Show current thinking level in Telegram picker by obviyus · Pull Request #78278 · openclaw/openclaw

obviyus · 2026-05-06T04:46:55Z

Summary:

Show the current thinking level above Telegram's native /think picker.
Resolve the displayed level from the target session override first, then agent/default model thinking config.
Cover explicit session and configured-default cases in Telegram native command tests.

Real behavior proof:

Maintainer tested the Telegram /think picker after the fix; the picker now shows the current thinking level before the option buttons. Screenshot evidence: Show current thinking level in Telegram picker #78278 (comment)

Verification:

pnpm test extensions/telegram/src/bot-native-commands.session-meta.test.ts
pnpm exec oxfmt --check --threads=1 CHANGELOG.md extensions/telegram/src/bot-native-commands.ts extensions/telegram/src/bot-native-commands.session-meta.test.ts
pnpm check:changed

clawsweeper · 2026-05-06T04:50:12Z

Codex review: passed.

Summary
The PR updates Telegram native /think argument menu rendering to prefix the current thinking level, adds precedence tests, and adds a changelog entry.

Reproducibility: yes. at source level: current main renders the Telegram native /think picker with only the generic argument-menu title while the docs say no-argument /think shows the current level. The contributor screenshot also proves the corrected visible behavior after the patch.

Real behavior proof
Sufficient (screenshot): The PR comment includes a real Telegram screenshot showing /think displaying the current thinking level above the native picker after the fix.

Next step before merge
No repair lane is needed; this automerge-opted PR has no actionable code findings and exact-head checks can gate merge.

Security
Cleared: The diff only changes Telegram command display logic, focused tests, and the changelog, with no dependency, workflow, secret, package, or code-execution surface change.

Review details

Best possible solution:

Land the PR once exact-head merge gates accept the supplied proof and CI, keeping shared thinking default resolution as the source of truth.

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

Yes, at source level: current main renders the Telegram native /think picker with only the generic argument-menu title while the docs say no-argument /think shows the current level. The contributor screenshot also proves the corrected visible behavior after the patch.

Is this the best way to solve the issue?

Yes. The patch keeps the change inside Telegram native command title formatting, reuses the shared session/default thinking resolver path, and adds focused precedence coverage.

What I checked:

Current main lacks picker status text: Current main sends the generic command argument menu title directly for Telegram native menus, so the /think picker only says to choose a level. (extensions/telegram/src/bot-native-commands.ts:1009, 6febffb6feb0)
Documented expected behavior: The thinking docs say sending /think with no argument should show the current thinking level. Public docs: docs/tools/thinking.md. (docs/tools/thinking.md:53, 6febffb6feb0)
PR head adds a Telegram-only title wrapper: The PR head adds resolveTelegramThinkMenuCurrentLevel and formatTelegramCommandArgMenuTitle, then uses the wrapper only when rendering the native /think picker. (extensions/telegram/src/bot-native-commands.ts:259, b8b9c46b5816)
Focused regression coverage: The PR head covers explicit session thinking level, configured default, target-model default over global default, and per-agent default precedence for Telegram native menus. (extensions/telegram/src/bot-native-commands.session-meta.test.ts:514, b8b9c46b5816)
Real Telegram proof inspected: The contributor's screenshot shows /status with Think: off, then /think displaying Current thinking level: off. above the native picker options. (b8b9c46b5816)
Visible exact-head checks: The GitHub check-runs API showed the visible exact-head build, docs, lint/type, security, and changed-path checks completed successfully for the PR head. (b8b9c46b5816)

Likely related people:

steipete: Introduced the native /think menu session-model alignment path that this PR extends and has recent substantial Telegram native-command maintenance. (role: introduced behavior / recent maintainer; confidence: high; commits: c6770d369468, 05eda57b3c72; files: extensions/telegram/src/bot-native-commands.ts, extensions/telegram/src/bot-native-commands.session-meta.test.ts, src/auto-reply/commands-registry.ts)
Takhoffman: Recently changed the shared thinking default resolver contract that the Telegram title helper now delegates to. (role: adjacent owner; confidence: medium; commits: 87eee6e640ab; files: src/agents/model-thinking-default.ts, src/agents/model-selection.test.ts, src/auto-reply/reply/model-selection.ts)
obviyus: Has prior merged maintenance in the Telegram native-command session metadata path, independent of authoring this PR. (role: recent maintainer; confidence: medium; commits: c57960b8d1ea; files: extensions/telegram/src/bot-native-commands.ts)

Codex review notes: model gpt-5.5, reasoning high; reviewed against 6febffb6feb0.

obviyus · 2026-05-06T04:54:50Z

Tested manually, shows current thinking level now.

obviyus · 2026-05-06T04:55:09Z

@clawsweeper automerge

clawsweeper · 2026-05-06T04:56:34Z

ClawSweeper 🐠 automerge status

No new branch changes from this pass. ClawSweeper left the branch untouched instead of making a noisy edit.

