feat(cron): Automation Blueprints — parameterized automation templates across every surface by teknium1 · Pull Request #41309 · NousResearch/hermes-agent

teknium1 · 2026-06-07T13:49:52Z

Summary

Pick an automation by name and Hermes asks you for what it needs — no cron syntax, no slot=value typing. One blueprint definition renders natively on every surface (dashboard form, CLI/TUI/messenger slash command, agent conversation, docs catalog), and every path ends at the same cron.jobs.create_job — there is no second job engine.

This PR has three layers:

Suggested Cron Jobs — Hermes can propose automations and you accept them with one tap via /suggestions, instead of assembling cron jobs by hand. Sources: a curated catalog, blueprint-carrying skills, and (reserved) usage/integration detectors. Consent-first: nothing schedules without explicit acceptance; dismissals latch.
Automation Blueprints — parameterized templates with typed slots (time/enum/text/weekdays). The slot schema (cron/blueprint_catalog.py) is the single source of truth; four renderers consume it. 14 curated blueprints spanning daily/weekly/general (morning brief, important-mail monitor, weekly review, news digest, meal plan, habit check-in, hydration nudge, learning drip, and more).
- Dashboard / desktop app — a Blueprints tab renders each blueprint's slots as a form; submit → POST /api/cron/blueprints/instantiate fills + creates the job (no agent turn).
- Desktop — a hermes://blueprint/<key>?slot=val deep-link routes into the chat composer pre-filled.
- Docs — a generated catalog page with copy-paste commands.
Conversational fill — /blueprint <name> (alias /bp) name-matches a blueprint (exact → prefix → substring → fuzzy; ambiguous lists candidates) and seeds the agent to ask you for each value one at a time, then calls the existing cronjob tool. The slot=value one-liner remains as the deterministic dashboard/docs/power-user shortcut. No new tool.

How the conversational fill stays invariant-safe

The seed enters as a normal user turn — never a synthetic injection.

Shared handler returns BlueprintCommandResult{text, agent_seed}; match_blueprint() + build_blueprint_seed() are the shared pieces.
Gateway: dispatch rewrites event.text to the seed and falls through to the agent (the same pattern /steer uses).
CLI: handler sets a one-shot self._pending_agent_seed; the interactive loop consumes it right after process_command() and runs it as the next turn.

Changes (by surface)

Core — cron/suggestions.py (store: add/list/accept/dismiss, dedup+latch, pending cap), cron/suggestion_catalog.py, cron/blueprint_catalog.py (AutomationBlueprint + BlueprintSlot, 14 blueprints, 4 renderers, fill_blueprint), tools/blueprints.py (blueprint↔job bridge), hermes_cli/suggestions_cmd.py + hermes_cli/blueprint_cmd.py (shared handlers); CommandDef + CLI dispatch + gateway dispatch.
Dashboard — blueprint endpoints, AutomationBlueprints.tsx gallery+form, CronPage sub-tab, api.ts.
Desktop — hermes:// deep-link end to end.
Docs — generated Automation Blueprints catalog page + sidebar entry; creating-skills.md blueprint section.

Naming note: this feature was developed as "Cron Recipes" and rebranded to Automation Blueprints before merge (final commit renames every identifier, route, deep-link, and doc — no behavior change).

Validation

	Result
`tests/cron/` (blueprints, suggestions, schedule, validation, renderers, handlers)	pass
`tests/tools/test_blueprints.py` + blueprint web endpoints	pass
Targeted suite post-rename (cron + blueprints + web_server + commands)	874 pass
E2E	name-match variants → seed built → agent path; direct `slot=val` → `fill_blueprint` → `create_job` → persisted job (schedule/deliver/origin correct)

Rebased onto current main; linear history, contributor authorship preserved.

