Merge pull request #65 from ndycode/feat/gpt-5.4-support-v5.4.2

feat: add GPT-5.4 support and docs refresh

Author: ndycode

CHANGELOG.md

@@ -25,6 +25,23 @@ all notable changes to this project. dates are ISO format (YYYY-MM-DD).
 - **doctor safe-fix edge path**: `codex-doctor fix` now reports a clear non-crashing message when no eligible account is available for auto-switch.
 - **first-time import flow**: `codex-import` no longer fails with `No accounts to export` when storage is empty; pre-import backup is skipped cleanly in zero-account setups.
 
+## [5.4.2] - 2026-03-05
+
+### added
+
+- **gpt-5.4 + gpt-5.4-pro runtime support**: added model-map normalization and request-transform coverage for `gpt-5.4` (general) and optional `gpt-5.4-pro`.
+- **gpt-5.4-pro fallback edge**: default unsupported-model fallback chain now includes `gpt-5.4-pro -> gpt-5.4` when fallback policy is enabled.
+
+### changed
+
+- **template defaults updated to gpt-5.4**: modern + legacy config templates now use `gpt-5.4` variants as the default general-purpose family.
+- **docs refresh for 5.4 rollout**: README, getting-started, configuration, troubleshooting, docs index, and config docs now reflect `gpt-5.4` defaults and optional `gpt-5.4-pro` usage.
+- **test matrix expanded for 5.4**: unit, integration, and property tests now explicitly cover `gpt-5.4` and `gpt-5.4-pro` normalization/reasoning/fallback paths.
+
+### fixed
+
+- **quota probe model order**: quota snapshot probing now includes `gpt-5.4` first before legacy Codex probe models.
+
 ## [5.4.0] - 2026-02-28
 
 ### changed

README.md

@@ -3,14 +3,14 @@
 [![npm version](https://img.shields.io/npm/v/oc-chatgpt-multi-auth.svg)](https://www.npmjs.com/package/oc-chatgpt-multi-auth)
 [![npm downloads](https://img.shields.io/npm/dw/oc-chatgpt-multi-auth.svg)](https://www.npmjs.com/package/oc-chatgpt-multi-auth)
 
-OAuth plugin for OpenCode that lets you use ChatGPT Plus/Pro rate limits with models like `gpt-5.2`, `gpt-5-codex`, and `gpt-5.1-codex-max` (plus optional entitlement-gated Spark IDs and legacy Codex aliases).
+OAuth plugin for OpenCode that lets you use ChatGPT Plus/Pro rate limits with models like `gpt-5.4`, `gpt-5-codex`, and `gpt-5.1-codex-max` (plus optional/manual `gpt-5.4-pro`, entitlement-gated Spark IDs, and legacy Codex aliases).
 
 > [!NOTE]
 > **Renamed from `opencode-openai-codex-auth-multi`** — If you were using the old package, update your config to use `oc-chatgpt-multi-auth` instead. The rename was necessary because OpenCode blocks plugins containing `opencode-openai-codex-auth` in the name.
 
 ## What You Get
 
-- **GPT-5.2, GPT-5 Codex, GPT-5.1 Codex Max** and all GPT-5.x variants via ChatGPT OAuth
+- **GPT-5.4, GPT-5 Codex, GPT-5.1 Codex Max** and all GPT-5.x variants via ChatGPT OAuth
 - **Multi-account support** — Add up to 20 ChatGPT accounts, health-aware rotation with automatic failover
 - **Per-project accounts** — Each project gets its own account storage (new in v4.10.0)
 - **Workspace-aware identity persistence** — Keeps workspace/org identity stable across token refresh and verify-flagged restore flows
@@ -91,7 +91,7 @@ This writes the config to `~/.config/opencode/opencode.json`, backs up existing
 4. **Use it:**
 
    ```bash
-   opencode run "Hello" --model=openai/gpt-5.2 --variant=medium
+   opencode run "Hello" --model=openai/gpt-5.4 --variant=medium
    ```
 
 </details>
@@ -119,7 +119,7 @@ This writes the config to `~/.config/opencode/opencode.json`, backs up existing
 ### Verification
 
 ```bash
-opencode run "Hello" --model=openai/gpt-5.2 --variant=medium
+opencode run "Hello" --model=openai/gpt-5.4 --variant=medium
 ```
 
