-sonnet-5anthropic | mini-swe-agentpublished configuration | low | No passes | 0/4 |
| claude-sonnet-5anthropic | mini-swe-agentpublished configuration | medium | Mixed | 1/4 |
| claude-sonnet-5anthropic | mini-swe-agentpublished configuration | high | Mixed | 3/4 |
| claude-sonnet-5anthropic | mini-swe-agentpublished configuration | xhigh | Mixed | 2/4 |
| claude-sonnet-5anthropic | mini-swe-agentpublished configuration | max | All passed | 4/4 |
| gemini-3-1-pro-previewvertex_ai | mini-swe-agentpublished configuration | high | No passes | 0/4 |
| gemini-3-5-flashvertex_ai | mini-swe-agentpublished configuration | medium | Mixed | 2/4 |
| glm-5-2zai | mini-swe-agentpublished configuration | high | Mixed | 2/4 |
| glm-5-2zai | mini-swe-agentpublished configuration | max | Mixed | 3/4 |
| gpt-5-4openai | mini-swe-agentpublished configuration | xhigh | All passed | 4/4 |
| gpt-5-5openai | mini-swe-agentpublished configuration | low | Mixed | 2/4 |
| gpt-5-5openai | mini-swe-agentpublished configuration | medium | Mixed | 1/4 |
| gpt-5-5openai | mini-swe-agentpublished configuration | high | All passed | 4/4 |
| gpt-5-5openai | mini-swe-agentpublished configuration | xhigh | All passed | 4/4 |
| gpt-5-6-lunaopenai | mini-swe-agentpublished configuration | low | No passes | 0/4 |
| gpt-5-6-lunaopenai | mini-swe-agentpublished configuration | medium | No passes | 0/4 |
| gpt-5-6-lunaopenai | mini-swe-agentpublished configuration | high | Mixed | 2/4 |
| gpt-5-6-lunaopenai | mini-swe-agentpublished configuration | xhigh | All passed | 4/4 |
| gpt-5-6-lunaopenai | mini-swe-agentpublished configuration | max | All passed | 4/4 |
| gpt-5-6-solopenai | mini-swe-agentpublished configuration | low | All passed | 4/4 |
| gpt-5-6-solopenai | mini-swe-agentpublished configuration | medium | All passed | 4/4 |
| gpt-5-6-solopenai | mini-swe-agentpublished configuration | high | All passed | 4/4 |
| gpt-5-6-solopenai | mini-swe-agentpublished configuration | xhigh | All passed | 4/4 |
| gpt-5-6-solopenai | mini-swe-agentpublished configuration | max | All passed | 4/4 |
| gpt-5-6-terraopenai | mini-swe-agentpublished configuration | low | Mixed | 2/4 |
| gpt-5-6-terraopenai | mini-swe-agentpublished configuration | medium | Mixed | 2/4 |
| gpt-5-6-terraopenai | mini-swe-agentpublished configuration | high | Mixed | 3/4 |
| gpt-5-6-terraopenai | mini-swe-agentpublished configuration | xhigh | All passed | 4/4 |
| gpt-5-6-terraopenai | mini-swe-agentpublished configuration | max | All passed | 4/4 |
| kimi-k2-7-codeopenrouter | mini-swe-agentpublished configuration | default | All passed | 4/4 |