Bohan Jiang dcc2d58251 MUL-6737: fix(daemon): raise the agent inactivity budget to 2h and derive the tool budget (#7685) ...

The idle watchdog was sized to notice a hang quickly (30m), but the two costs it trades between are not symmetric: force-stopping a healthy run throws away the work and flips the issue to blocked, while noticing a hang late only holds a concurrency slot.

- DefaultAgentIdleWatchdog 30m -> 2h, sized by the longest legitimate silent step.
- AgentToolWatchdog now derives from the idle budget in both directions; MULTICA_AGENT_TOOL_WATCHDOG still overrides and 0 keeps its 'never force-stop during a tool call' meaning.
- Watchdog tick capped at 5m, so worst-case detection is budget + 5m instead of budget * 1.5.
- Dropped the unreachable 30s tick floor (window >= 1m implies window/2 >= 30s) and asserted the property it was written for directly.
- Removed the dead MULTICA_CODEX_TIMEOUT from .env.example; documented the generic watchdog and Codex timeout rows in CLI_AND_DAEMON.md; synced four doc locales.

2026-08-28 16:08:08 +08:00

..

testdata

fix(agent): fail a run whose provider session ran out of context (MUL-5739) (#6422)

2026-08-05 15:41:15 +08:00

acp_deliverable_test.go

feat(agent): add ZeroClaw as a native ACP runtime (MUL-6511) (#7351)

2026-08-24 14:39:08 +08:00

acp_deliverable.go

refactor(agent): share acpDeliverableTracker across ACP backends (MUL-5405) (#6044)

2026-07-28 21:18:12 +08:00

acp_effort_test.go

MUL-5991 feat(agent): enable ACP thinking_level for the hermes provider (jcode) (#6814)

2026-08-13 16:42:47 +08:00

acp_effort_unix_test.go

MUL-6260 fix(daemon): treat custom runtime fixed_args as the argv prefix (#7052)

2026-08-17 15:11:36 +08:00

acp_effort.go

MUL-5991 feat(agent): drive ACP thinking_level from the backend's own configOptions (reasonix first) (#6752)

2026-08-11 16:22:51 +08:00

acp_terminal_other_test.go

MUL-6464 fix(agent): support ACP terminals for Kimi runtime (#7323)

2026-08-24 13:37:18 +08:00

acp_terminal_status_other.go

MUL-6464 fix(agent): support ACP terminals for Kimi runtime (#7323)

2026-08-24 13:37:18 +08:00

acp_terminal_status_windows.go

MUL-6464 fix(agent): support ACP terminals for Kimi runtime (#7323)

2026-08-24 13:37:18 +08:00

acp_terminal_test.go

MUL-6464 fix(agent): support ACP terminals for Kimi runtime (#7323)

2026-08-24 13:37:18 +08:00

acp_terminal.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

acp_usage_test.go

MUL-5810: fix(agent): reconcile ACP terminal usage (#6503)

2026-08-06 17:02:02 +08:00

acp_usage.go

MUL-5810: fix(agent): reconcile ACP terminal usage (#6503)

2026-08-06 17:02:02 +08:00

agent_supported_types_test.go

feat(agent): add ZeroClaw as a native ACP runtime (MUL-6511) (#7351)

2026-08-24 14:39:08 +08:00

agent_test_executable_test.go

fix(test): prevent agent CLI execution in default tests (#5789)

2026-07-23 01:59:06 +08:00

agent_test.go

fix(daemon): own the openclaw CLI process tree so its deadline is enforceable (MUL-5467, MUL-5630, MUL-6736) (#6275)

2026-08-28 14:04:10 +08:00

agent.go

feat(agent): add ZeroClaw as a native ACP runtime (MUL-6511) (#7351)

2026-08-24 14:39:08 +08:00

antigravity_test.go

fix(agent): preserve newlines in Antigravity streamed text (#6717)

2026-08-24 14:43:46 +08:00

antigravity.go

MUL-6737: fix(daemon): raise the agent inactivity budget to 2h and derive the tool budget (#7685)

