openclaw-code-agent 4.5.0 → 4.5.2

package/README.md

@@ -127,9 +127,9 @@ Because worktree isolation defaults to `delegate`, `defaultWorkdir` should norma
 
 Chat-launched sessions route updates back to their originating chat thread. For agent-launched tool sessions without an origin route, configure `fallbackChannel` or `agentChannels` in the reference guide.
 
-The current package targets and validates against the OpenClaw SDK package `openclaw@2026.6.5`, while keeping the plugin peer floor at `>=2026.4.21`. No host upgrade or host config change is required for this plugin compatibility update. OpenClaw `2026.6.5` changes plugin runtime/install lookup, plugin SDK exports, approval normalization, cron/session delivery, Telegram callback and topic delivery, runtime tool allowlists, Codex App Server recovery, and adjacent bundled/external agent plugins, but `openclaw-code-agent` does not need new SDK imports for them: the manifest already declares `contracts.tools`, the plugin still imports only `openclaw/plugin-sdk/plugin-entry`, and its own session store, wake routing, callbacks, worktree flows, and harness model restrictions remain plugin-owned.
+The current package targets and validates against the OpenClaw SDK package `openclaw@2026.6.8`, while keeping the plugin peer floor at `>=2026.4.21`. No host upgrade or host config change is required for this plugin compatibility update. OpenClaw `2026.6.8` changes channel delivery, agent/Gateway recovery, provider/model replay hardening, usage footer hooks, managed plugin update repair, and release/test reliability; this release also includes Codex App Server startup/resume hardening, worktree decision follow-through fixes, and the Hono production audit override needed by the current dependency tree. `openclaw-code-agent` does not need new SDK imports for the OpenClaw changes: the manifest already declares `contracts.tools`, the plugin still imports only `openclaw/plugin-sdk/plugin-entry`, and its own session store, wake routing, callbacks, worktree flows, and harness model restrictions remain plugin-owned.
 
-If you use Codex, make sure the local `codex` command or `OPENCLAW_CODEX_APP_SERVER_COMMAND` override is available and authenticated. Codex-specific defaults live under `harnesses.codex`: `reasoningEffort` is sent as `reasoningEffort`, and `fastMode: true` sends `service_tier: "fast"` on Codex App Server thread, resume, and turn payloads. When Codex auth is inconsistent, this is the recommended `~/.codex/config.toml` setting:
+If you use Codex, make sure the local `codex` command or `OPENCLAW_CODEX_APP_SERVER_COMMAND` override is available and authenticated. Codex-specific defaults live under `harnesses.codex`: `reasoningEffort` is sent as `reasoningEffort`, and `fastMode: true` sends `service_tier: "fast"` on Codex App Server thread, resume, and turn payloads. The Codex harness starts the app server with stdio listener args by default, only sends UUID-shaped backend thread IDs to `thread/resume`, and reports startup timeouts with redacted recent stderr. When Codex auth is inconsistent, this is the recommended `~/.codex/config.toml` setting:
 
 ```toml
 forced_login_method = "chatgpt"