9c32ea4063
fix(agent): harden runner delivery validation
2026-07-27 16:01:57 +08:00
7d3b53bbce
test(skills): expand local agent reliability coverage
2026-07-26 22:27:42 +08:00
4bae8728a6
test(skills): harden local agent QA automation
2026-07-26 21:29:30 +08:00
3ca724d18e
fix: use per-bot admins for command events ( #2359 )
...
* fix: use per-bot admins for command events
* style: format rerank provider changes
---------
Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com >
2026-07-26 17:02:51 +08:00
dd8d1007a1
feat: support Space rerank models ( #2358 )
...
Co-authored-by: chan <dadachann@users.noreply.github.com >
2026-07-26 16:37:34 +08:00
e32210301a
fix(agent): migrate official runner ids
2026-07-24 20:50:25 +08:00
38e35d328a
feat(web): add marketplace likes ( #2352 )
...
Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com >
2026-07-24 15:16:37 +08:00
4226f71f05
fix(runtime): make plugin and box connectors resilient ( #2347 )
...
Preserve the contributor-authored MCP timeout commit and the follow-up configurable timeout and runtime robustness fixes.
2026-07-23 20:25:21 +08:00
283c6949f4
fix(mcp): validate tool call timeout config
2026-07-23 18:26:41 +08:00
0dfae76e39
fix(mcp): make tool call timeout configurable
2026-07-23 18:26:37 +08:00
7677d1a288
fix(mcp): add 30s timeout to prevent MCP tool calls from hanging indefinitely
...
Previously, MCP tool calls via call_tool() had no timeout, so a hung MCP
server would block the entire session indefinitely (exacerbated by
concurrency.session=1). This wraps the call in asyncio.timeout(30) and
raises an Exception on expiry, letting the LLM recover gracefully.
Closes #2339
2026-07-23 18:26:18 +08:00
a53a41b1ca
feat(web): trim dynamic form strings on save ( #2349 )
2026-07-23 18:14:54 +08:00
73e47ea2d4
fix(mcp): keep waiting for box recovery
2026-07-23 17:41:27 +08:00
06e03af994
fix(runtime): complete reconnect recovery paths
2026-07-23 17:28:31 +08:00
9cbbaf617b
fix(runtime): consume sdk shutdown fix
2026-07-23 16:46:48 +08:00
210e5349d9
fix(runtime): preserve lockfile metadata
2026-07-23 16:34:03 +08:00
a2f6814517
fix(runtime): pin robust sdk release
2026-07-23 16:28:33 +08:00
8511178666
fix(runtime): harden connector lifecycle
2026-07-23 16:03:26 +08:00
6b13c37c3b
feat(agent): integrate structured runner interactions
2026-07-22 11:32:17 +08:00
998b76d53a
fix(runtime): make plugin and box connectors resilient
2026-07-21 18:43:24 +08:00
1765c43262
Revert "fix(runtime): make plugin and box connectors resilient"
...
This reverts commit 0b461e5830
2026-07-21 18:43:01 +08:00
0b461e5830
fix(runtime): make plugin and box connectors resilient
2026-07-21 18:41:22 +08:00
e3df35e7f7
test(workspace): harden release gate automation
2026-07-20 17:13:19 +08:00
7615c40f73
fix(plugin): extend knowledge retrieval timeout
2026-07-20 17:12:55 +08:00
76c5003c21
fix(localagent): stop re-seeding stream accumulator with previous round content ( #2329 )
...
When the LLM (e.g. MiniMax-M3) returns multiple rounds after tool calls, the _StreamAccumulator was initialized with initial_content=first_content, causing every subsequent round to repeat the entire first message. Remove the re-seeding so each round starts with a clean accumulator.
Add regression test verifying multi-round tool call content is not duplicated.
2026-07-20 16:38:11 +08:00
e4d4860446
fix(platform): resolve post-rebase compatibility
2026-07-19 23:03:54 +08:00
8afab5fa49
fix(mcp): recover box stdio sessions after disconnect
2026-07-19 22:47:09 +08:00
3359951837
test(workspace): add top-down release gates
2026-07-19 22:46:01 +08:00
7706634c34
test(agent): add complex local agent regression coverage
2026-07-19 22:46:01 +08:00
cfa7c7b336
fix(tools): support skill mount root discovery
2026-07-19 22:46:01 +08:00
0c8eb90a75
docs(agent-runner): record release probe results
2026-07-19 22:46:01 +08:00
9f28d6949a
fix(agent-runner): unify streamed completion delivery
2026-07-19 22:46:01 +08:00
8a7c3fcefe
fix(agent-runner): aggregate non-streaming replies
2026-07-19 22:46:01 +08:00
54c872b74f
fix(agent-runner): close sandbox skill authoring flow
2026-07-19 22:46:01 +08:00
c55be79f9f
fix(agent-runner): prepare local runner functional tests
2026-07-19 22:46:01 +08:00
1af106aa92
fix(agent-runner): validate clean marketplace onboarding
2026-07-19 22:46:01 +08:00
d88d05e27c
feat(agent-runner): enforce 4.x host-owned execution
2026-07-19 22:46:01 +08:00
9aa71d54e3
feat(agent-runner): finalize 4.x processor integration
2026-07-19 22:45:15 +08:00
457408ad7f
feat(market): support AgentRunner component filters
2026-07-19 22:45:15 +08:00
1d8601f4a6
feat(wizard): add scenario templates and EBA release gate
2026-07-19 22:44:08 +08:00
0c0f5d8061
feat(wizard): start bot setup from scenarios
2026-07-19 22:44:08 +08:00
c3aa4cfc97
feat(agent-platform): add scenario-based route creation
2026-07-19 22:44:08 +08:00
b8d8bbadd5
feat(agent-platform): explain route conflicts and fallback
2026-07-19 22:44:08 +08:00
3aeae92707
test(skills): add bot event routing product flow
2026-07-19 22:44:08 +08:00
00fb6f8236
feat(agent-platform): productize bot event route testing
2026-07-19 22:44:08 +08:00
4cbb9415bf
feat(agent-platform): show bot route runtime status
2026-07-19 22:44:08 +08:00
ee11e97e86
feat(agent-platform): add bot route dry-run
2026-07-19 22:44:08 +08:00
428161110f
docs: add EBA productization release plan
2026-07-19 22:44:07 +08:00
7fb393b85b
refactor: consolidate bot event routing
2026-07-19 22:44:07 +08:00
662627142e
test(agent-runner): strengthen local agent e2e gate
2026-07-19 22:42:40 +08:00
huanghuoguoguo