Skip to content

Commit 3186e7a

Browse files
vincentkocvincentkoc
authored
Merge branch 'main' into fix/problem-bundle-lsp-cancel
2 parents 880303e + ba826be commit 3186e7a

648 files changed

Lines changed: 16565 additions & 1772 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎.agents/skills/autoreview/SKILL.md‎

Lines changed: 11 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@ description: "Pre-commit/ship code review: Codex default; optional Claude, Pi, D
77

88
Run the bundled structured review helper as a closeout check. This is code review, not Guardian `auto_review` approval routing.
99

10-
Codex review is the default when no engine is set. It uses `gpt-5.5` by default, usually delivers the best review results, and should remain the normal final closeout engine. Claude review is optional and uses `claude-fable-5` by default.
10+
Codex review is the default when no engine is set. It uses `gpt-5.6-sol` by default, usually delivers the best review results, and should remain the normal final closeout engine. Claude review is optional and uses `claude-fable-5` by default.
1111

1212
For user-visible behavior, pair autoreview with `behavior-validator`. Autoreview is source-aware and judges the change bundle; behavior validation is source-blind and judges the running product or tool against a behavior contract. A clean autoreview is not proof that a UI, CLI, API, or generated artifact works from the user's perspective.
1313

@@ -185,13 +185,13 @@ Run multiple reviewers against one frozen bundle:
185185
Set reviewer models and thinking/effort explicitly:
186186

187187
```bash
188-
"$AUTOREVIEW" --reviewers codex,claude --model codex=gpt-5.5 --thinking codex=high --model claude=claude-fable-5 --thinking claude=max
188+
"$AUTOREVIEW" --reviewers codex,claude --model codex=gpt-5.6-sol --thinking codex=high --model claude=claude-fable-5 --thinking claude=max
189189
```
190190

191191
Inline syntax is also supported for simple model IDs:
192192

193193
```bash
194-
"$AUTOREVIEW" --reviewers codex:gpt-5.5:high,claude:claude-fable-5:max
194+
"$AUTOREVIEW" --reviewers codex:gpt-5.6-sol:high,claude:claude-fable-5:max
195195
```
196196

197197
For models with slashes or extra colons, prefer keyed form:
@@ -200,9 +200,9 @@ For models with slashes or extra colons, prefer keyed form:
200200
"$AUTOREVIEW" --engine pi --model anthropic/claude-sonnet-4 --thinking high
201201
"$AUTOREVIEW" --engine opencode --model opencode/north-mini-code-free --thinking high
202202
"$AUTOREVIEW" --engine cursor --model auto --cursor-allow-workspace-instructions
203-
"$AUTOREVIEW" --reviewers codex,pi --model codex=gpt-5.5 --model pi=anthropic/claude-sonnet-4
204-
"$AUTOREVIEW" --reviewers codex,opencode --model codex=gpt-5.5 --model opencode=opencode/north-mini-code-free
205-
"$AUTOREVIEW" --reviewers codex,cursor --model codex=gpt-5.5 --model cursor=auto --cursor-allow-workspace-instructions
203+
"$AUTOREVIEW" --reviewers codex,pi --model codex=gpt-5.6-sol --model pi=anthropic/claude-sonnet-4
204+
"$AUTOREVIEW" --reviewers codex,opencode --model codex=gpt-5.6-sol --model opencode=opencode/north-mini-code-free
205+
"$AUTOREVIEW" --reviewers codex,cursor --model codex=gpt-5.6-sol --model cursor=auto --cursor-allow-workspace-instructions
206206
```
207207

208208
`--reviewers all` covers Codex, Claude, Copilot, Pi, and OpenCode. Cursor requires both explicit selection (`--engine cursor` or named in `--reviewers`) and `--cursor-allow-workspace-instructions` because the current Cursor CLI does not document a per-run flag that ignores project-local instructions/config. Droid selection currently fails closed because its CLI cannot disable both project instructions and all tools.
@@ -215,14 +215,14 @@ Recommended model defaults:
215215

216216
| Engine | Default model | Source note |
217217
| ------------------- | ---------------- | ----------------------------------------------------- |
218-
| **codex** (default) | `gpt-5.5` | OpenAI's current GPT-5.5 alias |
218+
| **codex** (default) | `gpt-5.6-sol` | OpenAI's current high-capability GPT-5.6 tier |
219219
| **claude** | `claude-fable-5` | Anthropic's most capable widely released Claude model |
220220

221221
CLI flags and environment variables override these defaults. Droid, Copilot, Pi, Cursor, and OpenCode do not get built-in model defaults here because their provider catalogs are external to the Codex/Claude closeout path and may vary by installation.
222222

223223
| Engine | Model flag | Example model IDs | Thinking flag | Accepted levels |
224224
| ------------------- | -------------------------- | ---------------------------------------------------------------------------- | ----------------------------- | ------------------------------------------------------ |
225-
| **codex** (default) | `codex --model X exec ...` | `gpt-5.5`, `gpt-5.5-2026-04-23` | `-c model_reasoning_effort=Y` | `none`, `minimal`, `low`, `medium`, `high`, `xhigh` |
225+
| **codex** (default) | `codex --model X exec ...` | `gpt-5.6-sol`, `gpt-5.6-luna` | `-c model_reasoning_effort=Y` | `none`, `minimal`, `low`, `medium`, `high`, `xhigh` |
226226
| **claude** | `claude --model X` | `claude-fable-5`, `claude-opus-4-8`, `claude-sonnet-4-6`, `claude-haiku-4-5` | `--effort Y` | `low`, `medium`, `high`, `xhigh`, `max` |
227227
| **droid** | currently refused | Factory model IDs | `-r, --reasoning-effort Y` | `off`, `none`, `low`, `medium`, `high`, `xhigh`, `max` |
228228
| **copilot** | `copilot --model X` | `gpt-5.2`, Copilot model aliases | not supported | n/a |
@@ -236,7 +236,7 @@ Examples matching current `main` behavior:
236236

237237
```bash
238238
# Codex with explicit model and reasoning
239-
"$AUTOREVIEW" --engine codex --model gpt-5.5 --thinking high
239+
"$AUTOREVIEW" --engine codex --model gpt-5.6-sol --thinking high
240240

