oc-codex-multi-auth 6.9.1 → 6.10.1

package/README.md

@@ -5,7 +5,7 @@
 [![CI](https://github.com/ndycode/oc-codex-multi-auth/actions/workflows/ci.yml/badge.svg)](https://github.com/ndycode/oc-codex-multi-auth/actions/workflows/ci.yml)
 [![MIT license](https://img.shields.io/npm/l/oc-codex-multi-auth.svg)](LICENSE)
 
-`oc-codex-multi-auth` is an OpenCode plugin for ChatGPT Plus/Pro OAuth, Codex and GPT-5 model routing, multi-account rotation, account switching, health checks, quota visibility, diagnostics, and recovery tools. It installs the OpenCode provider/TUI configuration, registers a `codex-*` command toolkit, and routes OpenCode OpenAI SDK requests through the ChatGPT-backed Codex flow with local account state.
+`oc-codex-multi-auth` is an OpenCode plugin for ChatGPT Plus/Pro OAuth, Codex and GPT-5 model routing (including GPT-5.6 Sol/Terra/Luna), multi-account rotation, account switching, health checks, quota visibility, diagnostics, and recovery tools. It installs the OpenCode provider/TUI configuration, registers a 24-tool `codex-*` command toolkit, and routes OpenCode OpenAI SDK requests through the ChatGPT-backed Codex flow with local account state.
 
 Use it when you want OpenCode to run Codex-style coding workflows from your own ChatGPT subscription while keeping accounts visible, switchable, health-checked, and recoverable from the terminal.
 
@@ -20,10 +20,10 @@ Use it when you want OpenCode to run Codex-style coding workflows from your own
 ## What You Get
 
 - OpenCode plugin support for ChatGPT Plus/Pro OAuth and Codex/GPT-5 coding workflows
-- Ready-to-use GPT-5.5, GPT-5.5 Fast, GPT-5.4 Mini, GPT-5.4 Nano, GPT-5.1, and Codex model templates
-- Compact modern OpenCode config with variant-based selectors, plus explicit legacy selector IDs when needed
+- GPT-5.6 Sol, Terra, and Luna (responses-lite path) plus GPT-5.5, GPT-5.5 Fast, GPT-5.4 Mini, GPT-5.4 Nano, GPT-5.1, and Codex model templates
+- Compact modern OpenCode config with 12 base families and 53 variant presets; explicit legacy selector IDs when needed
 - Stateless Codex-compatible request handling with `store: false` and `reasoning.encrypted_content`
-- Multi-account rotation with health-aware selection, cooldowns, automatic token refresh, and failover
+- Multi-account rotation with hybrid health scoring, cooldowns, automatic token refresh, and failover
 - Explicit saved-account listing, account switching, labeling, tagging, notes, health checks, and diagnostics
 - Per-project account storage under `~/.opencode/projects/<project-key>/...`
 - Guided setup, doctor, next-action, dashboard, export/import, keychain, and troubleshooting tools
@@ -46,10 +46,10 @@ Use it when you want OpenCode to run Codex-style coding workflows from your own
 
 | Surface | Purpose |
 | --- | --- |
-| `oc-codex-multi-auth` | npm installer bin; updates `~/.config/opencode/opencode.json`, manages `tui.json`, normalizes stale plugin entries, and clears OpenCode plugin cache |
+| `oc-codex-multi-auth` | npm installer bin; updates `~/.config/opencode/opencode.json`, manages `tui.json`, normalizes stale plugin entries, and clears OpenCode plugin cache. Also runs standalone commands: `doctor`, `status`, `list`, `limits`, `dashboard`, `health`, `diag`, `warm` |
 | OpenCode plugin entry (`index.ts`) | auth loader, OAuth login modes, provider fetch pipeline, account rotation, retry/failover, and `codex-*` tool registry |
 | OpenCode TUI plugin (`tui.ts`) | prompt quota status, quota details, shared quota cache, and active-account-aware display |
-| 21 `codex-*` tools | setup, help, status, list, switch, limits, health, metrics, doctor, dashboard, backup, keychain, diagnostics, and recovery actions |
+| 24 `codex-*` tools | setup, help, status, list, switch, warm, limits, health, metrics, doctor, dashboard, pool, backup, keychain, diagnostics, and recovery actions |
 
 The plugin does not replace OpenCode. OpenCode remains the host; this package installs provider/TUI config and supplies the OAuth-backed Codex request pipeline that OpenCode calls.
 
