@axiomantic/garden 0.2.7 → 0.2.8

package/SKILL.md

@@ -295,12 +295,11 @@ To prevent silent deadlocks when workers stall, crash, or fail to re-arm listene
 2. **Watchdog Window**: If a worker fails to respond within the expected turn window (e.g. 5–10 minutes) and `rhizo probe` reveals `NO_LISTENER` or unread inbox items:
    - **Escalate Immediately**: Prompt the operator via `ask_question` with the diagnostic status.
    - **Actionable Remediation**: Offer options to (1) re-arm the listener in the worker's terminal session (`rhizo listen <worker>`), (2) reboot the agent harness, or (3) reassign the task via `rhizo reroute <worker> <new_worker>`.
-3. **Orchestrator Self-Audit Watchdog & Stepped Backoff Protocol (GVR-014, GVR-015)**:
-   - For harnesses supporting `schedule` (e.g. Antigravity), arm a debounced watchdog timer (`schedule(DurationSeconds=cadence, Prompt="...", TimerCondition="any")`).
-   - **Stepped Backoff & 4-Strike Cap**: Starts at base 15m (900s). On consecutive quiescent checks with a stable listener, backs off (15m $\rightarrow$ 30m $\rightarrow$ 60m $\rightarrow$ 120m) and stands down at check 4 (`recommended_cadence=0`), preventing infinite token-eating polling loops.
+3. **Orchestrator Self-Audit Watchdog (ONLY for OpenAI Codex / ChatGPT)**:
+   - **Antigravity & OpenCode Exemption**: In Google Antigravity and OpenCode, DO NOT schedule timers or cron tasks (`schedule(...)`). Antigravity natively and reactively wakes up on background process completion when `rhizo listen` delivers a message.
+   - **Codex / ChatGPT Watchdog Only**: In OpenAI Codex Desktop / CLI where background processes cannot reactively wake the harness, arm a scheduled watchdog timer or cron job with stepped backoff (15m $\rightarrow$ 30m $\rightarrow$ 60m $\rightarrow$ 120m $\rightarrow$ Stand Down at check 4).
    - **Reset Invariant**: Resets immediately to base 15m (streak 0) on any listener failure, unread inbox backlog, outbound task dispatch (`rhizo send`/`enqueue`), worker reply, or user chat prompt.
-   - **Replace, Never Stack**: Kills previous timer via `manage_task(Action='kill')` before arming a new one. Arriving worker traffic cancels the timer automatically with zero token overhead.
-   - When the timer fires, execute the short check: `rhizo watchdog check --agent <orchestrator> --json` and follow `next_action` (`SCHEDULE_TIMER` or `STAND_DOWN`).
+   - When the timer fires in Codex, execute the short check: `rhizo watchdog check --agent <orchestrator> --json` and follow `next_action` (`SCHEDULE_TIMER` or `STAND_DOWN`).
 
 ---
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@axiomantic/garden",
-  "version": "0.2.7",
+  "version": "0.2.8",
   "description": "Multi-Agent Swarm Orchestration, Empirical Dialectics & Ceremonies on top of Rhizo & Vine",
   "main": "bin/run.js",
   "bin": {

