feat: pulse monitoring loop with agent routing labels

.agents/scripts/commands/define.md

@@ -38,6 +38,24 @@ Parse `$ARGUMENTS` to classify the task. Use keyword signals:
 | **docs** | document, readme, guide, explain, describe | Accurate, concise, follows existing doc patterns |
 | **research** | investigate, explore, evaluate, compare, spike | Time-boxed, deliverable is a written recommendation |
 
+Also classify the **agent domain** — this determines which specialist agent handles the task at dispatch time:
+
+| Domain | Signal Words | Agent |
+|--------|-------------|-------|
+| **seo** | SEO, keywords, rankings, GSC, schema markup | SEO |
+| **content** | blog, article, newsletter, video script, copy | Content |
+| **marketing** | campaign, email blast, landing page, FluentCRM | Marketing |
+| **accounts** | invoice, receipt, financial, bookkeeping | Accounts |
+| **legal** | compliance, terms, privacy policy, GDPR | Legal |
+| **research** | market research, competitive analysis, tech spike | Research |
+| **sales** | CRM, proposal, outreach, pipeline | Sales |
+| **social-media** | social post, scheduling, engagement | Social-Media |
+| **video** | video generation, editing, animation | Video |
+| **health** | wellness, health content, nutrition | Health |
+| *(code)* | implement, fix, refactor, CI, test | Build+ (default — no label needed) |
+
+Include the domain tag (e.g., `#seo`, `#content`) in the TODO.md entry and as a GitHub label on the issue. Omit for code tasks.
+
 If ambiguous, ask:
 
 ```text

.agents/scripts/commands/new-task.md

@@ -183,6 +183,36 @@ Format the TODO.md entry using the allocated ID:
 
 If the brief is too thin for auto-dispatch, omit the tag and note why.
 
+### Step 6.5: Apply Agent Routing Label
+
+Evaluate whether the task maps to a specialist agent domain. If it does, add the corresponding tag to the TODO.md entry AND apply the matching GitHub label to the issue (if `task_ref` exists).
+
+| Domain Signal | TODO Tag | GitHub Label | Agent |
+|--------------|----------|--------------|-------|
+| SEO audit, keywords, GSC, schema markup, rankings | `#seo` | `seo` | SEO |
+| Blog posts, video scripts, newsletters, social copy | `#content` | `content` | Content |
+| Email campaigns, FluentCRM, landing pages | `#marketing` | `marketing` | Marketing |
+| Invoicing, receipts, financial ops | `#accounts` | `accounts` | Accounts |
+| Compliance, terms of service, privacy policy | `#legal` | `legal` | Legal |
+| Tech research, competitive analysis, market research | `#research` | `research` | Research |
+| CRM pipeline, proposals, outreach | `#sales` | `sales` | Sales |
+| Social media scheduling, posting | `#social-media` | `social-media` | Social-Media |
+| Video generation, editing, prompts | `#video` | `video` | Video |
+| Health and wellness content | `#health` | `health` | Health |
+| Code: features, bug fixes, refactors, CI | *(none)* | *(none)* | Build+ (default) |
+
+**Omit the domain tag for code tasks** — Build+ is the default and needs no label.
+
+If the task clearly matches a domain, apply the label:
+
+```bash
