@damian87/omp 0.12.0 → 0.14.0

package/.github/skills/schedule/SKILL.md

@@ -37,14 +37,39 @@ the `omp schedule …` commands on the user's behalf.
    ```bash
    omp schedule add --id <id> --cron "<expr>" --prompt "<text>" \
      [--allow-all-tools] [--cwd <dir>] [--model <m>] [--timeout <ms>] \
-     [--max-runs <n>] [--ttl-hours <h>] --json
+     [--max-runs <n>] [--ttl-hours <h>] \
+     [--notify-target slack:<ID>] [--notify-desktop] [--notify-open-omp] --json
    ```
    Jobs auto-expire after 72h by default (`--ttl-hours`) — set a longer TTL or a
    `--max-runs` cap as needed. Use `--dry-run` to preview the OS entry first.
+
+   **End-of-run notifications (all opt-in, default off; failures never affect the job):**
+   - `--notify-target slack:<C|G|D|U…>` — post the run summary to Slack (needs
+     `SLACK_BOT_TOKEN`; falls back to `SLACK_HOME_CHANNEL` when no target).
+   - `--notify-desktop` — fire a native desktop notification (job id + status +
+     one-line summary). Transport per OS: **macOS → `osascript`** (the only path
+     that reliably displays on Sequoia; shown under "Script Editor", **not
+     clickable**); **Linux/Windows → node-notifier** (notify-send / SnoreToast).
+   - `--notify-open-omp` — make the notification's click open an interactive `omp`
+     session in the schedule state root (the SessionStart banner then surfaces the
+     latest result). **Requires a click-capable transport**, which on macOS means a
+     system `terminal-notifier` enabled via `OMP_NOTIFY_USE_TERMINAL_NOTIFIER=1`
+     (`brew install terminal-notifier`). Note: terminal-notifier does **not**
+     display on some macOS Sequoia builds — if notifications stop appearing,
+     unset that env to fall back to osascript (display-only). Disable desktop
+     notifications entirely with `OMP_DISABLE_DESKTOP_NOTIFY=1`.
+
+   Slack and desktop are independent and can be combined on one job.
 4. **Confirm** by listing: `omp schedule list --json`.
 5. **Trigger now** to test it once: `omp schedule run-now --id <id>`.
 6. **Inspect** results: `omp schedule status --id <id> --json` (recent results
-   are also surfaced automatically at the start of future sessions).
+   are also surfaced automatically at the start of future sessions). To pull up
+   the latest run with full context by id — e.g. after seeing a desktop
+   notification titled `schedule: <id>` — run `omp schedule open <id>`, which
+   prints the latest status, summary, and the full captured output. Add `--tmux`
+   to instead drop into an interactive `omp` session (auto-wrapped in tmux) rooted
+   at the project; the SessionStart banner surfaces *recent* scheduled runs there
+   (not pinned to `<id>`) — for this id's exact output, use plain `omp schedule open <id>`.
 7. **Remove** when done: `omp schedule remove --id <id>` (fully uninstalls the OS
    entry; do NOT delete `.omp/state/schedule/` by hand).
 

package/.github/skills/verify-byok/SKILL.md

@@ -0,0 +1,50 @@
+---
+name: verify-byok
+description: Verify an omp change end-to-end — static gate (build/tsc/tests/lint/catalog) plus a live BYOK run that drives Copilot/teams on a real model and captures evidence. Use before merging any PR that touches hooks, comms, team, launch, or skills.
+argument-hint: "<branch-or-PR to verify>"
+---
+
+# verify-byok — evidence-based verification for omp changes
+
+**Invocation:** `/verify-byok <branch-or-PR>`
+
+Prove a change actually works, not just that it compiles. Two gates: a **static** gate (cheap, always) and a **live BYOK** gate (drives real Copilot CLI sessions on a Bring-Your-Own-Key model so no GitHub quota is needed). Report **real command output**, never claims. Be honest about what you did NOT test.
+
+## When to use
+Before merging any PR — especially ones touching `hooks/`, `scripts/*.mjs`, `src/comms`, `src/team`, `src/copilot/launch`, `src/copilot/trust`, or `.github/skills`. Anything whose behavior only appears at runtime (tmux submit keys, hook firing, trust dialog, model tool-calls) needs the live gate.
+
+## Prerequisites (one-time, persistent)
+- `~/.omp/.env` holds BYOK: `COPILOT_PROVIDER_BASE_URL=https://openrouter.ai/api/v1`, `COPILOT_PROVIDER_TYPE=openai`, `COPILOT_PROVIDER_API_KEY=…`, `COPILOT_MODEL=…`, `COPILOT_PROVIDER_MODEL_ID=…`. omp auto-loads it; `~/.zshrc` sourcing it makes direct `copilot` BYOK too.
+- Free model `openai/gpt-oss-120b:free` exercises plumbing but botches structured edits/`apply_patch` and narrates instead of acting — use a capable model (`anthropic/claude-sonnet-4.5` + `COPILOT_PROVIDER_MODEL_ID=claude-sonnet-4`) when verifying that real tasks complete.
+- Folder trust: a session only skips the "Do you trust this folder?" dialog if the cwd is in `~/.copilot/config.json#trustedFolders` (`--yolo` does NOT skip it). `omp` auto-adds it on launch; `/private/tmp` is pre-trusted.
+
+## Static gate (run from the branch worktree)
+```bash
+npm run build                              # tsc
+npx tsc -p tsconfig.json --noEmit          # type-clean
+npx vitest run                             # ALL must pass — note the count
+node dist/src/cli.js lint:skills --root .  # 0 issues
+node dist/src/cli.js catalog validate      # PASS
+```
+A merged-overlap PR? Confirm the test count rose (new tests survived the rebase) and old behavior's tests still pass.
+
+## Live BYOK gate
+Build the branch CLI first (`npm run build`); installed `omp` may be older. Drive Copilot inside tmux (each pane is a pty). **Submit with the `Enter` key name, never `C-m`** — Copilot ≥1.0.61 ignores `C-m`.
+
+1. **Launch + reach a model:** `tmux new-session -d -s vbyok -c <dir>` → send `omp` (or `omp --madmax` for bypass) → wait for `/ commands`. Confirm the model line shows your BYOK model and `Session: 0 AIC used` (0 AI Credits = not on GitHub quota). Send a prompt, send `Enter`, confirm a real reply.
+2. **Exercise the changed surface** — pick the user-visible behavior the change claims:
+   - hooks → tail `<cwd>/.omp/state/hooks.log` for the events firing;
+   - team → run a 2-worker team, confirm files/artifacts on disk and the script's `🎉 All N agents completed!` (read the raw stdout, not the leader's summary);
+   - cost/minify → pipe a postToolUse payload to `scripts/post-tool-use.mjs` and check `modifiedResult` + raw preserved + ledger `savedTokens` + `omp cost`.
+3. **Capture evidence**: `tmux capture-pane -p -t <session>` plus the on-disk artifact. Keep transcripts.
+
+## Reporting (mandatory)
+- PASS/FAIL table with the actual captured output (model line, reply, artifact contents, ledger numbers).
+- State the model used and that no GitHub quota was consumed.
+- **Honest limitations**: heuristics (e.g. pane-scrape completion detection), model-quality effects (free model botching edits), anything gated/conditional, and anything you did NOT exercise.
+- Never report "works" without exercising the user-visible surface — verify before asserting.
+
+## Anti-patterns
+- Trusting a subagent's "Complete." — re-run the gate yourself.
+- `C-m` to submit to Copilot (use `Enter`).
+- Concluding from a green build alone — runtime bugs (env propagation, trust dialog, submit keys) pass the build and fail live.

