oc-codex-multi-auth 6.1.3 → 6.1.6

package/README.md

@@ -8,6 +8,8 @@ Badges: CI + OpenSSF Scorecard will turn green once Phase 3 Batch A (CI workflow
 [![Node.js Version](https://img.shields.io/node/v/oc-codex-multi-auth.svg)](https://nodejs.org)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 
+<img width="1227" height="702" alt="cover" src="https://github.com/user-attachments/assets/b796eb2f-282e-468a-ba6a-acadf09d731b" />
+
 Use your ChatGPT Plus/Pro subscription inside OpenCode with OAuth login, GPT-5/Codex model presets, and multi-account failover.
 
 `oc-codex-multi-auth` is an OpenCode plugin for developers who want Codex-first GPT-5 workflows in OpenCode without switching to separate Platform API credentials for personal use. It uses the same official OAuth flow as the Codex CLI, adds model templates for current GPT-5 families, and can rotate across multiple ChatGPT accounts when one account is rate-limited or unavailable.
@@ -15,7 +17,7 @@ Use your ChatGPT Plus/Pro subscription inside OpenCode with OAuth login, GPT-5/C
 ## What This Project Does
 
 - Adds an OpenCode plugin that authenticates with ChatGPT Plus/Pro through official OAuth
-- Ships ready-to-use GPT-5.5 templates, explicit `gpt-5.5-medium` / `gpt-5.5-high` selectors, `gpt-5-codex`, and related GPT-5 families
+- Ships ready-to-use GPT-5.5 OAuth model templates, variant picker presets, optional explicit selector IDs, `gpt-5-codex`, and related GPT-5 families
 - Routes requests through a stateless Codex-compatible request pipeline with automatic token refresh
 - Supports multi-account rotation, per-project account storage, and guided onboarding commands
 
@@ -29,7 +31,7 @@ npx -y oc-codex-multi-auth@latest
 opencode auth login
 
 # 3. Run a prompt in OpenCode
-opencode run "Explain this repository" --model=openai/gpt-5.5-medium
+opencode run "Explain this repository" --model=openai/gpt-5.5 --variant=medium
 ```
 
 What the installer does:
@@ -39,17 +41,19 @@ What the installer does:
 - normalizes the plugin entry to `"oc-codex-multi-auth"`
 - clears the cached plugin copy so OpenCode reinstalls the latest package
 
-By default, the installer now writes a full catalog config that includes both:
-- modern base model entries such as `gpt-5.5` for `--variant` workflows
-- explicit preset entries such as `gpt-5.5-medium` / `gpt-5.5-high` so the shipped catalog is visible directly in model pickers
+By default, the installer writes the compact UI config:
+- model picker entries stay on actual OAuth model families such as `gpt-5.5` and `gpt-5.5-fast`
+- reasoning presets are selected through OpenCode's model variant picker (`none`, `low`, `medium`, `high`, `xhigh`)
+- rerunning the default installer removes explicit preset entries and stale base models from earlier plugin catalogs
 
-Tested live on OpenCode `1.14.22`: explicit GPT-5.5 model IDs like `openai/gpt-5.5-medium` and `openai/gpt-5.5-high` work directly. Some OpenCode releases still reject bare `openai/gpt-5.5` on the CLI even when the base config entry exists in the effective config.
+If you prefer direct model IDs such as `openai/gpt-5.5-medium` or `openai/gpt-5.5-fast-medium`, install with `--full`.
 
 ## Example Usage
 
 ```bash
 # General GPT-5 workflow
-opencode run "Summarize the failing test and suggest a fix" --model=openai/gpt-5.5-medium
+opencode run "Summarize the failing test and suggest a fix" --model=openai/gpt-5.5 --variant=medium
+opencode run "Summarize the failing test and suggest a fix" --model=openai/gpt-5.5-fast --variant=medium
 
 # Codex-focused workflow
 opencode run "Refactor the retry logic and update the tests" --model=openai/gpt-5-codex --variant=high
@@ -86,7 +90,7 @@ OpenCode users often want the same GPT-5 and Codex model experience they use in
 
 ## Common Workflows
 
-- Personal coding sessions in OpenCode using `gpt-5.5-medium`, `gpt-5.5-high`, or `gpt-5-codex`
+- Personal coding sessions in OpenCode using `gpt-5.5` / `gpt-5.5-fast` with variants, or `gpt-5-codex`
 - Switching between personal and workspace-linked ChatGPT accounts
 - Keeping separate account pools per project or monorepo
 - Recovering from unsupported-model, auth, or rate-limit issues with guided commands
@@ -106,10 +110,10 @@ See [Architecture](docs/development/ARCHITECTURE.md) for implementation details.
 