241241
# Codex fast mode (priority service tier); needs a model whose catalog lists the tier, silently standard otherwise
242242
"$AUTOREVIEW" --engine codex --codex-speed fast
@@ -277,7 +277,7 @@ loader such as an untracked `.envrc`; the helper does not write a config file.
277277
| `AUTOREVIEW_MODEL` | Override the built-in default `--model` for all engines |
278278
| `AUTOREVIEW_THINKING` | Default `--thinking` for all engines |
279279
| `AUTOREVIEW_FALLBACK_MODEL` | Default Claude `--fallback-model` chain |
280-
| `AUTOREVIEW_<ENGINE>_MODEL` | Per-engine model override, for example `AUTOREVIEW_CODEX_MODEL=gpt-5.5` |
280+
| `AUTOREVIEW_<ENGINE>_MODEL` | Per-engine model override, for example `AUTOREVIEW_CODEX_MODEL=gpt-5.6-sol` |
281281
| `AUTOREVIEW_<ENGINE>_THINKING` | Per-engine thinking override |
282282
| `AUTOREVIEW_CODEX_CONFIG` | Default Codex `-c key=value` overrides, semicolon-separated, e.g. `service_tier="fast"`; isolation flags still win |
283283
| `AUTOREVIEW_CODEX_SPEED` | Default Codex service tier: `fast` (priority), `flex`, or `default`; silently standard when the model does not list the tier |
@@ -346,7 +346,7 @@ The helper:
346346
- supports `--dry-run`, `--parallel-tests`, `--parallel-tests-shell`, `--prompt`, repo-relative `--prompt-file`, repo-relative `--dataset`, `--no-tools`, `--no-web-search`, repeatable Codex-only `--codex-config key=value`, Codex-only `--codex-speed fast|flex|default`, and commit refs
347347
- supports `--stream-engine-output` or `AUTOREVIEW_STREAM_ENGINE_OUTPUT=1` for live engine text while preserving structured validation; Codex, Claude, and Cursor hide tool/file event details, emit compact activity summaries, and report usage at turn completion
348348
- supports opt-in review panels with `--panel` / `--reviewers`, plus per-engine `--model`, `--thinking`, and Claude `--fallback-model`
349-
- uses built-in model defaults `codex=gpt-5.5` and `claude=claude-fable-5`; honors `AUTOREVIEW_MODEL`, `AUTOREVIEW_THINKING`, `AUTOREVIEW_FALLBACK_MODEL`, and per-engine `AUTOREVIEW_<ENGINE>_MODEL` / `AUTOREVIEW_<ENGINE>_THINKING` environment overrides when CLI flags are omitted
349+
- uses built-in model defaults `codex=gpt-5.6-sol` and `claude=claude-fable-5`; honors `AUTOREVIEW_MODEL`, `AUTOREVIEW_THINKING`, `AUTOREVIEW_FALLBACK_MODEL`, and per-engine `AUTOREVIEW_<ENGINE>_MODEL` / `AUTOREVIEW_<ENGINE>_THINKING` environment overrides when CLI flags are omitted
350350
- allows read-only tools and web search by default where the selected CLI supports them; forbids nested review in the prompt; Codex is run through `codex exec` with auth-only user settings, read-only sandbox, reviewed-repo instruction/config/rule isolation flags, and structured output
351351
- runs Claude with `--safe-mode` (`v2.1.169+`), `--setting-sources user`, MCP disabled, explicit allowed tools, and `--fallback-model` when set, so reviewed-repo hooks/skills/MCP do not affect the review run while normal auth still works; managed settings policy can still apply
352352
- refuses Droid reviews until the CLI exposes a complete project-instruction and tool-isolation contract