Infographic

github-actions · 2026-06-07T13:50:43Z

🔎 Lint report: `feat/suggested-cron-jobs` vs `origin/main`

ruff

Total: 0 on HEAD, 0 on base (➖ 0)

🆕 New issues: none

✅ Fixed issues: none

Unchanged: 0 pre-existing issues carried over.

ty (type checker)

Total: 10757 on HEAD, 10719 on base (🆕 +38)

🆕 New issues (20):

Rule	Count
`invalid-argument-type`	10
`not-subscriptable`	3
`unresolved-attribute`	3
`unresolved-import`	3
`unsupported-operator`	1

First entries

tests/cron/test_suggestions.py:198: [not-subscriptable] not-subscriptable: Cannot subscript object of type `None` with no `__getitem__` method
cron/scripts/classify_items.py:215: [unresolved-attribute] unresolved-attribute: Attribute `get` is not defined on `None` in union `dict[str, Any] | None`
tests/cron/test_suggestions.py:198: [invalid-argument-type] invalid-argument-type: Method `__getitem__` of type `bound method str.__getitem__(key: SupportsIndex | slice[SupportsIndex | None, SupportsIndex | None, SupportsIndex | None], /) -> str` cannot be called with key of type `Literal["monitor"]` on object of type `str`
tests/tools/test_blueprints.py:12: [unresolved-import] unresolved-import: Cannot resolve imported module `pytest`
hermes_cli/cli_commands_mixin.py:1302: [unresolved-attribute] unresolved-attribute: Object of type `Self@_handle_blueprint_command` has no attribute `_console_print`
tests/cron/test_suggestions.py:198: [not-subscriptable] not-subscriptable: Cannot subscript object of type `float` with no `__getitem__` method
tests/cron/test_suggestions.py:198: [invalid-argument-type] invalid-argument-type: Method `__getitem__` of type `Overload[(i: SupportsIndex, /) -> Unknown, (s: slice[SupportsIndex | None, SupportsIndex | None, SupportsIndex | None], /) -> list[Unknown]]` cannot be called with key of type `Literal["monitor"]` on object of type `list[Unknown]`
tests/cron/test_blueprint_catalog.py:14: [unresolved-import] unresolved-import: Cannot resolve imported module `pytest`
tests/cron/test_suggestions.py:197: [unsupported-operator] unsupported-operator: Operator `in` is not supported between objects of type `Literal["monitor"]` and `str | dict[Unknown, Unknown] | list[Unknown] | ... omitted 31 union elements`
tests/cron/test_suggestions.py:198: [invalid-argument-type] invalid-argument-type: Method `__getitem__` of type `Overload[(i: SupportsIndex, /) -> str, (s: slice[SupportsIndex | None, SupportsIndex | None, SupportsIndex | None], /) -> list[str]]` cannot be called with key of type `Literal["monitor"]` on object of type `list[str]`
tests/cron/test_suggestions.py:198: [not-subscriptable] not-subscriptable: Cannot subscript object of type `int` with no `__getitem__` method
tests/cron/test_suggestions.py:198: [invalid-argument-type] invalid-argument-type: Method `__getitem__` of type `bound method str.__getitem__(key: SupportsIndex | slice[SupportsIndex | None, SupportsIndex | None, SupportsIndex | None], /) -> str` cannot be called with key of type `Literal["provider"]` on object of type `str`
tests/cron/test_blueprint_catalog.py:145: [invalid-argument-type] invalid-argument-type: Argument to function `blueprint_deeplink` is incorrect: Expected `AutomationBlueprint`, found `AutomationBlueprint | None`
tests/cron/test_blueprint_catalog.py:150: [invalid-argument-type] invalid-argument-type: Argument to function `blueprint_catalog_entry` is incorrect: Expected `AutomationBlueprint`, found `AutomationBlueprint | None`
hermes_cli/cli_commands_mixin.py:1277: [unresolved-attribute] unresolved-attribute: Object of type `Self@_handle_suggestions_command` has no attribute `_console_print`
tests/cron/test_suggestions.py:13: [unresolved-import] unresolved-import: Cannot resolve imported module `pytest`
tests/cron/test_blueprint_catalog.py:140: [invalid-argument-type] invalid-argument-type: Argument to function `blueprint_slash_command` is incorrect: Expected `AutomationBlueprint`, found `AutomationBlueprint | None`
tests/cron/test_suggestions.py:198: [invalid-argument-type] invalid-argument-type: Method `__getitem__` of type `Overload[(i: SupportsIndex, /) -> Unknown, (s: slice[SupportsIndex | None, SupportsIndex | None, SupportsIndex | None], /) -> list[Unknown]]` cannot be called with key of type `Literal["provider"]` on object of type `list[Unknown]`
tests/cron/test_blueprint_catalog.py:121: [invalid-argument-type] invalid-argument-type: Argument to function `fill_blueprint` is incorrect: Expected `AutomationBlueprint`, found `AutomationBlueprint | None`
tests/cron/test_blueprint_catalog.py:128: [invalid-argument-type] invalid-argument-type: Argument to function `blueprint_form_schema` is incorrect: Expected `AutomationBlueprint`, found `AutomationBlueprint | None`

✅ Fixed issues: none

Unchanged: 5611 pre-existing issues carried over.

