iam-brain · iam-brain · Feb 8, 2026 · Feb 8, 2026 · Feb 8, 2026 · Feb 8, 2026
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -35,46 +35,25 @@ more deterministic account management.
 ### Docs
 - **Multi-account guide**: clarified repair/quarantine behavior and legacy handling.
 
-## [4.5.24] - 2026-01-31
-
-**UI Polish release**: Final alignment tweaks for `codex-status`.
-
-### Fixed
-- **Dashboard Padding**: fine-tuned padding for Plan column and Usage bars to perfectly match the grid alignment.
-
-## [4.5.23] - 2026-01-31
-
-**UI Polish release**: New "Obsidian Dashboard" theme for `codex-status`.
-
-### Changed
-- **Visual Overhaul**: `codex-status` now features the "Obsidian Dashboard" theme:
-  - **High-Density Layout**: Clean, wall-less design with perfect grid alignment.
-  - **Status Pills**: Color-coded badges (ACTIVE/ENABLED/DISABLED) for instant status recognition.
-  - **Dynamic Usage Bars**: Quota bars shift color (Blue -> Yellow -> Red) based on consumption.
-  - **Precision Timers**: Reset timers now include dates for long-term limits (e.g., `resets 09:32 on 3 Feb`).
-
 ## [4.5.21] - 2026-01-31
 
 **Parallel Rotation Resilience release**: atomic sync across multiple machine sessions.
 
 ### Fixed
 - **Unauthorized Recovery**: main request loop now recovers from `401 Unauthorized` by re-syncing with disk and retrying, matching the official Codex CLI's robustness.
-- **Ghost Rotations**: `codex-status` tool now persists rotated tokens to disk immediately, preventing drift that previously invalidated other active sessions.
 - **Token Overwrite Race**: implemented **Timestamp Arbitration** in storage merges; the most recently active session (`lastUsed`) now always wins, preventing stale sessions from corrupting the authoritative machine state.
 
 ### Changed
 - **Strict Identity Uniqueness**: all account matching now strictly uses the `accountId + email + plan` composite key to ensure global uniqueness across different workspaces and subscriptions.
 
 ## [4.5.20] - 2026-01-31
 
-**Reliability & Identity Hardening release**: codex-status stability, memory safety, and identity-based tracking.
+**Reliability & Identity Hardening release**: status tracking stability, memory safety, and identity-based tracking.
 
 ### Changed
-- **codex-status Read-Only**: tool no longer forces token refresh; uses existing valid tokens and falls back to cached snapshots on failure.
 - **Identity-Based Trackers**: `HealthScoreTracker` and `TokenBucketTracker` now key on `accountId|email|plan` instead of array index for stability across account changes.
 - **Periodic Cleanup**: both trackers now auto-prune stale entries (24h for health, 1h for tokens) to prevent memory growth.
 - **Console Logging**: migrated `console.error` calls to `logWarn` to respect debug settings and avoid TUI corruption.
-- **Command Templates**: updated slash commands to output results exactly as returned by tools.
 
 ### Added
 - **logCritical()**: new always-enabled logger for critical issues that bypass debug flags.
@@ -84,36 +63,19 @@ more deterministic account management.
 ### Fixed
 - **Memory Leak**: `RateLimitTracker` now cleans up stale entries periodically (every 60s).
 
-## [4.5.19] - 2026-01-31
-
-**Slash Commands release**: register codex tools as TUI slash commands.
-
-### Added
-- **Slash Commands**: `/codex-status`, `/codex-switch-accounts`, `/codex-toggle-account` now available via config hook.
-
-## [4.5.18] - 2026-01-31
-
-**Tool Consolidation release**: finalized renaming of status and account management tools to match the `codex-*` namespace.
-
-### Changed
-- **Tool Consolidation**: renamed `openai-accounts` and `status-codex` to a single authoritative `codex-status` tool.
-- **Account Management**: renamed `openai-accounts-switch` to `codex-switch-accounts` and `openai-accounts-toggle` to `codex-toggle-account`.
-- **Lazy Refresh**: tool calls now only refresh tokens if they are within the `tokenRefreshSkewMs` window (default 60s), reducing unnecessary network roundtrips.
-- **Code Hardening**: implemented SSE stream memory guards (1MB buffer limit) and removed redundant imports and logic in `index.ts`.
-
 ## [4.5.17] - 2026-01-31
 
 **Authoritative Status release**: active fetching from official OpenAI `/wham/usage` endpoints and perfect protocol alignment.
 
 ### Added
-- **Active Usage Fetching**: tools now actively fetch real-time rate limit data from `https://chatgpt.com/backend-api/wham/usage` (ChatGPT plans) and `https://api.openai.com/api/codex/usage` (API plans).
+- **Active Usage Fetching**: status tracking now actively fetches real-time rate limit data from `https://chatgpt.com/backend-api/wham/usage` (ChatGPT plans) and `https://api.openai.com/api/codex/usage` (API plans).
 - **Protocol Alignment**: refactored `CodexStatusManager` to match the official `codex-rs v0.92.0` data structures and TUI formatting.
 - **Detailed Reset Dates**: long-term resets (>24h) now display the full date and time (e.g., `resets 18:10 on 5 Feb`).
 