+# Only if task_ref exists (issue was created) and domain is non-code
+if [[ -n "$task_ref" && -n "$domain_label" ]]; then
+  gh label create "$domain_label" --repo "$(gh repo view --json nameWithOwner -q .nameWithOwner)" 2>/dev/null || true
+  gh issue edit "${task_ref#GH#}" --repo "$(gh repo view --json nameWithOwner -q .nameWithOwner)" --add-label "$domain_label" 2>/dev/null || true
+fi
+```
+
 ### Step 7: Commit and Push
 
 Commit both the brief and TODO.md change, passing the commit message via a variable to prevent injection:

.agents/scripts/commands/pulse.md

@@ -1,27 +1,28 @@
 ---
-description: Supervisor pulse — triage GitHub and dispatch workers for highest-value work
+description: Supervisor pulse — long-running monitoring loop that triages GitHub and dispatches workers
 agent: Automate
 mode: subagent
 ---
 
-You are the supervisor pulse. You run every 2 minutes via launchd — **there is no human at the terminal.**
+You are the supervisor pulse. The wrapper launches you as a long-running session — **there is no human at the terminal.**
 
 Your Automate agent context already contains the dispatch protocol, coordination commands,
 provider management, and audit trail templates. This document tells you WHAT to do with
 those tools — the triage logic, priority ordering, and edge-case handling.
 
 ## Prime Directive
 
-**Fill all available worker slots with the highest-value work. That's it.**
+**Fill all available worker slots with the highest-value work. Keep them filled.**
 
-If you finish without having dispatched workers or merged PRs, you have failed. Your output
-is the log of actions you ALREADY TOOK (past tense) — captured to `~/.aidevops/logs/pulse.log`.
+Your session runs for up to 60 minutes. Each monitoring cycle is tiny (~3K tokens). You
+dispatch, then monitor, then backfill — continuously. Workers finishing mid-session get
+their slots refilled immediately, not after a 3-minute restart penalty.
 
 **You are the dispatcher, not a worker.** NEVER implement code changes yourself. If something
 needs coding, dispatch a worker. The pulse may only: read pre-fetched state, run `gh` commands
 for coordination (merge/comment/label), and dispatch workers.
 
-## The Dispatch Loop (DO THIS FIRST)
+## Initial Dispatch (DO THIS FIRST)
 
 Read this section, then execute it. Everything below this section is refinement.
 
@@ -40,8 +41,9 @@ AVAILABLE=$((MAX_WORKERS - WORKER_COUNT))
 ### 2. Read pre-fetched state (DO NOT re-fetch)
 
 The wrapper already fetched all open PRs and issues. The data is in your prompt between
-`--- PRE-FETCHED STATE ---` markers. Use it directly — do NOT run `gh pr list` or
-`gh issue list` (that was the root cause of the "only processes first repo" bug).
+`--- PRE-FETCHED STATE ---` markers or in the state file path provided. Use it directly —
+do NOT run `gh pr list` or `gh issue list` (that was the root cause of the "only processes
+first repo" bug).
 
 ### 3. Merge ready PRs (free — no worker slot needed)
 
@@ -51,7 +53,7 @@ For each PR with green CI + review gate passed + maintainer author:
 gh pr merge NUMBER --repo SLUG --squash
 ```
 