2026-08-28 16:08:08 +08:00

browser_mcp_config_test.go

MUL-4103: harden Windows browser MCP config (#4976)

2026-07-06 16:14:03 +08:00

browser_mcp_config.go

MUL-4103: harden Windows browser MCP config (#4976)

2026-07-06 16:14:03 +08:00

builtin_runtimes.go

MUL-6362: redact secrets from provider command logs (#7206)

2026-08-19 16:07:53 +08:00

claude_cancel_unix_test.go

fix(agent): reap claude process group on cancellation (#5918) [MUL-5288] (#5957)

2026-07-27 02:01:41 +08:00

claude_context_exhausted_test.go

fix(agent): fail a run whose provider session ran out of context (MUL-5739) (#6422)

2026-08-05 15:41:15 +08:00

claude_deadlock_test.go

fix(agent): deliver the OpenCode prompt on stdin, not argv (MUL-5841) (#6552)

2026-08-07 12:31:55 +08:00

claude_test.go

MUL-5785 fix(agent): return an empty output when a stream-json run has no final text (#6557)

2026-08-07 14:38:03 +08:00

claude.go

fix(daemon): own the openclaw CLI process tree so its deadline is enforceable (MUL-5467, MUL-5630, MUL-6736) (#6275)

2026-08-28 14:04:10 +08:00

codebuddy_discovery_fallback_test.go

MUL-6260 fix(daemon): treat custom runtime fixed_args as the argv prefix (#7052)

2026-08-17 15:11:36 +08:00

codebuddy_test.go

MUL-5846 fix(agent): stop launching CodeBuddy with MCP disabled (#6556)

2026-08-07 15:22:01 +08:00

codebuddy.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

codex_cleanup_unix_test.go

MUL-5155: KAP-1051: diagnose Codex thread/start timeouts fail-closed (#5759)

2026-07-23 15:09:50 +08:00

codex_test.go

fix(codex): wait for authoritative turn completion (#7554)

2026-08-26 14:33:08 +08:00

codex.go

fix(daemon): own the openclaw CLI process tree so its deadline is enforceable (MUL-5467, MUL-5630, MUL-6736) (#6275)

2026-08-28 14:04:10 +08:00

copilot_invocation_other.go

fix(daemon): fix Copilot CLI invocation on Windows and strip shell quotes from custom args (MUL-2876)

2026-06-01 23:28:51 +08:00

copilot_invocation_test.go

fix(agent): spawn Copilot's native binary on Windows so the prompt survives (MUL-5586) (#6236)

2026-07-31 16:09:36 +08:00

copilot_invocation_windows_test.go

fix(agent): spawn Copilot's native binary on Windows so the prompt survives (MUL-5586) (#6236)

2026-07-31 16:09:36 +08:00

copilot_invocation_windows.go

fix(agent): spawn Copilot's native binary on Windows so the prompt survives (MUL-5586) (#6236)

2026-07-31 16:09:36 +08:00

copilot_invocation.go

fix(agent): spawn Copilot's native binary on Windows so the prompt survives (MUL-5586) (#6236)

2026-07-31 16:09:36 +08:00

copilot_test.go

fix(agent): rank Copilot usage sources, fix model attribution, surface the token gap (MUL-5712) (#6373)

2026-08-04 18:03:34 +08:00

copilot.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

cursor_execute_unix_test.go

fix(agent): raise the agent stream scanner cap to 32 MiB and share it (MUL-5722) (#6383)

2026-08-05 13:09:25 +08:00

cursor_integration_test.go

MUL-5231 fix(agent): parse Cursor top-level thinking and tool_call events (#5846)

2026-07-24 01:52:15 +08:00

cursor_invocation_other.go

fix(agent/cursor): route Windows launcher through PowerShell -File to preserve multi-line prompts (#1709)

2026-04-29 14:00:15 +08:00

cursor_invocation_test.go

fix(agent/cursor): remove obsolete 'chat' subcommand from argv (#3077) (#3092)

