Merge pull request #175 from anurag008w/fix/whatsapp-runtime-ok-false-positive

fix(guardian+startup): guardian exits after first run; non-atomic config writes

fix(whatsapp): don't trust inspect exit code alone in whatsapp_plugin_runtime_ok

Merge pull request #174 from anurag008w/codex/investigate-whatsapp-crashing-issues

Merge branch 'main' into codex/investigate-whatsapp-crashing-issues

Preserve WhatsApp channel config and auto-install WhatsApp runtime on startup

Merge pull request #173 from anurag008w/codex/investigate-whatsapp-crashing-issues

Auto-install @openclaw/whatsapp runtime and preserve saved WhatsApp channel config

Merge pull request #172 from anurag008w/codex/fix-chrome-launch-errors-in-openclaw

fix: align env builder runtime fields

Merge pull request #171 from anurag008w/codex/fix-chrome-launch-errors-in-openclaw

fix: disable broken WhatsApp plugin before gateway

Merge pull request #170 from anurag008w/codex/fix-chrome-launch-errors-in-openclaw

fix: skip redundant latest OpenClaw install

Merge pull request #169 from anurag008w/codex/fix-chrome-launch-errors-in-openclaw

feat: add remote CDP browser mode

fix: preserve proxied undici request options

Merge pull request #168 from anurag008w/browser-fix

fix(providers): inject apiKey, baseUrl, and api type for non-plugin providers

fix(version): install pinned version when image has nothing bundled (Case 5)

fix: remove --no-dbus (fake flag) and silent-failing ln -sf

fix: remove protected executablePath key + fix npm path in runtime upgrade

fix(version): OPENCLAW_VERSION env bundle no longer ignored + runtime upgrade

fix(browser): resolve CDP http_unreachable, dbus socket, and GCM errors

fix : websocket keepalive, and keep guardian persistence

Implement proxy retry chain: 3x proxy, 1x direct, 1x final proxy

Merge pull request #165 from anurag008w/fix/fetch-error-code-and-http-thought-strip

fix: key rotation infinite suspension loop, round-robin broken, strike decay, WA double-reject

fix: fetch network errors, Gemini thought-strip in http patch, guardian interval cleanup

Merge pull request #164 from anurag008w/fix/gemini-thought-signature-and-stale-plugin-allow

fix: Gemini thought_signature 400 error, stale clawhub plugin, latest models & aliases (May 2026)

Merge pull request #163 from anurag008w/feat/llm-fallback-models

feat: LLM fallback models, May 2026 model updates, and bug fixes

Merge pull request #162 from anurag008w/feat/llm-fallback-models

fix: preserve existing manual fallbacks in config on restart

fix: remove duplicate fallback echo from JSON build block

feat: add LLM_FALLBACK_MODELS env var for automatic model failover

fix: handle WebSocket upgrade in Worker

fix(cloudflare-proxy): handle WebSocket upgrade in Worker without body/redirect

fix: IPv4 forcing, proxy fallback, browser symlink noise, model injection, WA stall recovery

Reject non-WebSocket upgrades and make devdata/openclaw prunes resilient to partial snapshots

Harden Jupyter devdata prune behavior for deleted files and copy races

Add optional reuse of suspended keys as last-resort and treat 429/402 as strike-bearing failures

Default to last-resort key reuse when all keys are suspended

Preserve fetch semantics and caller headers when injecting keys

fix retry/body safety and rpc cleanup in request patch paths

harden fetch arg builder for Request inputs and query providers

Add rotator verbosity & transient-failure handling; enable POST retries; make config/state snapshot writes safer

Avoid misleading rotator fetch errors for non-provider requests

Merge injected model providers using '*' to preserve provider fields in start.sh