feat: optimize GPT-5.6 defaults and reasoning

agent-schema.json

@@ -1036,7 +1036,7 @@
             ],
             [
               "backup_model",
-              "openai/gpt-5-mini"
+              "openai/gpt-5.6"
             ]
           ]
         },
@@ -1518,7 +1518,7 @@
           "description": "Whether to track usage"
         },
         "thinking_budget": {
-          "description": "Controls reasoning effort/budget. Use 'none' or 0 to disable thinking. OpenAI: string levels ('minimal','low','medium','high','xhigh'). Anthropic: integer token budget (1024-32768), 'adaptive' (adaptive thinking with high effort by default), 'adaptive/<effort>' where effort is low/medium/high/xhigh/max ('xhigh' is supported by Claude Opus 4.7+), or effort levels ('low','medium','high','xhigh','max') which use adaptive thinking with the given effort. Amazon Bedrock (Claude): integer token budget or effort levels ('low','medium','high') mapped to token budgets. Google Gemini 2.5: integer token budget (-1 for dynamic, 0 to disable, 24576 max). Google Gemini 3: string levels ('minimal' Flash only,'low','medium','high'). Thinking is only enabled when explicitly configured.",
+          "description": "Controls reasoning effort/budget. Use 'none' or 0 to disable thinking. OpenAI: string levels ('none','minimal','low','medium','high','xhigh','max') — 'xhigh' requires gpt-5.2+; 'none' and 'max' require gpt-5.6+ (Sol/Terra/Luna); 'minimal' is not accepted on gpt-5.6+. Anthropic: integer token budget (1024-32768), 'adaptive' (adaptive thinking with high effort by default), 'adaptive/<effort>' where effort is low/medium/high/xhigh/max ('xhigh' is supported by Claude Opus 4.7+), or effort levels ('low','medium','high','xhigh','max') which use adaptive thinking with the given effort. Amazon Bedrock (Claude): integer token budget or effort levels ('low','medium','high') mapped to token budgets. Google Gemini 2.5: integer token budget (-1 for dynamic, 0 to disable, 24576 max). Google Gemini 3: string levels ('minimal' Flash only,'low','medium','high'). Thinking is only enabled when explicitly configured.",
           "oneOf": [
             {
               "type": "string",
@@ -1615,7 +1615,7 @@
           "examples": [
             [
               "anthropic/claude-sonnet-4-5",
-              "openai/gpt-5",
+              "openai/gpt-5.6",
               "dmr/ai/qwen3"
             ]
           ]

cmd/root/doctor_test.go

@@ -101,7 +101,7 @@ func TestDoctorCommand_ChatGPTLoginSource(t *testing.T) {
 
 	require.NoError(t, err)
 	assert.Regexp(t, `chatgpt\s+found\s+CHATGPT_OAUTH_TOKEN\s+chatgpt-login`, output)
-	assert.Contains(t, output, "auto -> chatgpt/gpt-5.2")
+	assert.Contains(t, output, "auto -> chatgpt/gpt-5.6")
 	assert.Contains(t, output, "No issues found.")
 	assert.NotContains(t, output, "chatgpt-access-token", "secret values must never be printed")
 }
@@ -266,7 +266,7 @@ func TestDoctorCommand_JSON(t *testing.T) {
 	assert.Equal(t, dmrStatusReachable, report.DMR.Status)
 	assert.Equal(t, []string{"ai/qwen3:latest"}, report.DMR.Models)
 	assert.Equal(t, "openai", report.AutoModel.Provider)
-	assert.Equal(t, "gpt-5", report.AutoModel.Model)
+	assert.Equal(t, "gpt-5.6", report.AutoModel.Model)
 	assert.True(t, report.AutoModel.Usable)
 	assert.Empty(t, report.Issues)
 

cmd/wasm/README.md

@@ -188,6 +188,7 @@ are intentionally tiny:
 | File | Purpose |
 | --- | --- |
 | `pkg/cache/lock_js.go` | No-op file-lock stubs (single-threaded js). |
+| `pkg/userconfig/lock_js.go` | No-op file-lock stubs for the user config file (single-threaded js). |
 | `pkg/desktop/sockets_js.go` | Returns empty Docker Desktop paths. |
 | `pkg/desktop/connection_js.go` | Refuses Unix-socket / named-pipe dials. |
 | `pkg/desktop/connection_other.go` | Build tag updated to `!windows && !js`. |

docs/concepts/models/index.md

@@ -125,11 +125,22 @@ Control how much the model "thinks" before responding:
 