@@ -76,12 +76,24 @@ The plugin does not replace OpenCode. OpenCode remains the host; this package in
 <details open>
 <summary><b>For Humans</b></summary>
 
-### Option A: Standard install
+### Option A: Standard install (compact modern)
+
+Default mode writes 12 base OAuth model families and leaves reasoning depth to OpenCode's variant picker.
 
 ```bash
 npx -y oc-codex-multi-auth@latest
 ```
 
+Installer flags:
+
+| Flag | Effect |
+| --- | --- |
+| (default) / `--modern` | Compact modern catalog: 12 bases, 53 variants |
+| `--full` | Compact bases plus 53 explicit selector IDs |
+| `--legacy` | Explicit-only catalog for older OpenCode |
+| `--dry-run` | Show actions without writing |
+| `--no-cache-clear` | Skip clearing the OpenCode plugin cache |
+
 ### Option B: Full explicit model catalog
 
 Use this when you want direct selector IDs such as `openai/gpt-5.5-medium` in addition to OpenCode variants.
@@ -100,6 +112,20 @@ opencode auth login
 
 The installer updates `~/.config/opencode/opencode.json`, backs up the previous config, normalizes the plugin entry to `"oc-codex-multi-auth"`, enables the TUI status plugin in `~/.config/opencode/tui.json`, and clears the OpenCode cached plugin copy so OpenCode reinstalls the latest package.
 
+### Standalone CLI (no agent / no token cost)
+
+```bash
+oc-codex-multi-auth status
+oc-codex-multi-auth list
+oc-codex-multi-auth warm
+oc-codex-multi-auth doctor
+oc-codex-multi-auth health
+oc-codex-multi-auth limits
+oc-codex-multi-auth dashboard
+oc-codex-multi-auth diag
+# or: npx -y oc-codex-multi-auth@latest warm --json
+```
+
 </details>
 
 <details>
@@ -113,7 +139,7 @@ The installer updates `~/.config/opencode/opencode.json`, backs up the previous
    - `opencode auth login`
 3. Validate config:
    - `opencode debug config`
-4. Run a smoke request:
+4. Run a smoke request (compact modern selectors):
    - `opencode run "Explain this repository" --model=openai/gpt-5.5 --variant=medium`
 5. Inspect plugin state with the OpenCode tool surface:
    - `codex-status`
@@ -146,6 +172,7 @@ Run a prompt with compact modern selectors:
 ```bash
 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
+opencode run "Plan the refactor" --model=openai/gpt-5.6-sol --variant=high
 ```
 
 Use Codex-focused routing:
@@ -210,7 +237,8 @@ Most of these also run as a **direct CLI** with no agent/model involvement (no t
 
 - stateless request handling forces `store: false`
 - `reasoning.encrypted_content` is preserved for multi-turn continuity
-- account rotation is health-aware and avoids repeatedly selecting cooling accounts
+- GPT-5.6 tiers use the responses-lite request shape and default client identity `opencode`; other models default to `codex_cli_rs`
+- account rotation is health-aware (`rotationStrategy` default `hybrid`) and avoids repeatedly selecting cooling accounts
 - 5xx bursts, network failures, and quota responses penalize account health
 - token refresh is queued to avoid refresh races
 - unsupported-model handling is strict by default, with opt-in fallback controls
@@ -304,13 +332,14 @@ Selected runtime/environment overrides:
 | `CODEX_AUTH_REQUEST_TRANSFORM_MODE=legacy` | Re-enable legacy Codex request rewriting |
 | `CODEX_MODE=0/1` | Disable/enable bridge prompt behavior |
 | `CODEX_TUI_V2=0/1` | Disable/enable codex-style tool output |
-| `CODEX_TUI_COLOR_PROFILE=truecolor|ansi256|ansi16` | Force terminal color profile |
-| `CODEX_TUI_GLYPHS=ascii|unicode|auto` | Force terminal glyph style |
-| `CODEX_TUI_MASK_EMAIL=0/1` | Hide account email in TUI quota status only |
+| `CODEX_TUI_COLOR_PROFILE=truecolor\|ansi256\|ansi16` | Force terminal color profile |
+| `CODEX_TUI_GLYPHS=ascii\|unicode\|auto` | Force terminal glyph style |
+| `CODEX_TUI_MASK_EMAIL=0/1` | Mask account emails across account-display surfaces (list/status/limits/health/dashboard/menus + TUI quota status) |
 | `CODEX_TUI_MASK_EMAIL_DETAILS=0/1` | Also hide account email in quota details when prompt masking is enabled |
 | `CODEX_AUTH_PER_PROJECT_ACCOUNTS=0/1` | Disable/enable per-project account pools |
 | `CODEX_AUTH_AUTO_UPDATE=0/1` | Disable/enable daily npm update check and cache refresh |
-| `CODEX_AUTH_UNSUPPORTED_MODEL_POLICY=strict|fallback` | Control unsupported-model retry behavior |
+| `CODEX_AUTH_ROTATION_STRATEGY=hybrid\|sticky\|round-robin` | Account selection strategy |
+| `CODEX_AUTH_UNSUPPORTED_MODEL_POLICY=strict\|fallback` | Control unsupported-model retry behavior |
 | `CODEX_AUTH_ACCOUNT_ID=<id>` | Force a specific workspace/account id |
 | `CODEX_AUTH_FETCH_TIMEOUT_MS=<ms>` | Request timeout override |
 | `CODEX_AUTH_STREAM_STALL_TIMEOUT_MS=<ms>` | SSE stream stall timeout override |
@@ -318,6 +347,8 @@ Selected runtime/environment overrides:
 | `CODEX_PLUGIN_LOG_BODIES=1` | Include raw request/response bodies in logs; sensitive |
 | `CODEX_KEYCHAIN=1` | Opt in to OS-native keychain account storage |
 
