farcasclaudiu/openclaw
1
0
Fork 0
mirror of https://github.com/farcasclaudiu/openclaw.git synced 2026-06-29 07:01:40 +03:00
Code Issues Packages Projects Releases Wiki Activity

chore: apply local workspace updates (#9911)

Browse Source 
* chore: apply local workspace updates

* fix: resolve prep findings after rebase (#9898) (thanks @gumadeiras)

* refactor: centralize model allowlist normalization (#9898) (thanks @gumadeiras)

* fix: guard model allowlist initialization (#9911)

* docs: update changelog scope for #9911

* docs: remove model names from changelog entry (#9911)

* fix: satisfy type-aware lint in model allowlist (#9911)
This commit is contained in:
Gustavo Madeira Santana
2026-02-05 16:54:44 -05:00
committed by GitHub
parent 93b450349f
commit 4629054403
72 changed files with 722 additions and 251 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/gateway/cli-backends.md
+7 -5
View File
@@ -25,13 +25,13 @@ want “always works” text responses without relying on external APIs.
You can use Claude Code CLI **without any config** (OpenClaw ships a built-in default):
```bash
openclaw agent --message "hi" --model claude-cli/opus-4.5
openclaw agent --message "hi" --model claude-cli/opus-4.6
```
Codex CLI also works out of the box:
```bash
openclaw agent --message "hi" --model codex-cli/gpt-5.2-codex
openclaw agent --message "hi" --model codex-cli/gpt-5.3-codex
```
If your gateway runs under launchd/systemd and PATH is minimal, add just the
@@ -62,11 +62,12 @@ Add a CLI backend to your fallback list so it only runs when primary models fail
agents: {
defaults: {
model: {
primary: "anthropic/claude-opus-4-5",
fallbacks: ["claude-cli/opus-4.5"],
primary: "anthropic/claude-opus-4-6",
fallbacks: ["claude-cli/opus-4.6", "claude-cli/opus-4.5"],
},
models: {
"anthropic/claude-opus-4-5": { alias: "Opus" },
"anthropic/claude-opus-4-6": { alias: "Opus" },
"claude-cli/opus-4.6": {},
"claude-cli/opus-4.5": {},
},
},
@@ -112,6 +113,7 @@ The provider id becomes the left side of your model ref:
input: "arg",
modelArg: "--model",
modelAliases: {
"claude-opus-4-6": "opus",
"claude-opus-4-5": "opus",
"claude-sonnet-4-5": "sonnet",
},
docs/gateway/configuration-examples.md
+4 -4
View File
@@ -226,13 +226,13 @@ Save to `~/.openclaw/openclaw.json` and you can DM the bot from that number.
userTimezone: "America/Chicago",
model: {
primary: "anthropic/claude-sonnet-4-5",
fallbacks: ["anthropic/claude-opus-4-5", "openai/gpt-5.2"],
fallbacks: ["anthropic/claude-opus-4-6", "openai/gpt-5.2"],
},
imageModel: {
primary: "openrouter/anthropic/claude-sonnet-4-5",
},
models: {
"anthropic/claude-opus-4-5": { alias: "opus" },
"anthropic/claude-opus-4-6": { alias: "opus" },
"anthropic/claude-sonnet-4-5": { alias: "sonnet" },
"openai/gpt-5.2": { alias: "gpt" },
},
@@ -496,7 +496,7 @@ If more than one person can DM your bot (multiple entries in `allowFrom`, pairin
workspace: "~/.openclaw/workspace",
model: {
primary: "anthropic/claude-sonnet-4-5",
fallbacks: ["anthropic/claude-opus-4-5"],
fallbacks: ["anthropic/claude-opus-4-6"],
},
},
}
@@ -534,7 +534,7 @@ If more than one person can DM your bot (multiple entries in `allowFrom`, pairin
agent: {
workspace: "~/.openclaw/workspace",
model: {
primary: "anthropic/claude-opus-4-5",
primary: "anthropic/claude-opus-4-6",
fallbacks: ["minimax/MiniMax-M2.1"],
},
},
docs/gateway/configuration.md
+14 -14
View File
