Track upstream ductor release v0.19.0

[github-actions]

Upstream published a new release: v0.19.0.

• Published: 2026-07-12T07:34:04Z
• URL: https://github.com/PleasePrompto/ductor/releases/tag/v0.19.0

Suggested follow-up

1. Review the upstream changelog and commits.
2. Decide which changes need to be ported into this fork.
3. Track any fork-specific conflicts before merging or cherry-picking.

Upstream release notes

ductor v0.19.0

The biggest community release so far: Slack becomes ductor's third chat transport, reasoning effort gets a first-class /effort command, and a wave of contributor PRs makes background tasks, cron delivery, and Codex noticeably more reliable. Ten merged PRs, four squashed bugs — thank you all. 💜

TL;DR

• Slack transport — run your agents from Slack (Socket Mode, wizard setup, native streaming, all 8 languages). Install with the slack extra.
• /effort — set reasoning effort per chat/topic, now for Claude (--effort, including max) and Codex. Every topic keeps its own level.
• Topic-scoped process kills — /model, /new, /reset, and error recovery no longer abort other topics' in-flight work or background tasks.
• Background tasks hardened — completed results survive cancel races, resume can't overlap a live run, DUCTOR_TASK_ID finally reaches task subprocesses, and finished-task history prunes itself.
• Cron delivery tracking — if Telegram is down when a cron result lands, you'll see it (last: success (delivery failed)) and the full result is preserved for resend instead of vanishing.
• Codex prompts via stdin — no more Argument list too long, and prompts stay out of /proc and logs. Codex resumes also re-assert your selected model and effort now.
• append_system_prompt_files — inject your own files (glossary, style guide, …) into the system prompt on every turn.
• Selector polish — model and effort keyboards render two buttons per row instead of one unreadable line.

Slack transport (PleasePrompto#114)

@victor-develop battle-tested this in a long-lived fork and backported it upstream: a full Slack transport speaking the same orchestrator as Telegram and Matrix — Socket Mode (no public webhook needed), onboarding wizard integration, thread-aware routing, media, and Slack-native streaming with graceful fallback. Config mirrors the Matrix pattern (pip install "ductor[slack]", then ductor onboarding). Closes PleasePrompto#165.

Per-session reasoning effort (PleasePrompto#164)

@ryuhaneul brought effort to parity with model selection: /effort (or the thinking-level step in /model) applies to the current chat or topic only, the main chat sets the global default, and /status shows the active level. Claude gains --effort support for the first time (low … max); Codex keeps -c model_reasoning_effort — now actually switchable at runtime.

Reliability

• Topic-scoped kills (fix: scope model-switch/reset/error process kills to the invoking topic PleasePrompto/ductor#166, @ryuhaneul) — six call sites used to sweep the whole chat and killed sibling topics' subprocesses (exit 143, billed work lost). Now they only touch the invoking topic; background tasks and named sessions are exempt, exactly as /stop always promised.
• Cancel vs. completion race (fix: don't discard a finished task result when cancel races completion PleasePrompto/ductor#167, @ryuhaneul) — a cancel arriving while a finished task result was being delivered silently discarded it. The delivery is now shielded; done means delivered.
• Resume overlap guard (Background task resume can overlap an in-flight run and emit stale completion results PleasePrompto/ductor#158, reported by @Tony-ooo) — resuming a task whose previous run was still alive spawned a second execution and delivered intermediate state as "completed". Resume now refuses while a run is in flight.
• DUCTOR_TASK_ID (Background task ask_parent cannot see DUCTOR_TASK_ID in some runs PleasePrompto/ductor#159, reported by @Tony-ooo) — ask_parent.py no longer dies with "DUCTOR_TASK_ID not set"; the id is derived from the task's process label and injected into the subprocess env (Docker included).
• Cron delivery tracking (Cron result delivery can silently fail while job is recorded as success PleasePrompto/ductor#160, reported by @Tony-ooo) — execution success and delivery success are recorded separately in cron_jobs.json; on delivery failure the original result text is kept so it can be resent without re-running the job.
• Task history retention (fix(tasks): prune finished task history PleasePrompto/ductor#138, @attid) — tasks.json stops growing forever: finished tasks are pruned by age (finished_retention_hours, default 7 days) and count (finished_keep_last, default 100), running/waiting tasks are never touched.
• Startup survives unreachable users — a configured user who never pressed /start ("chat not found") no longer crashes the boot notification path.