2026-05-27 16:40:29 +08:00

cursor_invocation_windows_test.go

fix(agent/cursor): remove obsolete 'chat' subcommand from argv (#3077) (#3092)

2026-05-27 16:40:29 +08:00

cursor_invocation_windows.go

fix(daemon): fix Copilot CLI invocation on Windows and strip shell quotes from custom args (MUL-2876)

2026-06-01 23:28:51 +08:00

cursor_invocation.go

fix(agent/cursor): route Windows launcher through PowerShell -File to preserve multi-line prompts (#1709)

2026-04-29 14:00:15 +08:00

cursor_stdin_unix_test.go

fix(agent/cursor): send prompt on stdin so CLI-like flags cannot be re-tokenised (MUL-4992) (#5711)

2026-07-21 16:01:04 +08:00

cursor_stdin_windows_test.go

fix(agent/cursor): send prompt on stdin so CLI-like flags cannot be re-tokenised (MUL-4992) (#5711)

2026-07-21 16:01:04 +08:00

cursor_stream_fixture_unix_test.go

fix(agent): make cursor stream protocol drift loud instead of silent (MUL-5434) (#6089)

2026-07-29 15:15:41 +08:00

cursor_test.go

fix(agent): make cursor stream protocol drift loud instead of silent (MUL-5434) (#6089)

2026-07-29 15:15:41 +08:00

cursor.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

deveco_models.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

deveco_test.go

fix(agent): pair failed tool results for OpenCode (MUL-5802) (#6497)

2026-08-06 15:22:32 +08:00

deveco.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

dim_integration_test.go

MUL-5959: feat(agent): add Dim (DimCode) ACP runtime (#6675)

2026-08-20 12:54:46 +08:00

dim_test.go

MUL-5959: feat(agent): add Dim (DimCode) ACP runtime (#6675)

2026-08-20 12:54:46 +08:00

dim_windows_test.go

MUL-5959: feat(agent): add Dim (DimCode) ACP runtime (#6675)

2026-08-20 12:54:46 +08:00

dim.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

dsh_integration_test.go

feat(runtime): add DeepSeek Harness support (#6923)

2026-08-13 23:18:17 +08:00

dsh_test.go

MUL-6260 fix(daemon): treat custom runtime fixed_args as the argv prefix (#7052)

2026-08-17 15:11:36 +08:00

dsh.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

exec_fixture_unix_test.go

fix(landing): scope landing route to always-light palette (MUL-1277) (#1537)

2026-04-23 01:52:46 +08:00

exec_fixture_windows_test.go

fix(agent/opencode): bypass npm .cmd shim on Windows to preserve multi-line prompts (#1718)

2026-04-27 12:16:56 +08:00

exec_format_other.go

MUL-6164 feat(runtime): take an unusable agent CLI offline and refuse its triggers with the fix (#6966)

2026-08-14 18:56:40 +08:00

exec_format_test.go

MUL-6164 feat(runtime): take an unusable agent CLI offline and refuse its triggers with the fix (#6966)

2026-08-14 18:56:40 +08:00

exec_format_windows.go

MUL-6164 feat(runtime): take an unusable agent CLI offline and refuse its triggers with the fix (#6966)

2026-08-14 18:56:40 +08:00

exec_format.go

MUL-6164 feat(runtime): take an unusable agent CLI offline and refuse its triggers with the fix (#6966)

2026-08-14 18:56:40 +08:00

grok_integration_test.go

fix(test): prevent agent CLI execution in default tests (#5789)

2026-07-23 01:59:06 +08:00

grok_test.go

fix(agent): discover Grok reasoning effort catalog (#7252)

2026-08-24 15:03:47 +08:00

grok.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

handoff_version_test.go

MUL-3416: Issue pre-trigger preview + Handoff Note (#4383)

2026-06-23 13:17:13 +08:00

hermes_effort_execute_unix_test.go

MUL-5991 feat(agent): enable ACP thinking_level for the hermes provider (jcode) (#6814)

2026-08-13 16:42:47 +08:00

hermes_integration_test.go

MUL-5810: fix(agent): reconcile ACP terminal usage (#6503)