@@ -1547,8 +1547,8 @@ The `responsePrefix` string can include template variables that resolve dynamica
| Variable | Description | Example |
| ----------------- | ---------------------- | --------------------------- |
| `{model}` | Short model name | `claude-opus-4-5`, `gpt-4o` |
| `{modelFull}` | Full model identifier | `anthropic/claude-opus-4-5` |
| `{model}` | Short model name | `claude-opus-4-6`, `gpt-4o` |
| `{modelFull}` | Full model identifier | `anthropic/claude-opus-4-6` |
| `{provider}` | Provider name | `anthropic`, `openai` |
| `{thinkingLevel}` | Current thinking level | `high`, `low`, `off` |
| `{identity.name}` | Agent identity name | (same as `"auto"` mode) |
@@ -1564,7 +1564,7 @@ Unresolved variables remain as literal text.
}
```
Example output: `[claude-opus-4-5 | think:high] Here's my response...`
Example output: `[claude-opus-4-6 | think:high] Here's my response...`
WhatsApp inbound prefix is configured via `channels.whatsapp.messagePrefix` (deprecated:
`messages.messagePrefix`). Default stays **unchanged**: `"[openclaw]"` when
@@ -1710,7 +1710,7 @@ Z.AI GLM-4.x models automatically enable thinking mode unless you:
OpenClaw also ships a few built-in alias shorthands. Defaults only apply when the model
is already present in `agents.defaults.models`:
- `opus` -> `anthropic/claude-opus-4-5`
- `opus` -> `anthropic/claude-opus-4-6`
- `sonnet` -> `anthropic/claude-sonnet-4-5`
- `gpt` -> `openai/gpt-5.2`
- `gpt-mini` -> `openai/gpt-5-mini`
@@ -1719,18 +1719,18 @@ is already present in `agents.defaults.models`:
If you configure the same alias name (case-insensitive) yourself, your value wins (defaults never override).
Example: Opus 4.5 primary with MiniMax M2.1 fallback (hosted MiniMax):
Example: Opus 4.6 primary with MiniMax M2.1 fallback (hosted MiniMax):
```json5
{
agents: {
defaults: {
models: {
"anthropic/claude-opus-4-5": { alias: "opus" },
"anthropic/claude-opus-4-6": { alias: "opus" },
"minimax/MiniMax-M2.1": { alias: "minimax" },
},
model: {
primary: "anthropic/claude-opus-4-5",
primary: "anthropic/claude-opus-4-6",
fallbacks: ["minimax/MiniMax-M2.1"],
},
},
@@ -1786,7 +1786,7 @@ Example:
agents: {
defaults: {
models: {
"anthropic/claude-opus-4-5": { alias: "Opus" },
"anthropic/claude-opus-4-6": { alias: "Opus" },
"anthropic/claude-sonnet-4-1": { alias: "Sonnet" },
"openrouter/deepseek/deepseek-r1:free": {},
"zai/glm-4.7": {
@@ -1800,7 +1800,7 @@ Example:
},
},
model: {
primary: "anthropic/claude-opus-4-5",
primary: "anthropic/claude-opus-4-6",
fallbacks: [
"openrouter/deepseek/deepseek-r1:free",
"openrouter/meta-llama/llama-3.3-70b-instruct:free",
@@ -2011,7 +2011,7 @@ Typing indicators:
- `session.typingIntervalSeconds`: per-session override for the refresh interval.
See [/concepts/typing-indicators](/concepts/typing-indicators) for behavior details.
`agents.defaults.model.primary` should be set as `provider/model` (e.g. `anthropic/claude-opus-4-5`).
`agents.defaults.model.primary` should be set as `provider/model` (e.g. `anthropic/claude-opus-4-6`).
Aliases come from `agents.defaults.models.*.alias` (e.g. `Opus`).
If you omit the provider, OpenClaw currently assumes `anthropic` as a temporary
deprecation fallback.
@@ -2485,7 +2485,7 @@ the built-in `opencode` provider from pi-ai; set `OPENCODE_API_KEY` (or
Notes:
- Model refs use `opencode/<modelId>` (example: `opencode/claude-opus-4-5`).
- Model refs use `opencode/<modelId>` (example: `opencode/claude-opus-4-6`).