package/README.md

@@ -60,6 +60,82 @@ That's it.
 
 ---
 
+## Architecture
+
+oh-my-copilot is two things working together: a **shell CLI** (`omp`) that wraps and scripts the GitHub Copilot CLI, and a **Copilot plugin** that ships in-session slash skills, custom agents, and native lifecycle hooks. Both feed the same orchestration modes, the same file-based memory, and the same `.omp` state — so whether you drive from the shell, an in-session `/skill`, Slack, or cron, you hit one coherent system.
+
+```mermaid
+flowchart TB
+  subgraph Surfaces["① Where you drive it"]
+    SH["Shell CLI<br/><code>omp</code> / <code>omp --madmax</code>"]
+    IDE["In-session <code>/skills</code><br/>(Copilot plugin)"]
+    GW["Gateway<br/>Slack / messaging"]
+    CRON["Cron<br/><code>omp schedule</code>"]
+  end
+
+  subgraph Copilot["② GitHub Copilot CLI (wrapped)"]
+    CP["copilot session"]
+    HK["Lifecycle hooks<br/>sessionStart · sessionEnd · agentStop<br/>pre/postToolUse · userPromptSubmitted"]
+    PS["Plugin skills + agents<br/>ralph · ralplan · team · council<br/>code-review · tdd · research · …"]
+  end
+
+  subgraph Orchestration["③ Orchestration modes"]
+    direction LR
+    RALPH["ralph<br/>PRD verify/fix loop"]
+    UW["ultrawork<br/>parallel fan-out"]
+    UQA["ultraqa<br/>QA cycles"]
+    AP["autopilot"]
+    TEAM["team<br/>tmux multi-agent"]
+    COUNCIL["council<br/>weighted consensus"]
+  end
+
+  subgraph Learning["④ Memory & learning loop"]
+    direction LR
+    MR["memory-review<br/>cheap model, end-of-session"]
+    PM["project-memory<br/>directives + notes"]
+    SE["self-evolve<br/>skill drafts"]
+    DL["daily-log"]
+    IM["instructions-memory<br/>→ copilot-instructions.md"]
+  end
+
+  subgraph Store["⑤ Config & state"]
+    direction LR
+    G["~/.omp<br/>global config + .env"]
+    P[".omp/<br/>project config · memory<br/>cost · trace · mode-state"]
+    SST["~/.copilot/session-state<br/>events.jsonl transcripts"]
+  end
+
+  SH --> CP
+  GW --> CP
+  CRON --> CP
+  IDE --> PS
+  CP --> HK
+  PS --> Orchestration
+  SH --> Orchestration
+  HK -- "agentStop drives the loop" --> Orchestration
+  Orchestration --> P
+
+  HK -- "sessionEnd (detached)" --> MR
+  SH -- "wrapper fallback (headless -p)" --> MR
+  MR -- reads transcript --> SST
+  MR -- "facts" --> PM
+  MR -- "procedures" --> SE
+  MR -- "rules (gated)" --> PM
+  PM --> IM
+  DL --> IM
+  IM -- "injected next session" --> CP
+
+  G -. config .-> MR
+  P -. config .-> MR
+  Orchestration -. cost/trace .-> P
+```
+
+**The flow:** you launch a Copilot session from any surface ①. It runs through the wrapped Copilot CLI ②, where plugin hooks and skills can spin up orchestration modes ③ (ralph/ultrawork/ultraqa/team/council). When the session ends, the **learning loop** ④ fires — a cheap model reviews the transcript and writes durable **notes**, gated **directives**, and **skill drafts**, which `instructions-memory` injects into the *next* session so it starts smarter. Everything persists in layered config/state ⑤: global `~/.omp`, per-project `.omp/`, and Copilot's own session transcripts.
+
+> The learning loop is **opt-in** (`omp config set memory-mode on`) and runs on a cheap model (`gpt-5-mini` by default) — the expensive reasoning already happened in your main session. See [docs/memory-mode.md](docs/memory-mode.md).
+
+---
+
 ## Features
 
