Results / truncation.text-stream
Streamed text cut off by the output token limit
The model stops at the output token limit in the middle of a streamed plain-text answer.
Bug class: Truncation not reported as truncation
The provider stopped at the output token limit, but the library reports a normal finish, a generic parse error, or a partial result as success.
Agents accept partial output or retry without raising the limit, and structured pipelines ingest incomplete records.
Requirements
| Level | Id | Check | Requirement | Providers |
|---|---|---|---|---|
| MUST | cause-is-truncation | truncation_is_signalled | The caller can tell that the stream stopped at the token limit. | All |
| SHOULD | text-reported | text_matches_truth | The streamed text is reported exactly as the provider sent it. | All |
| SHOULD | usage-reported | usage_matches_truth | Output token usage is reported, and matches the provider's count. | All |
Fixtures
| Provider | Tier | any-llm | litellm | pydantic-ai | tanstack-ai | vercel-ai |
|---|---|---|---|---|---|---|
| anthropic | documented | ✓ PASS | ✓ PASS | ✓ PASS | ✓ PASS | ✓ PASS |
| gemini | recorded | ✓ PASS | ✓ PASS | ✓ PASS | ✓ PASS | ✓ PASS |
| ollama | recorded | ✓ PASS | ✓ PASS | – UNSUPPORTED | ✓ PASS | – UNSUPPORTED |
| ollama-openai | recorded | ✓ PASS | ✓ PASS | ✓ PASS | ✓ PASS | ✓ PASS |
| openai-chat | recorded | ✓ PASS | ✓ PASS | ✓ PASS | ✓ PASS | ✓ PASS |
| openai-responses | recorded | ✓ PASS | ✓ PASS | ✓ PASS | ✓ PASS | ✓ PASS |