omnius 1.0.24 → 1.0.26

package/README.md

@@ -276,7 +276,7 @@ The agent uses tools autonomously in a loop — reading errors, fixing code, and
 
 <div align="right"><a href="#top">back to top</a></div>
 
-- **61 autonomous tools** — file I/O, shell, grep, web search/fetch/crawl, memory (read/write/search), sub-agents, background tasks, image/OCR/PDF, git, diagnostics, vision, desktop automation, browser automation, temporal agency (scheduler/reminders/agenda), structured files, code sandbox, transcription, skills, opencode delegation, cron agents, nexus P2P networking + x402 micropayments, **COHERE cognitive stack** (persistent REPL, recursive LLM calls, memory metabolism, identity kernel, reflection, exploration)
+- **60+ autonomous tools** — file I/O, shell, grep, web search/fetch/crawl, memory (read/write/search), sub-agents, background tasks, image/OCR/PDF, git, diagnostics, vision, desktop automation, browser automation, temporal agency (scheduler/reminders/agenda), structured files, code sandbox, transcription, skills, opencode delegation, cron agents, nexus P2P networking + x402 micropayments, **COHERE cognitive stack** (persistent REPL, recursive LLM calls, memory metabolism, identity kernel, reflection, exploration)
 - **Moondream vision** — see and interact with the desktop via Moondream VLM (caption, query, detect, point-and-click)
 - **Image generation with TUI previews** — `/image <prompt>` and the `generate_image` tool create PNGs under `.omnius/images/`, support explicit `--model` selection, try a ranked quality fallback ladder from FLUX.1 dev / SD3.5 Large down to lightweight smoke-test models when setup or generation fails, and render generated, pasted, screenshot, and camera-capture images as auto-sized ASCII previews via the bundled `image-to-ascii` renderer
 - **Sound and music generation** — `/sound` and `/music` generate WAV files under `.omnius/audio/`, auto-create backend venvs under `.omnius/audio-gen/`, and fall back from high-quality Stable Audio / AudioLDM / MusicGen tiers to smaller practical models when a larger setup or model download fails. Stable Audio uses Diffusers `StableAudioPipeline` instead of the build-prone `stable-audio-tools` package
@@ -337,7 +337,7 @@ The daemon auto-installs Python dependencies (OpenCLIP, torchaudio + soundfile,
 - **Structured file reading** — parse CSV, TSV, JSON, Markdown tables with binary format detection
 - **On-device web search** — DuckDuckGo (free, no API keys, fully private)
 - **Browser automation** — headless Chrome control via Selenium: navigate, click, type, screenshot, read DOM — auto-starts on first use with self-bootstrapping Python venv
-- **Temporal agency** — schedule future tasks via OS cron, set cross-session reminders, flag attention items — startup injection surfaces due items automatically
+- **Temporal agency** — schedule future tasks via OS cron, set scoped minimal reminders, and trigger future agent actions on interval, 24-hour clock, weekly, monthly, or yearly schedules
 - **Web crawling** — multi-page web scraping with Crawlee/Playwright for deep documentation extraction
 - **Task templates** — specialized system prompts and tool recommendations for code, document, analysis, plan tasks
 - **Inference capability scoring** — canirun.ai-style hardware assessment at first launch and on demand: memory/compute/speed scores, per-model compatibility matrix, `/models` runtime fit ratings, `/image list` image-model fit ratings, and recommended model selection
@@ -2127,8 +2127,8 @@ On startup and `/model` switch, Omnius detects your RAM/VRAM and creates an opti
 | `skill_list` | Discover available AIWG skills |
 | `skill_execute` | Run an AIWG skill |
 | **Temporal Agency** | |
-| `scheduler` | Schedule tasks for automatic future execution via OS cron (presets, natural language, raw cron) |
-| `reminder` | Set cross-session reminders with priority, due dates, tags — surfaces at startup |
+| `scheduler` / `cronjob` | Schedule tasks for automatic future execution via OS cron (intervals, 24-hour clock, weekly/monthly/yearly, raw cron) |
+| `reminder` / `remind` / `reminders` | Set scoped minimal reminders or scheduled action triggers with priority, recurrence, tags, and context |
 | `agenda` | Unified view of reminders, schedules, and attention items with startup brief |
 | **AIWG SDLC** | |
 | `aiwg_setup` | Deploy AIWG SDLC framework |
@@ -3198,22 +3198,24 @@ Agent: scheduler(action="create", task="run npm audit and fix vulnerabilities",
 