Diagnostics are surfaced as warnings — this check never fails the build.

Hermes can propose automations and let the user accept them with one tap via /suggestions, instead of making them assemble cron jobs by hand. Every proposal — wherever it originates — flows through one surface. Sources (the 'where suggestions come from'): - catalog: curated starter automations (daily briefing, important-mail monitor, weekly review, workday-start reminder) via /suggestions catalog - recipe: installing a skill that carries a metadata.hermes.recipe block registers a suggestion instead of auto-scheduling - usage / integration: reserved for the background-review detector and account-connect triggers (sources defined; emitters land next) Pieces: - cron/suggestions.py — the store. add/list/accept/dismiss, dedup+latch by key (dismissed proposals never re-offered), pending cap so it can't become a nag wall. Accepting calls the existing cron.jobs.create_job — there is NO second job engine. Mirrors jobs.py storage (atomic writes, lock, 0600). - cron/suggestion_catalog.py — the curated set. The important-mail monitor entry is where the old proactive-monitor poll->classify->surface engine lives now (cron/scripts/classify_items.py + the 'monitor' aux task), as ONE catalog automation rather than a standalone feature. - tools/recipes.py — recipe<->job bridge; register_recipe_suggestion() makes a recipe source 'recipe' of this surface. recipe_to_job_spec() is the single translation both the direct and suggestion paths share. - hermes_cli/suggestions_cmd.py — shared /suggestions handler (CLI + gateway never drift); /suggestions [accept N|dismiss N|catalog|clear]. - Wired: CommandDef + CLI dispatch (cli.py) + gateway dispatch (gateway/run.py) + aux 'monitor' task (config.py) + recipe-install hook (skills_hub.py). Consent-first throughout: nothing auto-schedules; acceptance is always explicit; dismissals latch. Supersedes #41122 (proactive-monitor) and #41127 (recipes): both fold in here as a catalog entry and a suggestion source respectively. Tests: store (dedup/cap/accept/dismiss/latch), catalog seeding+idempotency, recipe->suggestion bridge, command handler, aux config. E2E: recipe SKILL.md -> parsed -> suggested -> accepted -> real cron job persisted to jobs.json.

…every surface A 'recipe' is a one-place definition of an automation that every surface renders natively. The slot schema (cron/recipe_catalog.py) is the single source of truth; four renderers consume it, and all paths end at the same cron.jobs.create_job — no second job engine. Form where there's a screen, conversation where there's a chat line: - Dashboard / GUI app: a Recipes sub-tab on the Cron page renders each recipe's typed slots as a form (time-picker, enum dropdown, free-text); submit POSTs /api/cron/recipes/instantiate which fills + creates the job. - CLI / TUI / messengers: /cron-recipe lists the catalog, shows a recipe's fields, or fills + creates from a pasted 'key slot=val' command. The shared handler (hermes_cli/cron_recipe_cmd.py) names any missing/invalid slot so the agent can ask a targeted follow-up. - Docs: a generated Cron Recipes catalog page (website, .mdx + React cards) shows each recipe with a copy-paste command and a 'Send to App' button. - Desktop: a hermes:// URL scheme (Electron single-instance lock + setAsDefaultProtocolClient + open-url/second-instance) routes hermes://cron-recipe/<key>?slot=val into the chat composer pre-filled. Typed slots (time/enum/text/weekdays) with defaults: users never type raw cron — recipes parameterize time-of-day and weekday sets and translate to cron expressions; a free-text 'schedule' slot is the full-flexibility escape hatch. Consent-first throughout: nothing schedules without an explicit submit or send. Core: - cron/recipe_catalog.py — CronRecipe + RecipeSlot, 5 curated recipes, recipe_form_schema / recipe_slash_command / recipe_deeplink / recipe_catalog_entry renderers, fill_recipe (validate + translate to create_job kwargs). - hermes_cli/cron_recipe_cmd.py — shared /cron-recipe handler (CLI + TUI + gateway never drift). CommandDef + dispatch in commands.py / cli.py / gateway/run.py. Dashboard: GET /api/cron/recipes + POST /api/cron/recipes/instantiate (web_server.py), CronRecipes.tsx gallery+form, Segmented sub-tab on CronPage, api.ts methods + types. Desktop: hermes:// scheme end to end (main.cjs deep-link router + ready-queue, preload onDeepLink/signalDeepLinkReady, global.d.ts types, desktop-controller composer prefill, electron-builder protocols key). Docs: extract-cron-recipes.py generator wired into prebuild.mjs, cron-recipes-catalog.mdx + CronRecipesCatalog React component, sidebar entry. Generated index json gitignored like skills.json. Tests: 23 core (catalog/slots/schedule-resolution/validation/renderers/command handler/generator) + 5 web_server endpoint tests. E2E verified end to end: slot fill -> create_job -> persisted job with correct schedule/deliver/origin.