 ### Changed
 - **Inverted Usage Display**: status bars now show **"% left"** instead of "% used", correctly representing remaining quota.
 - **Standardized Labels**: updated window labels to "5 hour limit:" and "Weekly limit:".
-- **Proactive Tool Hydration**: tool calls now force a token refresh and identity repair to ensure the authoritative `/usage` endpoint receives a valid Bearer token.
+- **Proactive Hydration**: status fetches now force a token refresh and identity repair to ensure the authoritative `/usage` endpoint receives a valid Bearer token.
 - **Enhanced UI Alignment**: applied strict padding and "Always Render Both" logic to ensure vertical and horizontal table stability even with missing or "unknown" data.
 
 ### Fixed
@@ -137,8 +99,8 @@ more deterministic account management.
 **Global Cache path release**: ensure cross-process visibility.
 
 ### Fixed
-- **Global Snapshot Path**: corrected `getCachePath` to always use the system configuration directory (`~/.config/opencode/cache`), ensuring that rate limit data captured by the proxy is visible to CLI tools regardless of project scope.
-- **Table Alignment**: refactored `openai-accounts` and `status-codex` into a strict ASCII table format to prevent horizontal shifting.
+- **Global Snapshot Path**: corrected `getCachePath` to always use the system configuration directory (`~/.config/opencode/cache`), ensuring that rate limit data captured by the proxy is visible across project scopes.
+- **Table Alignment**: refactored account/status table output into a strict ASCII format to prevent horizontal shifting.
 
 ## [4.5.13] - 2026-01-30
 
@@ -157,7 +119,7 @@ more deterministic account management.
 ### Changed
 - **Async Status Hardening**: refactored `CodexStatusManager` to use non-blocking async I/O (`fs.promises`) and promise-based initialization gates to prevent concurrency races.
 - **Cross-Process Hydration**: ensured status snapshots are stored globally even when using per-project account storage, allowing all projects to share real-time rate limit visibility.
-- **Tool UI Refinement**: refactored `openai-accounts` and `status-codex` output into a strictly aligned ASCII table format for better readability.
+- **Status UI Refinement**: refactored account/status output into a strictly aligned ASCII table format for better readability.
 - **Lost Updates Prevention**: implemented timestamp-based (`updatedAt`) merge arbitration under lock (`proper-lockfile`) to ensure newest state wins across concurrent processes.
 - **Security Hardening**: primary accounts and snapshots cache files now use restrictive `0600` permissions.
 
@@ -175,7 +137,7 @@ more deterministic account management.
 - **Persistent Snapshots**: rate limit data is now persisted to `~/.config/opencode/cache/codex-snapshots.json` for cross-process visibility between the proxy and CLI tools.
 
 ### Tests
-- **Status Fixtures**: added `codex-status-snapshots.json` and `codex-headers.json` for deterministic testing of rate limit parsing and rendering.
+- **Status Fixtures**: added snapshot and header fixtures for deterministic testing of rate limit parsing and rendering.
 
 ## [4.5.10] - 2026-01-30
 

diff --git a/README.md b/README.md
@@ -99,18 +99,6 @@ Personality descriptions come from:
 The filename (case-insensitive) defines the key (e.g., `Idiot.md`), and the file contents are used verbatim.
 
 Built-ins: `none`, `default` (uses model runtime defaults), `friendly`, `pragmatic` (fallback if unset). Any other key requires a matching personality file.
----
-## ⌨️ Slash Commands (TUI)
-In the OpenCode TUI, you can use these commands to manage your accounts and monitor usage:
-
-| Command | Description |
-|---------|-------------|
-| `/codex-status` | Shows current rate limits (5h/Weekly), credits, and account status (percent left). |
-| `/codex-switch-accounts <index>` | Switch the active account by its 1-based index from the status list. |
-| `/codex-toggle-account <index>` | Enable or disable an account by its 1-based index (prevents auto-selection). |
-| `/codex-remove-account <index>` | Remove an account by its 1-based index. |
-
----
 ## ✅ Features
 - ChatGPT Plus/Pro OAuth authentication (official flow)
 - Model presets across GPT‑5.3 Codex / GPT‑5.2 / GPT‑5.2 Codex / GPT‑5.1 families
@@ -124,8 +112,8 @@ In the OpenCode TUI, you can use these commands to manage your accounts and moni
 - Strict account identity matching (`accountId` + `email` + `plan`)
 - Hybrid account selection strategy (health score + token bucket + LRU bias)
 - Optional round-robin account rotation (maximum throughput)
-- OpenCode TUI toasts + `codex-status` / `codex-switch-accounts` tools
-- **Authoritative Codex Status**: Real-time rate limit monitoring (5h/Weekly) with ASCII status bars
+- OpenCode TUI toasts for account switching and rate-limit events
+- **Authoritative Status Tracking**: Real-time rate limit monitoring (5h/Weekly) with cached snapshots
 ---
 ## 🛡️ Safety & Reliability
 - Hard-stop safety gate for all-accounts rate-limit/auth-failure loops

diff --git a/RELEASE_NOTES.md b/RELEASE_NOTES.md
@@ -12,6 +12,6 @@ Bugfix release: toast debounce configuration and legacy account removal.
 **Reliability & Data Safety**
 