package/skills/garden/SKILL.md

@@ -295,12 +295,11 @@ To prevent silent deadlocks when workers stall, crash, or fail to re-arm listene
 2. **Watchdog Window**: If a worker fails to respond within the expected turn window (e.g. 5–10 minutes) and `rhizo probe` reveals `NO_LISTENER` or unread inbox items:
    - **Escalate Immediately**: Prompt the operator via `ask_question` with the diagnostic status.
    - **Actionable Remediation**: Offer options to (1) re-arm the listener in the worker's terminal session (`rhizo listen <worker>`), (2) reboot the agent harness, or (3) reassign the task via `rhizo reroute <worker> <new_worker>`.
-3. **Orchestrator Self-Audit Watchdog & Stepped Backoff Protocol (GVR-014, GVR-015)**:
-   - For harnesses supporting `schedule` (e.g. Antigravity), arm a debounced watchdog timer (`schedule(DurationSeconds=cadence, Prompt="...", TimerCondition="any")`).
-   - **Stepped Backoff & 4-Strike Cap**: Starts at base 15m (900s). On consecutive quiescent checks with a stable listener, backs off (15m $\rightarrow$ 30m $\rightarrow$ 60m $\rightarrow$ 120m) and stands down at check 4 (`recommended_cadence=0`), preventing infinite token-eating polling loops.
+3. **Orchestrator Self-Audit Watchdog (ONLY for OpenAI Codex / ChatGPT)**:
+   - **Antigravity & OpenCode Exemption**: In Google Antigravity and OpenCode, DO NOT schedule timers or cron tasks (`schedule(...)`). Antigravity natively and reactively wakes up on background process completion when `rhizo listen` delivers a message.
+   - **Codex / ChatGPT Watchdog Only**: In OpenAI Codex Desktop / CLI where background processes cannot reactively wake the harness, arm a scheduled watchdog timer or cron job with stepped backoff (15m $\rightarrow$ 30m $\rightarrow$ 60m $\rightarrow$ 120m $\rightarrow$ Stand Down at check 4).
    - **Reset Invariant**: Resets immediately to base 15m (streak 0) on any listener failure, unread inbox backlog, outbound task dispatch (`rhizo send`/`enqueue`), worker reply, or user chat prompt.
-   - **Replace, Never Stack**: Kills previous timer via `manage_task(Action='kill')` before arming a new one. Arriving worker traffic cancels the timer automatically with zero token overhead.
-   - When the timer fires, execute the short check: `rhizo watchdog check --agent <orchestrator> --json` and follow `next_action` (`SCHEDULE_TIMER` or `STAND_DOWN`).
+   - When the timer fires in Codex, execute the short check: `rhizo watchdog check --agent <orchestrator> --json` and follow `next_action` (`SCHEDULE_TIMER` or `STAND_DOWN`).
 
 ---
 

package/skills/launch-workers/SKILL.md

@@ -104,8 +104,9 @@ The Orchestrator presents the generated prompt blocks to the operator with clear
    - `rhizo open "<name>" "<tags>"`
    - `rhizo hook install --codex --agent "<name>"` (if running in Codex CLI/Desktop)
    - `rhizo listen "<name>"` (blocking foreground command with infinite wait)
-5. **Scheduled Health Check Template (For Codex / Antigravity / Schedulers)**:
-   If workers configure a recurring 15-minute listener health check, prompts include the bulletproof 4-step template:
+5. **Scheduled Health Check Template (ONLY for OpenAI Codex / ChatGPT CLI)**:
+   In Google Antigravity (using background `run_command`) and OpenCode (using background ear), DO NOT configure scheduled tasks; reactive background process completion handles wakeups natively.
+   In Codex Desktop / CLI where sessions cannot wake from background process exits without external stimulation, prompts include the bulletproof 4-step template:
    - STEP 1: Inspect completed subagents/tasks for unhandled delivered tasks and execute them immediately (never stay quiet with pending work).
    - STEP 2: Inspect active tasks to verify a listener is currently running, and re-arm if missing.
    - STEP 3: Run `rhizo probe <name> --json` and drain any inbox backlog.

package/skills/orchestrate-swarm/SKILL.md

@@ -85,9 +85,9 @@ Whenever the Lead Orchestrator dispatches a task, broadcasts instructions, or aw
 
 FORBIDDEN: Never yield the conversation turn to the operator after dispatching work without an active background listener running. Yielding a turn without a listener severs the swarm's physical lifeline, trapping worker replies in Redis and causing silent swarm stalls.
 
-Safety Net (Scheduled Timer Watchdog & Debouncer Protocol — Stepped Backoff & 4-Strike Cap):
-In harnesses supporting `schedule` (e.g. Google Antigravity), arm a debounced watchdog timer to ensure an orchestrator session is never abandoned if a listener fails to arm or terminates prematurely.
-- **Base Cadence & Stepped Backoff**:
+Safety Net (Scheduled Watchdog Protocol — ONLY for OpenAI Codex / ChatGPT):
+- **Antigravity & OpenCode Exemption**: In Google Antigravity (using background `run_command(CommandLine="rhizo listen <orchestrator>", IsDaemon=false, WaitMsBeforeAsync=500)`) and OpenCode (using background ear), DO NOT schedule timers or cron tasks (`schedule(...)`). Antigravity's task manager natively and reactively resumes execution on process exit when `rhizo listen` delivers a message, with zero timer overhead.
+- **Codex / ChatGPT Watchdog Only**: In OpenAI Codex Desktop / CLI where background processes cannot reactively wake the harness, arm a scheduled watchdog timer or cron job using stepped backoff:
   - Initial / After Activity: Base 15 minutes (`DurationSeconds=900`).
   - Quiescent Check 1 (Streak 1): 30 minutes (`DurationSeconds=1800`).
   - Quiescent Check 2 (Streak 2): 60 minutes (`DurationSeconds=3600`).
@@ -100,18 +100,14 @@ In harnesses supporting `schedule` (e.g. Google Antigravity), arm a debounced wa
   3. Any outbound task dispatch (`rhizo send`, `rhizo enqueue`, `rhizo reply`).
   4. Any worker gate report or message receipt.
   5. Any operator interaction or new prompt in chat.
-- **Replace, Never Stack Invariant**:
-  Harnesses prohibit concurrent timers with `TimerCondition="any"`. Before setting a timer, inspect running tasks with `manage_task(Action='list')`. If an existing watchdog task is active (`toolName == "schedule"` or prompt includes `[RHIZO WATCHDOG]`), cancel it via `manage_task(Action='kill', TaskId=...)`.
 - **Stand Down Invariants**:
-  1. When all tasks in `implementation_plan.md` are complete (`- [x]` 100%), kill any running watchdog timer and do not reschedule.
+  1. When all tasks in `implementation_plan.md` are complete (`- [x]` 100%), cancel any running watchdog timer and do not reschedule.
   2. When the watchdog reaches `substatus: "MAX_STREAK_REACHED"` (streak 4/4), stand down and do not reschedule. The background listener process (`rhizo listen`) remains continuously active on Redis `BRPOP` and will wake the session on any new message.
-- **Zero-Token Happy Path**:
-  Because `TimerCondition="any"` is set, any arriving worker message or background task completion automatically cancels the timer early before it expires. The timer only fires if the orchestrator was silent and deaf for the full cadence duration.
-- **The Short Check (When Timer Fires)**:
+- **The Short Check (When Timer Fires in Codex)**:
   Run `rhizo watchdog check --agent <name> --json`.
   * If `ACTION_REQUIRED: REARM_LISTENER`: start `rhizo listen <name>` in background and schedule base timer (`DurationSeconds=900`).
   * If `ACTION_REQUIRED: UNREAD_MESSAGES`: drain messages with `rhizo drain 10 <name>`, start listener, and schedule base timer (`DurationSeconds=900`).
-  * If `OK: LISTENING`: listener is healthy; check `recommended_cadence`. If `next_action == "SCHEDULE_TIMER"`, schedule timer with `DurationSeconds=recommended_cadence` and return to sleep with minimal or no user-facing chat output.
+  * If `OK: LISTENING`: listener is healthy; check `recommended_cadence`. If `next_action == "SCHEDULE_TIMER"`, schedule timer with `DurationSeconds=recommended_cadence`.
   * If `STAND_DOWN: MAX_STREAK_REACHED` or `STAND_DOWN: IDLE`: stand down and do NOT reschedule.
 </CRITICAL>