Skip to content

Commit f105662

Browse files
ndycodendycode
committed
fix: docs
1 parent 88db8e6 commit f105662

File tree

5 files changed

+152
-11
lines changed

5 files changed

+152
-11
lines changed

‎README.md‎

Lines changed: 56 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -33,7 +33,7 @@ Follow me on [X @nummanthinks](https://x.com/nummanthinks) for future updates an
3333
## Features
3434

3535
- ✅ **ChatGPT Plus/Pro OAuth authentication** - Use your existing subscription
36-
- ✅ **10 pre-configured GPT 5.1 variants** - GPT 5.1, GPT 5.1 Codex, GPT 5.1 Codex Max, and GPT 5.1 Codex Mini presets for common reasoning levels (including new `xhigh` for Codex Max)
36+
- ✅ **12 pre-configured GPT 5.1 variants** - GPT 5.1, GPT 5.1 Codex, GPT 5.1 Codex Max, and GPT 5.1 Codex Mini presets for common reasoning levels (including `gpt-5.1-codex-max-low/medium/high/xhigh`)
3737
- ⚠️ **GPT 5.1 only** - Older GPT 5.0 models are deprecated and may not work reliably
3838
- ✅ **Zero external dependencies** - Lightweight with only @openauthjs/openauth
3939
- ✅ **Auto-refreshing tokens** - Handles token expiration automatically
@@ -146,6 +146,54 @@ Follow me on [X @nummanthinks](https://x.com/nummanthinks) for future updates an
146146
"store": false
147147
}
148148
},
149+
"gpt-5.1-codex-max-low": {
150+
"name": "GPT 5.1 Codex Max Low (OAuth)",
151+
"limit": {
152+
"context": 272000,
153+
"output": 128000
154+
},
155+
"options": {
156+
"reasoningEffort": "low",
157+
"reasoningSummary": "detailed",
158+
"textVerbosity": "medium",
159+
"include": [
160+
"reasoning.encrypted_content"
161+
],
162+
"store": false
163+
}
164+
},
165+
"gpt-5.1-codex-max-medium": {
166+
"name": "GPT 5.1 Codex Max Medium (OAuth)",
167+
"limit": {
168+
"context": 272000,
169+
"output": 128000
170+
},
171+
"options": {
172+
"reasoningEffort": "medium",
173+
"reasoningSummary": "detailed",
174+
"textVerbosity": "medium",
175+
"include": [
176+
"reasoning.encrypted_content"
177+
],
178+
"store": false
179+
}
180+
},
181+
"gpt-5.1-codex-max-high": {
182+
"name": "GPT 5.1 Codex Max High (OAuth)",
183+
"limit": {
184+
"context": 272000,
185+
"output": 128000
186+
},
187+
"options": {
188+
"reasoningEffort": "high",
189+
"reasoningSummary": "detailed",
190+
"textVerbosity": "medium",
191+
"include": [
192+
"reasoning.encrypted_content"
193+
],
194+
"store": false
195+
}
196+
},
149197
"gpt-5.1-codex-max-xhigh": {
150198
"name": "GPT 5.1 Codex Max Extra High (OAuth)",
151199
"limit": {
@@ -251,8 +299,9 @@ Follow me on [X @nummanthinks](https://x.com/nummanthinks) for future updates an
251299
**Global config**: `~/.config/opencode/opencode.json`
252300
**Project config**: `<project>/.opencode.json`
253301

254-
This gives you 8 GPT 5.1 variants with different reasoning levels:
302+
This gives you 12 GPT 5.1 variants with different reasoning levels:
255303
- **gpt-5.1-codex** (low/medium/high) - Latest Codex model presets
304+
- **gpt-5.1-codex-max** (low/medium/high/xhigh) - Codex Max presets (`gpt-5.1-codex-max-low/medium/high/xhigh`)
256305
- **gpt-5.1-codex-mini** (medium/high) - Latest Codex mini tier presets
257306
- **gpt-5.1** (low/medium/high) - Latest general-purpose reasoning presets
258307

@@ -325,7 +374,7 @@ If using the full configuration, select from the model picker in opencode, or sp
325374
# Use different reasoning levels for gpt-5.1-codex
326375
opencode run "simple task" --model=openai/gpt-5.1-codex-low
327376
opencode run "complex task" --model=openai/gpt-5.1-codex-high
328-
opencode run "large refactor" --model=openai/gpt-5.1-codex-max
377+
opencode run "large refactor" --model=openai/gpt-5.1-codex-max-high
329378
opencode run "research-grade analysis" --model=openai/gpt-5.1-codex-max-xhigh
330379