 - **Toast Spam Fix**: Notifications for rate-limit account switching now respect the 60s debounce timer (`rateLimitToastDebounceMs`) instead of the 2s dedupe window, preventing UI spam during heavy load.
-- **Account Removal Safety**: `codex-remove-account` now safely removes accounts even if their tokens were rotated in memory during the same session, preventing "zombie" accounts from persisting in storage.
+- **Account Removal Safety**: account removal now safely handles in-memory token rotations during the same session, preventing "zombie" accounts from persisting in storage.
 
 **Full Changelog**: https://github.com/iam-brain/opencode-openai-codex-multi-auth/compare/v4.5.24...v4.5.25
diff --git a/config/README.md b/config/README.md
@@ -6,19 +6,21 @@ This directory contains the official opencode configuration files for the OpenAI
 
 **Two configuration files are available based on your OpenCode version:**
 
-| File | OpenCode Version | Description |
-|------|------------------|-------------|
-| [`opencode-modern.json`](./opencode-modern.json) | **v1.0.210+ (Jan 2026+)** | Compact config using variants system - 6 models with built-in reasoning level variants |
-| [`opencode-legacy.json`](./opencode-legacy.json) | **v1.0.209 and below** | Extended config with separate model entries for each reasoning level - 20+ individual model definitions |
+| File                                             | OpenCode Version          | Description                                                                                             |
+| ------------------------------------------------ | ------------------------- | ------------------------------------------------------------------------------------------------------- |
+| [`opencode-modern.json`](./opencode-modern.json) | **v1.0.210+ (Jan 2026+)** | Compact config using variants system - 6 models with built-in reasoning level variants                  |
+| [`opencode-legacy.json`](./opencode-legacy.json) | **v1.0.209 and below**    | Extended config with separate model entries for each reasoning level - 20+ individual model definitions |
 
 ### Which one should I use?
 
 **If you have OpenCode v1.0.210 or newer** (check with `opencode --version`):
+
 ```bash
 cp config/opencode-modern.json ~/.config/opencode/opencode.jsonc
 ```
 
 **If you have OpenCode v1.0.209 or older**:
+
 ```bash
 cp config/opencode-legacy.json ~/.config/opencode/opencode.jsonc
 ```
@@ -29,12 +31,13 @@ OpenCode v1.0.210+ introduced a **variants system** that allows defining reasoni
 
 **What you get:**
 
-| Config File | Model Families | Reasoning Variants | Total Models |
-|------------|----------------|-------------------|--------------|
-| `opencode-modern.json` | 6 | Built-in variants (low/medium/high/xhigh) | 6 base models with 19 total variants |
-| `opencode-legacy.json` | 6 | Separate model entries | 20 individual model definitions |
+| Config File            | Model Families | Reasoning Variants                        | Total Models                         |
+| ---------------------- | -------------- | ----------------------------------------- | ------------------------------------ |
+| `opencode-modern.json` | 6              | Built-in variants (low/medium/high/xhigh) | 6 base models with 19 total variants |
+| `opencode-legacy.json` | 6              | Separate model entries                    | 20 individual model definitions      |
 
 Both configs provide:
+
 - ✅ All supported GPT 5.x variants: gpt-5.3-codex, gpt-5.2, gpt-5.2-codex, gpt-5.1, gpt-5.1-codex, gpt-5.1-codex-max, gpt-5.1-codex-mini
 - ✅ Proper reasoning effort settings for each variant (including `xhigh` for Codex Max/5.2)
 - ✅ Context limits (272k context / 128k output for all Codex families)
@@ -52,11 +55,13 @@ Both configs provide:
 ## Usage
 
 1. **Check your OpenCode version**:
+
    ```bash
    opencode --version
    ```
 
 2. **Copy the appropriate config** based on your version:
+
    ```bash
    # For v1.0.210+ (recommended):
    cp config/opencode-modern.json ~/.config/opencode/opencode.jsonc
@@ -66,6 +71,7 @@ Both configs provide:
    ```
 
 3. **Run opencode**:
+
    ```bash
    # Modern config (v1.0.210+):
    opencode run "task" --model=openai/gpt-5.3-codex --variant=medium