From 0a9a76d2be39a52831edc1b2d97262153ff66daa Mon Sep 17 00:00:00 2001 From: "openclaw-docs-sync[bot]" Date: Fri, 24 Apr 2026 01:49:46 +0000 Subject: [PATCH] chore(sync): mirror docs from openclaw/openclaw@903308dbf2f909baddb70f441222ad4fc064a25c --- .openclaw-sync/source.json | 4 ++-- docs/concepts/qa-e2e-automation.md | 14 +++++++------- docs/help/testing.md | 6 +++--- 3 files changed, 12 insertions(+), 12 deletions(-) diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json index 93cf75977..4da476dc1 100644 --- a/.openclaw-sync/source.json +++ b/.openclaw-sync/source.json @@ -1,5 +1,5 @@ { "repository": "openclaw/openclaw", - "sha": "86f69ba5a06ae256906c3a26308801e0b84e0091", - "syncedAt": "2026-04-24T01:41:03.210Z" + "sha": "903308dbf2f909baddb70f441222ad4fc064a25c", + "syncedAt": "2026-04-24T01:48:15.958Z" } diff --git a/docs/concepts/qa-e2e-automation.md b/docs/concepts/qa-e2e-automation.md index 2d5ee45a9..af0b43e20 100644 --- a/docs/concepts/qa-e2e-automation.md +++ b/docs/concepts/qa-e2e-automation.md @@ -207,7 +207,7 @@ refs and write a judged Markdown report: ```bash pnpm openclaw qa character-eval \ - --model openai-codex/gpt-5.5,thinking=xhigh \ + --model openai/gpt-5.4,thinking=medium,fast \ --model openai/gpt-5.2,thinking=xhigh \ --model openai/gpt-5,thinking=xhigh \ --model anthropic/claude-opus-4-6,thinking=high \ @@ -215,7 +215,7 @@ pnpm openclaw qa character-eval \ --model zai/glm-5.1,thinking=high \ --model moonshot/kimi-k2.5,thinking=high \ --model google/gemini-3.1-pro-preview,thinking=high \ - --judge-model openai-codex/gpt-5.5,thinking=xhigh,fast \ + --judge-model openai/gpt-5.4,thinking=xhigh,fast \ --judge-model anthropic/claude-opus-4-6,thinking=high \ --blind-judge-models \ --concurrency 16 \ @@ -227,13 +227,13 @@ scenarios should set the persona through `SOUL.md`, then run ordinary user turns such as chat, workspace help, and small file tasks. The candidate model should not be told that it is being evaluated. The command preserves each full transcript, records basic run stats, then asks the judge models in fast mode with -`xhigh` reasoning to rank the runs by naturalness, vibe, and humor. +`xhigh` reasoning where supported to rank the runs by naturalness, vibe, and humor. Use `--blind-judge-models` when comparing providers: the judge prompt still gets every transcript and run status, but candidate refs are replaced with neutral labels such as `candidate-01`; the report maps rankings back to real refs after parsing. -Candidate runs default to `high` thinking, with `xhigh` for OpenAI models that -support it. Override a specific candidate inline with +Candidate runs default to `high` thinking, with `medium` for GPT-5.4 and `xhigh` +for older OpenAI eval refs that support it. Override a specific candidate inline with `--model provider/model,thinking=`. `--thinking ` still sets a global fallback, and the older `--model-thinking ` form is kept for compatibility. @@ -247,12 +247,12 @@ Candidate and judge model runs both default to concurrency 16. Lower `--concurrency` or `--judge-concurrency` when provider limits or local gateway pressure make a run too noisy. When no candidate `--model` is passed, the character eval defaults to -`openai-codex/gpt-5.5`, `openai/gpt-5.4`, `openai/gpt-5.2`, `anthropic/claude-opus-4-6`, +`openai/gpt-5.4`, `openai/gpt-5.2`, `openai/gpt-5`, `anthropic/claude-opus-4-6`, `anthropic/claude-sonnet-4-6`, `zai/glm-5.1`, `moonshot/kimi-k2.5`, and `google/gemini-3.1-pro-preview` when no `--model` is passed. When no `--judge-model` is passed, the judges default to -`openai-codex/gpt-5.5,thinking=xhigh,fast` and +`openai/gpt-5.4,thinking=xhigh,fast` and `anthropic/claude-opus-4-6,thinking=high`. ## Related docs diff --git a/docs/help/testing.md b/docs/help/testing.md index 43a329639..318f585f0 100644 --- a/docs/help/testing.md +++ b/docs/help/testing.md @@ -680,7 +680,7 @@ Docker notes: `agent` method: - load the bundled `codex` plugin - select `OPENCLAW_AGENT_RUNTIME=codex` - - send a first gateway agent turn to `openai/gpt-5.5` with the Codex harness forced + - send a first gateway agent turn to `openai/gpt-5.4` with the Codex harness forced - send a second turn to the same OpenClaw session and verify the app-server thread can resume - run `/codex status` and `/codex models` through the same gateway command @@ -690,7 +690,7 @@ Docker notes: denied so the agent asks back - Test: `src/gateway/gateway-codex-harness.live.test.ts` - Enable: `OPENCLAW_LIVE_CODEX_HARNESS=1` -- Default model: `openai/gpt-5.5` +- Default model: `openai/gpt-5.4` - Optional image probe: `OPENCLAW_LIVE_CODEX_HARNESS_IMAGE_PROBE=1` - Optional MCP/tool probe: `OPENCLAW_LIVE_CODEX_HARNESS_MCP_PROBE=1` - Optional Guardian probe: `OPENCLAW_LIVE_CODEX_HARNESS_GUARDIAN_PROBE=1` @@ -708,7 +708,7 @@ OPENCLAW_LIVE_CODEX_HARNESS=1 \ OPENCLAW_LIVE_CODEX_HARNESS_IMAGE_PROBE=1 \ OPENCLAW_LIVE_CODEX_HARNESS_MCP_PROBE=1 \ OPENCLAW_LIVE_CODEX_HARNESS_GUARDIAN_PROBE=1 \ - OPENCLAW_LIVE_CODEX_HARNESS_MODEL=openai/gpt-5.5 \ + OPENCLAW_LIVE_CODEX_HARNESS_MODEL=openai/gpt-5.4 \ pnpm test:live -- src/gateway/gateway-codex-harness.live.test.ts ```