 ### Orchestration Modes
@@ -205,9 +281,10 @@ omp gateway notify --text "<msg>" [--target slack:C…|G…|D…|U… [:thread_t
 omp slack serve                             # deprecated alias of `gateway serve --only slack`
 omp slack doctor [--json]                   # deprecated alias of `gateway status --only slack`
 omp env init [--force]                      # write ~/.omp/.env (interactive Slack token setup)
-omp schedule add --id <id> --cron "*/15 * * * *" --prompt "<text>" [--allow-all-tools] [--cwd <dir>] [--model <m>] [--timeout <ms>] [--max-runs N] [--ttl-hours H] [--notify-target slack:U0123ABCD] [--dry-run]
+omp schedule add --id <id> --cron "*/15 * * * *" --prompt "<text>" [--allow-all-tools] [--cwd <dir>] [--model <m>] [--timeout <ms>] [--max-runs N] [--ttl-hours H] [--notify-target slack:U0123ABCD] [--notify-desktop] [--notify-open-omp] [--dry-run]
 omp schedule list                           # registered jobs + OS-install status
 omp schedule status <id>                    # last run + result summary
+omp schedule open <id> [--tmux]             # print this id's latest status + full output (--tmux: open an omp session)
 omp schedule run-now <id>                   # trigger one run immediately
 omp schedule remove <id>                    # uninstall the OS entry + delete the job
 omp goal set "<objective>" | read [--json]
@@ -227,6 +304,8 @@ Environment overrides:
 - `OMP_COPILOT_BIN` — alternate `copilot` binary
 - `OMP_BIN` — absolute path to the `omp` wrapper written into OS-scheduler entries (overrides `which omp`)
 - `OMP_SKIP_USER_ENV` — when `1`, skip auto-loading `~/.omp/.env` (useful for hermetic CI runs)
+- `OMP_DISABLE_DESKTOP_NOTIFY` — when set, suppress all `--notify-desktop` notifications
+- `OMP_NOTIFY_USE_TERMINAL_NOTIFIER` — when set (+ a system `terminal-notifier` on PATH), use it for desktop notifications so the click can open omp; otherwise macOS uses `osascript` (display-only)
 
 **Scheduled jobs** register a durable per-job entry with the OS scheduler (macOS launchd,
 Linux systemd-user timers, or a managed `crontab` block as a cross-platform fallback) that
@@ -234,8 +313,13 @@ invokes `omp schedule run --id <id>` on the cron schedule. Each tick spawns a fr
 session; overlapping runs are locked out and every run is killed at its `--timeout`
 (default 5 min). Jobs default to **read-only** (`--allow-all-tools` is opt-in and prints a
 warning) and auto-expire after 72h unless `--ttl-hours`/`--max-runs` say otherwise. Recent
-run results are surfaced automatically at the start of new Copilot sessions. Always use
-`omp schedule remove`, never delete `.omp/state/schedule/` by hand, so the OS entry is
+run results are surfaced automatically at the start of new Copilot sessions, and
+`omp schedule open <id>` prints any job's latest status + full captured output on demand.
+Opt into end-of-run **notifications** (default off; failures never affect the job): `--notify-target slack:…`
+posts to Slack, and `--notify-desktop` fires a native notification (job id + status + one-line
+summary) — on macOS via `osascript` (display-only; for a clickable notification that opens omp,
+set `OMP_NOTIFY_USE_TERMINAL_NOTIFIER=1` with a system `terminal-notifier` and add `--notify-open-omp`).
+Always use `omp schedule remove`, never delete `.omp/state/schedule/` by hand, so the OS entry is
 uninstalled cleanly.
 
 ### Chat bridge: drive Copilot from Slack
@@ -269,7 +353,7 @@ omp grows in vertical slices. Items aren't pinned to specific semver versions
 
