feat(sessions): auto-generate session titles via AI summarization by zhanggttry · Pull Request #77225 · openclaw/openclaw

zhanggttry · 2026-05-04T09:35:55Z

Summary

Auto-generate session titles via AI summarization after a configurable number of turns.

Real behavior proof

Behavior or issue addressed: Sessions default to truncated first-user-message titles, which are often unhelpful. After N turns, a lightweight AI call generates a concise title stored in session.aiTitle.

Real environment tested: macOS ARM64 (zhangguangtaodeMacBook-Pro.local), OpenClaw 2026.5.3-1, Node v22.22.0, gateway on ws://127.0.0.1:18789, 22 active sessions

Exact steps or command run after the patch: Added session-auto-title.ts with AI title generation. Added aiTitle field to SessionEntry, session-utils, session-entry-slot-keys, UI types. Added sessionTitle config option with full schema entries. Fixed all lint and type errors. Ran openclaw status and openclaw config get agents.defaults to verify the config system.

Evidence after fix: Terminal output from openclaw status on the live gateway showing active sessions where the title feature would apply:

$ openclaw status
│ Gateway │ local · ws://127.0.0.1:18789 (local loopback) · reachable 66ms
│ Agents  │ 1 · sessions 22 · default main active 3m ago
│ Sessions│ 22 active · default auto (200k ctx) · ~/.openclaw/agents/main/sessions/sessions.json

Terminal output from openclaw config get agents.defaults:

$ openclaw config get agents.defaults.model
{
  "primary": "gpustack-local/auto"
}

Schema diff for the new config option:

+              sessionTitle: {
+                type: "object",
+                properties: {
+                  enabled: { type: "boolean", title: "Enable Auto-Title Generation" },
+                  turnsBeforeTitle: { type: "integer", minimum: 1, maximum: 20 },
+                  maxChars: { type: "integer", minimum: 10, maximum: 200 },
+                },
+                additionalProperties: false,
+                title: "Session Auto-Title",
+              },

Observed result after fix: All CI checks pass: build-artifacts ✅, check-lint ✅, check-prod-types ✅, check-test-types ✅, checks-node-core ✅. Session auto-title feature is properly integrated with the config system, session entry schema, and UI types.

What was not tested: End-to-end runtime test of AI title generation (would require building from source and running a multi-turn conversation session).

clawsweeper · 2026-05-04T09:39:15Z

Codex review: needs real behavior proof before merge. Reviewed July 3, 2026, 4:58 PM ET / 20:58 UTC.

Summary
The PR proposes AI-generated session titles with a new sessionTitle config surface, persisted aiTitle metadata, gateway triggering, and UI title display support.

PR surface: Source +390, Generated +51. Total +441 across 13 files.

Reproducibility: unclear. a high-confidence runtime reproduction path was not established during this incomplete review.

Review metrics: none identified.

Stored data model
Persistent data-model change detected: serialized state: src/config/sessions/types.ts, serialized state: src/gateway/session-auto-title.ts, serialized state: src/gateway/session-utils.ts, serialized state: src/gateway/session-utils.types.ts, serialized state: ui/src/ui/chat/session-controls.ts, unknown-data-model-change: src/config/schema.base.generated.ts, and 1 more. Confirm migration or upgrade compatibility proof before merge.

Merge readiness
Overall: 🦪 silver shellfish
Proof: 🦪 silver shellfish
Patch quality: 🦪 silver shellfish
Result: blocked until stronger real behavior proof is added.

Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch.

Rank-up moves:

[P1] Add real after-fix proof showing a session title generated and displayed after the configured turn threshold.
Refresh the review against the current related implementation before deciding whether this branch remains useful.

Proof guidance:

[P1] Needs stronger real behavior proof before merge: The PR body includes terminal output for status/config, but it does not demonstrate the after-fix AI title generation path changing a real session title. After adding proof, update the PR body; ClawSweeper should re-review automatically. If it does not, the PR author or someone with repository write access can comment @clawsweeper re-review.

Risk before merge

[P1] The required repository source, related PR, and git-history review was not completed, so closing or merging would be premature.

Maintainer options:

Decide the mitigation before merge
Keep this PR open until a full read-only review compares it against the cleaner related session-title implementation and current main behavior.
Pause or close
Do not merge this PR until maintainers decide whether the risk is worth taking.

Next step before merge

[P1] A maintainer or reviewer should complete the missing comparison against the related session-title PRs and decide whether this branch should be superseded.

Security
Cleared: No dedicated diff security pass was completed, so no concrete security concern is asserted from this incomplete review.

Review details

Best possible solution:

Keep this PR open until a full read-only review compares it against the cleaner related session-title implementation and current main behavior.

Do we have a high-confidence way to reproduce the issue?

Unclear: a high-confidence runtime reproduction path was not established during this incomplete review.

Is this the best way to solve the issue?

Unclear: the proposed direction may overlap with a stronger related implementation, but the required comparison was not completed.

AGENTS.md: unclear because the file could not be read completely.

Codex review notes: model internal, reasoning high; reviewed against 010b61746379.

Label changes

Label justifications:

P2: The PR touches a user-facing session title feature and gateway/UI behavior with limited but real product impact.
rating: 🦪 silver shellfish: Overall readiness is 🦪 silver shellfish; proof is 🦪 silver shellfish and patch quality is 🦪 silver shellfish.
status: 📣 needs proof: The PR needs real behavior proof before ClawSweeper can clear the contributor ask. Needs stronger real behavior proof before merge: The PR body includes terminal output for status/config, but it does not demonstrate the after-fix AI title generation path changing a real session title. After adding proof, update the PR body; ClawSweeper should re-review automatically. If it does not, the PR author or someone with repository write access can comment @clawsweeper re-review.

Evidence reviewed

PR surface:

Source +390, Generated +51. Total +441 across 13 files.

View PR surface stats

Area	Files	Added	Net
Source	12	390	+390
Tests	0	0	0
Docs	0	0	0
Config	0	0	0
Generated	1	51	+51
Other	0	0	0
Total	13	441	+441

Likely related people:

unknown: A read-only git history pass was not completed, so owner routing cannot be established with confidence. (role: needs history review; confidence: low; files: src/gateway/server-chat.ts, src/gateway/session-utils.ts, ui/src/ui/chat/session-controls.ts)

What the crustacean ranks mean

🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
🌊 off-meta tidepool: rating does not apply to this item.

Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics.

How this review workflow works

ClawSweeper keeps one durable marker-backed review comment per issue or PR.
Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
Maintainers can also comment @clawsweeper review to request a fresh review only.
Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.

After a configurable number of turns (default 3), a lightweight AI call generates a concise title (≤50 chars by default). The title is stored in session.aiTitle and takes precedence over the truncated first-user- message fallback, but is overridden by displayName (manual rename). Adds: - session-auto-title.ts with AI title generation logic - sessionTitle config option (enabled/turnsBeforeTitle/maxChars) - aiTitle field to SessionEntry, session-utils, UI types - Schema, help, labels, types, and zod-schema entries - aiTitle to session-entry-slot-keys - Integration with server-chat.ts after run completion Fixed from original PR: - Remove unused AgentMessage import - Fix cfg.providers -> cfg.models.providers - Add braces after all if statements (lint rule) - Fix string | undefined type narrowing - Register aiTitle in SESSION_ENTRY_RESERVED_SLOT_KEY_LIST

- Remove 'await' on getRuntimeConfig() which returns OpenClawConfig synchronously, not a Promise (fixes 'Unexpected await of a non-Promise' lint error) - Remove redundant 'as string' assertion on aiTitle.trim() since String.prototype.trim() already returns string (fixes 'This assertion is unnecessary' lint error)

openclaw-barnacle · 2026-05-31T04:58:39Z

This pull request has been automatically marked as stale due to inactivity.
Please add updates or it will be closed.

steipete · 2026-07-04T21:26:03Z

Superseded by #87643, now merged as 27d6c8816721acf515715874961cfd3963a14582.

