Remove the proposed public `maxReseedHistoryChars` config surface and scale Claude CLI reseed history automatically from the resolved context tier instead.
Claude CLI 200K-context runs now keep a 64K-character reseed slice, 1M Opus/Sonnet runs use the bounded 256KiB cap, and non-Claude CLI backends keep the existing 12KiB default. This preserves the intended long-context behavior without adding another config option.
Verification:
- `node scripts/run-vitest.mjs src/agents/cli-runner/session-history.test.ts src/agents/cli-runner/prepare.test.ts`
- `node scripts/run-vitest.mjs src/agents/cli-runner/prepare.test.ts -t "automatic Claude CLI cap"`
- `node scripts/run-oxlint.mjs src/agents/cli-runner/prepare.ts src/agents/cli-runner/prepare.test.ts src/agents/cli-runner/session-history.ts src/agents/cli-runner/session-history.test.ts src/config/types.agent-defaults.ts src/config/zod-schema.core.ts`
- `pnpm check:changed` via Testbox `tbx_01kska2twjxb925xft9dj82hvb`
- GitHub PR checks green
Closes#83985
Co-authored-by: Abdel Gomez-Perez <nabdel07@icloud.com>
Generate the public config JSON Schema from accepted input shapes so transform-backed fields remain renderable in the Control UI. Keep transform output schemas representable with explicit string pipes, align analyzer metadata handling, and cover the generated schema plus browser-safe UI render shapes.
Co-authored-by: Altay <altay@hey.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Preserve legacy numeric stable git tags while excluding named semver prerelease tags from stable git channel detection and status display.
Thanks @goldmar.
Remove the Telegram DM thread reply policy config and use Telegram bot capability as the single source of truth for DM topic session splitting.
DM messages with message_thread_id now split into thread-scoped sessions only when Telegram getMe reports has_topics_enabled for the bot. Doctor removes retired dm.threadReplies and direct.*.threadReplies keys, docs explain the upgrade behavior, and startup keeps cached bot info as a non-auth fallback when a fresh probe fails.
Refs #86513.
Thanks @alexph-dev.
Verification:
- pnpm docs:list
- pnpm exec oxfmt --check --threads=1 extensions/telegram/src/channel.ts extensions/telegram/src/channel.gateway.test.ts extensions/telegram/src/doctor-contract.ts extensions/telegram/src/doctor.test.ts
- git diff --check
- node scripts/run-vitest.mjs extensions/telegram/src/channel.gateway.test.ts extensions/telegram/src/doctor.test.ts extensions/telegram/src/bot/helpers.test.ts extensions/telegram/src/bot-message-context.dm-threads.test.ts extensions/telegram/src/config-schema.test.ts
- pnpm config:channels:check
- pnpm config:docs:check
- .agents/skills/autoreview/scripts/autoreview --mode local
- GitHub Actions: CI 26468039803, Workflow Sanity 26468040057, OpenGrep 26468039472, Real behavior proof 26468036483, CodeQL 26468039466, CodeQL Critical Quality 26468039473
Known CI caveat: checks-windows-node-test failed before tests because Windows runner setup left Node 22.19.0 active while the job requested Node 24.x; the same setup failure is present on current main CI run 26468063947.
Move meeting notes into core transcripts, remove the bundled meeting-notes plugin/API, and require explicit transcripts.enabled before exposing the recording-capable tool.
Forward OpenAI-compatible frequency_penalty, presence_penalty, and seed params through the gateway/chat-completions path while keeping Responses untouched.
Verification:
- pnpm test src/gateway/openai-http.test.ts src/agents/pi-embedded-runner/extra-params.sampling.test.ts src/agents/openai-transport-stream.test.ts
- CI passed on head 9abb9466d9 after rerunning cancelled jobs: preflight, critical quality network-runtime-boundary, security high, checks, docs, Real behavior proof.
Co-authored-by: lellansin <lellansin@gmail.com>
Behavior addressed: Native Codex app-server threads now disable Codex's built-in personality on thread/start, thread/resume, turn/start, bound conversation turns, and /btw side-thread forks so OpenClaw agent workspace identity stays authoritative.
Real environment tested: Local OpenClaw source checkout plus GitHub CI on PR #85891.
Exact steps or command run after this patch: pnpm test extensions/codex/src/app-server/thread-lifecycle.test.ts extensions/codex/src/app-server/side-question.test.ts extensions/codex/src/conversation-binding.test.ts extensions/codex/src/app-server/schema-normalization-runtime-contract.test.ts; pnpm check:docs; pnpm prompt:snapshots:check; OPENCLAW_ADDITIONAL_BOUNDARY_SHARD=1/4 OPENCLAW_ADDITIONAL_BOUNDARY_CONCURRENCY=4 node scripts/run-additional-boundary-checks.mjs.
Evidence after fix: Focused Codex test shard passed 4 files / 79 tests; docs check passed; prompt snapshots are current; CI passed all code/quality checks, with only Real behavior proof failing as unrelated proof-bot gating for this non-channel change.
Observed result after fix: App-server request snapshots and unit tests include personality: "none" on native Codex start/resume/turn/fork paths.
What was not tested: A live Codex app-server model run was not executed.
Co-authored-by: Beru <beru@lastguru.lv>
scripts/docs-spellcheck.sh uses set -u and constructs args=( ... "${write_flag[@]}" ), where write_flag may be an empty array. On bash 3.2 (still the default /bin/bash on macOS), referencing an empty array under set -u raises an unbound variable error. Newer bash (>= 4.4) handles this expression correctly, which is why the script ships green on Linux CI runners.
Switch to the bash 3.2-safe parameter expansion ${write_flag[@]+"${write_flag[@]}"}: it expands to nothing when the array is empty and to the array contents otherwise, preserving --write behavior unchanged.
Also fixes overrideable -> overridable in docs/reference/test.md, which the now-running spellcheck surfaces.
Repro:
bash scripts/docs-spellcheck.sh # was: write_flag[@]: unbound variable, exit 1
bash scripts/docs-spellcheck.sh # now: codespell runs to completion
