ai-agentmanager 1.2.1 → 1.3.0

package/CHANGELOG.md

@@ -1,5 +1,20 @@
 # Changelog
 
+## 1.3.0 (2026-10-31)
+
+- **Review changes:** each agent's changes in one screen: changed files, the diff file by file (new files included), line comments sent to the agent as one message, **Commit all**, and **Push & open PR** with `gh`. `agentmgr changes`, `comment`, `commit`, `pr`.
+- **Land tab:** every agent's open pull request by what it needs: ready to merge, needs fixes, behind its base, waiting, drafts, with **Merge**, **Auto-merge**, **Update** (merge the base branch in and push, or ask the agent) and **Ask to fix**. `agentmgr land`.
+- **Failing checks and requested changes go back to the agent:** once per commit, at most 3 times per pull request (`landing` in config.json).
+- **Pull request status:** checks, review decision and conflicts on each agent's pull requests.
+- **Triggers:** labeled GitHub issues start agents (in the repos or owners you list, once per issue), `/agent …` comments on an agent's pull request from the repo's owners, members or collaborators reach the agent, and `POST /api/hooks/agents` with a token starts agents from Jira automation, CI or scripts. No session watches, so no tokens are spent. **Assistant → Triggers…**, `agentmgr triggers`.
+- **Linear:** Linear issue links are recognized like Jira's (the agent is named `ENG-42`, one agent per issue for the assistant), and the assistant can watch Linear issues assigned to you.
+- **Repo memory:** agents record what they learn about a repository (`agentmgr learn`, allowed without a prompt), and every later agent there starts with it. **Repo memory** on an agent to view and tidy it, `agentmgr memory`.
+- **Playbooks:** saved requests with `{{values}}` filled in at run time, run in several projects at once (one agent each), by hand or on a schedule (every hour, day, weekday or week). **Backlog → Playbooks**, **Save as playbook…** in New agents, `agentmgr playbook`.
+- **Results:** **Results** in the top bar shows how agents did over a period: PRs opened and merged, merge rate, median time to a first PR and to merge, cost per merged PR, by engine and model, by source and by project. `agentmgr stats`.
+- **Spend and budgets:** the same dialog shows today's cost, the last two weeks and the costliest agents. A budget per agent (an alert at 80%, the session closed at 100% until you raise it) and a daily limit that stops new agents from starting. `agentmgr spend`, `agentmgr edit --budget`.
+- **Getting started:** with no agent open, a checklist shows what is set up (first agent, Slack alerts, assistant or triggers, phone access, a budget), each with the button that does it, and anything this machine is missing (from `agentmgr doctor`).
+- **Refresh** no longer does nothing when a background refresh is already running; it waits and then checks pull requests.
+
 ## 1.2.1 (2026-10-30)
 
 - **Edit an agent:** **Edit** on an agent changes its name, its request (and can tell the agent about the change), priority, permission mode and model (from its next launch). `agentmgr edit`.

package/README.md

@@ -27,6 +27,13 @@ Run one background [Claude Code](https://claude.com/claude-code) agent per inten
 - **Priority.** Mark agents P0–P3. P0 and P1 are highlighted, and lists sort by priority.
 - **Share for review.** One click writes an **Analysis**, **Design**, **Flow** or **Proposal** document from the agent's work. Copy it as Markdown, download it, or print it to PDF with diagrams.
 - **Human vs AI.** It splits the open questions about the work into the top 5 that need your judgment and the ones a model can answer from the evidence. It answers those, then a second model double-checks every answer.
+- **Review changes.** Each agent's diff file by file, line comments sent back to the agent as one message, then **Commit all** and **Push & open PR**, without leaving the page.
+- **Landing.** A **Land** tab with every agent's open pull request: ready to merge, needs fixes, behind, waiting. Failing checks and requested changes go back to the agent automatically (a few times at most); **Update**, **Ask to fix** and **Merge** in one click.
+- **Triggers.** A label on a GitHub issue starts an agent for it, `/agent …` comments on an agent's pull request reach the agent, and a webhook starts agents from Jira automation or CI. No model watches, so no tokens are spent waiting.
+- **Repo memory.** What one agent learns about a repo (how to run its tests, a gotcha) is recorded in one line and given to every later agent there.
+- **Playbooks.** Saved requests with `{{values}}`, run in several projects at once (one agent each), by hand or every hour, day, weekday or week.
+- **Results.** Merge rate, time to a first PR and to merge, and cost per merged PR, by engine and model, by source and by project.
+- **Budgets.** What agents cost today and lately, a budget per agent (an alert at 80%, closed at 100%) and a daily limit for all of them.
 - **Plan review.** Optionally, the agent writes an implementation plan and waits for your approval before changing anything.
 - **Insights.** Why, What, How and Now for any agent, three memorable points each.
 - **Explain.** One click gives a plain-language explanation of the intent and the insight behind the problem and solution. It comes from a separate tool-less Claude call, so the agent isn't interrupted.
@@ -76,13 +83,13 @@ Runs on macOS and Linux; on Windows, use WSL2. Requires Node 20+, `git`, and the
 
 ```sh
 npm install -g ai-agentmanager          # the latest release
-npm install -g ai-agentmanager@1.2.1    # or a specific one
+npm install -g ai-agentmanager@1.3.0    # or a specific one
 ```
 
