feat(tui): add cache-expiry hint dialog for resumed and idle sessions (v2 engine) - #2646
Merged
Conversation
…nd emit telemetry Track consecutive turn-scoped LLM requests per agent; when the cache-read token count drops by more than 5% and by more than 2000 tokens between requests, log a debug line and emit cache_break_detected with both usages, the drop ratio, and the interval. Operation requests (e.g. compaction) act as a baseline barrier so expected drops are not reported.
… (v2 engine) Resuming a long-idle session or submitting after a long idle stretch re-sends the whole history with an expired context cache. Show a dialog offering to compact, start a new session, continue as-is, or never ask again (persisted as cache_expiry_hint in tui.toml). Thresholds come from the client_configs endpoint (estimated_cache_duration) via a generic per-name cached client; only OAuth-managed providers participate.
🦋 Changeset detectedLatest commit: 69fd057 The changes in this PR will be included in the next version bump. This PR includes changesets to release 1 package
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
commit: |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: c0d33bc4c0
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
…flows Cold-cache submits during the in-flight config fetch are now swallowed and replayed through a FIFO chain, so a later prompt can never overtake the stashed one. Both the resume and idle paths re-check the current session after the async fetch: a switch mid-flight drops the dialog (resume) or hands the stashed input back to the editor instead of sending it into the wrong session (idle).
Collaborator
Author
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 1d380ffcd0
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
Collaborator
Author
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 9b7ff8f111
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
When several submits are swallowed during the cold-config fetch and the first dialog is dismissed (or its compact/new action fails), the stashed inputs were restored while later chained submits were still released — reordering the conversation. Chained submits now follow the fate of the message that opened the dialog, and multiple restores append newline-joined instead of overwriting the editor.
Caches are per-model, so a cache-read drop after /model is expected, not a break. The baseline now carries the model and only same-model records are compared.
Collaborator
Author
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: e0a2513739
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
… hint The v2 resume replay also carries local-only state records (permission, plan, config updates, approval results) that slash commands append without an LLM request. Filter lastActiveAt to message/compaction records so a recent local change no longer masks an expired cache.
…convention State the domain role, collaborators, and scope instead of narrating implementation steps; the behavior guards now live in the code alone.
Collaborator
Author
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 4180109a81
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
The resume dialog is fire-and-forget over an async config fetch; if the user already sent the first prompt by the time it resolves, mounting would overlay an active turn and its actions would hit the live session. Re-check streamingPhase/isCompacting after the await, next to the session check.
Collaborator
Author
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: c92e4445a0
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
Move the detector out of the engine so the telemetry event carries the client's own identity (which client produced it is now attributable). The TUI observes main-loop turn.step.completed usage directly, with the same guards: first-step/unmeasured/all-zero records skipped, model change and compaction reset the baseline. The agent-core-v2 cacheBreak module is removed.
Contributor
|
❌ Nix build failed |
…tches A model or effort change mid-session busts the prompt-cache key — that is a real cache break worth attributing, not noise. The baseline now carries model and effort, the same-model exemption is gone, and cache_break_detected reports prev/curr model and effort alongside both usages.
Collaborator
Author
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: ffc2e342f9
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
- carry the pre-dialog media extraction through compact/new resends so pasted attachments survive the image-store clear on a new session - reset the cache-break baseline after /undo — the context cut makes the next cache-read drop expected - release the stashed submit when a foreground operation started during the cold-config fetch instead of mounting the dialog over it - count a completed compaction as activity so the next submit is not judged against the pre-compaction timestamp
Collaborator
Author
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 568ca2b2f7
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
Collaborator
Author
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: f382bf7060
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
Collaborator
Author
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: eea6b30f42
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
Merged
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.
Related Issue
No linked issue — the problem is explained below.
Problem
Resuming a long-idle session, or submitting a message after the session has been idle for a long stretch, re-sends the entire history with the server-side context cache already expired — slower, more expensive, and silent today. On large sessions a single uncached replay burns a visible chunk of quota, with no warning and no cheaper alternative offered.
What changed
cache_expiry_hint = falseintui.toml, applied on/reloadtoo). The submitted input is stashed and re-sent automatically after compact / new session; Esc restores it without sending. Each resume and each idle cycle prompts at most once; submits swallowed during a cold-config fetch are replayed in order.cache_durationand its context is at leastmin_tokens_to_hint, both from the publicclient_configsendpoint (estimated_cache_duration). The newclient-configsutility (per-name schema validation, 1-day in-process cache, anonymous-capable) is generic so future client configs plug in with one name + schema. Only OAuth-managed providers participate; any missing data (no config, no usage, unknown model) silently skips the hint.cache_break_detectedwhen a step's cache-read drops >5% and >2000 tokens below the previous step, with both usages, the drop ratio, and the interval — so the event is attributable to the client that produced it. Unmeasured/all-zero usage, model changes, and compactions reset the comparison instead of reporting.Checklist
gen-changesetsskill, or this PR needs no changeset.gen-docsskill, or this PR needs no doc update.