 ### Already shipped
 
-- **Scheduled tasks** (v0.6.0) — durable local cron: `omp schedule add --id pr-watch --cron "*/15 * * * *" --prompt "…"` plus `/schedule` in-session. Each job registers an OS-scheduler entry (launchd / systemd-user / crontab fallback) that fires a fresh agent session, survives reboot, locks out overlap, and surfaces results at the next session start.
+- **Scheduled tasks** (v0.6.0) — durable local cron: `omp schedule add --id pr-watch --cron "*/15 * * * *" --prompt "…"` plus `/schedule` in-session. Each job registers an OS-scheduler entry (launchd / systemd-user / crontab fallback) that fires a fresh agent session, survives reboot, locks out overlap, and surfaces results at the next session start. Opt-in end-of-run notifications (`--notify-target` Slack, `--notify-desktop` native) and `omp schedule open <id>` to pull up a run's full output by id.
 - **Chat bridge — Slack inbound** (v0.8.0) — `omp gateway` runs long-lived chat connectors that forward messages into a running Copilot tmux session and post replies back. Slack is the first connector (Socket Mode, no public URL). `omp env init` walks you through one-time token setup; tokens live in `~/.omp/.env` (auto-loaded on every invocation). See [`docs/slack-setup.md`](docs/slack-setup.md).
 - **Slack outbound — `omp gateway notify`** — stateless REST `chat.postMessage` from any process (cron `--notify-target`, in-session `/slack <message>`, ad-hoc `omp gateway notify --text "..."`). Default destination from `SLACK_HOME_CHANNEL`; explicit `--target slack:C…/G…/D…/U…` overrides; `U…` auto-resolves to a DM via `conversations.open`.
 - **Weighted-consensus council** — multi-model council with role weights + minority report. Via `omp council` or `/weighted-consensus`.

package/catalog/capabilities.json

@@ -908,6 +908,29 @@
           "notes": "Use /slack from .github/skills/slack/SKILL.md."
         }
       }
+    },
+    {
+      "id": "verify-byok",
+      "name": "verify-byok",
+      "title": "BYOK verification",
+      "category": "verification",
+      "summary": "Static + live BYOK verification of omp changes with evidence capture.",
+      "notes": "Maintainer verification skill: static gate plus a live Copilot/team run on a BYOK model.",
+      "defaultCommand": "verify-byok",
+      "phase1": true,
+      "sourceSkill": "verify-byok",
+      "providers": {
+        "copilot": "supported"
+      },
+      "support": {
+        "copilot": "native"
+      },
+      "providerSupport": {
+        "copilot": {
+          "state": "native",
+          "notes": "Use /verify-byok from .github/skills/verify-byok/SKILL.md."
+        }
+      }
     }
   ]
 }

package/catalog/skills-general.json

@@ -528,6 +528,31 @@
       },
       "projection": "project-skill",
       "phase1": true
+    },
+    {
+      "name": "verify-byok",
+      "capabilityId": "verify-byok",
+      "capabilityIds": [
+        "verify-byok"
+      ],
+      "source": ".github/skills/verify-byok/SKILL.md",
+      "sourcePath": ".github/skills/verify-byok/SKILL.md",
+      "canonicalPath": ".github/skills/verify-byok/SKILL.md",
+      "description": "Verify an omp change with a static gate plus a live BYOK run.",
+      "summary": "Verify an omp change with a static gate plus a live BYOK run.",
+      "support": "project-skill",
+      "aliases": [],
+      "slashCommands": [
+        "verify-byok"
+      ],
+      "projections": {
+        "copilot": {
+          "command": "/verify-byok",
+          "state": "supported"
+        }
+      },
+      "projection": "project-skill",
+      "phase1": true
     }
   ]
 }