 </details>
@@ -132,7 +132,8 @@ opencode run "Hello" --model=openai/gpt-5.2 --variant=medium
 
 | Model | Variants | Notes |
 |-------|----------|-------|
-| `gpt-5.2` | none, low, medium, high, xhigh | Latest GPT-5.2 with reasoning levels |
+| `gpt-5.4` | none, low, medium, high, xhigh | Latest GPT-5.4 with reasoning levels |
+| `gpt-5.4-pro` | low, medium, high, xhigh | Optional manual model for deeper reasoning; fallback default is `gpt-5.4-pro -> gpt-5.4` |
 | `gpt-5-codex` | low, medium, high | Canonical Codex model for code generation (default: high) |
 | `gpt-5.3-codex-spark` | low, medium, high, xhigh | Spark IDs are supported by the plugin, but access is entitlement-gated by account/workspace |
 | `gpt-5.1-codex-max` | low, medium, high, xhigh | Maximum context Codex |
@@ -145,10 +146,10 @@ Config templates intentionally omit Spark model IDs by default to reduce entitle
 **Using variants:**
 ```bash
 # Modern OpenCode (v1.0.210+)
-opencode run "Hello" --model=openai/gpt-5.2 --variant=high
+opencode run "Hello" --model=openai/gpt-5.4 --variant=high
 
 # Legacy OpenCode (v1.0.209 and below)
-opencode run "Hello" --model=openai/gpt-5.2-high
+opencode run "Hello" --model=openai/gpt-5.4-high
 ```
 
 <details>
@@ -170,8 +171,8 @@ Add this to your `~/.config/opencode/opencode.json`:
         "store": false
       },
       "models": {
-        "gpt-5.2": {
-          "name": "GPT 5.2 (OAuth)",
+        "gpt-5.4": {
+          "name": "GPT 5.4 (OAuth)",
           "limit": { "context": 272000, "output": 128000 },
           "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] },
           "variants": {
@@ -258,7 +259,7 @@ Optional Spark model block (manual add only when entitled):
 }
 ```
 
-For legacy OpenCode (v1.0.209 and below), use `config/opencode-legacy.json` which has individual model entries like `gpt-5.2-low`, `gpt-5.2-medium`, etc.
+For legacy OpenCode (v1.0.209 and below), use `config/opencode-legacy.json` which has individual model entries like `gpt-5.4-low`, `gpt-5.4-medium`, etc.
 
 </details>
 
@@ -661,15 +662,15 @@ OpenCode uses `~/.config/opencode/` on **all platforms** including Windows.
 1. Use `openai/` prefix:
    ```bash
    # Correct
-   --model=openai/gpt-5.2
+   --model=openai/gpt-5.4
 
    # Wrong
-   --model=gpt-5.2
+   --model=gpt-5.4
    ```
 
 2. Verify model is in your config:
    ```json
-   { "models": { "gpt-5.2": { ... } } }
+   { "models": { "gpt-5.4": { ... } } }
    ```
 
 </details>
@@ -697,6 +698,7 @@ OpenCode uses `~/.config/opencode/` on **all platforms** including Windows.
      "unsupportedCodexPolicy": "fallback",
      "fallbackOnUnsupportedCodexModel": true,
      "unsupportedCodexFallbackChain": {
+       "gpt-5.4-pro": ["gpt-5.4"],
        "gpt-5-codex": ["gpt-5.2-codex"],
        "gpt-5.3-codex": ["gpt-5-codex", "gpt-5.2-codex"],
        "gpt-5.3-codex-spark": ["gpt-5-codex", "gpt-5.3-codex", "gpt-5.2-codex"]
@@ -843,6 +845,7 @@ Create `~/.opencode/openai-codex-auth-config.json` for optional settings:
 | `streamStallTimeoutMs` | `45000` | Abort non-stream parsing if SSE stalls (ms) |
 
 Default unsupported-model fallback chain (used when `unsupportedCodexPolicy` is `fallback`):
+- `gpt-5.4-pro -> gpt-5.4` (if `gpt-5.4-pro` is selected manually)
 - `gpt-5.3-codex -> gpt-5-codex -> gpt-5.2-codex`
 - `gpt-5.3-codex-spark -> gpt-5-codex -> gpt-5.3-codex -> gpt-5.2-codex` (applies if you manually select Spark model IDs)
 - `gpt-5.2-codex -> gpt-5-codex`

config/README.md

@@ -34,7 +34,7 @@ opencode --version
 OpenCode v1.0.210+ added model `variants`, so one model entry can expose multiple reasoning levels. That keeps modern config much smaller while preserving the same effective presets.
 
 Both templates include:
-- GPT-5.2, GPT-5 Codex, GPT-5.1, GPT-5.1 Codex, GPT-5.1 Codex Max, GPT-5.1 Codex Mini
+- GPT-5.4, GPT-5 Codex, GPT-5.1, GPT-5.1 Codex, GPT-5.1 Codex Max, GPT-5.1 Codex Mini
 - Reasoning variants per model family
 - `store: false` and `include: ["reasoning.encrypted_content"]`
 - Context metadata (272k context / 128k output)
@@ -50,14 +50,14 @@ If your workspace is entitled, you can add Spark model IDs manually.
 Modern template (v1.0.210+):
 