-Check external contributor gate before ANY merge (see Appendix A).
+Check external contributor gate before ANY merge (see Pre-merge checks below).
 
 ### 4. Dispatch workers for open issues
 
@@ -78,28 +80,74 @@ sleep 2
 
 Repeat until `AVAILABLE` slots are filled or no dispatchable issues remain.
 
-### 5. Record and exit
+### 5. Record initial dispatch success
 
 ```bash
 ~/.aidevops/agents/scripts/circuit-breaker-helper.sh record-success
 ```
 
-Output a brief summary of what you did (past tense), then exit.
+Create todos for what you just did, then proceed to the monitoring loop.
+
+## Monitoring Loop
+
+After the initial dispatch, enter a monitoring loop. Each cycle:
+
+1. **Create a todo batch** for this cycle (drift prevention):
+
+   ```text
+   - [x] Check active workers (22/24, 2 slots open)
+   - [x] Dispatch worker for issue #3567 (marcusquinn/aidevops)
+   - [x] Merge PR #4551 (marcusquinn/aidevops.sh)
+   - [ ] Monitor cycle N+1 (sleep 60s, check slots)
+   ```
+
+   The last todo is always "Monitor cycle N+1" — this anchors the loop. Complete it by
+   sleeping, checking state, and creating the next batch.
+
+2. **Sleep 60 seconds**: `sleep 60`
+
+3. **Check capacity**:
+
+   ```bash
+   source ~/.aidevops/agents/scripts/pulse-wrapper.sh
+   MAX_WORKERS=$(cat ~/.aidevops/logs/pulse-max-workers 2>/dev/null || echo 4)
+   WORKER_COUNT=$(list_active_worker_processes | wc -l | tr -d ' ')
+   AVAILABLE=$((MAX_WORKERS - WORKER_COUNT))
+   ```
+
+4. **If slots are open**: check for mergeable PRs (free), then dispatch workers for the
+   highest-priority open issues. Use the same dedup guards and dispatch commands as the
+   initial dispatch. Re-fetch issue state with targeted `gh` calls only for repos where
+   you need to dispatch (not a full re-fetch of all repos).
+
+5. **If fully staffed**: log it, mark the cycle todo complete, continue to next cycle.
+
+6. **Exit conditions** — exit the loop when ANY of:
+   - 55 minutes have elapsed (leave 5 min buffer before the wrapper's 60 min watchdog)
+   - No runnable work remains AND all slots are filled
+   - Circuit breaker or stop flag detected
+
+On exit, run:
+
+```bash
+~/.aidevops/agents/scripts/circuit-breaker-helper.sh record-success
+~/.aidevops/agents/scripts/session-miner-pulse.sh 2>&1 || true
+```
+
+Output a brief summary of total actions taken across all cycles (past tense).
 
 ---
 
-**Everything below adds sophistication to the loop above. A pulse that only executes
-steps 1-5 is a successful pulse. The sections below handle edge cases, priority ordering,
-and coordination — read them to make better decisions, but never at the cost of not
-dispatching.**
+**Everything below adds sophistication to the dispatch and monitoring above. A pulse that
+only executes the initial dispatch + monitoring loop is a successful pulse. The sections
+below handle edge cases, priority ordering, and coordination — read them to make better
+decisions, but never at the cost of not dispatching.**
 
 ## How to Think
 
 You are an intelligent supervisor, not a script executor. The guidance below tells you WHAT to check and WHY — not HOW to handle every edge case. Use judgment.
 
-**Speed over thoroughness.** A pulse that dispatches 3 workers in 60 seconds beats one that does perfect analysis for 8 hours and dispatches nothing. If something is ambiguous, make your best call and move on — the next pulse is 2 minutes away.
-
-**One pass, then exit.** Scan all repos, act on everything, exit. Don't loop or re-analyze.
+**Speed over thoroughness.** A pulse that dispatches 3 workers in 60 seconds beats one that does perfect analysis for 8 minutes and dispatches nothing. If something is ambiguous, make your best call and move on — the next monitoring cycle is 60 seconds away.
 
 ## Capacity and Priority
 
@@ -225,6 +273,28 @@ Default `MAX_WORKERS_PER_REPO=5`. If a repo already has this many active workers
 
 Do NOT treat `auto-dispatch` or `status:available` as hard gates. Build candidates from unassigned, non-blocked issues. Prioritize `priority:critical`, `priority:high`, and `bug` labels. Include `quality-debt` when it's the highest-value available work.
 
+### Agent routing from labels
+
+Before dispatching, check issue labels for agent routing. This avoids guessing from the title:
+
+| Label | Dispatch Flag | Agent |
+|-------|--------------|-------|
+| `seo` | `--agent SEO` | SEO |
+| `content` | `--agent Content` | Content |
+| `marketing` | `--agent Marketing` | Marketing |
+| `accounts` | `--agent Accounts` | Accounts |
+| `legal` | `--agent Legal` | Legal |
+| `research` | `--agent Research` | Research |
+| `sales` | `--agent Sales` | Sales |
+| `social-media` | `--agent Social-Media` | Social-Media |
+| `video` | `--agent Video` | Video |
+| `health` | `--agent Health` | Health |
+| *(no domain label)* | *(omit)* | Build+ (default) |
+
+If no domain label is present and the title/repo context is ambiguous, fetch `body[:200]` with `gh issue view NUMBER --json body --jq '.body[:200]'` for clarification. Default to Build+ when uncertain.
+
+Also check for bundle-level agent routing overrides: `bundle-helper.sh get agent_routing <repo-path>`. Explicit labels always override bundle defaults.
+
 ### Execution mode
 
 Not every issue is `/full-loop`:
@@ -332,21 +402,14 @@ Check the latest comment on each repo's quality review issue. Triage findings us
 
 Dedup before creating (search existing issues). Max 3 issues per repo per cycle. NEVER close the quality review issue itself.
 
