doc: add context-limit and exceedance errors guidance to tool-timeouts#146
Open
dembrane-sam-bot wants to merge 1 commit into
Open
doc: add context-limit and exceedance errors guidance to tool-timeouts#146dembrane-sam-bot wants to merge 1 commit into
dembrane-sam-bot wants to merge 1 commit into
Conversation
dembrane-sam-bot
enabled auto-merge
July 17, 2026 05:14
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What is this change?
Adds context-limit and exceedance errors guidance to . It outlines how to recognize model exceptions and details the protocol for resolving them (avoiding unconstrained retries, applying range-bound/chunked reading, and enforcing temporal limits).
What did Sam notice that led to this?
During start-of-day maintenance, we noticed session failed with a token limit exceedance while querying large files during journal read loops. Rather than treating this as a simple transient failure, the mentor-review pass flagged this as a structural vulnerability requiring codified guidance to ensure we fail-safe and apply range-bound operations.
Tier?
Tier 1 (Prose/capabilities).
Confidence
Fully confident in this addition.