package/dist/src/cli.js

@@ -26,7 +26,8 @@ function printResult(result, json) {
     }
 }
 function help() {
-    return `oh-my-copilot\n\nRun \`omp\` with no arguments to launch copilot (permissions bypass OFF).\nUse \`omp help\` to show this list.\n\nCommands:\n  (no args)                                     launch copilot (bypass OFF by default)\n  version [--json]\n  list [--json]\n  setup [--dry-run] [--scope project|user] [--plugin-root <dir>] [--json]\n  doctor [--json] [--copilot-bin <path>] [--skip-copilot] [--hooks]\n  cost [--json] [--session <id>] [--days <n>]\n  launch -- <args...>\n  --madmax [args...]                          (bare-flag launch with permissions bypass; alias of --yolo)\n  team <N:role> "<task>" [--name <name>] [--json]\n  team status <name> [--json]\n  team shutdown <name> [--json]\n  team api claim-task --input '<json>' [--json]\n  team api transition-task-status --input '<json>' [--json]\n  team api send-message --input '<json>' [--json]\n  team api broadcast --input '<json>' [--json]\n  team api mailbox-list --input '<json>' [--json]\n  team api mailbox-mark-delivered --input '<json>' [--json]\n  council "<question>" [--models a,b,c|m:role:weight] [--context <text|@file>] [--rubric <text|@file>] [--synth <model>] [--probe] [--timeout <ms>] [--synth-timeout <ms>] [--min-survivors <n>] [--max-concurrency <n>] [--tmp-dir <dir>] [--json]\n  comms status [--session <name>] [--json]      (is copilot on + online? auto-discovers session)\n  comms send --text "<prompt>" [--force] [--session <name>] [--json]\n  comms recv [--wait] [--lines <n>] [--timeout <ms>] [--session <name>] [--json]\n  comms ask --text "<prompt>" [--force] [--lines <n>] [--timeout <ms>] [--session <name>] [--json]\n  gateway serve [--only <name>[,<name>]]        (run all configured connectors; today: slack)\n  gateway status [--json] [--only <name>[,...]] (per-connector readiness; no sockets opened)\n  gateway doctor [--json] [--only <name>[,...]] (alias for 'gateway status')\n  gateway notify --text "<msg>" [--target slack:C\\|D\\|G\\|U... [:thread_ts]] [--thread-ts <ts>] [--json]\n                                                (one-shot outbound Slack post; falls back to SLACK_HOME_CHANNEL)\n  slack serve                                   (deprecated alias for 'gateway serve --only slack')\n  slack doctor [--json]                         (deprecated alias for 'gateway status --only slack')\n  env init [--force]                            (interactive: write ~/.omp/.env with Slack tokens + optional SLACK_HOME_CHANNEL)\n                                                non-interactive: set OMP_INIT_BOT_TOKEN/OMP_INIT_APP_TOKEN/OMP_INIT_HOME_CHANNEL\n                                                (env vars preferred over --bot-token/--app-token/--home-channel flags)\n  (--session is optional when exactly one omp-<digits> tmux session is running)\n${registeredCommandHelpLines().join("\n")}\n  ralph start "<task>" [--max-iterations <n>] [--session-id <id>] [--json]\n  ralph status [--json]\n  ralph tick [--json]\n  ralph cancel [--json]\n  ultrawork start "<objective>" [--task-count <n>] [--summary <s>] [--json]\n  ultrawork status [--json]\n  ultrawork cancel [--json]\n  ultraqa start "<goal>" [--max-cycles <n>] [--json]\n  ultraqa cycle pass|fail|pending [--json]\n  ultraqa status [--json]\n  ultraqa cancel [--json]\n  schedule add --id <id> --cron "<expr>" --prompt "<text>" [--bin copilot] [--model <m>] [--cwd <dir>] [--timeout <ms>] [--max-runs <n>] [--ttl-hours <h>] [--allow-all-tools] [--notify-target slack:<ID>] [--dry-run] [--json]\n  schedule list [--json]\n  schedule status <id> [--json]\n  schedule run-now <id> [--json]\n  schedule remove <id> [--json]\n  goal set "<objective>" [--json]\n  goal read [--json]\n  memory sync [--json]                          (render goal+directives into copilot-instructions.md)\n  daily-log set-goal "<text>" [--json]\n  daily-log add "<text>" [--json]\n  daily-log read [--days <n>] [--json]\n  daily-log prune [--keep-days <n>] [--json]\n  state write <key> <val> [--ttl <s>] | read|delete|status <key> | list | cleanup [--json]\n  project-memory read [<id>] | index | add-note "<title>" [--body "<text>"] | add-directive "<rule>" [--json]\n  trace timeline [<sessionId>] [--limit <n>] | summary [<sessionId>] | add <sessionId> <event> [<json>] [--json]\n  catalog list [--json]\n  catalog validate [--json]\n  catalog capability <id> [--json]\n  project inspect [--json]\n  skill install <skill-dir> [--root <repo>] [--scope project|user] [--dry-run] [--json]\n  lint:skills [--root <repo>]\n  sync:dry-run [--root <repo>]\n  jira:dry-run [--root <repo>]\n  jira render <plan-file> [--root <repo>] [--json]\n  jira apply <ticket-key-or-plan-file> --comment|--update|--transition|--link [--dry-run] [--json]\n`;
+    return `oh-my-copilot\n\nRun \`omp\` with no arguments to launch copilot (permissions bypass OFF).\nUse \`omp help\` to show this list.\n\nCommands:\n  (no args)                                     launch copilot (bypass OFF by default)\n  version [--json]\n  list [--json]\n  setup [--dry-run] [--scope project|user] [--plugin-root <dir>] [--json]\n  doctor [--json] [--copilot-bin <path>] [--skip-copilot] [--hooks]\n  cost [--json] [--session <id>] [--days <n>]\n  launch -- <args...>\n  --madmax [args...]                          (bare-flag launch with permissions bypass; alias of --yolo)\n  team <N:role> "<task>" [--name <name>] [--json]\n  team status <name> [--json]\n  team shutdown <name> [--json]\n  team api claim-task --input '<json>' [--json]\n  team api transition-task-status --input '<json>' [--json]\n  team api send-message --input '<json>' [--json]\n  team api broadcast --input '<json>' [--json]\n  team api mailbox-list --input '<json>' [--json]\n  team api mailbox-mark-delivered --input '<json>' [--json]\n  council "<question>" [--models a,b,c|m:role:weight] [--context <text|@file>] [--rubric <text|@file>] [--synth <model>] [--probe] [--timeout <ms>] [--synth-timeout <ms>] [--min-survivors <n>] [--max-concurrency <n>] [--tmp-dir <dir>] [--json]\n  comms status [--session <name>] [--json]      (is copilot on + online? auto-discovers session)\n  comms send --text "<prompt>" [--force] [--session <name>] [--json]\n  comms recv [--wait] [--lines <n>] [--timeout <ms>] [--session <name>] [--json]\n  comms ask --text "<prompt>" [--force] [--lines <n>] [--timeout <ms>] [--session <name>] [--json]\n  gateway serve [--only <name>[,<name>]]        (run all configured connectors; today: slack)\n  gateway status [--json] [--only <name>[,...]] (per-connector readiness; no sockets opened)\n  gateway doctor [--json] [--only <name>[,...]] (alias for 'gateway status')\n  gateway notify --text "<msg>" [--target slack:C\\|D\\|G\\|U... [:thread_ts]] [--thread-ts <ts>] [--json]\n                                                (one-shot outbound Slack post; falls back to SLACK_HOME_CHANNEL)\n  slack serve                                   (deprecated alias for 'gateway serve --only slack')\n  slack doctor [--json]                         (deprecated alias for 'gateway status --only slack')\n  env init [--force]                            (interactive: write ~/.omp/.env with Slack tokens + optional SLACK_HOME_CHANNEL)\n                                                non-interactive: set OMP_INIT_BOT_TOKEN/OMP_INIT_APP_TOKEN/OMP_INIT_HOME_CHANNEL\n                                                (env vars preferred over --bot-token/--app-token/--home-channel flags)\n  (--session is optional when exactly one omp-<digits> tmux session is running)\n${registeredCommandHelpLines().join("\n")}\n  ralph start "<task>" [--max-iterations <n>] [--session-id <id>] [--json]\n  ralph status [--json]\n  ralph tick [--json]\n  ralph cancel [--json]\n  ultrawork start "<objective>" [--task-count <n>] [--summary <s>] [--json]\n  ultrawork status [--json]\n  ultrawork cancel [--json]\n  ultraqa start "<goal>" [--max-cycles <n>] [--json]\n  ultraqa cycle pass|fail|pending [--json]\n  ultraqa status [--json]\n  ultraqa cancel [--json]\n  schedule add --id <id> --cron "<expr>" --prompt "<text>" [--bin copilot] [--model <m>] [--cwd <dir>] [--timeout <ms>] [--max-runs <n>] [--ttl-hours <h>] [--allow-all-tools] [--notify-target slack:<ID>] [--notify-desktop] [--notify-open-omp] [--dry-run] [--json]
+                                                (--notify-desktop: native OS notification on completion [macOS uses osascript]; --notify-open-omp: click opens an omp session in the state root — needs OMP_NOTIFY_USE_TERMINAL_NOTIFIER=1 + terminal-notifier on macOS)\n  schedule list [--json]\n  schedule status <id> [--json]\n  schedule open <id> [--tmux] [--json]          (show this id's latest status + full output; --tmux instead opens an interactive omp session in the project — recent runs show via the startup banner)\n  schedule run-now <id> [--json]\n  schedule remove <id> [--json]\n  goal set "<objective>" [--json]\n  goal read [--json]\n  memory sync [--json]                          (render goal+directives into copilot-instructions.md)\n  config get [--json] | config set memory-mode on|off | config set memory-review-model <slug> | config set memory-review-min-messages <n> [--global]\n                                                (--global writes ~/.omp/config.json; applies to every project. project .omp/config.json overrides it)\n  memory-review --session <uuid|latest> [--model <slug>] [--json]   (cheap-model end-of-session review; opt-in via memory-mode)\n  daily-log set-goal "<text>" [--json]\n  daily-log add "<text>" [--json]\n  daily-log read [--days <n>] [--json]\n  daily-log prune [--keep-days <n>] [--json]\n  state write <key> <val> [--ttl <s>] | read|delete|status <key> | list | cleanup [--json]\n  project-memory read [<id>] | index | add-note "<title>" [--body "<text>"] | add-directive "<rule>" | prune-notes --keep <n>|--older-than <days> [--json]\n  trace timeline [<sessionId>] [--limit <n>] | summary [<sessionId>] | add <sessionId> <event> [<json>] [--json]\n  catalog list [--json]\n  catalog validate [--json]\n  catalog capability <id> [--json]\n  project inspect [--json]\n  skill install <skill-dir> [--root <repo>] [--scope project|user] [--dry-run] [--json]\n  lint:skills [--root <repo>]\n  sync:dry-run [--root <repo>]\n  jira:dry-run [--root <repo>]\n  jira render <plan-file> [--root <repo>] [--json]\n  jira apply <ticket-key-or-plan-file> --comment|--update|--transition|--link [--dry-run] [--json]\n`;
 }
 async function resolveExistingInputPath(value) {
     const { existsSync } = await import("node:fs");
@@ -40,6 +41,33 @@ async function resolveExistingInputPath(value) {
     return direct;
 }
 const BARE_LAUNCH_FLAGS = new Set(["--madmax", "--yolo"]);
+// Snapshot existing Copilot session dirs BEFORE launch, so after a headless run
+// we can identify the exact session it created (instead of guessing "latest").
+async function snapshotSessionsForReview() {
+    try {
+        const { listSessionIds } = await import("./memory-review/transcript.js");
+        return listSessionIds();
+    }
+    catch {
+        return [];
+    }
+}
+// Headless `copilot -p` skips hooks, so when omp launched copilot in headless
+// mode we detach the end-of-session memory review here. We review the session
+// that appeared since `before` — never a guessed "latest" — and skip if none
+// is identifiable. Best-effort: a failure here must never affect the launch.
+async function maybeTriggerHeadlessReview(argv, cwd, before) {
+    try {
+        const { triggerHeadlessReview } = await import("./memory-review/trigger.js");
+        const { newestSessionSince } = await import("./memory-review/transcript.js");