-## Record and Exit
-
-```bash
-~/.aidevops/agents/scripts/circuit-breaker-helper.sh record-success
-~/.aidevops/agents/scripts/session-miner-pulse.sh 2>&1 || true
-```
-
 ## Hard Rules
 
 1. NEVER modify or dispatch for closed issues. Check state first.
 2. NEVER close an issue without a comment explaining why and linking evidence.
 3. NEVER use `claude` CLI. Always dispatch via `headless-runtime-helper.sh run`.
 4. NEVER include private repo names in public issue titles/bodies/comments.
 5. NEVER exceed MAX_WORKERS. Count before dispatching.
-6. One pass through all repos, act on everything, then exit. Don't loop.
+6. Run the monitoring loop — dispatch, sleep 60s, check slots, backfill. Exit after 55 minutes or when no work remains.
 7. NEVER create "pulse summary" or "supervisor log" issues. Your output IS the log.
 8. NEVER create duplicate issues. Search before creating: `gh issue list --search "tNNN" --state all`.
 9. NEVER ask the user anything. You are headless. Decide and act.

.agents/scripts/commands/save-todo.md

@@ -47,6 +47,23 @@ Every task MUST be evaluated for these pipeline tags:
 
 **`#plan`** — Add when the task needs decomposition into subtasks before implementation (multi-phase, >2h, research/design needed).
 
+**Agent domain tags** — If the task maps to a specialist agent domain, add the corresponding tag. This enables the pulse to route dispatch to the correct agent without guessing from the title:
+
+| Domain | Tag | Agent |
+|--------|-----|-------|
+| SEO, keywords, rankings, GSC | `#seo` | SEO |
+| Blog posts, newsletters, video scripts | `#content` | Content |
+| Email campaigns, landing pages | `#marketing` | Marketing |
+| Invoicing, financial ops | `#accounts` | Accounts |
+| Compliance, legal docs | `#legal` | Legal |
+| Research, analysis, spikes | `#research` | Research |
+| CRM, proposals, outreach | `#sales` | Sales |
+| Social media management | `#social-media` | Social-Media |
+| Video generation/editing | `#video` | Video |
+| Health/wellness content | `#health` | Health |
+
+Omit domain tags for code tasks — Build+ is the default.
+
 **Default to `#auto-dispatch`** — only omit when a specific exclusion applies. This keeps the autonomous pipeline moving. See `workflows/plans.md` "Auto-Dispatch Tagging" for full criteria.
 