 ```bash
-opencode run "task" --model=openai/gpt-5.2 --variant=medium
+opencode run "task" --model=openai/gpt-5.4 --variant=medium
 opencode run "task" --model=openai/gpt-5-codex --variant=high
 ```
 
 Legacy template (v1.0.209 and below):
 
 ```bash
-opencode run "task" --model=openai/gpt-5.2-medium
+opencode run "task" --model=openai/gpt-5.4-medium
 opencode run "task" --model=openai/gpt-5-codex-high
 ```
 
@@ -71,9 +71,11 @@ Current defaults are strict entitlement handling:
 - `unsupportedCodexPolicy: "strict"` returns entitlement errors directly
 - set `unsupportedCodexPolicy: "fallback"` (or `CODEX_AUTH_UNSUPPORTED_MODEL_POLICY=fallback`) to enable automatic fallback retries
 - `fallbackToGpt52OnUnsupportedGpt53: true` keeps the legacy `gpt-5.3-codex -> gpt-5.2-codex` edge inside fallback mode
+- `gpt-5.4-pro -> gpt-5.4` is included by default in fallback mode (relevant only if you add `gpt-5.4-pro` manually)
 - `unsupportedCodexFallbackChain` lets you override fallback order per model
 
 Default fallback chain (when policy is `fallback`):
+- `gpt-5.4-pro -> gpt-5.4` (if you manually select `gpt-5.4-pro`)
 - `gpt-5.3-codex -> gpt-5-codex -> gpt-5.2-codex`
 - `gpt-5.3-codex-spark -> gpt-5-codex -> gpt-5.3-codex -> gpt-5.2-codex` (only relevant if Spark IDs are added manually)
 - `gpt-5.2-codex -> gpt-5-codex`

config/opencode-legacy.json

@@ -15,8 +15,8 @@
         "store": false
       },
       "models": {
-        "gpt-5.2-none": {
-          "name": "GPT 5.2 None (OAuth)",
+        "gpt-5.4-none": {
+          "name": "GPT 5.4 None (OAuth)",
           "limit": {
             "context": 272000,
             "output": 128000
@@ -40,8 +40,8 @@
             "store": false
           }
         },
-        "gpt-5.2-low": {
-          "name": "GPT 5.2 Low (OAuth)",
+        "gpt-5.4-low": {
+          "name": "GPT 5.4 Low (OAuth)",
           "limit": {
             "context": 272000,
             "output": 128000
@@ -65,8 +65,8 @@
             "store": false
           }
         },
-        "gpt-5.2-medium": {
-          "name": "GPT 5.2 Medium (OAuth)",
+        "gpt-5.4-medium": {
+          "name": "GPT 5.4 Medium (OAuth)",
           "limit": {
             "context": 272000,
             "output": 128000
@@ -90,8 +90,8 @@
             "store": false
           }
         },
-        "gpt-5.2-high": {
-          "name": "GPT 5.2 High (OAuth)",
+        "gpt-5.4-high": {
+          "name": "GPT 5.4 High (OAuth)",
           "limit": {
             "context": 272000,
             "output": 128000
@@ -115,8 +115,8 @@
             "store": false
           }
         },
-        "gpt-5.2-xhigh": {
-          "name": "GPT 5.2 Extra High (OAuth)",
+        "gpt-5.4-xhigh": {
+          "name": "GPT 5.4 Extra High (OAuth)",
           "limit": {
             "context": 272000,
             "output": 128000

config/opencode-modern.json

@@ -15,8 +15,8 @@
         "store": false
       },
       "models": {
-        "gpt-5.2": {
-          "name": "GPT 5.2 (OAuth)",
+        "gpt-5.4": {
+          "name": "GPT 5.4 (OAuth)",
           "limit": {
             "context": 272000,
             "output": 128000

docs/configuration.md

@@ -34,7 +34,8 @@ controls how much thinking the model does.
 
 | model | supported values |
 |-------|------------------|
-| `gpt-5.2` | none, low, medium, high, xhigh |
+| `gpt-5.4` | none, low, medium, high, xhigh |
+| `gpt-5.4-pro` | low, medium, high, xhigh (optional/manual model) |
 | `gpt-5-codex` | low, medium, high (default: high) |
 | `gpt-5.3-codex` | low, medium, high, xhigh (legacy alias to `gpt-5-codex`) |
 | `gpt-5.3-codex-spark` | low, medium, high, xhigh (entitlement-gated legacy alias; add manually) |
@@ -44,14 +45,14 @@ controls how much thinking the model does.
 | `gpt-5.1-codex-mini` | medium, high |
 | `gpt-5.1` | none, low, medium, high |
 
