Bohan Jiang 0af67c8159 fix(agent/openclaw): block tasks if openclaw < 2026.5.5 with upgrade hint (#2181) ...

PR #2101 swapped the openclaw runtime adapter from reading --json on
stderr to stdout. That fixed openclaw 2026.5+ but inverted the breakage
for pre-2026.5 builds — those still write JSON to stderr, so the
adapter now sees an empty stdout and falls through to the same
"openclaw returned no parseable output" failure that 2026.5+ users
saw before #2101.

Add a per-task version gate inside openclawBackend.Execute that runs
`openclaw --version`, parses the dotted version, and rejects anything
below 2026.5.5 with a hardcoded upgrade hint:

    openclaw <detected> is below the minimum supported version 2026.5.5.
    Run `openclaw update` to upgrade and try again.

The check is intentionally per-task and uncached so users who upgrade
do not need to restart the daemon — the next task automatically
re-checks. ~20ms per task is negligible vs. the typical run.

Co-authored-by: multica-agent <github@multica.ai>

2026-05-07 02:11:47 +08:00

..

testdata

fix(agent/openclaw): read --json from stdout, not stderr (#2101)

2026-05-07 01:50:16 +08:00

agent_test.go

feat(agent): add Kiro CLI ACP runtime (#1780)

2026-04-28 17:03:46 +08:00

agent.go

feat: add backend default agent args env vars (#1807)

2026-04-29 16:49:48 +08:00

claude_test.go

feat: add backend default agent args env vars (#1807)

2026-04-29 16:49:48 +08:00

claude.go

feat: add backend default agent args env vars (#1807)

2026-04-29 16:49:48 +08:00

codex_test.go

fix(codex): handle MCP elicitation server requests correctly (#1944)

2026-05-04 21:05:37 +08:00

codex.go

fix(codex): handle MCP elicitation server requests correctly (#1944)

2026-05-04 21:05:37 +08:00

copilot_test.go

fix(chat): preserve chat session resume pointer across failures (#1360)

2026-04-19 22:50:33 -07:00

copilot.go

fix(daemon): suppress agent terminal windows on Windows (#1474)

2026-04-23 17:23:00 +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): route Windows launcher through PowerShell -File to preserve multi-line prompts (#1709)

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

cursor_invocation_windows_test.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_windows.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.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_test.go

…

cursor.go

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

2026-04-29 14:00:15 +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

gemini_test.go

…

gemini.go

fix(daemon): suppress agent terminal windows on Windows (#1474)

2026-04-23 17:23:00 +08:00

hermes_test.go

fix(daemon): trust the agent's session id from session/resume across ACP backends (#2070)

2026-05-06 14:15:40 +08:00

hermes.go

fix(daemon): trust the agent's session id from session/resume across ACP backends (#2070)

2026-05-06 14:15:40 +08:00

kimi_test.go

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

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

kimi.go

fix(daemon): trust the agent's session id from session/resume across ACP backends (#2070)

2026-05-06 14:15:40 +08:00

kiro_test.go

fix(agent): ignore Kiro session/load history replay (#1789)

2026-04-28 17:50:13 +08:00

kiro.go

fix(daemon): trust the agent's session id from session/resume across ACP backends (#2070)

2026-05-06 14:15:40 +08:00

models_test.go

fix(agent): expose GPT-5.5 family in Codex runtime model picker (#2020)

2026-05-03 11:12:51 +08:00

models.go

fix(agent): expose GPT-5.5 family in Codex runtime model picker (#2020)

2026-05-03 11:12:51 +08:00

openclaw_test.go

fix(agent/openclaw): block tasks if openclaw < 2026.5.5 with upgrade hint (#2181)

2026-05-07 02:11:47 +08:00

openclaw.go

fix(agent/openclaw): block tasks if openclaw < 2026.5.5 with upgrade hint (#2181)

2026-05-07 02:11:47 +08:00

opencode_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

opencode.go

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

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

pi.go

fix(daemon): suppress agent terminal windows on Windows (#1474)

2026-04-23 17:23:00 +08:00

proc_other.go

fix(daemon): suppress agent terminal windows on Windows (#1474)

2026-04-23 17:23:00 +08:00

proc_windows_test.go

fix(daemon): use CREATE_NEW_CONSOLE to stop grandchild console popups on Windows (#1521) (#1643)

2026-04-25 01:40:15 +08:00

proc_windows.go

fix(daemon): use CREATE_NEW_CONSOLE to stop grandchild console popups on Windows (#1521) (#1643)

2026-04-25 01:40:15 +08:00

stderr_tail.go

feat(agent): surface agent CLI stderr tail in failure messages (#1674)

2026-04-26 10:55:21 +08:00

version_test.go

refactor(quick-create): exempt git-describe daemons from CLI gate (#2108)

2026-05-06 09:00:11 +08:00

version.go

refactor(quick-create): exempt git-describe daemons from CLI gate (#2108)

2026-05-06 09:00:11 +08:00