+Boolean env overrides are truthy only for the literal string `"1"`.
+
 Validate config after changes:
 
 ```bash
@@ -434,7 +465,7 @@ codex-doctor deep=true format="json"
 
 ## Release Notes
 
-- Current package version: `6.1.8`
+- Current package version: `6.9.1`
 - Changelog: [CHANGELOG.md](CHANGELOG.md)
 - Releases are automated with [release-please](https://github.com/googleapis/release-please)
 

package/config/README.md

@@ -1,15 +1,29 @@
 # Configuration
 
-This directory contains the official OpenCode config templates for `oc-codex-multi-auth`.
+This directory contains the official OpenCode config templates for `oc-codex-multi-auth` v6.9.1.
 
 ## Required: choose the right config file
 
 | File | OpenCode version | Description |
 |------|------------------|-------------|
-| [`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 |
+| [`opencode-modern.json`](./opencode-modern.json) | **v1.0.210+** | Variant-based config: **12 base models**, **53 variants** total |
+| [`opencode-legacy.json`](./opencode-legacy.json) | **v1.0.209 and below** | Legacy explicit entries: **53** individual model definitions |
 
-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.
+## Install modes
+
+| Installer flag | What gets written |
+|----------------|-------------------|
+| default / `--modern` | Compact modern: 12 base OAuth families + variant picker |
+| `--full` | Modern bases **plus** explicit legacy selector IDs |
+| `--legacy` | Explicit-only catalog (53 preset model entries) |
+
+```bash
+npx -y oc-codex-multi-auth@latest          # compact modern (default)
+npx -y oc-codex-multi-auth@latest --full   # modern + explicit IDs
+npx -y oc-codex-multi-auth@latest --legacy # explicit only
+```
+
+Rerun the default installer to remove explicit preset IDs and stale base models left by earlier plugin catalogs.
 
 ## Quick pick
 
@@ -33,19 +47,47 @@ opencode --version
 
 ## Why there are two templates
 
-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.
+OpenCode v1.0.210+ added model `variants`, so one model entry can expose multiple reasoning levels. That keeps modern config smaller while preserving the same effective presets.
 
 Both templates include:
-- 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
+
+### Base model families (12)
+
+| Base | Variants (modern) |
+|------|-------------------|
+| `gpt-5.6-sol` | low, medium, high, xhigh, max, ultra |
+| `gpt-5.6-terra` | low, medium, high, xhigh, max, ultra |
+| `gpt-5.6-luna` | low, medium, high, xhigh, max |
+| `gpt-5.5` | none, low, medium, high, xhigh |
+| `gpt-5.5-fast` | none, low, medium, high, xhigh |
+| `gpt-5.4-mini` | none, low, medium, high, xhigh |
+| `gpt-5.4-nano` | none, low, medium, high, xhigh |
+| `gpt-5.1-codex-max` | low, medium, high, xhigh |
+| `gpt-5.1-codex` | low, medium, high |
+| `gpt-5.1-codex-mini` | medium, high |
+| `gpt-5.1` | none, low, medium, high |
+| `gpt-5-codex` | low, medium, high |
+
+Shared template requirements:
+
 - `store: false` and `include: ["reasoning.encrypted_content"]`
-- 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)
+- Context metadata:
+  - `gpt-5.6-sol` / `gpt-5.6-terra` / `gpt-5.6-luna` / `gpt-5.5` / `gpt-5.5-fast`: context **1,050,000**, output **128,000**
+  - `gpt-5.4-mini` / `gpt-5.4-nano` / Codex models (`gpt-5-codex`, `gpt-5.1-codex*`, …): context **400,000**, output **128,000**
+  - `gpt-5.1`: context **272,000**, output **128,000**
+
+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-5.6-sol`; the separate OpenCode variant picker exposes the reasoning presets.
+