 | Provider   | Format     | Values                                                              | Default                          |
 | ---------- | ---------- | ------------------------------------------------------------------- | -------------------------------- |
-| OpenAI     | string     | `minimal`, `low`, `medium`, `high`, `xhigh`                         | `medium` (always-reasoning models only) |
+| OpenAI     | string     | `minimal`, `low`, `medium`, `high`, `xhigh`, `max`                  | `medium` (always-reasoning models only) |
 | Anthropic  | int or str | 1024–32768 tokens, or `adaptive`, `adaptive/<effort>`, effort level | off                              |
 | Gemini 2.5 | int        | 0 (off), -1 (dynamic), or token count                               | -1 (dynamic)                     |
 | Gemini 3   | string     | `minimal`, `low`, `medium`, `high`                                  | varies                           |
-| All        | string/int | `none` or `0` to disable                                            | —                                |
+| All        | string/int | `none` or `0` clears docker-agent's local config                    | —                                |
+
+`none` and `0` are not universal API-level disable switches. On genuine OpenAI
+gpt-5.6+ endpoints (Sol/Terra/Luna), `none` is a real `reasoning_effort` value
+that docker-agent sends as-is and the model does not reason. On older OpenAI
+models, `none`/`0` only clear the local `thinking_budget` — omitting the field
+has the same effect — and the model falls back to the API's own default effort
+(still reasoning internally for always-reasoning models like the o-series).
+Providers with a true optional-thinking switch (Gemini 2.5, Claude, local
+models) are fully disabled by `none`/`0`. See the
+[Thinking / Reasoning guide](../../guides/thinking/index.md#disabling-thinking)
+for the full per-provider breakdown.
 
 ```yaml
 models:
@@ -140,8 +151,8 @@ models:
 
   fast-responder:
     provider: openai
-    model: gpt-5
-    thinking_budget: none # disable thinking
+    model: gpt-5.6
+    thinking_budget: none # real API-level disable on gpt-5.6+
 ```
 
 > [!NOTE]

docs/configuration/models/index.md

@@ -278,8 +278,8 @@ Uses effort levels as strings:
 models:
   gpt:
     provider: openai
-    model: gpt-5
-    thinking_budget: low # minimal | low | medium | high | xhigh
+    model: gpt-5.6
+    thinking_budget: low # none | minimal | low | medium | high | xhigh | max (xhigh needs gpt-5.2+; none/max need gpt-5.6+; minimal dropped on gpt-5.6+)
 ```
 
 ### Anthropic
@@ -325,13 +325,23 @@ models:
 
 ### Disabling Thinking
 
-Works for all providers:
-
 ```yaml
 thinking_budget: none # or 0
 ```
 
-Models that always reason (OpenAI o-series, gpt-5, Gemini 3) fall back to the API default and still reason internally.
+`none` and `0` both clear docker-agent's local thinking configuration (omitting `thinking_budget` has the same effect); neither is guaranteed to reach the API as a real "off" switch:
+
+- **OpenAI gpt-5.6+** (Sol/Terra/Luna) is the only case with a genuine API-level `none` reasoning effort: docker-agent sends it as-is and the model does not reason.
+- **Older OpenAI reasoning models** (o-series, gpt-5 through gpt-5.5) have no such switch: `none`/`0` just clear the local config, and the model falls back to the API's own default effort and still reasons internally. Same for other always-reasoning models (Gemini 3).
+- Providers with a true optional-thinking switch (Gemini 2.5, Claude, local models) are fully disabled by `none`/`0`.
+
+```yaml
+models:
+  fast-responder:
+    provider: openai
+    model: gpt-5.6
+    thinking_budget: none # real API-level disable on gpt-5.6+
+```
 
 See the [Thinking / Reasoning guide](../../guides/thinking/index.md) for per-provider details, including AWS Bedrock and Docker Model Runner.
 

docs/guides/thinking/index.md

@@ -23,7 +23,7 @@ docker-agent exposes this through a single `thinking_budget` field on any named
 
 | Provider            | Format     | Values                                                                                  | Default            |
 | ------------------- | ---------- | --------------------------------------------------------------------------------------- | ------------------ |
-| OpenAI              | string     | `minimal`, `low`, `medium`, `high`, `none`; `xhigh` on gpt-5.2+ only                    | `medium` (API default) |
+| OpenAI              | string     | `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max`; `xhigh` on gpt-5.2+, `none`/`max` on gpt-5.6+ only, `minimal` dropped on gpt-5.6+ | `medium` (API default) |
 | Anthropic           | int or str | 1024–32768 tokens, or `minimal`–`max`, `adaptive`, `adaptive/<effort>`, `none`          | off                |
 | Gemini 2.5          | int        | `0` (off), `-1` (dynamic), or token count (max 24576 / 32768)                           | `-1` (dynamic)     |
 | Gemini 3            | string     | `minimal`, `low`, `medium`, `high`                                                      | API default (model-dependent) |
@@ -36,33 +36,34 @@ String values are case-insensitive. The full set of accepted strings is `none`,
 
 ## OpenAI
 
-OpenAI reasoning models (o-series, gpt-5, gpt-5-mini) use a string effort level that maps to their `reasoning_effort` API parameter. The `xhigh` level is only accepted by gpt-5.2 and later minor versions; o-series and earlier gpt-5 releases top out at `high`.
+OpenAI reasoning models (o-series, gpt-5, gpt-5-mini, gpt-5.6 family) use a string effort level that maps to their `reasoning_effort` API parameter. The `xhigh` level requires gpt-5.2+; `none` and `max` require gpt-5.6+ (Sol/Terra/Luna); `minimal` is dropped on gpt-5.6+.
 
