Google Cloud Support directed us here because our reproduction uses the Gemini Developer API / Google AI Studio.
We are investigating a long tool-using conversation where the model exhausts its output budget in thinking and returns neither a visible answer nor a function call. We would appreciate guidance on expected behaviour and supported thinking controls.
Environment
- Native REST request to
https://generativelanguage.googleapis.com/v1alpha/models/gemini-4-argon:generateContent, bypassing proxies and the evaluation SDK. - History contains 48 function calls with matching tool responses. Historical thought signatures, function names and argument objects were preserved.
- Signed-history prompt token count: 295,553.
- Output cap: 8,192 tokens. Signed replays explicitly used
thinkingConfig.thinkingLevel=loworhigh, withincludeThoughts=true. No separate numeric thinking budget was imposed.
Native replay results
Tests were run on November 3, 2026; all returned HTTP 200. One attempt per condition, without retries.
| Condition | Duration | Thinking tokens | Candidate tokens | Result |
|---|---|---|---|---|
| Signatures preserved, low | 91.769s | 8,189 | 3 | MAX_TOKENS; thought text only; no answer/functionCall |
| Signatures preserved, high | 103.775s | 8,189 | 3 | Same outcome |
| Signatures preserved, high; remove only 48 empty text parts before function calls | 131.389s | 8,189 | 3 | Same outcome |
| Diagnostic control: high; replace historical signatures with skip_thought_signature_validator | 12.346s | Not reported | 241 | STOP with a functionCall |
The third condition reported 293,504 cached input tokens. The diagnostic control had 254,209 prompt tokens, so it changes historical thought state and prompt size. It is not an equivalent-quality comparison or a proposed workaround.
These capped requests demonstrate budget exhaustion, not an indefinite hang. We understand that thinking consumes output budget; we have not established that this behaviour is a product defect or that a larger cap would fail.
Questions for the Gemini team
- Is it expected that
thinkingLevel=lowcan consume essentially the entire 8,192-token output budget without leaving an answer or next tool call on this history? Are there supported controls to bound thinking separately for this exact model? - Are there known degradation or looping cases with long signed tool histories? What history-preservation or compaction rules are recommended without discarding reasoning context?
- How should a tool-using client recover from a thought-only
MAX_TOKENSresponse while preserving valid signatures and conversation state? - Both v1alpha and v1beta
models.getreturnedversion=3.0,inputTokenLimit=1048576, andoutputTokenLimit=32768. Please confirm the supported output ceiling and how it relates to thinking tokens for this model/API.
The complete conversation contains confidential task data and cannot be posted publicly. We have native response IDs for all four requests. Could a Google team member provide a private channel to share those IDs and, subject to authorization, the exact reproduction? No API keys, prompts or signature values are included here.