Unverified50% confidenceBenchmarkExact time
On July 13, 2025, the same canary repository was used for testing: Claude Code 2.1.204 only sent POST api.anthropic.com/v1/messages; Codex sent model conversations to chatgpt.com via WebSocket along with telemetry; Gemini 0.38.2 ran idle in API-key mode with no bundle, and a real task hit a 429 quota error. None of the three uploaded a repository bundle.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/15/2026
First Seen
Valid until: 10/29/2026
Sources
Related Entities
Related Claims
UnverifiedGemini exposes a chat completions endpoint that is compatible with the OpenAI format.68% similarUnverifiedPlatforms such as ChatGPT and Gemini have not opened systematic answer-scraping interfaces, requiring tool providers to rely on other methods to collect data.66% similarUnverifiedIn the Gemini API's continuation protocol, a single streaming request is capped at 65,536 tokens, while a non-streaming direct HTTP request is 32,768.65% similarUnverifiedWhen Gemini's quota is exhausted it throws a gRPC-style RESOURCE_EXHAUSTED error wrapped in an HTTP 429 response, rather than returning a custom header suite.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1040629API
curl https://kongchang.com/api/v1/knowledge/claims/1040629MCP
get_claim(id=1040629)