 Use the quick-start path above for the fastest setup. For full setup, local development installs, legacy OpenCode support, and verification steps, see [Getting Started](docs/getting-started.md).
 
-If you prefer the compact variant-only config on OpenCode `v1.0.210+`, use:
+For direct selector IDs in scripts or older habits, use the full catalog:
 
 ```bash
-npx -y oc-codex-multi-auth@latest --modern
+npx -y oc-codex-multi-auth@latest --full
 ```
 
 ## Configuration

package/config/README.md

@@ -6,10 +6,10 @@ This directory contains the official OpenCode config templates for `oc-codex-mul
 
 | File | OpenCode version | Description |
 |------|------------------|-------------|
-| [`opencode-modern.json`](./opencode-modern.json) | **v1.0.210+** | Variant-based config: 9 base models with 34 total presets |
-| [`opencode-legacy.json`](./opencode-legacy.json) | **v1.0.209 and below** | Legacy explicit entries: 34 individual model definitions |
+| [`opencode-modern.json`](./opencode-modern.json) | **v1.0.210+** | Variant-based config: 9 base models with 36 total presets |
+| [`opencode-legacy.json`](./opencode-legacy.json) | **v1.0.209 and below** | Legacy explicit entries: 36 individual model definitions |
 
-The installer currently uses a merged full-catalog mode by default so users get both the modern base entries and the explicit preset entries without having to hand-edit `opencode.json`.
+The installer uses the compact modern template by default so the model picker shows only base OAuth model families. Rerun the default installer to remove explicit preset IDs and stale base models left by earlier plugin catalogs. Use `--full` when you want the explicit preset IDs installed too.
 
 ## Quick pick
 
@@ -36,12 +36,12 @@ 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-5.5, GPT-5.5 Pro, GPT-5.4 Mini, GPT-5.4 Nano, GPT-5 Codex, GPT-5.1, GPT-5.1 Codex, GPT-5.1 Codex Max, GPT-5.1 Codex Mini
+- GPT-5.5, GPT-5.5 Fast, GPT-5.4 Mini, GPT-5.4 Nano, 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 (`gpt-5.5`/`gpt-5.5-pro`: 1,050,000; `gpt-5.4-mini`/`gpt-5.4-nano`/Codex models: 400,000; `gpt-5.1`: 272,000; all output: 128,000)
+- Context metadata (`gpt-5.5`/`gpt-5.5-fast`: 1,050,000; `gpt-5.4-mini`/`gpt-5.4-nano`/Codex models: 400,000; `gpt-5.1`: 272,000; all output: 128,000)
 
-Use `opencode debug config` to verify that these template entries were merged into your effective config. On tested OpenCode `1.14.22`, `opencode models openai` exposes explicit GPT-5.5 entries such as `gpt-5.5-medium` / `gpt-5.5-high`, while bare `gpt-5.5` may still be omitted or rejected by provider lookup even when it exists in the effective config.
+Use `opencode debug config` to verify that these template entries were merged into your effective config. The default compact install shows base OAuth entries such as `gpt-5.5` / `gpt-5.5-fast`; the separate OpenCode variant picker exposes the reasoning presets.
 
 If your OpenCode runtime supports global compaction tuning, you can also set:
 - `model_context_window = 1050000`
@@ -55,17 +55,18 @@ If your workspace is entitled, you can add Spark model IDs manually.
 
 ## Usage examples
 
-Recommended real-session selectors (tested on OpenCode `1.14.22`):
+Recommended compact UI selectors:
 
 ```bash
-opencode run "task" --model=openai/gpt-5.5-medium
+opencode run "task" --model=openai/gpt-5.5 --variant=medium
+opencode run "task" --model=openai/gpt-5.5-fast --variant=medium
 opencode run "task" --model=openai/gpt-5-codex --variant=high
 ```
 
-If your OpenCode release already exposes bare GPT-5.5 base entries, the compact modern template also supports:
+If you need direct explicit selector IDs for scripts, install with:
 
 ```bash
-opencode run "task" --model=openai/gpt-5.5 --variant=medium
+npx -y oc-codex-multi-auth@latest --full
 ```
 
 ## Minimal config (advanced)
@@ -79,13 +80,12 @@ Current defaults are strict entitlement handling:
 - 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-5.5 -> gpt-5.4` is included by default for accounts/workspaces that do not yet expose GPT-5.5
-- `gpt-5.5-pro -> gpt-5.5` is included by default in fallback mode
+- user-typed `gpt-5.5-pro*` is canonicalized to `gpt-5.5` before fallback because GPT-5.5 Pro is ChatGPT-only, not a Codex-routable model
 - `gpt-5.4-pro -> gpt-5.4` remains available for older manual configs
 - `unsupportedCodexFallbackChain` lets you override fallback order per model
 
