- advance the disabled-dream cursor before touching the cron store so
the #4242 fix still applies when jobs.json is corrupt
- pin the gateway wiring: the disabled-path test now asserts both
dream and heartbeat are retired, not just unregistered
- cover remove_system_job on a fresh install with no store file
Disabling gateway.heartbeat (or agents.defaults.dream) only skipped
job registration on startup; the previously persisted system job in
<workspace>/cron/jobs.json kept firing, and remove_job refuses to
touch protected system jobs. Add CronService.remove_system_job for
startup reconciliation and call it from the gateway disabled branches
so the config toggle takes effect after restart.
When config.json has no channels configuration, the WebUI QR login
connect flow obtained a token but only saved it to account.json (state
file). The subsequent post-connect enable step (set_channel_config_enabled)
read config.json, found no weixin section, and wrote back a default
config with token="" - silently losing the freshly obtained credential.
Add _persist_connect_credentials to _commit_account so the token and
base_url are written to config.json before the enable step runs. This
covers both the WebUI connect flow and the CLI QR login path, mirroring
the established Feishu save_registration_result pattern.
When a stream stalls mid-response, both the retry layer and
FallbackProvider blocked recovery because content had already been
emitted via on_content_delta. This left users with truncated replies
and no automatic recovery.
For error_kind="timeout" specifically:
- _run_with_retry now suppresses delta callbacks and retries the same
model instead of returning immediately
- FallbackProvider now allows failover to a different model with
delta callbacks suppressed
Non-timeout errors retain the original "skip retry/failover after
streamed content" behavior to avoid duplicate output.
Wire up the existing office document extractors in document.py to
ReadFileTool by adding an extension guard and _read_office_doc() method
that follows the established PDF pattern. Handles missing libraries,
corrupt files, empty documents, and 128K truncation consistently.
SessionManager.save() previously used bare open("w") which could
truncate the JSONL file if the process crashed mid-write. Now writes
to a .tmp file and atomically replaces via os.replace(), matching the
pattern already used in qq.py.
_load() now attempts _repair() before returning None, recovering
valid lines from partially-written files. 12 new tests cover atomic
save correctness, temp-file cleanup on failure, and repair of
truncated/corrupt JSONL.
cowork-with:opencode(glm-5.1)