 ```yaml
 models:
   gpt-thinker:
     provider: openai
-    model: gpt-5-mini
-    thinking_budget: high   # minimal | low | medium | high | xhigh
+    model: gpt-5.6
+    thinking_budget: high   # none | minimal | low | medium | high | xhigh | max
 ```
 
 **Effort levels:**
 
 | Level     | Description                                              |
 | --------- | -------------------------------------------------------- |
-| `none`    | Don't request extra reasoning (alias for `0`); the API's own default still applies. |
-| `minimal` | Fastest; lightest reasoning pass.                        |
+| `none`    | No reasoning. Sent as-is on gpt-5.6+ (a real API value); on older models it just disables the local `thinking_budget` (the API's own default still applies). |
+| `minimal` | Fastest; lightest reasoning pass. Not accepted on gpt-5.6+ (dropped from the API). |
 | `low`     | Quick reasoning for straightforward tasks.               |
 | `medium`  | Balanced default.                                        |
 | `high`    | More thorough; recommended for complex tasks.            |
-| `xhigh`   | Near-maximum effort; slower but most accurate.           |
+| `xhigh`   | Near-maximum effort; slower but most accurate. Requires gpt-5.2+. |
+| `max`     | Maximum effort. Requires gpt-5.6+.                       |
 
-These effort levels (`minimal`–`xhigh`) are the **only** values accepted for OpenAI. Token counts, `max`, `adaptive`, and `adaptive/<effort>` are rejected with a configuration error at request time. The `xhigh` level is only supported by gpt-5.2 and later minor versions (e.g. gpt-5.2, gpt-5.4-mini); o-series and earlier gpt-5 releases top out at `high`. Older models (o1, o3-mini) only accept `low`/`medium`/`high` — sending an unsupported level returns an API error.
+Token counts, `adaptive`, and `adaptive/<effort>` are rejected with a configuration error at request time. `xhigh` is only supported by gpt-5.2 and later minor versions (e.g. gpt-5.2, gpt-5.4-mini); `none` and `max` are only supported by gpt-5.6 and later (Sol/Terra/Luna); `minimal` is not accepted on gpt-5.6+. Older models (o1, o3-mini) only accept `low`/`medium`/`high` — sending an unsupported level returns an API error.
 
 > [!WARNING]
 > **Tokens and max_tokens**
 >
-> OpenAI reasoning models always reason internally — even with `thinking_budget: none` there are hidden reasoning tokens that count against `max_tokens`. docker-agent automatically raises the output-token floor for its internal low-effort calls (e.g. title generation) so hidden reasoning cannot starve visible text output.
+> Older OpenAI reasoning models always reason internally — even with `thinking_budget: none` there are hidden reasoning tokens that count against `max_tokens`. On gpt-5.6+ (Sol/Terra/Luna), `none` is a real API value that genuinely disables reasoning. docker-agent automatically raises the output-token floor for its internal low-effort calls (e.g. title generation) so hidden reasoning cannot starve visible text output.
 
 ## Anthropic
 
@@ -311,7 +312,7 @@ models:
     thinking_budget: 0
 ```
 
-`none` and `0` clear docker-agent's thinking configuration — no thinking parameter is sent. Models that always reason (OpenAI o-series, gpt-5, Gemini 3) then fall back to the API's default behavior and still reason internally; only models with optional thinking (Gemini 2.5, Claude, local models) are fully disabled.
+`none` and `0` clear docker-agent's thinking configuration — no thinking parameter is sent. Models that always reason (OpenAI o-series, gpt-5 through gpt-5.5, Gemini 3) then fall back to the API's default behavior and still reason internally; gpt-5.6+ (Sol/Terra/Luna) sends `none` as a real API value that genuinely disables reasoning. Models with optional thinking (Gemini 2.5, Claude, local models) are also fully disabled.
 
