fix(models): honor provider context defaults

docs/.generated/config-baseline.sha256

@@ -1,4 +1,4 @@
-6fceeca87ecf3245c9f3a184f1ec66c8dee8df6e5a14c6d9d1924557f8d36408  config-baseline.json
-15b6223907d0930307e950752e6498edc40f7df597e8e36914490f7611eab413  config-baseline.core.json
+c4b54de7557cd14b35a629585ad706a4e7de411cc725bcbce921f22bfaf14ada  config-baseline.json
+3fd4da36f28b508f8e6ac4fceb18262244d8ed70df15244192032ec71027bb4f  config-baseline.core.json
 07963db49502132f26db396c56b36e018b110e6c55a68b3cb012d3ec96f43901  config-baseline.channel.json
 74b74cb18ac37c0acaa765f398f1f9edbcee4c43567f02d45c89598a1e13afb4  config-baseline.plugin.json

docs/concepts/model-providers.md

@@ -16,7 +16,7 @@ Reference for **LLM/model providers** (not chat channels like WhatsApp/Telegram)
     - Model refs use `provider/model` (example: `opencode/claude-opus-4-6`).
     - `agents.defaults.models` acts as an allowlist when set.
     - CLI helpers: `openclaw onboard`, `openclaw models list`, `openclaw models set <provider/model>`.
-    - `models.providers.*.models[].contextWindow` is native model metadata; `contextTokens` is the effective runtime cap.
+    - `models.providers.*.contextWindow` / `contextTokens` / `maxTokens` set provider-level defaults; `models.providers.*.models[].contextWindow` / `contextTokens` / `maxTokens` override them per model.
     - Fallback rules, cooldown probes, and session-override persistence: [Model failover](/concepts/model-failover).
   </Accordion>
   <Accordion title="OpenAI provider/runtime split">

docs/gateway/config-tools.md

@@ -429,6 +429,9 @@ OpenClaw uses the built-in model catalog. Add custom providers via `models.provi
     - `models.providers.*.api`: request adapter (`openai-completions`, `openai-responses`, `anthropic-messages`, `google-generative-ai`, etc).
     - `models.providers.*.apiKey`: provider credential (prefer SecretRef/env substitution).
     - `models.providers.*.auth`: auth strategy (`api-key`, `token`, `oauth`, `aws-sdk`).
+    - `models.providers.*.contextWindow`: default native context window for models under this provider when the model entry does not set `contextWindow`.
+    - `models.providers.*.contextTokens`: default effective runtime context cap for models under this provider when the model entry does not set `contextTokens`.
+    - `models.providers.*.maxTokens`: default output-token cap for models under this provider when the model entry does not set `maxTokens`.
     - `models.providers.*.timeoutSeconds`: optional per-provider model HTTP request timeout in seconds, including connect, headers, body, and total request abort handling.
     - `models.providers.*.injectNumCtxForOpenAICompat`: for Ollama + `openai-completions`, inject `options.num_ctx` into requests (default: `true`).
     - `models.providers.*.authHeader`: force credential transport in the `Authorization` header when required.
@@ -447,8 +450,8 @@ OpenClaw uses the built-in model catalog. Add custom providers via `models.provi
   </Accordion>
   <Accordion title="Model catalog entries">
     - `models.providers.*.models`: explicit provider model catalog entries.
-    - `models.providers.*.models.*.contextWindow`: native model context window metadata.
-    - `models.providers.*.models.*.contextTokens`: optional runtime context cap. Use this when you want a smaller effective context budget than the model's native `contextWindow`; `openclaw models list` shows both values when they differ.
+    - `models.providers.*.models.*.contextWindow`: native model context window metadata. This overrides provider-level `contextWindow` for that model.
+    - `models.providers.*.models.*.contextTokens`: optional runtime context cap. This overrides provider-level `contextTokens`; use it when you want a smaller effective context budget than the model's native `contextWindow`; `openclaw models list` shows both values when they differ.
     - `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.
   </Accordion>

docs/providers/ollama.md

@@ -462,7 +462,7 @@ For the full setup and behavior details, see [Ollama Web Search](/tools/ollama-s
   <Accordion title="Context windows">
     For auto-discovered models, OpenClaw uses the context window reported by Ollama when available, including larger `PARAMETER num_ctx` values from custom Modelfiles. Otherwise it falls back to the default Ollama context window used by OpenClaw.
 
-    You can override `contextWindow` and `maxTokens` in explicit provider config. To cap Ollama's per-request runtime context without rebuilding a Modelfile, set `params.num_ctx`; OpenClaw sends it as `options.num_ctx` for both native Ollama and the OpenAI-compatible Ollama adapter. Invalid, zero, negative, and non-finite values are ignored and fall back to `contextWindow`.
+    You can set provider-level `contextWindow`, `contextTokens`, and `maxTokens` defaults for every model under that Ollama provider, then override them per model when needed. To cap Ollama's per-request runtime context without rebuilding a Modelfile, set `params.num_ctx`; OpenClaw sends it as `options.num_ctx` for both native Ollama and the OpenAI-compatible Ollama adapter. Invalid, zero, negative, and non-finite values are ignored and fall back to `contextWindow`.
 
     Native Ollama model entries also accept the common Ollama runtime options under `params`, including `temperature`, `top_p`, `top_k`, `min_p`, `num_predict`, `stop`, `repeat_penalty`, `num_batch`, `num_thread`, and `use_mmap`. OpenClaw forwards only Ollama request keys, so OpenClaw runtime params such as `streaming` are not leaked to Ollama. Use `params.think` or `params.thinking` to send top-level Ollama `think`; `false` disables API-level thinking for Qwen-style thinking models.
 
@@ -471,6 +471,7 @@ For the full setup and behavior details, see [Ollama Web Search](/tools/ollama-s
       models: {
         providers: {
           ollama: {
+            contextWindow: 32768,
             models: [
               {
                 id: "llama3.3",