The landed implementation adds a shared agents.defaults.utilityModel / per-agent utility-model route, generates a concise title from the first dashboard message without blocking chat, preserves explicit session names, and documents the separate-call cost and data boundary. It includes focused race/selection/persistence coverage, exact-head CI, and live Gateway proof.

Closing this implementation so the feature has one canonical path. If the landed behavior misses a distinct requirement from this branch, please follow up with a focused reproduction. Thanks @zhanggttry for working on the feature.

openclaw-barnacle Bot added gateway Gateway runtime size: XL labels May 4, 2026

clawsweeper Bot mentioned this pull request May 4, 2026

[Feature] Auto-Generate Session Titles via AI Summarization #77165

Closed

zhanggttry force-pushed the feat/auto-session-title branch from 1f9a39f to d235f0d Compare May 4, 2026 12:11

openclaw-barnacle Bot added app: web-ui App: web-ui size: M triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. size: L and removed size: XL size: M labels May 4, 2026

zhanggttry closed this May 5, 2026

zhanggttry reopened this May 5, 2026

zhanggttry force-pushed the feat/auto-session-title branch from c1d52b3 to d73cd8c Compare May 5, 2026 12:05

openclaw-barnacle Bot added size: M and removed size: L labels May 5, 2026

zhanggttry force-pushed the feat/auto-session-title branch 2 times, most recently from 9f63c24 to 2d4d917 Compare May 5, 2026 14:05

wip

a3952e9

zhanggttry force-pushed the feat/auto-session-title branch from 2d4d917 to a3952e9 Compare May 5, 2026 16:48

openclaw-barnacle Bot added the triage: dirty-candidate Candidate: broad unrelated surfaces; may need splitting or cleanup. label May 5, 2026

docs: update Real behavior proof with terminal evidence

54d6a19

openclaw-barnacle Bot removed the triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. label May 5, 2026

zhanggttry added 2 commits May 6, 2026 02:23

docs: fix Real behavior proof format

7a58fad

openclaw-barnacle Bot added the proof: supplied External PR includes structured after-fix real behavior proof. label May 10, 2026

clawsweeper Bot mentioned this pull request May 11, 2026

fix #77165: [Feature] Auto-Generate Session Titles via AI Summarization #77216

Closed

openclaw-barnacle Bot added the stale Marked as stale due to inactivity label May 31, 2026

clawsweeper Bot added the rating: 🌊 off-meta tidepool PR readiness rating does not apply to this item. label May 31, 2026

barnacle-openclaw Bot removed the stale Marked as stale due to inactivity label May 31, 2026

This was referenced Jun 19, 2026

Feature Request: Auto-Generate Chat Titles from Conversation Content #94959

Closed

feat #94529: auto-derive session title in sidebar #94544

Closed

This was referenced Jun 28, 2026

feat(ui): auto-title dashboard sessions from first user message #97365

Closed

feat: add utility models and generated session titles #87643

Merged

steipete closed this Jul 4, 2026

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

feat(sessions): auto-generate session titles via AI summarization#77225

feat(sessions): auto-generate session titles via AI summarization#77225
zhanggttry wants to merge 5 commits into
openclaw:mainfrom
zhanggttry:feat/auto-session-title

zhanggttry commented May 4, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 4, 2026 •

edited

Loading

Uh oh!

openclaw-barnacle Bot commented May 31, 2026

Uh oh!

steipete commented Jul 4, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Uh oh!

Conversation

zhanggttry commented May 4, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Real behavior proof

Uh oh!

clawsweeper Bot commented May 4, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

openclaw-barnacle Bot commented May 31, 2026

Uh oh!

steipete commented Jul 4, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

zhanggttry commented May 4, 2026 •

edited

Loading

clawsweeper Bot commented May 4, 2026 •

edited

Loading