 Default fallback chain (when policy is `fallback`):
 - `gpt-5.5 -> gpt-5.4`
-- `gpt-5.5-pro -> gpt-5.5`
 - `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)

package/config/opencode-legacy.json

@@ -140,6 +140,131 @@
             "store": false
           }
         },
+        "gpt-5.5-fast-none": {
+          "name": "GPT 5.5 Fast None (OAuth)",
+          "limit": {
+            "context": 1050000,
+            "output": 128000
+          },
+          "modalities": {
+            "input": [
+              "text",
+              "image"
+            ],
+            "output": [
+              "text"
+            ]
+          },
+          "options": {
+            "reasoningEffort": "none",
+            "reasoningSummary": "auto",
+            "textVerbosity": "medium",
+            "include": [
+              "reasoning.encrypted_content"
+            ],
+            "store": false
+          }
+        },
+        "gpt-5.5-fast-low": {
+          "name": "GPT 5.5 Fast Low (OAuth)",
+          "limit": {
+            "context": 1050000,
+            "output": 128000
+          },
+          "modalities": {
+            "input": [
+              "text",
+              "image"
+            ],
+            "output": [
+              "text"
+            ]
+          },
+          "options": {
+            "reasoningEffort": "low",
+            "reasoningSummary": "auto",
+            "textVerbosity": "medium",
+            "include": [
+              "reasoning.encrypted_content"
+            ],
+            "store": false
+          }
+        },
+        "gpt-5.5-fast-medium": {
+          "name": "GPT 5.5 Fast Medium (OAuth)",
+          "limit": {
+            "context": 1050000,
+            "output": 128000
+          },
+          "modalities": {
+            "input": [
+              "text",
+              "image"
+            ],
+            "output": [
+              "text"
+            ]
+          },
+          "options": {
+            "reasoningEffort": "medium",
+            "reasoningSummary": "auto",
+            "textVerbosity": "medium",
+            "include": [
+              "reasoning.encrypted_content"
+            ],
+            "store": false
+          }
+        },
+        "gpt-5.5-fast-high": {
+          "name": "GPT 5.5 Fast High (OAuth)",
+          "limit": {
+            "context": 1050000,
+            "output": 128000
+          },
+          "modalities": {
+            "input": [
+              "text",
+              "image"
+            ],
+            "output": [
+              "text"
+            ]
+          },
+          "options": {
+            "reasoningEffort": "high",
+            "reasoningSummary": "detailed",
+            "textVerbosity": "medium",
+            "include": [
+              "reasoning.encrypted_content"
+            ],
+            "store": false
+          }
+        },
+        "gpt-5.5-fast-xhigh": {
+          "name": "GPT 5.5 Fast Extra High (OAuth)",
+          "limit": {
+            "context": 1050000,
+            "output": 128000
+          },
+          "modalities": {
+            "input": [
+              "text",
+              "image"
+            ],
+            "output": [
+              "text"
+            ]
+          },
+          "options": {
+            "reasoningEffort": "xhigh",
+            "reasoningSummary": "detailed",
+            "textVerbosity": "medium",
+            "include": [
+              "reasoning.encrypted_content"
+            ],
+            "store": false
+          }
+        },
         "gpt-5.4-mini-none": {
           "name": "GPT 5.4 Mini None (OAuth)",
           "limit": {

package/config/opencode-modern.json

@@ -58,6 +58,49 @@
             }
           }
         },
+        "gpt-5.5-fast": {
+          "name": "GPT 5.5 Fast (OAuth)",
+          "limit": {
+            "context": 1050000,
+            "output": 128000
+          },
+          "modalities": {
+            "input": [
+              "text",
+              "image"
+            ],
+            "output": [
+              "text"
+            ]
+          },
+          "variants": {
+            "none": {
+              "reasoningEffort": "none",
+              "reasoningSummary": "auto",
+              "textVerbosity": "medium"
+            },
+            "low": {
+              "reasoningEffort": "low",
+              "reasoningSummary": "auto",
+              "textVerbosity": "medium"
+            },
+            "medium": {
+              "reasoningEffort": "medium",
+              "reasoningSummary": "auto",
+              "textVerbosity": "medium"
+            },
+            "high": {
+              "reasoningEffort": "high",
+              "reasoningSummary": "detailed",
+              "textVerbosity": "medium"
+            },
+            "xhigh": {
+              "reasoningEffort": "xhigh",
+              "reasoningSummary": "detailed",
+              "textVerbosity": "medium"
+            }
+          }
+        },
         "gpt-5.4-mini": {
           "name": "GPT 5.4 Mini (OAuth)",
           "limit": {