Reworks the chat-line UX: pick a recipe by name and the agent asks you for what it needs, one question at a time, instead of forcing you to hand-type a slot=val command line. - /cron-recipe -> lists the catalog - /cron-recipe <name> -> forgiving name match (exact/prefix/substring/ fuzzy; ambiguous lists candidates), then seeds the agent with a natural-language fill request built from the recipe's typed slots + schedule and prompt templates. The agent asks for each value one at a time and calls the EXISTING cronjob tool. No new tool. - /cron-recipe <name> slot=val -> unchanged deterministic path (fill_recipe -> create_job) for the dashboard/docs/power user. Mechanism (no new plumbing, invariant-safe — the seed enters as a normal user turn, never a synthetic injection): - shared handler returns RecipeCommandResult{text, agent_seed}; match_recipe() and build_recipe_seed() are the new shared pieces. - gateway: dispatch rewrites event.text to the seed and falls through to the agent (the same pattern /steer uses). - CLI: handler sets a one-shot self._pending_agent_seed; the interactive loop consumes it right after process_command() and runs it as the next turn. The typed-slot schema stays the single source of truth (still validates the form/inline path via fill_recipe); the agent path just renders those slots into the questions to ask. Docs updated to lead with the name-then-ask flow.

…ot names, surface-aware UX Review fixes for the Cron Recipes stack before release: - hydration-move: */90 in the cron minute field silently wraps to hourly (croniter-verified) — 90/120-minute options never fired at their stated cadence. Replaced with an hour-field step (0 9-17/2 * * 1-5) and an interval_hours slot whose options (1/2/3h) all fire as labeled. - fill_recipe: reject unknown slot names. A typo'd 'tiem=07:15' used to silently create the job at the 08:00 default; now it 422s on the dashboard form and errors on the slash/deep-link paths with the valid slot list. - deliver slot: non-strict enum (options are suggestions, scheduler validates downstream) so slack/whatsapp/etc. users aren't locked out; GET /api/cron/recipes rewrites its options from cron_delivery_targets() so the dashboard form only offers configured platforms; help text no longer claims dashboard-created jobs deliver to 'the chat you set this up from' (the endpoint strips origin — they go to the home channel). - gateway: success/accept messages no longer point at /cron (cli_only); surface-aware hint instead. Conversational fill now sends the 'Setting up X — I'll ask you a couple of things…' ack before the agent turn, matching the CLI experience. - important-mail catalog entry: reference the urgency classifier by module path (python3 -m cron.scripts.classify_items) instead of baking an absolute host path into the job prompt — stale after relocation and nonexistent on remote terminal backends. cron/scripts is now a real package and ships in the wheel (pyproject packages.find). - export_recipe: interval schedules round-trip again — parse_schedule stores 'minutes' but the renderer only read 'seconds', so every interval job exported as the silent '0 9 * * *' fallback. - skills_hub install: say so when a recipe suggestion is dropped (latched dedup or pending cap) instead of printing nothing. Targeted tests: 58 cron/recipe + 261 web_server pass; E2E-validated all 14 recipes fill+parse, hydration cadences via croniter, typo rejection on slash + endpoint paths, surface-aware hints, and interval export round-trip.

