* ✨ feat(agent-management): paginate searchAgent with real totals and cap notice
The searchAgent tool silently clamped limit to 20 with no pagination and
reported totalCount as the returned page size, so models (and users) could
never discover agents beyond the 20 most recently updated ones.
- AgentModel: extract shared where builder, add countAgents (same
conditions as queryAgents)
- lambda router + client agent service: expose countAgents
- server tool runtime & AgentManagerRuntime: pass offset through, report
real totals (workspace + marketplace), emit explicit notes when the
requested limit is capped and when more pages exist, explain
out-of-range offsets instead of claiming no matches
- manifest: add offset param, document pagination
- agent-manager-runtime: add vitest config + test scripts (suite was
previously unrunnable), repair stale store mocks
* 👷 build(ci): wire 8 tested packages into the package test workflow
An audit found 8 packages carrying test:coverage scripts that were never
added to the CI PACKAGES allowlist, so their suites never ran:
- agent-gateway-client, device-gateway-client, device-identity,
eval-dataset-parser: already green, added as-is
- eval-rubric, fetch-sse: had no package-level vitest config, so vitest
fell back to the root config whose setup/aliases break outside src/ —
added minimal configs
- heterogeneous-agents: one assertion drifted (labels registry gained
amp/hermes/openclaw/opencode) with nobody noticing — updated
- agent-manager-runtime: wired in the previous commit
All 8 verified locally with the exact CI command
(bun run --filter <pkg> test:coverage).
* ✅ test(agent-management): cover searchAgent error path and market totalCount fallback
Codecov flagged 3 uncovered lines in the patch: the searchAgents catch
block (2 misses) and the totalCount ?? items.length fallback (1 partial).
Add the missing failure-path and fallback tests on both execution paths
(client AgentManagerRuntime + server tool runtime).
* 🐛 fix(agent-manager): guard createAgent against LLM double-encoded array fields
When an LLM calls createAgent, it can send plugins/tags/openingQuestions
as a JSON string (e.g. '["lobe-cloud-sandbox"]') instead of a proper
array. This caused jsonb to store a double-serialized string rather than
an array, breaking downstream ETL queries with "cannot get array length
of a scalar".
updateAgentConfig already had this guard (line 130+); apply the same
parseArrayParam helper to all three array fields in createAgent.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* 🐛 fix(agent-manager): guard server-side createAgent against double-encoded array fields
Same LLM double-encoding guard applied to the server-side execution path
(src/server/services/toolExecution/serverRuntimes/agentManagement.ts),
which directly calls agentModel.create() and was equally vulnerable.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
🐛 fix(skill): skip OAuth redirectUri on desktop to prevent broken app:// navigation
On desktop (Electron), window.location.origin is app://renderer which the system browser cannot navigate to. Skip passing redirectUri so market shows a default success page instead, relying on existing window-close monitoring and fallback polling to detect OAuth completion.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The 200-char truncation is no longer needed as the caller
already handles length limits.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: improve the inject model context plugins decriptions
fix: change the conversation-flow to change the subAgent message show place
fix: eslint fixed
fix: slove the inject not work problem
feat: add the lost agent management inject open
feat: add the AgentManagementInjector
fix: add the exec task mode & improve the Pre-load agents
fix: improve the executor import way & update the getEffectiveAgentId function
fix: slove the test problem
🐛 fix: support agnet manager ments (#12171)
feat: add the sub agents in context scope to support call subagent
refactor agent management implement
update
add builtin agent management
* fix types
* fix import
* fix test
* fix tests
* fix tests
AmAzing-