codex-multi-auth 2.0.1 → 2.1.0

package/README.md

@@ -22,8 +22,10 @@ Codex CLI-first multi-account OAuth manager for the official Codex CLI. The inst
 - Interactive dashboard for account actions and settings
 - Experimental settings tab for staged sync, backup, and refresh-guard controls
 - Forecast, report, fix, and doctor commands for operational safety
+- Local usage ledger, budgets, account policy controls, routing profiles, and monitor views for local governance
 - Runtime counters, budget/cooldown state, and multi-auth probe visibility in `codex auth status` / `codex auth report`
 - Default-on runtime Responses proxy for live account rotation inside forwarded Codex CLI/app sessions
+- Optional loopback-only local bridge for `/health`, `/v1/models`, and `/v1/responses`, protected by hashed local client tokens
 - Reversible packaged Codex app bind and user-level launcher routing helpers
 - Flagged account verification and restore flow
 - Session affinity and live account sync controls
@@ -134,7 +136,8 @@ codex auth switch 2
 codex auth forecast --live
 ```
 
-If browser launch is blocked, use the alternate login paths in [docs/getting-started.md](docs/getting-started.md#alternate-login-paths).
+If browser launch is blocked, use the alternate login paths in [docs/getting-started.md](docs/getting-started.md#alternate-login-paths).
+For remote or headless shells, prefer `codex auth login --device-auth`.
 
 ---
 
@@ -172,6 +175,10 @@ If browser launch is blocked, use the alternate login paths in [docs/getting-sta
 | `codex auth report --live --json` | How do I get the full machine-readable health report? |
 | `codex auth fix --live --model gpt-5.3-codex` | How do I run live repair probes with a chosen model? |
 | `codex auth why-selected --json` | Which account does the selector pick now, and why? |
+| `codex auth usage --since 24h --by project` | What local usage has been recorded recently? |
+| `codex auth monitor --json` | What is the combined usage, policy, quota, runtime, and project state? |
+| `codex auth bridge token create --label local-client` | How do I create a local bridge bearer token? |
+| `codex auth integrations --kind python` | How do I generate local bridge client snippets? |
 | `codex auth rotation status` | Is live runtime account rotation enabled for forwarded Codex sessions? |
 
 ### Reliability behavior
@@ -215,8 +222,13 @@ If browser launch is blocked, use the alternate login paths in [docs/getting-sta
 | Settings | `~/.codex/multi-auth/settings.json` |
 | Accounts | `~/.codex/multi-auth/openai-codex-accounts.json` |
 | Flagged accounts | `~/.codex/multi-auth/openai-codex-flagged-accounts.json` |
-| Quota cache | `~/.codex/multi-auth/quota-cache.json` |
+| Quota cache | `~/.codex/multi-auth/quota-cache.json` |
 | Runtime observability | `~/.codex/multi-auth/runtime-observability.json` |
+| Usage ledger | `~/.codex/multi-auth/usage/usage-ledger.jsonl` |
+| Account policies | `~/.codex/multi-auth/account-policies.json` |
+| Routing profiles | `~/.codex/multi-auth/routing-profiles.json` |
+| Budget guards | `~/.codex/multi-auth/budget-guards.json` |
+| Local client tokens | `~/.codex/multi-auth/local-client-tokens.json` |
 | Runtime app helper status | `~/.codex/multi-auth/runtime-rotation-app-helper.json` |
 | Persistent app bind state/logs | `~/.codex/multi-auth/app-bind/` |
 | Logs | `~/.codex/multi-auth/logs/codex-plugin/` |
@@ -305,7 +317,7 @@ codex auth login
 - Requests fail fast after repeated upstream 5xx errors: inspect `codex auth report --json` for runtime traffic and cooldown details
 - Storage cleanup fails with `EBUSY` / `EPERM` (Windows): run `codex auth doctor --fix` to retry, or manually remove `~/.codex/multi-auth/<project-key>/` and re-login
 - OAuth callback on port `1455` fails: free the port and re-run `codex auth login`
-- Browser launch is blocked or you are in a headless shell: re-run `codex auth login --manual` or set `CODEX_AUTH_NO_BROWSER=1`
+- Browser launch is blocked or you are in a headless shell: prefer `codex auth login --device-auth`; use `codex auth login --manual` or `CODEX_AUTH_NO_BROWSER=1` only when you need the callback-paste fallback
 - `missing field id_token` / `token_expired` / `refresh_token_reused`: re-login affected account
 
 </details>
@@ -345,11 +357,13 @@ codex auth doctor --json
 
 ---
 
-## Release Notes
-
-- Current stable: [docs/releases/v2.0.1.md](docs/releases/v2.0.1.md)
-- Previous stable: [docs/releases/v1.3.2.md](docs/releases/v1.3.2.md)
-- Earlier stable: [docs/releases/v1.3.1.md](docs/releases/v1.3.1.md)
+## Release Notes
+
+- Current stable: [docs/releases/v2.1.0.md](docs/releases/v2.1.0.md)
+- Previous stable: [docs/releases/v2.0.2.md](docs/releases/v2.0.2.md)
+- Earlier stable: [docs/releases/v2.0.1.md](docs/releases/v2.0.1.md)
+- Earlier stable: [docs/releases/v1.3.2.md](docs/releases/v1.3.2.md)
+- Stable archive: [docs/releases/v1.3.1.md](docs/releases/v1.3.1.md)
 - Full release archive: [docs/README.md#release-history](docs/README.md#release-history)
 - Archived prerelease: [docs/releases/v0.1.0-beta.0.md](docs/releases/v0.1.0-beta.0.md)
 

package/config/README.md

@@ -1,6 +1,6 @@
 # Config Templates
 
-These files are optional model/provider templates for host/plugin configurations that still load `codex-multi-auth` directly. The normal wrapper workflow uses `codex auth ...` and does not require these templates.
+These files are optional model/provider templates for host/plugin configurations that still load `codex-multi-auth` directly. The normal wrapper workflow uses `codex auth ...` and does not require these templates.
 
 ## Primary (Codex-named)
 
@@ -12,12 +12,12 @@ These files are optional model/provider templates for host/plugin configurations
 
 ## Notes
 
-- These templates are optional for the OAuth account manager flow and the runtime rotation proxy.
-- Core auth commands use `codex auth login`.
+- These templates are optional for the OAuth account manager flow and the runtime rotation proxy.
+- Core auth commands use `codex auth login`.
 
 ## Defaults Included
 
-- Current documented OpenAI/Codex model families (`gpt-5.5`, `gpt-5.4`, and `gpt-5.3-codex`)
+- Current documented OpenAI/Codex model families (`gpt-5.5`, `gpt-5.4`, and `gpt-5.3-codex`)
 - `store: false`
 - `include: ["reasoning.encrypted_content"]`
 - Sensible fallback behavior for unsupported model entitlements