+If your OpenCode runtime supports global compaction tuning, you can also set values near the largest context windows (for example ~1M context / slightly lower auto-compact limit). Prefer values that match your selected model family.
 
-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.
+## GPT-5.6 notes
 
-If your OpenCode runtime supports global compaction tuning, you can also set:
-- `model_context_window = 1050000`
-- `model_auto_compact_token_limit = 950000`
+- Served over the **responses-lite** path (`use_responses_lite`).
+- Preview entitlement: accounts without access auto-fallback  
+  `gpt-5.6-sol → gpt-5.6-terra → gpt-5.6-luna → gpt-5.5`  
+  (disable with `CODEX_AUTH_DISABLE_GPT56_AUTO_FALLBACK=1`).
+- Default client identity for 5.6 is host/opencode (`originator: opencode`); other families default to Codex CLI identity.
+- `ultra` is accepted as a client-side alias and sent as `max` on the wire (no subagent orchestration in this plugin).
 
 ## Spark model note
 
@@ -60,6 +102,7 @@ Recommended compact UI selectors:
 ```bash
 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-5.6-sol --variant=medium
 opencode run "task" --model=openai/gpt-5-codex --variant=high
 ```
 
@@ -75,29 +118,35 @@ A barebones debug template is available at [`minimal-opencode.json`](./minimal-o
 
 ## Unsupported-model behavior
 
-Current defaults are strict entitlement handling except for default public selectors that are commonly entitlement-gated:
-- `gpt-5.5` and canonical `gpt-5-codex` can auto-fallback through `gpt-5.4`, `gpt-5.4-mini`, then `gpt-5.4-nano` when the backend reports the selected model is not supported for the active account/workspace
+Current defaults are strict entitlement handling except for common default-selector entitlement gates:
+
+- **GPT-5.6** auto-fallback: `gpt-5.6-sol → gpt-5.6-terra → gpt-5.6-luna → gpt-5.5`
+- **`gpt-5.5`** and canonical **`gpt-5-codex`** can auto-fallback through `gpt-5.4`, `gpt-5.4-mini`, then `gpt-5.4-nano` when the backend reports the selected model is not supported
 - `unsupportedCodexPolicy: "strict"` returns other entitlement errors directly
 - set `unsupportedCodexPolicy: "fallback"` (or `CODEX_AUTH_UNSUPPORTED_MODEL_POLICY=fallback`) to enable the full fallback chain for manual/legacy selectors
 - `fallbackToGpt52OnUnsupportedGpt53: true` keeps the legacy `gpt-5.3-codex -> gpt-5.2-codex` edge inside 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
 - legacy Codex selectors such as `gpt-5.2-codex`, `gpt-5.3-codex`, and `gpt-5.3-codex-spark` normalize to canonical `gpt-5-codex`; if that canonical Codex model is gated, the default auto-fallback can retry through the GPT-5.4 family
+- set `CODEX_AUTH_DISABLE_GPT56_AUTO_FALLBACK=1` to disable GPT-5.6 auto-fallback
 - set `CODEX_AUTH_DISABLE_GPT55_AUTO_FALLBACK=1` to disable GPT-5.5 auto-fallback
 - set `CODEX_AUTH_DISABLE_CODEX_AUTO_FALLBACK=1` to disable canonical Codex/GPT-5.4-family auto-fallback
 - `gpt-5.4-pro -> gpt-5.4` remains available for older manual configs
 - `unsupportedCodexFallbackChain` lets you override fallback order per model
 
-Default fallback chain (auto-fallback for `gpt-5.5`/`gpt-5-codex` through the GPT-5.4 family; full chain when policy is `fallback`):
-- `gpt-5.5 -> gpt-5.4 -> gpt-5.4-mini -> gpt-5.4-nano`
-- `gpt-5-codex -> gpt-5.4 -> gpt-5.4-mini -> gpt-5.4-nano`
-- `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`
-- `gpt-5.1-codex -> gpt-5-codex`
+Default chains when generic fallback policy is enabled (and empty override map):
+
+- `gpt-5.6-sol → gpt-5.6-terra → gpt-5.6-luna → gpt-5.5` (also auto under default strict for preview gates)
+- `gpt-5.5 → gpt-5.4 → gpt-5.4-mini → gpt-5.4-nano`