‎.agents/skills/autoreview/scripts/autoreview‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -87,7 +87,7 @@ SECRET_VALUE_PATTERNS = [
8787
MAX_BUNDLE_TEXT_BYTES = 180_000
8888
DEFAULT_ENGINE_PATHS = ("/usr/local/bin", "/usr/bin", "/bin")
8989
DEFAULT_MODEL_BY_ENGINE = {
90-
"codex": "gpt-5.5",
90+
"codex": "gpt-5.6-sol",
9191
"claude": "claude-fable-5",
9292
}
9393
THINKING_LEVELS_BY_ENGINE = {
@@ -3123,12 +3123,12 @@ def parse_args() -> argparse.Namespace:
31233123
parser.add_argument("--base")
31243124
parser.add_argument("--commit", default="HEAD")
31253125
parser.add_argument("--engine", choices=ENGINE_CHOICES, default=os.environ.get("AUTOREVIEW_ENGINE", "codex"))
3126-
parser.add_argument("--reviewers", help="Comma-separated review panel, e.g. codex,claude,cursor or codex:gpt-5.5:high.")
3126+
parser.add_argument("--reviewers", help="Comma-separated review panel, e.g. codex,claude,cursor or codex:gpt-5.6-sol:high.")
31273127
parser.add_argument("--panel", action="store_true", help="Run a Codex/Claude review panel unless --engine changes the first reviewer.")
31283128
parser.add_argument(
31293129
"--model",
31303130
action="append",
3131-
help="Model for all reviewers or engine=model. Repeatable. Defaults: codex=gpt-5.5, claude=claude-fable-5.",
3131+
help="Model for all reviewers or engine=model. Repeatable. Defaults: codex=gpt-5.6-sol, claude=claude-fable-5.",
31323132
)
31333133
parser.add_argument("--thinking", action="append", help="Thinking/effort for all reviewers or engine=level. Repeatable. Codex: none, minimal, low, medium, high, xhigh. Claude: low, medium, high, xhigh, max. Droid: off, none, low, medium, high. Pi: off, minimal, low, medium, high, xhigh. OpenCode: minimal, low, medium, high, max. Cursor: none.")
31343134
parser.add_argument(
@@ -3533,7 +3533,7 @@ def self_test_config_defaults() -> None:
35333533
]
35343534
with preserve_env(keys):
35353535
default_codex = reviewer_args(reviewer_test_args(engine="codex"))[0]
3536-
if default_codex.model != "gpt-5.5":
3536+
if default_codex.model != "gpt-5.6-sol":
35373537
raise SystemExit(f"self-test config defaults failed: default codex model={default_codex.model!r}")
35383538
default_claude = reviewer_args(reviewer_test_args(engine="claude"))[0]
35393539
if default_claude.model != "claude-fable-5":