- If you enable an allowlist via `agents.defaults.models`, add each model you plan to use.
- Shortcut: `openclaw onboard --auth-choice opencode-zen`.
@@ -2493,8 +2493,8 @@ Notes:
{
agents: {
defaults: {
model: { primary: "opencode/claude-opus-4-5" },
models: { "opencode/claude-opus-4-5": { alias: "Opus" } },
model: { primary: "opencode/claude-opus-4-6" },
models: { "opencode/claude-opus-4-6": { alias: "Opus" } },
},
},
}
@@ -2652,7 +2652,7 @@ Use MiniMax M2.1 directly without LM Studio:
agent: {
model: { primary: "minimax/MiniMax-M2.1" },
models: {
"anthropic/claude-opus-4-5": { alias: "Opus" },
"anthropic/claude-opus-4-6": { alias: "Opus" },
"minimax/MiniMax-M2.1": { alias: "Minimax" },
},
},
docs/gateway/heartbeat.md
+1 -1
View File
@@ -83,7 +83,7 @@ and logged; a message that is only `HEARTBEAT_OK` is dropped.
defaults: {
heartbeat: {
every: "30m", // default: 30m (0m disables)
model: "anthropic/claude-opus-4-5",
model: "anthropic/claude-opus-4-6",
includeReasoning: false, // default: false (deliver separate Reasoning: message when available)
target: "last", // last | none | <channel id> (core or plugin, e.g. "bluebubbles")
to: "+15551234567", // optional channel-specific override
docs/gateway/local-models.md
+3 -3
View File
@@ -21,7 +21,7 @@ Best current local stack. Load MiniMax M2.1 in LM Studio, enable the local serve
defaults: {
model: { primary: "lmstudio/minimax-m2.1-gs32" },
models: {
"anthropic/claude-opus-4-5": { alias: "Opus" },
"anthropic/claude-opus-4-6": { alias: "Opus" },
"lmstudio/minimax-m2.1-gs32": { alias: "Minimax" },
},
},
@@ -68,12 +68,12 @@ Keep hosted models configured even when running local; use `models.mode: "merge"
defaults: {
model: {
primary: "anthropic/claude-sonnet-4-5",
fallbacks: ["lmstudio/minimax-m2.1-gs32", "anthropic/claude-opus-4-5"],
fallbacks: ["lmstudio/minimax-m2.1-gs32", "anthropic/claude-opus-4-6"],
},
models: {
"anthropic/claude-sonnet-4-5": { alias: "Sonnet" },
"lmstudio/minimax-m2.1-gs32": { alias: "MiniMax Local" },
"anthropic/claude-opus-4-5": { alias: "Opus" },
"anthropic/claude-opus-4-6": { alias: "Opus" },
},
},
},
docs/gateway/security/index.md
+1 -1
View File
@@ -243,7 +243,7 @@ Even with strong system prompts, **prompt injection is not solved**. System prom
- Run sensitive tool execution in a sandbox; keep secrets out of the agent’s reachable filesystem.
- Note: sandboxing is opt-in. If sandbox mode is off, exec runs on the gateway host even though tools.exec.host defaults to sandbox, and host exec does not require approvals unless you set host=gateway and configure exec approvals.
- Limit high-risk tools (`exec`, `browser`, `web_fetch`, `web_search`) to trusted agents or explicit allowlists.
- **Model choice matters:** older/legacy models can be less robust against prompt injection and tool misuse. Prefer modern, instruction-hardened models for any bot with tools. We recommend Anthropic Opus 4.5 because it’s quite good at recognizing prompt injections (see [“A step forward on safety”](https://www.anthropic.com/news/claude-opus-4-5)).
- **Model choice matters:** older/legacy models can be less robust against prompt injection and tool misuse. Prefer modern, instruction-hardened models for any bot with tools. We recommend Anthropic Opus 4.6 (or the latest Opus) because it’s strong at recognizing prompt injections (see [“A step forward on safety”](https://www.anthropic.com/news/claude-opus-4-5)).
Red flags to treat as untrusted: