- Agents/skills: apply the full effective tool policy pipeline to inline `command-dispatch: tool` skill dispatch before owner-only filtering, preserving configured allow, deny, sandbox, sender, group, and subagent restrictions. (#78525)

- Providers/GitHub Copilot: request identity-encoded Copilot API responses across token exchange, catalog, model calls, usage, and embeddings so compressed Business-account error payloads no longer reach JSON parsers as gzip bytes. Fixes #82871. Thanks @tonyfe01.

- Telegram: preserve replied-to bot messages, captions, and media metadata in group reply chains so follow-up replies understand what the user is reacting to. (#82863)

- Providers/Together: update PI runtime packages to 0.74.1 and emit Together-style `reasoning.enabled`/`max_tokens` controls for reasoning-capable OpenAI-completions models.

- Agents/diagnostics: split slow embedded-run `attempt-dispatch` startup summaries into workspace, prompt, runtime-plan, and final dispatch subspans so traces identify the delayed setup phase. Fixes #82782. (#82783) Thanks @galiniliev.

- CLI/media: accept HTTP(S) URLs in `openclaw infer image describe --file`, fetching remote images through the guarded media path instead of treating URLs as local files. Fixes #82837. (#82854) Thanks @neeravmakwana.

- Agents/subagents: keep session-backed parent runs active when the child wait call times out before the child session has actually settled, so late subagent completions are reconciled instead of being lost. Fixes #82787. Thanks @ramitrkar-hash.

- `params` merge precedence (config): `agents.defaults.params` (global base) is overridden by `agents.defaults.models["provider/model"].params` (per-model), then `agents.list[].params` (matching agent id) overrides by key. See [Prompt Caching](/reference/prompt-caching) for details.

- `params.extra_body`/`params.extraBody`: advanced pass-through JSON merged into `api: "openai-completions"` request bodies for OpenAI-compatible proxies. If it collides with generated request keys, the extra body wins; non-native completions routes still strip OpenAI-only `store` afterward.

- `params.chat_template_kwargs`: vLLM/OpenAI-compatible chat-template arguments merged into top-level `api: "openai-completions"` request bodies. For `vllm/nemotron-3-*` with thinking off, the bundled vLLM plugin automatically sends `enable_thinking: false` and `force_nonempty_content: true`; explicit `chat_template_kwargs` override generated defaults, and `extra_body.chat_template_kwargs` still has final precedence. For vLLM Qwen thinking controls, set `params.qwenThinkingFormat` to `"chat-template"` or `"top-level"` on that model entry.

- `compat.thinkingFormat`: OpenAI-compatible thinking payload style. Use `"qwen"` for Qwen-style top-level `enable_thinking`, or `"qwen-chat-template"` for `chat_template_kwargs.enable_thinking` on Qwen-family backends that support request-level chat-template kwargs, such as vLLM. OpenClaw maps disabled thinking to `false` and enabled thinking to `true`.

- `compat.thinkingFormat`: OpenAI-compatible thinking payload style. Use `"together"` for Together-style `reasoning.enabled`, `"qwen"` for Qwen-style top-level `enable_thinking`, or `"qwen-chat-template"` for `chat_template_kwargs.enable_thinking` on Qwen-family backends that support request-level chat-template kwargs, such as vLLM. OpenClaw maps disabled thinking to `false` and enabled thinking to `true`.

- `compat.supportedReasoningEfforts`: per-model OpenAI-compatible reasoning effort list. Include `"xhigh"` for custom endpoints that truly accept it; OpenClaw then exposes `/think xhigh` in command menus, Gateway session rows, session patch validation, agent CLI validation, and `llm-task` validation for that configured provider/model. Use `compat.reasoningEffortMap` when the backend wants a provider-specific value for a canonical level.

- `params.preserveThinking`: Z.AI-only opt-in for preserved thinking. When enabled and thinking is on, OpenClaw sends `thinking.clear_thinking: false` and replays prior `reasoning_content`; see [Z.AI thinking and preserved thinking](/providers/zai#thinking-and-preserved-thinking).

- `localService`: optional provider-level process manager for local/self-hosted model servers. When the selected model belongs to that provider, OpenClaw probes `healthUrl` (or `baseUrl + "/models"`), starts `command` with `args` if the endpoint is down, waits up to `readyTimeoutMs`, then sends the model request. `command` must be an absolute path. `idleStopMs: 0` keeps the process alive until OpenClaw exits; a positive value stops the OpenClaw-spawned process after that many idle milliseconds. See [Local model services](/gateway/local-model-services).

- `models.providers.*.models.*.compat.supportsDeveloperRole`: optional compatibility hint. For `api: "openai-completions"` with a non-empty non-native `baseUrl` (host not `api.openai.com`), OpenClaw forces this to `false` at runtime. Empty/omitted `baseUrl` keeps default OpenAI behavior.

- `models.providers.*.models.*.compat.requiresStringContent`: optional compatibility hint for string-only OpenAI-compatible chat endpoints. When `true`, OpenClaw flattens pure text `messages[].content` arrays into plain strings before sending the request.

- `models.providers.*.models.*.compat.strictMessageKeys`: optional compatibility hint for strict OpenAI-compatible chat endpoints. When `true`, OpenClaw strips outgoing Chat Completions message objects to `role` and `content` before sending the request.

- `models.providers.*.models.*.compat.thinkingFormat`: optional thinking payload hint. Use `"qwen"` for top-level `enable_thinking`, or `"qwen-chat-template"` for `chat_template_kwargs.enable_thinking` on Qwen-family OpenAI-compatible servers that support request-level chat-template kwargs, such as vLLM.

- `models.providers.*.models.*.compat.thinkingFormat`: optional thinking payload hint. Use `"together"` for Together-style `reasoning.enabled`, `"qwen"` for top-level `enable_thinking`, or `"qwen-chat-template"` for `chat_template_kwargs.enable_thinking` on Qwen-family OpenAI-compatible servers that support request-level chat-template kwargs, such as vLLM.

</Accordion>

<Accordion title="Amazon Bedrock discovery">

```json

{

"@earendil-works/pi-agent-core": "0.74.0",

"@earendil-works/pi-ai": "0.74.0",

"@earendil-works/pi-coding-agent": "0.74.0",

"@earendil-works/pi-tui": "0.74.0"

"@earendil-works/pi-agent-core": "0.74.1",

"@earendil-works/pi-ai": "0.74.1",

"@earendil-works/pi-coding-agent": "0.74.1",

"@earendil-works/pi-tui": "0.74.1"

}

```

"dependencies": {

"@anthropic-ai/sdk": "0.95.2",

"@aws/bedrock-token-generator": "1.1.0",

"@earendil-works/pi-ai": "0.74.0"

"@earendil-works/pi-ai": "0.74.1"

},

"devDependencies": {

"@openclaw/plugin-sdk": "workspace:*"

"@aws-sdk/client-bedrock": "3.1047.0",

"@aws-sdk/client-bedrock-runtime": "3.1045.0",

"@aws-sdk/credential-provider-node": "3.972.41",

"@earendil-works/pi-ai": "0.74.0",

"@earendil-works/pi-ai": "0.74.1",

"@smithy/shared-ini-file-loader": "4.5.2"

},

"devDependencies": {

"type": "module",

"dependencies": {

"@anthropic-ai/vertex-sdk": "0.16.0",

"@earendil-works/pi-agent-core": "0.74.0",

"@earendil-works/pi-ai": "0.74.0"

"@earendil-works/pi-agent-core": "0.74.1",

"@earendil-works/pi-ai": "0.74.1"

},

"devDependencies": {

"@openclaw/plugin-sdk": "workspace:*"

"description": "OpenClaw Anthropic provider plugin",

"type": "module",

"dependencies": {

"@earendil-works/pi-ai": "0.74.0"

"@earendil-works/pi-ai": "0.74.1"

},

"devDependencies": {

"@openclaw/plugin-sdk": "workspace:*"

},

"type": "module",

"dependencies": {

"@earendil-works/pi-coding-agent": "0.74.0",

"@earendil-works/pi-coding-agent": "0.74.1",

"@openai/codex": "0.130.0",

"ajv": "8.20.0",

"ws": "8.20.1",

"description": "OpenClaw Fireworks provider plugin",

"type": "module",

"dependencies": {

"@earendil-works/pi-ai": "0.74.0"

"@earendil-works/pi-ai": "0.74.1"

},

"devDependencies": {

"@openclaw/plugin-sdk": "workspace:*"