 ## Choosing an Effort Level
 
@@ -328,7 +329,7 @@ models:
 
 While running in the TUI, press **Shift+Tab** to cycle the thinking effort level for the current model without editing your YAML config, or type `/effort <level>` to jump straight to a specific level (e.g. `/effort high`). Running `/effort` without an argument opens a picker listing the levels the current model supports:
 
-- The level steps through the model's supported range (model-specific), wrapping around — for example `none → minimal → low → medium → high → none` on OpenAI gpt-5/o-series, `none → minimal → low → medium → high → xhigh → none` on gpt-5.2+, `none → low → medium → high → max → none` on Anthropic Opus 4.6 and Sonnet 4.6, and `none → low → medium → high → xhigh → max → none` on Anthropic Opus 4.7+, Fable 5, and Mythos 5. For older Anthropic models (e.g. Sonnet 4.5) that only accept token budgets, effort-string cycling has no effect — use an integer `thinking_budget` in your YAML config instead.
+- The level steps through the model's supported range (model-specific), wrapping around — for example `none → minimal → low → medium → high → none` on OpenAI gpt-5/o-series, `none → minimal → low → medium → high → xhigh → none` on gpt-5.2+, `none → low → medium → high → xhigh → max → none` on gpt-5.6+ (no `minimal`), `none → low → medium → high → max → none` on Anthropic Opus 4.6 and Sonnet 4.6, and `none → low → medium → high → xhigh → max → none` on Anthropic Opus 4.7+, Fable 5, and Mythos 5. For older Anthropic models (e.g. Sonnet 4.5) that only accept token budgets, effort-string cycling has no effect — use an integer `thinking_budget` in your YAML config instead.
 - The current level is shown in the sidebar next to the model name (e.g. `openai/gpt-5 • high`).
 - This applies as a session override — it is **not** saved to the config file. The next session starts from the level defined in your YAML.
 - For models that don't support reasoning, and for remote runtimes, Shift+Tab is a no-op and an informational message is displayed.

docs/providers/chatgpt/index.md

@@ -17,7 +17,8 @@ Business plan rather than pay-per-token API credits.
 
 Under the hood, docker-agent talks to the ChatGPT Codex backend
 (`https://chatgpt.com/backend-api/codex`), which serves the `gpt-5` model
-family over the OpenAI Responses API.
+family over the OpenAI Responses API. GPT-5.6 (Sol/Terra/Luna) is served
+there too; GPT-5.2 and GPT-5.3-Codex are deprecated for ChatGPT sign-in.
 
 ## Prerequisites
 
@@ -52,7 +53,7 @@ rm ~/.config/cagent/chatgpt-auth.json      # sign out (remove the stored sign-in
 ```yaml
 agents:
   root:
-    model: chatgpt/gpt-5.2
+    model: chatgpt/gpt-5.6
     instruction: You are a helpful assistant.
 ```
 
@@ -62,7 +63,7 @@ agents:
 models:
   gpt:
     provider: chatgpt
-    model: gpt-5.2
+    model: gpt-5.6
     thinking_budget: medium
 
 agents:
@@ -75,12 +76,17 @@ agents:
 The Codex backend serves the models available to your ChatGPT plan,
 typically:
 
-| Model               | Best For                              |
-| ------------------- | ------------------------------------- |
-| `gpt-5.2`           | General purpose, strong reasoning     |
-| `gpt-5.2-codex`     | Agentic coding workflows              |
-| `gpt-5.1`           | Previous flagship                     |
-| `gpt-5.1-codex-mini`| Fast and cheap coding tasks           |
+| Model                | Best For                              |
+| -------------------- | -------------------------------------- |
+| `gpt-5.6`            | Alias for `gpt-5.6-sol`; general purpose, strong reasoning |
+| `gpt-5.6-sol`        | Frontier model, most capable          |
+| `gpt-5.6-terra`      | Everyday workhorse                    |
+| `gpt-5.6-luna`       | High-volume, cost-efficient           |
+| `gpt-5.2`            | Deprecated for ChatGPT sign-in        |
+| `gpt-5.2-codex`      | Deprecated for ChatGPT sign-in        |
+
+The effort picker exposes Low/Medium/High/XHigh/Max on the GPT-5.6 family
+(no Minimal).
 
 ## How It Works
 
@@ -114,7 +120,7 @@ refreshed.
 | Embeddings / reranking | Not supported | Supported |
 
 When both credentials are configured, automatic model selection prefers
-`openai`; pin `--model chatgpt/gpt-5.2` (or use a named model) to use the
+`openai`; pin `--model chatgpt/gpt-5.6` (or use a named model) to use the
 subscription.
 
 > [!NOTE]