fix(webui): keep tool activity paired without model calls#103821
Merged
Conversation
openclaw-barnacle
Bot
added
docs
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: b2ef5b1e4d
ℹ️ About Codex in GitHub
Your team has set up Codex to 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 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| continue; | ||
| } | ||
| const operation = readOperation(record.kind); | ||
| const section = startSection(collector, operation, sourcePath); |
Contributor
There was a problem hiding this comment.
When a structured Codex changes entry has a path/kind but no diff or stat (the projector explicitly preserves that shape when change.diff is absent), this still creates a section with the default {added: 0, removed: 0}. Once the paired result marks the card succeeded, the row renders a misleading +0 -0 stat even though the counts are unknown; omit the stat or require a real diff/stat before surfacing it.
Useful? React with 👍 / 👎.
openclaw-barnacle
Bot
added
app: android
openclaw-barnacle
Bot
removed
app: android
openclaw-barnacle
Bot
removed
extensions: qa-lab
channel: sms
Contributor
Author
|
Land-ready proof for exact head
Known proof gap: split-pane overflow was not separately screenshot-validated; the 1200px rendered artifact plus DOM/CSS regressions cover the changed rows. No open review findings. |
Contributor
|
Codex review: stale review; fresh review needed. Summary Next step |
Contributor
Author
|
Merged via squash.
|
This was referenced Jul 10, 2026
steipete
added a commit
that referenced
this pull request
Jul 11, 2026
Restores the chat.toolTitles path removed in #103821, gated behind the new gateway.controlUi.toolTitles opt-in (default false) so tool rendering stays fully deterministic with no background model calls unless an operator enables it. Disabled gateways answer { titles: {}, disabled: true } without loading the completion runtime, and clients stop asking for the session. When enabled, titles use canonical utility-model routing: an explicit utilityModel (operator-chosen provider, like every utility task), else the session provider's declared small-model default, honoring per-session model overrides and auth profiles; utilityModel "" disables titles and malformed refs fail closed — never the primary model. Tool inputs are redacted with the tools-mode redactor before cache keys or prompts, caller ids are bounded and never reach the model, and results cache in the per-agent SQLite cache_entries so repeat views never re-bill. Also completes two crestodian model-input mock factories that leaked into sibling tests under shared-registry CI shards. Fixes #103987
steipete
added a commit
that referenced
this pull request
Jul 11, 2026
…3989) * feat(webui): reintroduce opt-in AI purpose titles for tool calls Restores the chat.toolTitles path removed in #103821, gated behind the new gateway.controlUi.toolTitles opt-in (default false) so tool rendering stays fully deterministic with no background model calls unless an operator enables it. Disabled gateways answer { titles: {}, disabled: true } without loading the completion runtime, and clients stop asking for the session. When enabled, titles use canonical utility-model routing: an explicit utilityModel (operator-chosen provider, like every utility task), else the session provider's declared small-model default, honoring per-session model overrides and auth profiles; utilityModel "" disables titles and malformed refs fail closed — never the primary model. Tool inputs are redacted with the tools-mode redactor before cache keys or prompts, caller ids are bounded and never reach the model, and results cache in the per-agent SQLite cache_entries so repeat views never re-bill. Also completes two crestodian model-input mock factories that leaked into sibling tests under shared-registry CI shards. Fixes #103987 * fix(webui): redact tool-title inputs before truncation
github-actions Bot
pushed a commit
to Desicool/openclaw
that referenced
this pull request
Jul 11, 2026
…03821) * fix(webui): make tool activity rendering deterministic * fix(protocol): remove stale tool-title models * fix(i18n): translate tool activity labels * fix(i18n): translate tool activity labels
github-actions Bot
pushed a commit
to Desicool/openclaw
that referenced
this pull request
Jul 11, 2026
…nclaw#103989) * feat(webui): reintroduce opt-in AI purpose titles for tool calls Restores the chat.toolTitles path removed in openclaw#103821, gated behind the new gateway.controlUi.toolTitles opt-in (default false) so tool rendering stays fully deterministic with no background model calls unless an operator enables it. Disabled gateways answer { titles: {}, disabled: true } without loading the completion runtime, and clients stop asking for the session. When enabled, titles use canonical utility-model routing: an explicit utilityModel (operator-chosen provider, like every utility task), else the session provider's declared small-model default, honoring per-session model overrides and auth profiles; utilityModel "" disables titles and malformed refs fail closed — never the primary model. Tool inputs are redacted with the tools-mode redactor before cache keys or prompts, caller ids are bounded and never reach the model, and results cache in the per-agent SQLite cache_entries so repeat views never re-bill. Also completes two crestodian model-input mock factories that leaked into sibling tests under shared-registry CI shards. Fixes openclaw#103987 * fix(webui): redact tool-title inputs before truncation
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.
Closes #103554.
Follow-up to #103748, which merged while its review fixups were still being prepared.
What Problem This Solves
Fixes an issue where Control UI users could still get duplicated or orphaned tool-result rows for parallel and repeated tool calls, incomplete multi-file diffs, and misleading success/edit labels. The merged implementation also added a view-triggered model RPC for decorative titles, which could send tool arguments to a provider, spend utility-model tokens, and persist a new cache solely to label activity rows.
Why This Change Was Made
This keeps the useful redesign deterministic: call-ID-indexed pairing, semantic rows, bounded per-file diffs, truthful running/success/failure outcomes, and preserved edit details across history reloads. It removes the
chat.toolTitlesprotocol, gateway, cache, and UI path; tool activity no longer needs background model egress or spend.Codex compatibility was checked against the upstream raw freeform
apply_patchcontract and structured app-server file-change contract before implementing the parser/projector paths. AI-assisted by Codex; I reviewed the resulting behavior, source boundaries, tests, and rendered output.User Impact
Visual baseline
Evidence
tbx_01kx6bf52wd5bbyab8rkj4yc09: 601 focused assertions passed across UI, gateway, Codex event projection, and edit-diff paths.8241ab08773d68db2ae1ee41967e0ef036c19ad9175e6ee854c502043a1d7113.check:changedplus production build passed on Blacksmith Testbox. Exact PR-head CI is green: 55 jobs, zero failures (run 29110107026).No changelog edit: release notes are release-owned in the current prepare flow.