‎.agents/skills/clawsweeper/SKILL.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -140,7 +140,7 @@ pnpm run repair:dispatch -- jobs/openclaw/inbox/clawsweeper-openclaw-openclaw-12
140140
--mode autonomous \
141141
--runner blacksmith-4vcpu-ubuntu-2404 \
142142
--execution-runner blacksmith-16vcpu-ubuntu-2404 \
143-
--model gpt-5.5
143+
--model gpt-5.6-sol
144144
```
145145

146146
Do not dispatch a just-created job before the job file is committed and pushed;

‎.agents/skills/openclaw-live-updater/SKILL.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -38,7 +38,7 @@ Keep `/Users/steipete/openclaw` a read-only-to-the-agent deployment mirror: clea
3838

3939
Re-run the canonical freshness check immediately before every `pnpm openclaw` restart or probe so the source runner cannot hide stale output with an implicit auto-build. Every pass, including a no-update/current-build pass, must run deep RPC status and verbose health. If that first probe fails while the build is already exact-current, perform one managed Gateway restart and repeat both probes once. Do not rebuild a current exact-SHA artifact merely to self-heal the managed process; fail and diagnose if the one restart does not recover it.
4040

41-
3. If changed paths can affect macOS, the helper runs `scripts/restart-mac.sh --sign --wait --target-only` only after the exact-SHA JS/UI build completes. Target-only mode may stop the canonical `/Applications/OpenClaw.app` process and this checkout's exact `dist` process before launching the rebuilt `dist` app. It defers when another worktree, temporary bundle, test, or agent-owned OpenClaw process is active; it never kills that process. The script's immediate `OK` is not proof. The helper waits and requires the exact executable `/Users/steipete/openclaw/dist/OpenClaw.app/Contents/MacOS/OpenClaw`, then repeats Gateway RPC and health proof.
41+
3. If changed paths can affect macOS, the helper runs `scripts/restart-mac.sh --sign --wait --target-only` with `SKIP_TSC=1` and `SKIP_UI_BUILD=1` only after the exact-SHA JS/UI build completes. Reusing those artifacts keeps the live app bundle out of any later JavaScript build cleanup. Target-only mode may stop the canonical `/Applications/OpenClaw.app` process and this checkout's exact `dist` process before launching the rebuilt `dist` app. It defers when another worktree, temporary bundle, test, or agent-owned OpenClaw process is active; it never kills that process. The script's immediate `OK` is not proof. The helper waits and requires the exact executable `/Users/steipete/openclaw/dist/OpenClaw.app/Contents/MacOS/OpenClaw`, then repeats Gateway RPC and health proof.
4242

4343
Never kill another worktree, temporary bundle, test, or agent-owned OpenClaw process. If a foreign app prevents the exact target from staying alive, record the pending Mac attempt, report it, and retry on the next heartbeat. Escalate only after the conflict persists across repeated heartbeats; never claim Mac proof from another bundle or the short launch check. If `actions.macUiVerification` is true, exercise the changed behavior with the existing macOS/UI automation workflow after delayed exact-bundle proof.
4444

‎.agents/skills/openclaw-live-updater/scripts/update-main.mjs‎

Lines changed: 13 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -855,9 +855,20 @@ export function maintainMain(options, dependencies = {}) {
855855
};
856856
writeMaintenanceState(statePath, pendingState);
857857
try {
858+
// The exact-SHA JS build above already produced dist/control-ui. Letting
859+
// Mac packaging rebuild it can empty dist while the live app bundle is
860+
// there, defeating the staged-swap guarantee.
858861
runCommand(
859-
"bash",
860-
["scripts/restart-mac.sh", "--sign", "--wait", "--target-only"],
862+
"env",
863+
[
864+
"SKIP_TSC=1",
865+
"SKIP_UI_BUILD=1",
866+
"bash",
867+
"scripts/restart-mac.sh",
868+
"--sign",
869+
"--wait",
870+
"--target-only",
871+
],
861872
update.checkout,
862873
);
863874
const macTarget = verifyMacTarget(update.checkout);

‎.github/labeler.yml‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -380,6 +380,10 @@
380380
- any-glob-to-any-file:
381381
- "extensions/clawrouter/**"
382382
- "docs/providers/clawrouter.md"
383+
"extensions: crabbox":
384+
- changed-files:
385+
- any-glob-to-any-file:
386+
- "extensions/crabbox/**"
383387
"extensions: deepseek":
384388
- changed-files:
385389
- any-glob-to-any-file:

0 commit comments

Comments
 (0)