Executor outcome: source PR branch changed while the repair worker was preparing its push; requeue against the latest head.
Worker summary: this PR is the canonical automerge repair target. It is open, small, branch-writable, security-cleared, and has a passing ClawSweeper code review, but automerge is blocked by the failing Real behavior proof check, so the next deterministic action is to repair the contributor branch and rerun exact-head gates rather than merge or close.

Worker actions:

fix_needed on this PR: planned - Allowed actions include fix and raise_pr, but merge and close are blocked by job policy. Because the canonical contributor PR is useful and branch-writable, repair the contributor branch instead of replacing it.
build_fix_artifact on cluster:automerge-openclaw-openclaw-78278: planned - A cluster-scoped fix artifact is required for a maintainer-calibrated open canonical PR that is not merge-ready yet.

No branch push, rebase, replacement PR, merge, or ClawSweeper re-review was started on this pass.

fish notes: model gpt-5.5, reasoning high.

Automerge progress:

2026-05-06 05:18:03 UTC Codex write preflight (passed) in 28s Run: https://github.com/openclaw/clawsweeper/actions/runs/25417777132 danger-full-access

2026-05-06 05:21:49 UTC Codex edit 1 03e74756a82f (complete) in 4m 14s Run: https://github.com/openclaw/clawsweeper/actions/runs/25417777132 exit 0

2026-05-06 05:31:15 UTC validation and review 1 b8b9c46b5816 (base moved) in 13m 40s Run: https://github.com/openclaw/clawsweeper/actions/runs/25417777132 rebased

2026-05-06 05:31:20 UTC repair completed b8b9c46b5816 (branch updated) in 13m 45s Run: https://github.com/openclaw/clawsweeper/actions/runs/25417777132 initial automerge rebase is delegated to Codex repair

2026-05-06 05:31:19 UTC review queued b8b9c46b5816 (after repair)

2026-05-06 05:31:56 UTC automerge wait b8b9c46b5816 (blocked) in 14m 21s Run: https://github.com/openclaw/clawsweeper/actions/runs/25417777132 GitHub checks failed: Real behavior proof:FAILURE

2026-05-06 05:31:58 UTC repair finished b8b9c46b5816 (pushed) in 14m 23s Run: https://github.com/openclaw/clawsweeper/actions/runs/25417777132 repair_contributor_branch

2026-05-06 05:39:50 UTC review passed b8b9c46b5816 (structured ClawSweeper verdict: pass (sha=b8b9c46b5816704789725d89fcb6f606aa341...)

2026-05-06 05:40:17 UTC repair queued b8b9c46b5816 (autonomous) Run: https://github.com/openclaw/clawsweeper/actions/runs/25418521797

2026-05-06 05:43:12 UTC repair started (running) in 0s Run: https://github.com/openclaw/clawsweeper/actions/runs/25418521797 automerge-openclaw-openclaw-78278

2026-05-06 05:43:22 UTC validation plan (passed) in 10s Run: https://github.com/openclaw/clawsweeper/actions/runs/25418521797 pnpm check:changed

2026-05-06 05:43:42 UTC Codex write preflight (passed) in 30s Run: https://github.com/openclaw/clawsweeper/actions/runs/25418521797 danger-full-access

2026-05-06 05:49:23 UTC Codex edit 1 2a7fdec47c06 (complete) in 6m 12s Run: https://github.com/openclaw/clawsweeper/actions/runs/25418521797 exit 0

2026-05-06 05:52:56 UTC validation and review 1 5e6814bb1e0d (base moved) in 9m 45s Run: https://github.com/openclaw/clawsweeper/actions/runs/25418521797 rebased

2026-05-06 05:52:59 UTC repair completed (no branch change) in 9m 47s Run: https://github.com/openclaw/clawsweeper/actions/runs/25418521797 source PR branch changed while the repair worker was preparing its push; requeue against the latest head

2026-05-06 05:53:00 UTC repair finished (blocked) in 9m 48s Run: https://github.com/openclaw/clawsweeper/actions/runs/25418521797 source PR branch changed while the repair worker was preparing its push; requeue against the latest head

obviyus · 2026-05-06T05:46:31Z

@clawsweeper stop

clawsweeper · 2026-05-06T05:47:42Z

🦞✅
Got it. ClawSweeper will leave this item for human review.