+- `gpt-5-codex → gpt-5.4 → gpt-5.4-mini → gpt-5.4-nano`
+- `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 if Spark IDs are added manually)
+- `gpt-5.2-codex → gpt-5-codex`
+- `gpt-5.1-codex → gpt-5-codex`
 
 ## Additional docs
 
 - Main config reference: [`docs/configuration.md`](../docs/configuration.md)
 - Getting started: [`docs/getting-started.md`](../docs/getting-started.md)
+- Tools and CLI: [`docs/tools-and-cli.md`](../docs/tools-and-cli.md)
 - Troubleshooting: [`docs/troubleshooting.md`](../docs/troubleshooting.md)

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;AA6M/D;;;;;;;;;;;;;;;GAeG;AAEH,eAAO,MAAM,iBAAiB,EAAE,MAgvH/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;AA8M/D;;;;;;;;;;;;;;;GAeG;AAEH,eAAO,MAAM,iBAAiB,EAAE,MA8wH/B,CAAC;AAEF,eAAO,MAAM,gBAAgB,QAAoB,CAAC;AAElD,eAAe,iBAAiB,CAAC"}

package/dist/index.js

@@ -32,7 +32,7 @@ import { queuedRefresh } from "./lib/refresh-queue.js";
 import { openBrowserUrl } from "./lib/auth/browser.js";
 import { startLocalOAuthServer } from "./lib/auth/server.js";
 import { promptAddAnotherAccount, promptLoginMode } from "./lib/cli.js";
-import { getCodexMode, getRequestTransformMode, getFastSession, getFastSessionStrategy, getFastSessionMaxInputItems, getRetryProfile, getRetryBudgetOverrides, getRateLimitToastDebounceMs, getRetryAllAccountsMaxRetries, getRetryAllAccountsMaxWaitMs, getRetryAllAccountsRateLimited, getFallbackToGpt52OnUnsupportedGpt53, getUnsupportedCodexPolicy, getUnsupportedCodexFallbackChain, getTokenRefreshSkewMs, getSessionRecovery, getAutoResume, getAutoUpdate, getToastDurationMs, getPerProjectAccounts, getEmptyResponseMaxRetries, getEmptyResponseRetryDelayMs, getPidOffsetEnabled, getRotationStrategy, getModelAccountPool, getFetchTimeoutMs, getStreamStallTimeoutMs, getCodexTuiV2, getCodexTuiColorProfile, getCodexTuiGlyphMode, getBeginnerSafeMode, getCodexTuiMaskEmail, loadPluginConfig, } from "./lib/config.js";
+import { getCodexMode, getRequestTransformMode, getFastSession, getFastSessionStrategy, getFastSessionMaxInputItems, getRetryProfile, getRetryBudgetOverrides, getRateLimitToastDebounceMs, getRetryAllAccountsMaxRetries, getRetryAllAccountsMaxWaitMs, getRetryAllAccountsRateLimited, getFallbackToGpt52OnUnsupportedGpt53, getUnsupportedCodexPolicy, getUnsupportedCodexFallbackChain, getTokenRefreshSkewMs, getSessionRecovery, getAutoResume, getAutoUpdate, getToastDurationMs, getAccountToastsEnabled, getPerProjectAccounts, getEmptyResponseMaxRetries, getEmptyResponseRetryDelayMs, getPidOffsetEnabled, getRotationStrategy, getModelAccountPool, getFetchTimeoutMs, getStreamStallTimeoutMs, getCodexTuiV2, getCodexTuiColorProfile, getCodexTuiGlyphMode, getBeginnerSafeMode, getCodexTuiMaskEmail, loadPluginConfig, } from "./lib/config.js";
 import { AUTH_LABELS, CODEX_BASE_URL, DUMMY_API_KEY, LOG_STAGES, PLUGIN_NAME, PROVIDER_ID, ACCOUNT_LIMITS, } from "./lib/constants.js";
 import { initLogger, logRequest, logDebug, logInfo, logWarn, logError, setCorrelationId, clearCorrelationId, } from "./lib/logger.js";
 import { checkAndNotify } from "./lib/auto-update-checker.js";
@@ -896,6 +896,35 @@ export const OpenAIOAuthPlugin = async ({ client }) => {
             });
         }
     };
+    const reloadCachedAccountManager = async () => {
+        if (!cachedAccountManager)
+            return;
+        const previous = cachedAccountManager;
+        // Flush the outgoing manager's pending debounced save BEFORE reading
+        // fresh disk state. Otherwise a queued save from `previous` can fire
+        // after this reload and silently overwrite the single-use refresh