331380
# Use different reasoning levels for gpt-5.1
@@ -346,7 +395,9 @@ When using [`config/full-opencode.json`](./config/full-opencode.json), you get t
346395
| `gpt-5.1-codex-low` | GPT 5.1 Codex Low (OAuth) | Low | Fast code generation |
347396
| `gpt-5.1-codex-medium` | GPT 5.1 Codex Medium (OAuth) | Medium | Balanced code tasks |
348397
| `gpt-5.1-codex-high` | GPT 5.1 Codex High (OAuth) | High | Complex code & tools |
349-
| `gpt-5.1-codex-max` | GPT 5.1 Codex Max (OAuth) | High | Long-horizon builds, large refactors |
398+
| `gpt-5.1-codex-max-low` | GPT 5.1 Codex Max Low (OAuth) | Low | Fast exploratory large-context work |
399+
| `gpt-5.1-codex-max-medium` | GPT 5.1 Codex Max Medium (OAuth) | Medium | Balanced large-context builds |
400+
| `gpt-5.1-codex-max-high` | GPT 5.1 Codex Max High (OAuth) | High | Long-horizon builds, large refactors |
350401
| `gpt-5.1-codex-max-xhigh` | GPT 5.1 Codex Max Extra High (OAuth) | xHigh | Deep multi-hour agent loops, research/debug marathons |
351402
| `gpt-5.1-codex-mini-medium` | GPT 5.1 Codex Mini Medium (OAuth) | Medium | Latest Codex mini tier |
352403
| `gpt-5.1-codex-mini-high` | GPT 5.1 Codex Mini High (OAuth) | High | Codex Mini with maximum reasoning |
@@ -359,7 +410,7 @@ When using [`config/full-opencode.json`](./config/full-opencode.json), you get t
359410

360411
> **Note**: All `gpt-5.1-codex-mini*` presets map directly to the `gpt-5.1-codex-mini` slug with standard Codex limits (272k context / 128k output).
361412
>
362-
> **Note**: Codex Max uses the `gpt-5.1-codex-max` slug with 272k input and expanded ~400k output support plus `xhigh` reasoning.
413+
> **Note**: Codex Max presets use the `gpt-5.1-codex-max` slug with 272k input and expanded ~400k output support. Use `gpt-5.1-codex-max-low/medium/high/xhigh` to pick reasoning level (only `-xhigh` uses `xhigh` reasoning).
363414
364415
> **⚠️ Important**: GPT 5 models can be temperamental - some variants may work better than others, some may give errors, and behavior may vary. Stick to the presets above configured in `full-opencode.json` for best results.
365416

‎config/README.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -14,7 +14,7 @@ cp config/full-opencode.json ~/.config/opencode/opencode.json
1414

1515
**Why this is required:**
1616
- GPT 5 models can be temperamental and need proper configuration
17-
- Contains 10 verified GPT 5.1 model variants (Codex, Codex Max, Codex Mini, and general GPT 5.1)
17+
- Contains 12+ verified GPT 5.1 model variants (Codex, Codex Max, Codex Mini, and general GPT 5.1 including `gpt-5.1-codex-max-low/medium/high/xhigh`)
1818
- Includes all required metadata for OpenCode features
1919
- Guaranteed to work reliably
2020
- Global options for all models + per-model configuration overrides

‎config/full-opencode.json‎

Lines changed: 50 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -67,7 +67,55 @@
6767
"name": "GPT 5.1 Codex Max (OAuth)",
6868
"limit": {
6969
"context": 272000,
70-
"output": 400000
70+
"output": 128000
71+
},
72+
"options": {
73+
"reasoningEffort": "high",
74+
"reasoningSummary": "detailed",
75+
"textVerbosity": "medium",
76+
"include": [
77+
"reasoning.encrypted_content"
78+
],
79+
"store": false
80+
}
81+
},
82+
"gpt-5.1-codex-max-low": {
83+
"name": "GPT 5.1 Codex Max Low (OAuth)",
84+
"limit": {
85+
"context": 272000,
86+
"output": 128000
87+
},
88+
"options": {
89+
"reasoningEffort": "low",
90+
"reasoningSummary": "detailed",
91+
"textVerbosity": "medium",
92+
"include": [
93+
"reasoning.encrypted_content"
94+
],
95+
"store": false
96+
}
97+
},
98+
"gpt-5.1-codex-max-medium": {
99+
"name": "GPT 5.1 Codex Max Medium (OAuth)",
100+
"limit": {
101+
"context": 272000,
102+
"output": 128000
103+
},
104+
"options": {
105+
"reasoningEffort": "medium",
106+
"reasoningSummary": "detailed",
107+
"textVerbosity": "medium",
108+
"include": [
109+
"reasoning.encrypted_content"
110+
],
111+
"store": false
112+
}
113+
},
114+
"gpt-5.1-codex-max-high": {
115+
"name": "GPT 5.1 Codex Max High (OAuth)",
116+
"limit": {
117+
"context": 272000,
118+
"output": 128000
71119
},
72120
"options": {
73121
"reasoningEffort": "high",
@@ -83,7 +131,7 @@
83131
"name": "GPT 5.1 Codex Max Extra High (OAuth)",
84132
"limit": {
85133
"context": 272000,
86-
"output": 400000
134+
"output": 128000
87135
},
88136
"options": {
89137
"reasoningEffort": "xhigh",