+        const cliPath = join(packageRootFromImportMeta(import.meta.url), "dist", "src", "cli.js");
+        const sessionId = newestSessionSince(before) ?? "";
+        triggerHeadlessReview({ cwd, argv, cliPath, sessionId });
+    }
+    catch {
+        // never fail a launch on the review trigger
+    }
+}
 export async function runCli(argv = process.argv.slice(2)) {
     const [group, command, value] = argv;
     const json = hasFlag(argv, "--json");
@@ -70,11 +98,14 @@ export async function runCli(argv = process.argv.slice(2)) {
     // case argv is empty, so normalizeCopilotLaunchArgs emits no --yolo.
     if (!group || BARE_LAUNCH_FLAGS.has(group)) {
         const { launchCopilot } = await import("./copilot/launch.js");
+        const launchCwd = flagValue(argv, "--root") ?? process.cwd();
+        const beforeSessions = await snapshotSessionsForReview();
         const result = await launchCopilot({
             args: argv,
             bin: flagValue(argv, "--bin"),
-            cwd: flagValue(argv, "--root") ?? process.cwd(),
+            cwd: launchCwd,
         });
+        await maybeTriggerHeadlessReview(argv, launchCwd, beforeSessions);
         return json
             ? { ok: result.ok, exitCode: result.exitCode, output: result }
             : {
@@ -125,11 +156,14 @@ export async function runCli(argv = process.argv.slice(2)) {
         const dashIndex = argv.indexOf("--");
         const passthrough = dashIndex >= 0 ? argv.slice(dashIndex + 1) : argv.slice(1);
         const { launchCopilot } = await import("./copilot/launch.js");
+        const launchCwd = flagValue(argv, "--root") ?? process.cwd();
+        const beforeSessions = await snapshotSessionsForReview();
         const result = await launchCopilot({
             args: passthrough,
             bin: flagValue(argv, "--bin"),
-            cwd: flagValue(argv, "--root") ?? process.cwd(),
+            cwd: launchCwd,
         });
+        await maybeTriggerHeadlessReview(passthrough, launchCwd, beforeSessions);
         return json
             ? { ok: result.ok, exitCode: result.exitCode, output: result }
             : {
@@ -201,6 +235,80 @@ export async function runCli(argv = process.argv.slice(2)) {
         }
         return { ok: false, exitCode: 1, message: "Unknown memory subcommand. Try: memory sync" };
     }
+    if (group === "config") {
+        const { readMemoryConfig, setMemoryConfigValue } = await import("./memory-review/config.js");
+        const cwd = flagValue(argv, "--root") ?? process.cwd();
+        // OMP_HOME_OVERRIDE relocates the global ~/.omp config dir (test seam; also
+        // lets users point at a custom home). Undefined => os.homedir() default.
+        const homeDir = process.env.OMP_HOME_OVERRIDE || undefined;
+        // `--global` writes to ~/.omp/config.json so the setting applies everywhere.
+        const scope = hasFlag(argv, "--global") ? "global" : "project";
+        if (command === "get" || command === undefined) {
+            const cfg = readMemoryConfig(cwd, { homeDir });
+            return json
+                ? { ok: true, output: cfg }
+                : {
+                    ok: true,
+                    message: `memory-mode=${cfg.memoryMode}\nmemory-review-model=${cfg.memoryReviewModel}\nmemory-review-min-messages=${cfg.memoryReviewMinMessages}`,
+                };
+        }
+        if (command === "set") {
+            const setVal = argv[3];
+            const where = scope === "global" ? " (global ~/.omp)" : "";
+            if (value === "memory-mode") {
+                if (setVal !== "on" && setVal !== "off") {
+                    return { ok: false, exitCode: 1, message: "usage: omp config set memory-mode on|off [--global]" };
+                }
+                setMemoryConfigValue(cwd, "memoryMode", setVal, { scope, homeDir });
+                return json ? { ok: true, output: { memoryMode: setVal, scope } } : { ok: true, message: `memory-mode=${setVal}${where}` };
+            }
+            if (value === "memory-review-model") {
+                if (!setVal || setVal.startsWith("-")) {
+                    return { ok: false, exitCode: 1, message: "usage: omp config set memory-review-model <slug> [--global]" };
+                }
+                setMemoryConfigValue(cwd, "memoryReviewModel", setVal, { scope, homeDir });
+                return json ? { ok: true, output: { memoryReviewModel: setVal, scope } } : { ok: true, message: `memory-review-model=${setVal}${where}` };
+            }
+            if (value === "memory-review-min-messages") {
+                const n = Number(setVal);
+                if (!Number.isFinite(n) || n < 0) {
+                    return { ok: false, exitCode: 1, message: "usage: omp config set memory-review-min-messages <non-negative integer> [--global]" };
+                }
+                setMemoryConfigValue(cwd, "memoryReviewMinMessages", String(Math.floor(n)), { scope, homeDir });
+                return json ? { ok: true, output: { memoryReviewMinMessages: Math.floor(n), scope } } : { ok: true, message: `memory-review-min-messages=${Math.floor(n)}${where}` };
+            }
+            return { ok: false, exitCode: 1, message: "Unknown config key. Try: memory-mode | memory-review-model | memory-review-min-messages" };
+        }
+        return { ok: false, exitCode: 1, message: "Unknown config subcommand. Try: config get | config set <key> <value>" };
+    }
+    if (group === "memory-review") {
+        const { runMemoryReview } = await import("./memory-review/index.js");
+        const { createReviewSpawn } = await import("./memory-review/spawn.js");
+        const { isValidSessionId, latestSessionId } = await import("./memory-review/transcript.js");
+        const cwd = flagValue(argv, "--root") ?? process.cwd();