-the shipped config templates include 21 presets and do not add Spark by default. add `gpt-5.3-codex-spark` manually only for entitled workspaces.
+the shipped config templates include 21 presets and do not add optional IDs by default. add `gpt-5.4-pro` and/or `gpt-5.3-codex-spark` manually only for entitled workspaces.
 
 what they mean:
-- `none` - no reasoning phase (base models only, auto-converts to `low` for codex)
+- `none` - no reasoning phase (base models only; auto-converts to `low` for codex/pro families, including `gpt-5-codex` and `gpt-5.4-pro`)
 - `low` - light reasoning, fastest
 - `medium` - balanced (default)
 - `high` - deep reasoning
-- `xhigh` - max depth for complex tasks (default for legacy `gpt-5.3-codex` / `gpt-5.2-codex` aliases and `gpt-5.1-codex-max`)
+- `xhigh` - max depth for complex tasks (default for legacy `gpt-5.3-codex` / `gpt-5.2-codex` aliases and `gpt-5.1-codex-max`; available for `gpt-5.4` and optional `gpt-5.4-pro`)
 
 ### reasoningSummary
 
@@ -117,6 +118,7 @@ advanced settings go in `~/.opencode/openai-codex-auth-config.json`:
   "fallbackOnUnsupportedCodexModel": false,
   "fallbackToGpt52OnUnsupportedGpt53": true,
   "unsupportedCodexFallbackChain": {
+    "gpt-5.4-pro": ["gpt-5.4"],
     "gpt-5-codex": ["gpt-5.2-codex"]
   }
 }
@@ -147,7 +149,7 @@ The sample above intentionally sets `"retryAllAccountsMaxRetries": 3` as a bound
 | `unsupportedCodexPolicy` | `strict` | unsupported-model behavior: `strict` (return entitlement error) or `fallback` (retry with configured fallback chain) |
 | `fallbackOnUnsupportedCodexModel` | `false` | legacy fallback toggle mapped to `unsupportedCodexPolicy` (prefer using `unsupportedCodexPolicy`) |
 | `fallbackToGpt52OnUnsupportedGpt53` | `true` | legacy compatibility toggle for the `gpt-5.3-codex -> gpt-5.2-codex` edge when generic fallback is enabled |
-| `unsupportedCodexFallbackChain` | `{}` | optional per-model fallback-chain override (map of `model -> [fallback1, fallback2, ...]`) |
+| `unsupportedCodexFallbackChain` | `{}` | optional per-model fallback-chain override (map of `model -> [fallback1, fallback2, ...]`; default includes `gpt-5.4-pro -> gpt-5.4`) |
 | `sessionRecovery` | `true` | auto-recover from common api errors |
 | `autoResume` | `true` | auto-resume after thinking block recovery |
 | `tokenRefreshSkewMs` | `60000` | refresh tokens this many ms before expiry |
@@ -171,6 +173,7 @@ by default the plugin is strict (`unsupportedCodexPolicy: "strict"`). it returns
 set `unsupportedCodexPolicy: "fallback"` to enable model fallback after account/workspace attempts are exhausted.
 
 defaults when fallback policy is enabled and `unsupportedCodexFallbackChain` is empty:
+- `gpt-5.4-pro -> gpt-5.4` (if `gpt-5.4-pro` is selected manually)
 - `gpt-5.3-codex -> gpt-5-codex -> gpt-5.2-codex`
 - `gpt-5.3-codex-spark -> gpt-5-codex -> gpt-5.3-codex -> gpt-5.2-codex` (applies if you manually select Spark model IDs)
 - `gpt-5.2-codex -> gpt-5-codex`
@@ -184,6 +187,7 @@ custom chain example:
   "unsupportedCodexPolicy": "fallback",
   "fallbackOnUnsupportedCodexModel": true,
   "unsupportedCodexFallbackChain": {
+    "gpt-5.4-pro": ["gpt-5.4"],
     "gpt-5-codex": ["gpt-5.2-codex"],
     "gpt-5.3-codex": ["gpt-5-codex", "gpt-5.2-codex"],
     "gpt-5.3-codex-spark": ["gpt-5-codex", "gpt-5.3-codex", "gpt-5.2-codex"]
@@ -264,12 +268,12 @@ different settings for different models:
         "store": false
       },
       "models": {
-        "gpt-5.2-fast": {
-          "name": "fast gpt-5.2",
+        "gpt-5.4-fast": {
+          "name": "fast gpt-5.4",
           "options": { "reasoningEffort": "low" }
         },
-        "gpt-5.2-smart": {
-          "name": "smart gpt-5.2",
+        "gpt-5.4-smart": {
+          "name": "smart gpt-5.4",
           "options": { "reasoningEffort": "high" }
         }
       }
@@ -338,12 +342,12 @@ opencode
 ### verify model resolution
 