package/dist/index.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAKH,OAAO,KAAK,EAAE,MAAM,EAAe,MAAM,qBAAqB,CAAC;AA2L/D;;;;;;;;;;;;;;;GAeG;AAEH,eAAO,MAAM,iBAAiB,EAAE,MA60G/B,CAAC;AAEF,eAAO,MAAM,gBAAgB,QAAoB,CAAC;AAElD,eAAe,iBAAiB,CAAC"}
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAKH,OAAO,KAAK,EAAE,MAAM,EAAe,MAAM,qBAAqB,CAAC;AAiM/D;;;;;;;;;;;;;;;GAeG;AAEH,eAAO,MAAM,iBAAiB,EAAE,MAy3G/B,CAAC;AAEF,eAAO,MAAM,gBAAgB,QAAoB,CAAC;AAElD,eAAe,iBAAiB,CAAC"}

package/dist/index.js

@@ -55,6 +55,8 @@ import { prewarmOpenCodeCodexPrompt } from "./lib/prompts/opencode-codex.js";
 import { createSessionRecoveryHook, isRecoverableError, detectErrorType, getRecoveryToastContent, } from "./lib/recovery.js";
 import { matchesWorkspaceIdentity, upsertFlaggedAccountRecord, createRetryBudgetUsage, serializeSelectionExplainability, formatRoutingValue, formatExplainabilitySummary, } from "./lib/runtime.js";
 import { createToolRegistry, } from "./lib/tools/index.js";
+import { createUsageAccountFingerprint } from "./lib/codex-usage.js";
+import { clearTuiQuotaSnapshot, parseTuiQuotaSnapshotFromHeaders, writeTuiQuotaSnapshot, } from "./lib/tui-quota-cache.js";
 /**
  * OpenAI Codex OAuth authentication plugin for opencode
  *
@@ -290,6 +292,31 @@ export const OpenAIOAuthPlugin = async ({ client }) => {
             // Ignore when TUI is not available.
         }
     };
+    const clearPromptQuotaCache = async () => {
+        try {
+            await clearTuiQuotaSnapshot();
+        }
+        catch (error) {
+            logDebug(`[${PLUGIN_NAME}] Failed to clear TUI quota cache: ${error instanceof Error ? error.message : String(error)}`);
+        }
+    };
+    const recordPromptQuotaHeaders = async (response, account, accountCount) => {
+        try {
+            const snapshot = parseTuiQuotaSnapshotFromHeaders(response.headers, {
+                fingerprint: createUsageAccountFingerprint(account),
+                accountIndex: account.index + 1,
+                accountCount,
+                accountEmail: account.email?.trim() || undefined,
+                accountLabel: formatAccountLabel(account, account.index),
+            });
+            if (!snapshot)
+                return;
+            await writeTuiQuotaSnapshot(snapshot);
+        }
+        catch (error) {
+            logDebug(`[${PLUGIN_NAME}] Failed to record TUI quota headers: ${error instanceof Error ? error.message : String(error)}`);
+        }
+    };
     const resolveActiveIndex = (storage, family = "codex") => {
         const total = storage.accounts.length;
         if (total === 0)
@@ -844,6 +871,7 @@ export const OpenAIOAuthPlugin = async ({ client }) => {
                         storage.activeIndexByFamily[family] = index;
                     }
                     await saveAccounts(storage);
+                    await clearPromptQuotaCache();
                     // Reload manager from disk so we don't overwrite newer rotated
                     // refresh tokens with stale in-memory state.
                     if (cachedAccountManager) {
@@ -1357,6 +1385,10 @@ export const OpenAIOAuthPlugin = async ({ client }) => {
                                         }
                                         account.email =
                                             extractAccountEmail(accountAuth.access) ?? account.email;
+                                        // Keep the persisted active identity in step with the account used
+                                        // for this request so the TUI quota cache accepts the next real
+                                        // response-header snapshot instead of filtering it as stale.
+                                        accountManager.saveToDiskDebounced();
                                         if (accountCount > 1 &&
                                             accountManager.shouldShowAccountToast(account.index, rateLimitToastDebounceMs)) {
                                             const accountLabel = formatAccountLabel(account, account.index);
@@ -1480,6 +1512,7 @@ export const OpenAIOAuthPlugin = async ({ client }) => {
                                                 latencyMs: fetchLatencyMs,
                                                 headers: Object.fromEntries(response.headers.entries()),
                                             });
+                                            void recordPromptQuotaHeaders(response, account, accountCount);
                                             if (!response.ok) {
                                                 const contextOverflowResult = await handleContextOverflow(response, model);
                                                 if (contextOverflowResult.handled) {