Three install/bridge bugs that made every OpenClaw model call to the
bridge fail when driven by a non-bundled channel plugin (e.g. Fabric):
1. OpenClaw redacts secret-like keys before exposing pluginConfig to a
plugin, so config.bridgeApiKey was the literal __OPENCLAW_REDACTED__
sentinel. The bridge then validated Authorization against the
sentinel while the model provider sent the real key -> permanent
HTTP 401. Resolve the real shared secret from the raw on-disk config
(same pattern resolveAgent already uses); if still missing/redacted,
treat as no-auth on the loopback-only bridge instead of 401-locking.
2. install.mjs set the provider apiKey authoritatively but only
setIfMissing the plugin bridgeApiKey, so a stale prior value desynced
the pair. Make bridgeApiKey authoritative too (they must match).
3. The provider had no timeoutSeconds; a full bridged agent turn far
exceeds OpenClaw's default model-fetch timeout, so OpenClaw aborted
mid-turn and no reply was ever delivered. Default timeoutSeconds=600
(preserves a user override).
Verified live: bridge now returns 200 for the real key and a valid
OpenAI SSE completion; the fetch-timeout abort is gone.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
OpenClaw's LLM idle watchdog (default 120s) fires on lack of *model
progress*, not lack of bytes — an SSE comment frame (": keepalive\n\n")
keeps the TCP socket alive but isn't recognized as progress, so a long
quiet tool-call phase still idles out. When that happens OpenClaw falls
back to re-sending the prior turn's assistant text (pi-embedded:1308
fallbackAnswerText), producing duplicate-Discord-message symptoms.
Heartbeat now emits a real chat.completion.chunk with an empty content
delta every 30s. Clients drop empty deltas; the upstream idle watchdog
should count it as model progress because it's a real event on the
canonical streaming channel.
scripts/install.mjs now spreads the existing provider entry before
overriding script-managed fields, so user-added fields like
timeoutSeconds survive reinstall.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Migrate src/ → plugin/ (plugin/core/, plugin/web/, plugin/commands/)
and src/mcp/ → services/ per OpenClaw plugin dev spec
- Add Gemini CLI backend (plugin/core/gemini/sdk-adapter.ts) with GEMINI.md
system-prompt injection
- Inject bootstrap as stateless system prompt on every turn instead of
first turn only: Claude via --system-prompt, Gemini via workspace/GEMINI.md;
eliminates isFirstTurn branch, keeps skills in sync with OpenClaw snapshots
- Fix session-map-store defensive parsing (sessions ?? []) to handle bare {}
reset files without crashing on .find()
- Add docs/TEST_FLOW.md with E2E test scenarios and expected outcomes
- Add docs/claude/BRIDGE_MODEL_FINDINGS.md with contractor-probe results
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Complete the MCP tool call chain:
- contractor-agent bridge exposes /mcp/execute endpoint for tool callbacks
- openclaw-mcp-server.mjs proxies OpenClaw tool defs to Claude as MCP tools
- sdk-adapter passes --mcp-config on first turn with all OpenClaw tools
- tool-test plugin registers contractor_echo in globalThis tool handler map
- agent-config-writer auto-sets tools.profile=full so OpenClaw sends tool defs
- Fix --mcp-config arg ordering: prompt must come before <configs...> flag
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