 ```bash
-DEBUG_CODEX_PLUGIN=1 opencode run "test" --model=openai/gpt-5.2
+DEBUG_CODEX_PLUGIN=1 opencode run "test" --model=openai/gpt-5.4
 ```
 
 look for:
-```
-[openai-codex-plugin] Model config lookup: "gpt-5.2" → normalized to "gpt-5.2" for API {
+```text
+[openai-codex-plugin] Model config lookup: "gpt-5.4" → normalized to "gpt-5.4" for API {
   hasModelSpecificConfig: true,
   resolvedConfig: { ... }
 }
@@ -353,12 +357,12 @@ look for:
 
 ```bash
 # modern opencode (variants)
-ENABLE_PLUGIN_REQUEST_LOGGING=1 opencode run "test" --model=openai/gpt-5.2 --variant=low
-ENABLE_PLUGIN_REQUEST_LOGGING=1 opencode run "test" --model=openai/gpt-5.2 --variant=high
+ENABLE_PLUGIN_REQUEST_LOGGING=1 opencode run "test" --model=openai/gpt-5.4 --variant=low
+ENABLE_PLUGIN_REQUEST_LOGGING=1 opencode run "test" --model=openai/gpt-5.4 --variant=high
 
 # legacy presets (model names include the effort)
-ENABLE_PLUGIN_REQUEST_LOGGING=1 opencode run "test" --model=openai/gpt-5.2-low
-ENABLE_PLUGIN_REQUEST_LOGGING=1 opencode run "test" --model=openai/gpt-5.2-high
+ENABLE_PLUGIN_REQUEST_LOGGING=1 opencode run "test" --model=openai/gpt-5.4-low
+ENABLE_PLUGIN_REQUEST_LOGGING=1 opencode run "test" --model=openai/gpt-5.4-high
 
 # compare reasoning.effort in logs
 cat ~/.opencode/logs/codex-plugin/request-*-after-transform.json | jq '.reasoning.effort'