2026-08-06 17:02:02 +08:00

hermes_model_discovery_test.go

fix(agent): MUL-6606 surface hermes model-discovery failures instead of a silent empty catalog (#7464)

2026-08-24 13:42:39 +08:00

hermes_model_discovery_unix_test.go

fix(agent): MUL-6606 surface hermes model-discovery failures instead of a silent empty catalog (#7464)

2026-08-24 13:42:39 +08:00

hermes_resume_test.go

MUL-6053: fix(daemon): give Hermes conversations a session that survives the task (#6845)

2026-08-13 14:20:52 +08:00

hermes_test.go

MUL-5879: fix(agent): surface every in-flight built-in Hermes tool call (#7127)

2026-08-18 15:35:45 +08:00

hermes_tool_visibility_execute_unix_test.go

MUL-5879: fix(agent): surface every in-flight built-in Hermes tool call (#7127)

2026-08-18 15:35:45 +08:00

hermes.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

kimi_integration_test.go

MUL-5846 fix(agent): stop launching CodeBuddy with MCP disabled (#6556)

2026-08-07 15:22:01 +08:00

kimi_test.go

MUL-6464 fix(agent): support ACP terminals for Kimi runtime (#7323)

2026-08-24 13:37:18 +08:00

kimi.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

kiro_test.go

MUL-5810: fix(agent): reconcile ACP terminal usage (#6503)

2026-08-06 17:02:02 +08:00

kiro.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

launch_process_unix_test.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

launch_test.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

launch.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

mcode_cancel_unix_test.go

MUL-6273: feat(agent): add MiniMax Code ACP runtime (#7035)

2026-08-18 12:44:27 +08:00

mcode_integration_test.go

MUL-6273: feat(agent): add MiniMax Code ACP runtime (#7035)

2026-08-18 12:44:27 +08:00

mcode_test.go

MUL-6655 Fix MCode ACP session startup race (ZIC-199) (#7516)

2026-08-25 12:30:52 +08:00

mcode.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

mcp_config.go

feat: redesign agent Skills and MCP capabilities (#5277)

2026-07-12 02:53:17 +08:00

model_discovery_cache_key_test.go

MUL-6260 fix(daemon): treat custom runtime fixed_args as the argv prefix (#7052)

2026-08-17 15:11:36 +08:00

models_test.go

fix(agent): MUL-6606 surface hermes model-discovery failures instead of a silent empty catalog (#7464)

2026-08-24 13:42:39 +08:00

models.go

fix(daemon): own the openclaw CLI process tree so its deadline is enforceable (MUL-5467, MUL-5630, MUL-6736) (#6275)

2026-08-28 14:04:10 +08:00

omp_test.go

MUL-6471: fix(daemon): let pi and opencode reach custom providers (#7312)

2026-08-20 18:01:53 +08:00

openclaw_stdout_test.go

fix(agent): make readOpenclawStdout's cut-short decision atomic (MUL-6024) (#6765)

2026-08-11 18:40:13 +08:00

openclaw_stdout.go

fix(agent): make readOpenclawStdout's cut-short decision atomic (MUL-6024) (#6765)

2026-08-11 18:40:13 +08:00

openclaw_test.go

feat(openclaw): support connecting to existing OpenClaw gateway (#3260) [MUL-3158] (#3664)

2026-06-13 15:33:28 +08:00

openclaw.go

fix(daemon): own the openclaw CLI process tree so its deadline is enforceable (MUL-5467, MUL-5630, MUL-6736) (#6275)

2026-08-28 14:04:10 +08:00

opencode_cancel_unix_test.go

fix(agent): terminate opencode process group before closing stdout (#4533) (#4541)

2026-06-25 00:41:25 +08:00

opencode_mcp_test.go

fix(agent): deliver the OpenCode prompt on stdin, not argv (MUL-5841) (#6552)

2026-08-07 12:31:55 +08:00

opencode_mcp.go

feat(agent): consume OpenCode mcp_config via OPENCODE_CONFIG_CONTENT (#3098)