 Agent: scheduler(action="create", task="check API health", schedule="every 30 minutes")
        → Scheduled task created: sched-e5f6a7b8
+
+Agent: cronjob(action="create", task="weekly dependency review", schedule="weekly friday at 17:45")
+       → Alias for scheduler; scheduled task created
 ```
 
-Schedule formats: presets (`daily`, `hourly`, `every 5 minutes`, `weekly`), natural language (`in 30m`, `at 14:30`), or raw cron (`0 */2 * * *`).
+Schedule formats: presets (`daily`, `hourly`, `weekly`, `monthly`, `yearly`), intervals (`every 5 minutes`, `every 2 hours`), 24-hour clock times (`at 14:30`, `daily at 09:00`), weekly/monthly/yearly forms (`weekly friday at 17:45`, `monthly on 15 at 08:30`, `yearly on jan 15 at 09:00`), or raw cron (`0 */2 * * *`).
 
-**Reminder** — Cross-session messages-in-a-bottle:
+**Reminder** — Scoped minimal reminders or scheduled action triggers:
 
 ```
-Agent: reminder(action="set", message="Verify auth migration tokens after deploy", priority="high", due="tomorrow")
+Agent: reminder(action="set", kind="minimal", message="Verify auth migration tokens after deploy", priority="high", due="tomorrow")
        → Reminder set: rem-c4d5e6f7 (due: tomorrow morning)
 
-# Next startup:
-⚠ 1 urgent item(s) need attention
-  Reminder: Verify auth migration tokens after deploy
+Agent: remind(action="set", kind="action", message="Nightly health check", task_description="Check API health and file an agenda item if unhealthy", repeat="daily", time="21:00")
+       → Alias for reminder; action will trigger daily at 21:00
 ```
 
-Reminders support priority levels (`low`/`normal`/`high`/`critical`), due dates, tags, context, snoozing, and auto-surface at startup.
+`kind="minimal"` delivers raw reminder content only. `kind="action"` requires `task_description` and starts an agent task when due. Reminders support private/public scopes per surface (`tui`, `gui`, `telegram`, `api`, `global`), priority levels (`low`/`normal`/`high`/`critical`), due dates, interval/daily/weekly/monthly/yearly recurrence, tags, context, snoozing, and completion/dismissal.
 
 **Agenda** — Unified temporal dashboard:
 
@@ -3338,6 +3340,12 @@ Image surfaces are first-class in the terminal. `/image` generations, generated-
 | `/tools` | List agent-created custom tools |
 | `/skills [keyword]` | List/search available AIWG skills |
 | `/<skill-name> [args]` | Invoke an AIWG skill directly |
+| **Temporal Agency** | |
+| `/scheduler [menu\|list\|kill]` | Manage OS-backed scheduled agent tasks |
+| `/cron` | Alias for `/scheduler` |
+| `/remind [in 30m\|tomorrow\|at 14:30] <message>` | Set a scoped minimal reminder for the current TUI session |
+| `/reminder [list\|all]` | List scoped TUI reminders |
+| `/reminders` | Alias for `/reminder` |
 | **Workspace Explorer** | |
 | `/files` | Show searchable working-directory file overview |
 | `/files <query>` | Filter the working-directory file overview |
@@ -3557,7 +3565,7 @@ While the sub-agent is working, users see:
 
 ### Public User Isolation
 
-Public users get **per-chat isolated memory** — each chat has its own scoped memory namespace (`telegram-{chatId}-{topic}`) so public users can store and retrieve facts about their conversation without accessing or polluting global agent memory. Public tools include: `memory_read`, `memory_write` (scoped), `memory_search`, `web_search`, `web_fetch`.
+Public users get **per-chat isolated memory** — each chat has its own scoped memory namespace (`telegram-{chatId}-{topic}`) so public users can store and retrieve facts about their conversation without accessing or polluting global agent memory. Public tools include: `memory_read`, `memory_write` (scoped), `memory_search`, `web_search`, `web_fetch`, and scoped minimal reminders via `reminder`/`remind`.
 
 The bridge also maintains a per-chat conversation state file with recent history, participants, relationship signals, and lightweight Zettelkasten memory cards. Each Telegram group or private chat gets its own scoped personality document under `.omnius/scoped-personality/telegram-chat/`; that profile is updated as people talk and injected into future Telegram context so tone, pacing, names, and relationships stay available turn to turn.
 
@@ -3578,8 +3586,8 @@ Tools are gated per execution context. The system enforces strict separation bet
 |---------|--------------|-------|
 | `terminal` | All tools | Wide open — shell, file read/write, everything |
 | `telegram-admin-dm` | All except shell | Admin DM — full tools, shell blocked by default (overridable) |
-| `telegram-admin-group` | Read-only + web + vision/OCR | Admin in public group — no system mutation tools |
-| `telegram-public` | Memory r/w, web fetch/search, scoped creative tools | Public users — no arbitrary local file access or shell |
+| `telegram-admin-group` | Read-only + web + vision/OCR + scoped reminders | Admin in public group — no system mutation tools |
+| `telegram-public` | Memory r/w, web fetch/search, scoped creative tools, scoped minimal reminders | Public users — no arbitrary local file access or shell |
 | `api` | All tools | API endpoint — configurable |
 
 **System tools** (`shell`, `file_write`, `file_edit`, `file_read`, `file_patch`, `batch_edit`, `grep_search`, `glob_find`, `list_directory`, `code_sandbox`, `codebase_map`, `git_info`, etc.) are **never exposed** in public-facing contexts.