Over-context warnings now distinguish a hard token limit from the compaction window.
What's wrong with this entry?
When the conversation is over budget, the warning now says which kind of limit was hit: a hard token limit produces the "Context exceeds the N-token limit" wording, and anything else produces the compaction-window wording.
- The same distinction is exposed to tooling as an over-limit object carrying how many tokens over you are and which kind it is.
- The field is documented as describing how the window was resolved, not as a prediction of whether the API will accept the request.
"Present when total_tokens exceeds raw_max_tokens. kind says how the window was resolved
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
Related
Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.
-
v2.1.239
Skill text carried through compaction is no longer mistaken for a live request
Both mention compaction
-
v2.1.247
Summarizing uses the same prompt assembly as the rest of the conversation
Both mention compaction
-
v2.1.247
Compaction builds its system prompt with the shared assembler
Both mention compaction