2026-05-30 18:08:21 +08:00

opencode_stdin_helper_test.go

fix(agent): deliver the OpenCode prompt on stdin, not argv (MUL-5841) (#6552)

2026-08-07 12:31:55 +08:00

opencode_stdin_unix_test.go

fix(agent): deliver the OpenCode prompt on stdin, not argv (MUL-5841) (#6552)

2026-08-07 12:31:55 +08:00

opencode_stdin_windows_test.go

fix(agent): deliver the OpenCode prompt on stdin, not argv (MUL-5841) (#6552)

2026-08-07 12:31:55 +08:00

opencode_test.go

fix(agent): deliver the OpenCode prompt on stdin, not argv (MUL-5841) (#6552)

2026-08-07 12:31:55 +08:00

opencode.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

pi_invocation_other.go

MUL-2708: fix(agent): preserve multi-line Pi prompt on Windows by bypassing the .cmd shim (#3417)

2026-05-28 12:36:16 +08:00

pi_invocation_test.go

fix(agent): route all Windows Pi runs through powershell -Command to preserve stdin (#7392)

2026-08-24 14:37:26 +08:00

pi_invocation_windows_test.go

fix(agent): route all Windows Pi runs through powershell -Command to preserve stdin (#7392)

2026-08-24 14:37:26 +08:00

pi_invocation_windows.go

fix(agent): route all Windows Pi runs through powershell -Command to preserve stdin (#7392)

2026-08-24 14:37:26 +08:00

pi_invocation.go

fix(agent): route all Windows Pi runs through powershell -Command to preserve stdin (#7392)

2026-08-24 14:37:26 +08:00

pi_stdin_unix_test.go

MUL-6471: fix(daemon): let pi and opencode reach custom providers (#7312)

2026-08-20 18:01:53 +08:00

pi_stdin_windows_test.go

MUL-6471: fix(daemon): let pi and opencode reach custom providers (#7312)

2026-08-20 18:01:53 +08:00

pi_test.go

fix(pi): keep turn error when process exits 1 [MUL-6585] (#7451)

2026-08-24 14:02:33 +08:00

pi.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

proc_other.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

proc_windows_test.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

proc_windows.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

qoder_test.go

MUL-5843 fix(agent): stop silently dropping MCP servers on ACP runtimes (#6555)

2026-08-07 13:14:54 +08:00

qoder.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

qwen_invocation_other.go

MUL-5466 fix(agent): deliver the qwen prompt on stdin, not argv (#7343)

2026-08-24 15:08:14 +08:00

qwen_invocation_test.go

MUL-5466 fix(agent): deliver the qwen prompt on stdin, not argv (#7343)

2026-08-24 15:08:14 +08:00

qwen_invocation_windows_test.go

MUL-5466 fix(agent): deliver the qwen prompt on stdin, not argv (#7343)

2026-08-24 15:08:14 +08:00

qwen_invocation_windows.go

MUL-5466 fix(agent): deliver the qwen prompt on stdin, not argv (#7343)

2026-08-24 15:08:14 +08:00

qwen_invocation.go

MUL-5466 fix(agent): deliver the qwen prompt on stdin, not argv (#7343)

2026-08-24 15:08:14 +08:00

qwen_stdin_windows_test.go

MUL-5466 fix(agent): deliver the qwen prompt on stdin, not argv (#7343)

2026-08-24 15:08:14 +08:00

qwen_test.go

MUL-5466 fix(agent): deliver the qwen prompt on stdin, not argv (#7343)

2026-08-24 15:08:14 +08:00

qwen.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

qwenpaw_integration_test.go

feat: add QwenPaw ACP backend support (MUL-5355) (#5986)

2026-08-04 18:47:10 +08:00

qwenpaw_test.go

MUL-6260 fix(daemon): treat custom runtime fixed_args as the argv prefix (#7052)

2026-08-17 15:11:36 +08:00

qwenpaw.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

real_agent_smoke_integration_test.go

fix(test): prevent agent CLI execution in default tests (#5789)