…t the 50-cap CI tests the PR merged with current main, where the new /memory canonical command filled Slack's 50-slash cap: with btw/bg/reset all pinned ahead of canonicals, the last canonical (/debug) got clamped and the Telegram-parity test failed. Canonical commands must win slots over alias spellings — /new keeps its native slot and 'reset' stays reachable via /hermes reset. Also updates test_includes_aliases_as_first_class_slashes to assert the pinned-alias contract (_SLACK_PRIORITY_ALIASES survive) instead of a specific unpinned alias's survival, which was the same change-detector pattern the docstring already warned about.

Product rename across every surface: module/file names (blueprint_catalog, tools/blueprints, blueprint_cmd), slash command /cron-recipe -> /blueprint (alias /bp), dashboard API /api/cron/blueprints, desktop deep-link hermes://blueprint/<key>, docs catalog page + extract script, and the skill frontmatter block metadata.hermes.blueprint. No behavior change.

daimon-nous Bot added type/feature New feature or request comp/cron Cron scheduler and job management comp/cli CLI entry point, hermes_cli/, setup wizard comp/gateway Gateway runner, session dispatch, delivery P3 Low — cosmetic, nice to have labels Jun 7, 2026

teknium1 force-pushed the feat/suggested-cron-jobs branch from 7b49a62 to 57b9901 Compare June 8, 2026 01:51

teknium1 requested a review from a team June 8, 2026 01:51

teknium1 changed the title ~~feat(cron): Suggested Cron Jobs — one surface for proposed automations~~ feat(cron): Cron Recipes — parameterized automation templates across every surface Jun 8, 2026

teknium1 force-pushed the feat/suggested-cron-jobs branch 4 times, most recently from f5e2859 to 9b08c71 Compare June 8, 2026 17:02

teknium1 enabled auto-merge (rebase) June 11, 2026 16:50

OutThisLife previously approved these changes Jun 11, 2026

View reviewed changes

auto-merge was automatically disabled June 11, 2026 16:52
Rebase failed

teknium1 added 6 commits June 11, 2026 10:06

chore: retrigger CI (workflows did not fire on fdeae1b)

9c07e06

teknium1 force-pushed the feat/suggested-cron-jobs branch from 80123fd to 9c07e06 Compare June 11, 2026 17:07

teknium1 changed the title ~~feat(cron): Cron Recipes — parameterized automation templates across every surface~~ feat(cron): Automation Blueprints — parameterized automation templates across every surface Jun 11, 2026

teknium1 dismissed OutThisLife’s stale review via f4f7bc8 June 11, 2026 17:23

austinpickett self-requested a review June 11, 2026 17:39

austinpickett approved these changes Jun 11, 2026

View reviewed changes

teknium1 merged commit cb29e8a into main Jun 11, 2026
32 checks passed

teknium1 deleted the feat/suggested-cron-jobs branch June 11, 2026 17:49

BrewTestBot mentioned this pull request Jun 19, 2026

hermes-agent 2026.6.19 Homebrew/homebrew-core#288870

Merged

1 task

This was referenced Jun 20, 2026

chore: bump NousResearch/hermes-agent version from v2026.6.5 to v2026.6.19 Docker-Hub-sirmark/docker-hermes-agent#10

Merged

Upstream Hermes v2026.6.19 disponible (ultimo sync: v2026.6.5) samuelgradientai-sys/clawksis-agent#45

Closed

jasonalbers mentioned this pull request Jun 23, 2026

[Feature]: Windows Desktop Learn mode for approval-gated workflow discovery #51451

Open

tomfuertes mentioned this pull request Jun 23, 2026

chore: bump Hermes to v2026.6.19 (0.17.0) notambourine/hermes-agent-template#15

Merged

Navigation Menu

Uh oh!

feat(cron): Automation Blueprints — parameterized automation templates across every surface - #41309

feat(cron): Automation Blueprints — parameterized automation templates across every surface#41309
teknium1 merged 7 commits into
mainfrom
feat/suggested-cron-jobs

teknium1 commented Jun 7, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Jun 7, 2026 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Uh oh!

Conversation

teknium1 commented Jun 7, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

How the conversational fill stays invariant-safe

Changes (by surface)

Validation

Infographic

Uh oh!

github-actions Bot commented Jun 7, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔎 Lint report: feat/suggested-cron-jobs vs origin/main

ruff

ty (type checker)

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

teknium1 commented Jun 7, 2026 •

edited

Loading

github-actions Bot commented Jun 7, 2026 •

edited

Loading

🔎 Lint report: `feat/suggested-cron-jobs` vs `origin/main`