Repository navigation
Conversation
… relic - Dead letters: a panel (✕ N in the top bar) listing every failed tool call with agent, tool, args, first error line, and what the failure cost: the number of later identical calls by the same agent and their token cost. Click a row to select the tool call on the canvas. - Compaction: the parser recognizes the continuation summary Claude Code writes after a compaction, resets the session's context accounting to system prompt + summary, and emits context_compacted. The canvas shows a bubble with before → after tokens, the timeline gets a 'Compacted' block, and the transcript keeps the summary as a relic. https://claude.ai/code/session_01AGs5TZo6yxv7NHARHawyJf
|
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Two small things that give shape to events that are currently invisible.
Dead letters. A panel (
✕ Nin the top bar's panel group) lists every failed tool call: agent, tool, args, first line of the error, and what the failure cost, i.e. how many later identical calls the same agent made and their token cost. Clicking a row selects the tool call on the canvas. Derived entirely from the existingtoolCallsstate, no backend change.Compaction relic. The parser recognizes the continuation summary Claude Code writes as the first user message after a compaction. It resets the session's context accounting to system prompt + summary (the old context really is gone) and emits a
context_compactedevent. The orchestrator shows a bubble with before → after tokens, the timeline gets a 'Compacted' block, and the transcript keeps the summary text as the relic.https://claude.ai/code/session_01AGs5TZo6yxv7NHARHawyJf