From 53bdac249dbdba7724b7737250a89112675c0c82 Mon Sep 17 00:00:00 2001 From: Peter Steinberger Date: Sun, 5 Jul 2026 01:26:25 -0400 Subject: [PATCH] docs: restore source-backed contract details (#100182) --- docs/automation/cron-jobs.md | 2 +- docs/help/environment.md | 2 +- docs/help/testing-live.md | 2 ++ docs/nodes/talk.md | 2 +- docs/reference/full-release-validation.md | 4 ++-- docs/snippets/plugin-publish/minimal-package.json | 6 ++++++ 6 files changed, 13 insertions(+), 5 deletions(-) diff --git a/docs/automation/cron-jobs.md b/docs/automation/cron-jobs.md index cff3036dce1..0f240f32869 100644 --- a/docs/automation/cron-jobs.md +++ b/docs/automation/cron-jobs.md @@ -141,7 +141,7 @@ Fast mode follows the resolved live selection. If the selected model config has If a run hits a live model-switch handoff, cron retries with the switched provider/model and persists that selection (and any new auth profile) for the active run. Retries are bounded: after the initial attempt plus 2 switch retries, cron aborts instead of looping. -Before an isolated run starts, OpenClaw checks reachable local endpoints for configured `api: "ollama"` and `api: "openai-completions"` providers whose `baseUrl` is loopback, private-network, or `.local`. This preflight walks the job's configured fallback chain and only marks the run `skipped` once every candidate is unreachable; `--fallbacks ""` keeps that walk strict to just the primary model. A down endpoint records the run as `skipped` with a clear error instead of starting a model call. The result is cached for 5 minutes per endpoint (not per job or model), so many due jobs sharing a dead local Ollama/vLLM/SGLang/LM Studio server cost one probe instead of a request storm. Skipped preflight runs do not increment execution-error backoff; set `failureAlert.includeSkipped` to opt into repeated skip alerts. +Before an isolated run starts, OpenClaw checks reachable local endpoints for configured `api: "ollama"` and `api: "openai-completions"` providers whose `baseUrl` is loopback, private-network, or `.local`. Local-provider preflight checks walk configured fallbacks and only mark the run `skipped` once every candidate is unreachable; `--fallbacks ""` keeps that walk strict to just the primary model. A down endpoint records the run as `skipped` with a clear error instead of starting a model call. The result is cached for 5 minutes per endpoint (not per job or model), so many due jobs sharing a dead local Ollama/vLLM/SGLang/LM Studio server cost one probe instead of a request storm. Skipped preflight runs do not increment execution-error backoff; set `failureAlert.includeSkipped` to opt into repeated skip alerts. ### Command payloads diff --git a/docs/help/environment.md b/docs/help/environment.md index 712d19c88c1..caae6ea1b20 100644 --- a/docs/help/environment.md +++ b/docs/help/environment.md @@ -8,7 +8,7 @@ title: "Environment variables" --- OpenClaw pulls environment variables from multiple sources. The rule is **never override existing values**. -Workspace `.env` files are a lower-trust source: OpenClaw ignores provider credentials and protected runtime controls from workspace `.env` before applying precedence. +Workspace `.env` files are a lower-trust source: OpenClaw ignores provider credential environment variables from workspace `.env` files and protected runtime controls there before applying precedence. ## Precedence (highest to lowest) diff --git a/docs/help/testing-live.md b/docs/help/testing-live.md index 7328a6f9396..38ac4c3e666 100644 --- a/docs/help/testing-live.md +++ b/docs/help/testing-live.md @@ -65,6 +65,8 @@ The curated model lists below live in `src/agents/live-model-filter.ts` and change over time; treat the arrays there as the source of truth, not this page. +MiniMax M3 uses `minimax/MiniMax-M3` as its default provider/model reference. + ### Layer 1: Direct model completion (no gateway) - Test: `src/agents/models.profiles.live.test.ts` diff --git a/docs/nodes/talk.md b/docs/nodes/talk.md index 001f46594e2..5930ce01839 100644 --- a/docs/nodes/talk.md +++ b/docs/nodes/talk.md @@ -91,7 +91,7 @@ Supported keys: `voice` / `voice_id` / `voiceId`, `model` / `model_id` / `modelI | `providers.mlx.modelId` | `mlx-community/Soprano-80M-bf16` | | | `providers.elevenlabs.apiKey` | - | Falls back to `ELEVENLABS_API_KEY` (or gateway shell profile if available). | | `speechLocale` | device default | BCP 47 locale id for on-device Talk speech recognition on iOS/macOS. | -| `silenceTimeoutMs` | `700` ms macOS/Android, `900` ms iOS | Pause window before Talk sends the transcript. | +| `silenceTimeoutMs` | 700 ms on macOS and Android, 900 ms on iOS | Pause window before Talk sends the transcript. | | `interruptOnSpeech` | `true` | | | `outputFormat` | `pcm_44100` macOS/iOS, `pcm_24000` Android | Set `mp3_*` to force MP3 streaming. | | `consultThinkingLevel` | unset | Thinking level override for the agent run behind realtime `openclaw_agent_consult` calls. | diff --git a/docs/reference/full-release-validation.md b/docs/reference/full-release-validation.md index 4d61776ccc9..591a0e85a72 100644 --- a/docs/reference/full-release-validation.md +++ b/docs/reference/full-release-validation.md @@ -190,8 +190,8 @@ underlying QA runtime parity lane is advisory. Tideclaw alpha runs may still treat non-package-safety release-check lanes as advisory. When `live_suite_filter` explicitly requests a gated QA live lane such as Discord, WhatsApp, or Slack, the matching `OPENCLAW_RELEASE_QA_*_LIVE_CI_ENABLED` repo -variable must be enabled; otherwise input capture fails instead of silently -skipping the lane. Rerun `rerun_group=qa`, `qa-parity`, or `qa-live` when you +variable must be enabled; otherwise input capture fails instead of silently skipping the lane. +Rerun `rerun_group=qa`, `qa-parity`, or `qa-live` when you need fresh QA evidence. ## Evidence to keep diff --git a/docs/snippets/plugin-publish/minimal-package.json b/docs/snippets/plugin-publish/minimal-package.json index 45c7b27830d..a2cf37587e1 100644 --- a/docs/snippets/plugin-publish/minimal-package.json +++ b/docs/snippets/plugin-publish/minimal-package.json @@ -2,6 +2,12 @@ "name": "@myorg/openclaw-my-plugin", "version": "1.0.0", "type": "module", + "dependencies": { + "typebox": "1.1.39" + }, + "peerDependencies": { + "openclaw": ">=2026.3.24-beta.2" + }, "openclaw": { "extensions": ["./index.ts"], "compat": {