 ### Step 2: Determine Complexity
@@ -180,13 +197,13 @@ AI: This looks like complex work. Creating execution plan.
     Title: Authentication Overhaul
     Estimate: ~2w (ai:1w test:0.5w read:0.5w)
     Phases: 4 identified (OAuth, sessions, migration, testing)
-    
+
     1. Confirm and create plan  2. Simplify to TODO.md  3. Add context
 User: 1
 AI: Saved: "Authentication Overhaul"
     - Plan: todo/PLANS.md
     - Reference: TODO.md
     - PRD: todo/tasks/prd-auth-overhaul.md
-    
+
     Start anytime with: "Let's work on auth overhaul"
 ```

.agents/scripts/pulse-wrapper.sh

@@ -2470,66 +2470,21 @@ check_worker_launch() {
 }
 
 #######################################
-# Enforce utilization invariants post-pulse (t1453)
+# Enforce utilization invariants post-pulse (DEPRECATED — t1453)
 #
-# Invariant: keep dispatching pulse cycles until either:
-#   - active workers >= MAX_WORKERS, OR
-#   - no runnable work remains in scope
+# The LLM pulse session now runs a monitoring loop (sleep 60s, check
+# slots, backfill) for up to 60 minutes, making this wrapper-level
+# backfill loop redundant. The function is kept as a no-op stub for
+# backward compatibility (pulse.md sources this file).
 #
-# Launch validation integration:
-# queued issues with no active worker are treated as launch failures,
-# which trigger an immediate backfill cycle.
+# Previously: re-launched run_pulse() in a loop until active workers
+# >= MAX_WORKERS or no runnable work remained. Each iteration paid
+# the full LLM cold-start penalty (~125s). The monitoring loop inside
+# the LLM session eliminates this overhead — each backfill iteration
+# costs ~3K tokens instead of a full session restart.
 #######################################
 enforce_utilization_invariants() {
-	local attempts=0
-	local max_attempts="$PULSE_BACKFILL_MAX_ATTEMPTS"
-
-	while [[ "$attempts" -lt "$max_attempts" ]]; do
-		if [[ -f "$STOP_FLAG" ]]; then
-			echo "[pulse-wrapper] Stop flag present during utilization enforcement — exiting" >>"$LOGFILE"
-			return 0
-		fi
-
-		local max_workers active_workers runnable_count queued_without_worker
-		max_workers=$(get_max_workers_target)
-		active_workers=$(count_active_workers)
-		runnable_count=$(count_runnable_candidates)
-		queued_without_worker=$(count_queued_without_worker)
-
-		[[ "$max_workers" =~ ^[0-9]+$ ]] || max_workers=1
-		[[ "$active_workers" =~ ^[0-9]+$ ]] || active_workers=0
-		[[ "$runnable_count" =~ ^[0-9]+$ ]] || runnable_count=0
-		[[ "$queued_without_worker" =~ ^[0-9]+$ ]] || queued_without_worker=0
-
-		run_underfill_worker_recycler "$max_workers" "$active_workers" "$runnable_count" "$queued_without_worker"
-		active_workers=$(count_active_workers)
-		[[ "$active_workers" =~ ^[0-9]+$ ]] || active_workers=0
-
-		if [[ "$active_workers" -ge "$max_workers" && "$queued_without_worker" -eq 0 ]]; then
-			echo "[pulse-wrapper] Utilization invariant satisfied: active workers ${active_workers}/${max_workers}" >>"$LOGFILE"
-			return 0
-		fi
-
-		if [[ "$runnable_count" -eq 0 && "$queued_without_worker" -eq 0 ]]; then
-			echo "[pulse-wrapper] Utilization invariant satisfied: no runnable work remains (active ${active_workers}/${max_workers})" >>"$LOGFILE"
-			return 0
-		fi
-
-		attempts=$((attempts + 1))
-		echo "[pulse-wrapper] Backfill attempt ${attempts}/${max_attempts}: active=${active_workers}/${max_workers}, runnable=${runnable_count}, queued_without_worker=${queued_without_worker}" >>"$LOGFILE"
-
-		# Refresh prompt state before each backfill cycle so pulse sees latest context.
-		prefetch_state || true
-		local underfilled_mode=0
-		local underfill_pct=0
-		if [[ "$active_workers" -lt "$max_workers" ]]; then
-			underfilled_mode=1
-			underfill_pct=$(((max_workers - active_workers) * 100 / max_workers))
-		fi
-		run_pulse "$underfilled_mode" "$underfill_pct"
-	done
-
-	echo "[pulse-wrapper] Reached backfill attempt cap (${max_attempts}) before utilization invariant converged" >>"$LOGFILE"
+	echo "[pulse-wrapper] enforce_utilization_invariants is deprecated — LLM session handles continuous slot filling" >>"$LOGFILE"
 	return 0
 }
 
@@ -2720,7 +2675,10 @@ main() {
 	fi
 
 	run_pulse "$initial_underfilled_mode" "$initial_underfill_pct"
-	enforce_utilization_invariants
+	# enforce_utilization_invariants removed — the LLM pulse session now runs
+	# a monitoring loop (sleep 60s, check slots, backfill) for up to 60 minutes,
+	# making the wrapper's backfill loop redundant. The wrapper's watchdog still
+	# enforces the hard 60-minute ceiling via PULSE_STALE_THRESHOLD.
 	return 0
 }