+        let sessionId = flagValue(argv, "--session") ?? "";
+        if (!sessionId || sessionId === "latest") {
+            sessionId = latestSessionId() ?? "";
+        }
+        if (!sessionId) {
+            return { ok: false, exitCode: 1, message: "usage: omp memory-review --session <uuid|latest>" };
+        }
+        if (!isValidSessionId(sessionId)) {
+            return { ok: false, exitCode: 1, message: "invalid --session id" };
+        }
+        const res = await runMemoryReview({
+            cwd,
+            sessionId,
+            spawn: createReviewSpawn(flagValue(argv, "--bin")),
+            model: flagValue(argv, "--model"),
+        });
+        return json
+            ? { ok: true, output: res }
+            : {
+                ok: true,
+                message: res.ran ? `memory-review ran: ${JSON.stringify(res.summary)}` : `memory-review skipped: ${res.reason}`,
+            };
+    }
     if (group === "daily-log") {
         const { setDailyGoal, addLogEntry, readDailyLog, pruneDailyLog } = await import("./daily-log.js");
         const cwd = flagValue(argv, "--root") ?? process.cwd();
@@ -313,6 +421,20 @@ export async function runCli(argv = process.argv.slice(2)) {
         if (command === "index") {
             return { ok: true, output: { notes: pm.noteIndex(cwd) } };
         }
+        if (command === "prune-notes") {
+            const keepRaw = flagValue(argv, "--keep");
+            const olderRaw = flagValue(argv, "--older-than");
+            const keep = keepRaw !== undefined && Number.isFinite(Number(keepRaw)) ? Number(keepRaw) : undefined;
+            const olderThanDays = olderRaw !== undefined && Number.isFinite(Number(olderRaw)) ? Number(olderRaw) : undefined;
+            if (keep === undefined && olderThanDays === undefined) {
+                return { ok: false, exitCode: 1, message: "usage: omp project-memory prune-notes --keep <n> | --older-than <days>" };
+            }
+            const removed = pm.pruneNotes(cwd, { keep, olderThanDays });
+            syncInstructionsMemory(cwd); // refresh the managed block after pruning
+            return json
+                ? { ok: true, output: { removed } }
+                : { ok: true, message: `pruned ${removed.length} note${removed.length === 1 ? "" : "s"}` };
+        }
         if (command === "read" || command === undefined) {
             // `read <id>` loads one note's body on demand; bare `read` returns the
             // bounded summary (directives + note index — never note bodies).
@@ -327,7 +449,7 @@ export async function runCli(argv = process.argv.slice(2)) {
         return {
             ok: false,
             exitCode: 1,
-            message: 'Unknown project-memory subcommand. Try: project-memory read [<id>] | index | add-note "<title>" [--body "<text>"] | add-directive "<rule>"',
+            message: 'Unknown project-memory subcommand. Try: project-memory read [<id>] | index | add-note "<title>" [--body "<text>"] | add-directive "<rule>" | prune-notes --keep <n>|--older-than <days>',
         };
     }
     if (group === "trace") {
@@ -1242,6 +1364,8 @@ async function handleScheduleCommand(argv, json) {
             allowAllTools: hasFlag(argv, "--allow-all-tools"),
             dryRun: hasFlag(argv, "--dry-run"),
             notifyTarget,
+            notifyDesktop: hasFlag(argv, "--notify-desktop"),
+            notifyOpenOmp: hasFlag(argv, "--notify-open-omp"),
         });
         return json
             ? { ok: result.ok, exitCode: result.ok ? 0 : 1, output: result }
@@ -1278,10 +1402,39 @@ async function handleScheduleCommand(argv, json) {
             ? { ok: result.ok, exitCode: result.ok ? 0 : 1, output: result }
             : { ok: result.ok, exitCode: result.ok ? 0 : 1, message: result.message };
     }
+    if (command === "open" && targetId) {
+        const r = mod.openScheduleResult(cwd, targetId);
+        if (!r.ok)
+            return { ok: false, exitCode: 1, output: json ? r : undefined, message: r.error };
+        // --tmux: drop into an interactive omp session (auto-wrapped in tmux by
+        // launchCopilot) rooted at the project. The SessionStart [SCHEDULE RESULTS]
+        // banner surfaces RECENT unseen results across all jobs (not pinned to <id>,
+        // and cursor-gated) — for this id's exact output use `schedule open <id>`
+        // without --tmux. We resolve <id> first only to fail fast on a bad id.
+        if (hasFlag(argv, "--tmux")) {
+            const { launchCopilot } = await import("./copilot/launch.js");
+            const result = await launchCopilot({ args: [], cwd, env: { ...process.env, OMP_FORCE_TMUX_WRAP: "1" } });
+            return {
+                ok: result.ok,
+                exitCode: result.exitCode,
+                message: result.ok ? undefined : `failed to launch omp in tmux (exit ${result.exitCode})`,
+            };
+        }
+        if (json)
+            return { ok: true, output: r };
+        const j = r.job;
+        const header = `${j.id} — ${j.lastStatus ?? "(never run)"} @ ${j.lastRunAt ?? "-"}\n${j.lastSummary ?? ""}`.trim();
+        const body = r.logContent
+            ? `\n\n--- full output (${j.lastLogPath}) ---\n${r.logContent}`
+            : j.lastRunAt
+                ? `\n(log not found: ${j.lastLogPath ?? "n/a"})`
+                : "\n(no run recorded yet)";
+        return { ok: true, message: header + body };
+    }
     return {
         ok: false,
         exitCode: 1,
-        message: 'Unknown schedule subcommand. Try: schedule add --id <id> --cron "<expr>" --prompt "<text>" | list | status <id> | remove <id> | run-now <id>',
+        message: 'Unknown schedule subcommand. Try: schedule add --id <id> --cron "<expr>" --prompt "<text>" | list | status <id> | open <id> | remove <id> | run-now <id>',
     };
 }
 function isEntrypoint() {