I added clawsweeper:human-review, removed clawsweeper:automerge, and paused the automation trail until a maintainer asks again.

obviyus · 2026-05-06T05:54:52Z

Landed via rebase as 98cbf7f.

Verification:

pnpm test extensions/telegram/src/bot-native-commands.session-meta.test.ts
pnpm exec oxfmt --check --threads=1 CHANGELOG.md extensions/telegram/src/bot-native-commands.ts extensions/telegram/src/bot-native-commands.session-meta.test.ts
pnpm check:changed

openclaw-barnacle Bot added channel: telegram Channel integration: telegram size: S maintainer Maintainer-authored PR labels May 6, 2026

obviyus self-assigned this May 6, 2026

clawsweeper Bot added the clawsweeper:automerge Maintainer opted this PR into bounded ClawSweeper-reviewed automerge label May 6, 2026

clawsweeper Bot force-pushed the fix/telegram-think-current-level branch from 171a9ad to 5f83a20 Compare May 6, 2026 05:07

clawsweeper Bot added the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 6, 2026

clawsweeper Bot force-pushed the fix/telegram-think-current-level branch from 5f83a20 to b8b9c46 Compare May 6, 2026 05:31

github-actions Bot mentioned this pull request May 6, 2026

🦞 OpenClaw 生态日报 2026-05-06 ivanweng2077/big_model_radar#2

Open

clawsweeper Bot added clawsweeper:human-review Needs maintainer review before ClawSweeper can continue and removed clawsweeper:automerge Maintainer opted this PR into bounded ClawSweeper-reviewed automerge labels May 6, 2026

fix: show current think level in Telegram picker (openclaw#78278)

6a550f1

obviyus force-pushed the fix/telegram-think-current-level branch from b8b9c46 to 6a550f1 Compare May 6, 2026 05:52

obviyus merged commit 98cbf7f into openclaw:main May 6, 2026
105 of 107 checks passed

github-actions Bot mentioned this pull request May 6, 2026

📡 Upstream Digest — 2026-05-06 06:25 UTC curtismercier/openclaw-mods#780

Open

github-actions Bot pushed a commit to Desicool/openclaw that referenced this pull request May 9, 2026

fix: show current think level in Telegram picker (openclaw#78278)

58b47de

github-actions Bot pushed a commit to Desicool/openclaw that referenced this pull request May 24, 2026

fix: show current think level in Telegram picker (openclaw#78278)

006bdd5

jameslcowan pushed a commit to jameslcowan/openclaw that referenced this pull request Jun 2, 2026

fix: show current think level in Telegram picker (openclaw#78278)

4dee6f3

sablehead pushed a commit to sablehead/openclaw that referenced this pull request Jun 10, 2026

fix: show current think level in Telegram picker (openclaw#78278)

ae3ad56

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Show current thinking level in Telegram picker#78278

Show current thinking level in Telegram picker#78278
obviyus merged 1 commit into
openclaw:mainfrom
obviyus:fix/telegram-think-current-level

obviyus commented May 6, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 6, 2026 •

edited

Loading

Uh oh!

obviyus commented May 6, 2026

Uh oh!

obviyus commented May 6, 2026

Uh oh!

clawsweeper Bot commented May 6, 2026 •

edited

Loading

Uh oh!

obviyus commented May 6, 2026

Uh oh!

clawsweeper Bot commented May 6, 2026

Uh oh!

Uh oh!

obviyus commented May 6, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

obviyus commented May 6, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented May 6, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

obviyus commented May 6, 2026

Uh oh!

obviyus commented May 6, 2026

Uh oh!

clawsweeper Bot commented May 6, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

obviyus commented May 6, 2026

Uh oh!

clawsweeper Bot commented May 6, 2026

Uh oh!

Uh oh!

obviyus commented May 6, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

obviyus commented May 6, 2026 •

edited

Loading

clawsweeper Bot commented May 6, 2026 •

edited

Loading

clawsweeper Bot commented May 6, 2026 •

edited

Loading