2026-07-23 01:59:06 +08:00

reasonix_effort_execute_unix_test.go

MUL-5991 feat(agent): drive ACP thinking_level from the backend's own configOptions (reasonix first) (#6752)

2026-08-11 16:22:51 +08:00

reasonix_execute_unix_test.go

MUL-6260 fix(daemon): treat custom runtime fixed_args as the argv prefix (#7052)

2026-08-17 15:11:36 +08:00

reasonix_test.go

MUL-5992 fix(daemon): deny the Reasonix ask tool per task (supersedes #6745) (#6746)

2026-08-11 15:15:06 +08:00

reasonix.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

run_collect_lifecycle_test.go

fix(daemon): own the openclaw CLI process tree so its deadline is enforceable (MUL-5467, MUL-5630, MUL-6736) (#6275)

2026-08-28 14:04:10 +08:00

run_collect_quiet_test.go

fix(daemon): own the openclaw CLI process tree so its deadline is enforceable (MUL-5467, MUL-5630, MUL-6736) (#6275)

2026-08-28 14:04:10 +08:00

run_collect_quiet.go

fix(daemon): own the openclaw CLI process tree so its deadline is enforceable (MUL-5467, MUL-5630, MUL-6736) (#6275)

2026-08-28 14:04:10 +08:00

run_collect_test.go

fix(daemon): own the openclaw CLI process tree so its deadline is enforceable (MUL-5467, MUL-5630, MUL-6736) (#6275)

2026-08-28 14:04:10 +08:00

run_collect_windows_test.go

fix(daemon): own the openclaw CLI process tree so its deadline is enforceable (MUL-5467, MUL-5630, MUL-6736) (#6275)

2026-08-28 14:04:10 +08:00

run_collect.go

fix(daemon): own the openclaw CLI process tree so its deadline is enforceable (MUL-5467, MUL-5630, MUL-6736) (#6275)

2026-08-28 14:04:10 +08:00

stderr_tail.go

MUL-4903 fix(agent): harden Cursor terminal failures (#5559)

2026-07-17 13:09:20 +08:00

stream_json_final_output_test.go

MUL-5785 fix(agent): return an empty output when a stream-json run has no final text (#6557)

2026-08-07 14:38:03 +08:00

stream_json_result.go

MUL-5785 fix(agent): return an empty output when a stream-json run has no final text (#6557)

2026-08-07 14:38:03 +08:00

stream_scanner_test.go

fix(agent): raise the agent stream scanner cap to 32 MiB and share it (MUL-5722) (#6383)

2026-08-05 13:09:25 +08:00

stream_scanner.go

fix(agent): raise the agent stream scanner cap to 32 MiB and share it (MUL-5722) (#6383)

2026-08-05 13:09:25 +08:00

thinking_test.go

fix(agent): discover Grok reasoning effort catalog (#7252)

2026-08-24 15:03:47 +08:00

thinking.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

traecli_integration_test.go

fix(test): prevent agent CLI execution in default tests (#5789)

2026-07-23 01:59:06 +08:00

traecli_test.go

MUL-5810: fix(agent): reconcile ACP terminal usage (#6503)

2026-08-06 17:02:02 +08:00

traecli.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00

version_test.go

fix(daemon): own the openclaw CLI process tree so its deadline is enforceable (MUL-5467, MUL-5630, MUL-6736) (#6275)

2026-08-28 14:04:10 +08:00

version.go

feat(agent): add ZeroClaw as a native ACP runtime (MUL-6511) (#7351)

2026-08-24 14:39:08 +08:00

worktree_capability_contract_test.go

perf(ci): path-filter the backend jobs to skip irrelevant PRs (MUL-6389) (#7198)

2026-08-19 14:39:33 +08:00

zeroclaw_test.go

feat(agent): add ZeroClaw as a native ACP runtime (MUL-6511) (#7351)

2026-08-24 14:39:08 +08:00

zeroclaw.go

MUL-6658 fix(agent): own the runtime process tree on every backend (#7522) (#7531)

2026-08-25 16:27:46 +08:00