+        // tokens codex-health/codex-refresh just persisted via
+        // withAccountStorageTransaction — a lost-update on rotated credentials.
+        // Mirrors invalidateAccountManagerCache above.
+        try {
+            await previous.flushPendingSave();
+        }
+        catch (error) {
+            logWarn(`Failed to flush pending save while reloading account manager: ${error instanceof Error ? error.message : String(error)}`);
+        }
+        try {
+            const reloadedManager = await AccountManager.loadFromDisk();
+            cachedAccountManager = reloadedManager;
+            accountManagerPromise = Promise.resolve(reloadedManager);
+            // Dispose only after the replacement is installed so we never leak
+            // the outgoing manager's shutdown handler on every reload, and so a
+            // load failure leaves the working manager intact.
+            previous.disposeShutdownHandler();
+        }
+        catch (error) {
+            logWarn(`Failed to reload account manager: ${error instanceof Error ? error.message : String(error)}`);
+        }
+    };
     const persistAuthenticatedSelections = async (results, replaceAll) => {
         try {
             await persistAccountPool(results, replaceAll);
@@ -948,11 +977,7 @@ export const OpenAIOAuthPlugin = async ({ client }) => {
                     await clearPromptQuotaCache();
                     // Reload manager from disk so we don't overwrite newer rotated
                     // refresh tokens with stale in-memory state.
-                    if (cachedAccountManager) {
-                        const reloadedManager = await AccountManager.loadFromDisk();
-                        cachedAccountManager = reloadedManager;
-                        accountManagerPromise = Promise.resolve(reloadedManager);
-                    }
+                    await reloadCachedAccountManager();
                     await showToast(`Switched to account ${index + 1}`, "info");
                 }
             }
@@ -984,6 +1009,7 @@ export const OpenAIOAuthPlugin = async ({ client }) => {
                 accountManagerPromise = value;
             },
         },
+        reloadCachedAccountManager,
         runtimeMetrics,
         beginnerSafeModeRef: {
             get current() {
@@ -1126,6 +1152,7 @@ export const OpenAIOAuthPlugin = async ({ client }) => {
                     const fallbackToGpt52OnUnsupportedGpt53 = getFallbackToGpt52OnUnsupportedGpt53(pluginConfig);
                     const unsupportedCodexFallbackChain = getUnsupportedCodexFallbackChain(pluginConfig);
                     const toastDurationMs = getToastDurationMs(pluginConfig);
+                    const accountToastsEnabled = getAccountToastsEnabled(pluginConfig);
                     const fetchTimeoutMs = getFetchTimeoutMs(pluginConfig);
                     const streamStallTimeoutMs = getStreamStallTimeoutMs(pluginConfig);
                     const sessionRecoveryEnabled = getSessionRecovery(pluginConfig);
@@ -1497,7 +1524,8 @@ export const OpenAIOAuthPlugin = async ({ client }) => {
                                         // 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 &&
+                                        if (accountToastsEnabled &&
+                                            accountCount > 1 &&
                                             accountManager.shouldShowAccountToast(account.index, rateLimitToastDebounceMs)) {
                                             const accountLabel = formatAccountLabel(account, account.index, {
                                                 maskEmail: maskEmailEnabled,