‎docs/getting-started.md‎

Lines changed: 44 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -108,6 +108,48 @@ Add this to `~/.config/opencode/opencode.json`:
108108
"store": false
109109
}
110110
},
111+
"gpt-5.1-codex-max-low": {
112+
"name": "GPT 5.1 Codex Max Low (OAuth)",
113+
"limit": {
114+
"context": 272000,
115+
"output": 128000
116+
},
117+
"options": {
118+
"reasoningEffort": "low",
119+
"reasoningSummary": "detailed",
120+
"textVerbosity": "medium",
121+
"include": ["reasoning.encrypted_content"],
122+
"store": false
123+
}
124+
},
125+
"gpt-5.1-codex-max-medium": {
126+
"name": "GPT 5.1 Codex Max Medium (OAuth)",
127+
"limit": {
128+
"context": 272000,
129+
"output": 128000
130+
},
131+
"options": {
132+
"reasoningEffort": "medium",
133+
"reasoningSummary": "detailed",
134+
"textVerbosity": "medium",
135+
"include": ["reasoning.encrypted_content"],
136+
"store": false
137+
}
138+
},
139+
"gpt-5.1-codex-max-high": {
140+
"name": "GPT 5.1 Codex Max High (OAuth)",
141+
"limit": {
142+
"context": 272000,
143+
"output": 128000
144+
},
145+
"options": {
146+
"reasoningEffort": "high",
147+
"reasoningSummary": "detailed",
148+
"textVerbosity": "medium",
149+
"include": ["reasoning.encrypted_content"],
150+
"store": false
151+
}
152+
},
111153
"gpt-5.1-codex-max-xhigh": {
112154
"name": "GPT 5.1 Codex Max Extra High (OAuth)",
113155
"limit": {
@@ -200,7 +242,7 @@ Add this to `~/.config/opencode/opencode.json`:
200242

201243
**What you get:**
202244
- ✅ GPT 5.1 Codex (Low/Medium/High reasoning)
203-
- ✅ GPT 5.1 Codex Max (High/xHigh reasoning, larger outputs)
245+
- ✅ GPT 5.1 Codex Max (Low/Medium/High/xHigh reasoning presets, larger outputs)
204246
- ✅ GPT 5.1 Codex Mini (Medium/High reasoning)
205247
- ✅ GPT 5.1 (Low/Medium/High reasoning)
206248
- ✅ 272k context + 128k output window for core presets (Codex Max expands output to ~400k)
@@ -209,7 +251,7 @@ Add this to `~/.config/opencode/opencode.json`:
209251

210252
> **Note**: All `gpt-5.1-codex-mini*` presets use 272k context / 128k output limits.
211253
>
212-
> **Note**: Codex Max presets map to `gpt-5.1-codex-max` with 272k input and expanded ~400k output plus `xhigh` reasoning.
254+
> **Note**: Codex Max presets map to the `gpt-5.1-codex-max` slug with 272k input and expanded ~400k output. Use `gpt-5.1-codex-max-low/medium/high/xhigh` to pick the reasoning level (only `-xhigh` uses `xhigh` reasoning).
213255
214256
Prompt caching is enabled out of the box: when OpenCode sends its session identifier as `prompt_cache_key`, the plugin forwards it untouched so multi-turn runs reuse prior work. The CODEX_MODE bridge prompt bundled with the plugin is kept in sync with the latest Codex CLI release, so the OpenCode UI and Codex share the same tool contract. If you hit your ChatGPT subscription limits, the plugin returns a friendly Codex-style message with the 5-hour and weekly usage windows so you know when capacity resets.
215257

‎docs/index.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -82,7 +82,7 @@ opencode run "write hello world to test.txt" --model=openai/gpt-5-codex
8282
## Features
8383

8484
✅ **OAuth Authentication** - Secure ChatGPT Plus/Pro login
85-
✅ **GPT 5.1 Models** - gpt-5.1, gpt-5.1-codex, gpt-5.1-codex-max, gpt-5.1-codex-mini (10 pre-configured variants)
85+
✅ **GPT 5.1 Models** - gpt-5.1, gpt-5.1-codex, gpt-5.1-codex-max, gpt-5.1-codex-mini (12 pre-configured variants including `gpt-5.1-codex-max-low/medium/high/xhigh`)
8686
✅ **Per-Model Configuration** - Different reasoning effort, including new `xhigh` for Codex Max
8787
✅ **Multi-Turn Conversations** - Full conversation history with stateless backend
8888
✅ **Verified Configuration** - Use `config/full-opencode.json` for guaranteed compatibility

0 commit comments

Comments
 (0)