Codex

• Prompts via stdin (fix(codex): pass prompts via stdin PleasePrompto/ductor#137, @attid) — ductor's composed prompts (hooks + memory + context) could exceed the OS argv limit; they now stream through stdin on all platforms, which also keeps them out of /proc/<pid>/cmdline. The streaming path feeds stdin concurrently, so >64 KiB prompts can't deadlock.
• Resume re-asserts model (fix: re-assert the configured model when resuming a Codex session PleasePrompto/ductor#168, @ryuhaneul) — /model changes now apply to already-running Codex sessions on resume instead of being silently ignored (verified against the real codex exec resume grammar).
• Model lists refreshed (Refresh stale Codex/Gemini model lists to current CLI lineup PleasePrompto/ductor#155, @ryuhaneul) — RULES templates, tool help texts, and discovery fallbacks now match the current Codex/Gemini lineups; stale names like gpt-5.2-codex are gone.

Also in this release

• append_system_prompt_files (feat(config): inject configurable files into the system prompt PleasePrompto/ductor#157, @ryuhaneul) — workspace-relative files appended to the system prompt on every agent-driven turn (chat, named sessions, tasks, inter-agent); path-traversal safe, 256 KiB cap per file.
• /model persists in fresh topics (fix: persist /model selection in topics whose session is missing or stale PleasePrompto/ductor#169, @ryuhaneul) — selecting a model in a topic without a live session no longer silently discards the choice; count-based staleness now resets only the affected provider bucket instead of wiping all bucket history.
• Root installs work ([Bug]: No such file or directory: 'sudo' PleasePrompto/ductor#162, reported by @SpriteOvO) — onboarding as root (e.g. minimal containers without sudo) no longer crashes on loginctl enable-linger.
• Two-per-row selectors — /model and /effort keyboards are readable on phones again.
• Reply context stays intact: replying to any message (including cron/task posts) always carries the quoted text to the agent.

Merged PRs

• feat: Add Slack transport PleasePrompto/ductor#114 by @victor-develop — Slack transport
• Per-session reasoning effort for Claude and Codex PleasePrompto/ductor#164, fix: scope model-switch/reset/error process kills to the invoking topic PleasePrompto/ductor#166, fix: don't discard a finished task result when cancel races completion PleasePrompto/ductor#167, fix: re-assert the configured model when resuming a Codex session PleasePrompto/ductor#168, fix: persist /model selection in topics whose session is missing or stale PleasePrompto/ductor#169, feat(config): inject configurable files into the system prompt PleasePrompto/ductor#157, Refresh stale Codex/Gemini model lists to current CLI lineup PleasePrompto/ductor#155 by @ryuhaneul — effort, kill scoping, task races, Codex resume, topic model persistence, prompt files, model lists
• fix(codex): pass prompts via stdin PleasePrompto/ductor#137, fix(tasks): prune finished task history PleasePrompto/ductor#138 by @attid — Codex stdin prompts, task retention

And thanks to @Tony-ooo, @SpriteOvO, and @abhisheksoni27 for the sharp bug reports and the Slack nudge. 🙏

Verification

• pytest -p xdist -n 8 — full suite green (4,000+ tests, incl. the new Slack suite)
• ruff format --check ., ruff check . — clean
• mypy ductor_bot — clean (251 files, strict)
• Live smoke test against a real Telegram bot: chat/streaming, /model, /effort (flag verified in CLI argv), background task env, Codex stdin path
• ductor --version → ductor 0.19.0

Full changelog: PleasePrompto/ductor@v0.18.2...v0.19.0