 Or from the repository, at a release tag:
 
 ```sh
-git clone --branch v1.2.1 --depth 1 https://github.com/jdmunta/ai-agentmanager-core.git
+git clone --branch v1.3.0 --depth 1 https://github.com/jdmunta/ai-agentmanager-core.git
 cd ai-agentmanager-core
 npm install
 npm link            # optional: puts `agentmgr` on your PATH
@@ -102,7 +109,7 @@ npm link
 | Installed with | Update |
 | --- | --- |
 | npm | `npm install -g ai-agentmanager@latest` |
-| A clone at a release tag | `git fetch --tags && git checkout v1.2.1 && npm install` (the tag you want) |
+| A clone at a release tag | `git fetch --tags && git checkout v1.3.0 && npm install` (the tag you want) |
 | A clone of `main` | `git pull && npm install` |
 
 **Check your setup.** `agentmgr doctor` checks Node.js, Claude Code and its sign-in, git, `gh`, the data folder, the daemon's port and Chrome, and says how to fix anything missing.
@@ -369,6 +376,36 @@ Tick **Review the implementation plan first** in New agent (or the backlog), or
 
 Each card has at most **three points of about 12 words each**, so they're easy to remember and repeat. Insights uses the same context and the same separate, tool-less Claude call as Explain, so the agent isn't interrupted. Use Insights for a quick glance and Explain for the full briefing.
 
+## Review changes
+
+**Review changes** on an agent opens its changes against where its branch started (the merge base with the branch it came from), new files included:
+
+- **Files and diff.** The changed files on the left with lines added and removed, and the diff file by file on the right. Click a file header to fold it; very large files start folded.
+- **Line comments.** Click **+** next to a line (or its line number) to comment on it, and add an overall comment if you like. **Send to agent** types them into the agent as one message, each with its file, line and the code it is about, and asks it to address them. Comments not sent yet are kept in this browser.
+- **Commit all** commits everything in the worktree, new files included, with your git name and email.
+- **Push & open PR** pushes the branch and opens a pull request with `gh`, against the branch the agent started from (title from your text, or from the commits; **Draft** if you like). With a pull request already open, it pushes to it. The pull request is linked to the agent.
+
+The same from the API: `GET /api/agents/:id/changes`, `POST …/changes/comments`, `…/changes/commit`, `…/changes/pr`. Plugins can refuse a commit or a pull request (`agent.commit`, `agent.pr`).
+
+## Landing pull requests
+
+The **Land** tab lists every agent's open pull request by what it needs to get merged, ready ones first:
+
+- **Ready to merge**: checks pass and GitHub says it can merge. **Merge** merges it with `gh` (squash by default) and deletes the branch on GitHub.
+- **Needs fixes**: failing checks, changes requested, or conflicts. **Ask to fix** sends them to the agent.
+- **Behind its base**: **Update** merges the branch it targets into the agent's branch and pushes, when the agent is idle and its work is committed. Otherwise, or when the merge conflicts (it is undone), the agent is asked to do it.
+- **Waiting** for checks or a review, and **Drafts**. **Auto-merge** turns on GitHub's auto-merge, so it merges once it may.
+
+Each agent's pull requests show the same tags (checks, review, conflicts). Pull requests are checked every couple of minutes for running agents, and every few minutes for closed agents with a PR still open.
+
+**Failures go back to the agent by themselves.** When checks fail on an agent's pull request, the agent is told which ones and how to read their logs; when a reviewer requests changes, it is told to read and address the review. Each commit is reported once, and at most 3 times per pull request, so an agent can't loop on a broken main. Change this at the bottom of the Land tab, with `agentmgr land set`, or in config.json:
+
+```json
+"landing": { "fixChecks": true, "fixReviews": true, "maxFixes": 3, "mergeMethod": "squash", "deleteBranch": true }
+```
+
+From a terminal: `agentmgr land` lists them, `agentmgr land update|fix|merge <agent>` (`--auto` for auto-merge). With `agentmgr changes`, `comment`, `commit` and `pr` you can review and open the pull request too. Plugins can refuse a merge (`agent.merge`).
+
 ## Results
 
 The **Results** card is the first thing in the Brief panel, and `agentmgr show` lists it too. It shows:
@@ -469,6 +506,27 @@ Queue asks instead of starting them. Use **+ Add** in the Backlog tab, **Queue i
 
 The backlog is saved with the rest of the state.
 
+## Playbooks
+
+Saved requests you run again: **Backlog → Playbooks**, **Save as playbook…** in New agents, or `agentmgr playbook`. A playbook is a request, the projects to run it in (one agent each), and optionally a model, permission mode, priority and schedule:
+
+- **Values at run time.** Write `{{name}}` in the request for something you fill in when it runs: "Upgrade `{{package}}` to the latest version, fix what breaks and open a pull request". **Run now** asks for each value; `agentmgr playbook run Upgrade --var package=react`.
+- **Several projects at once.** "Bump the Node version" in every repo starts one agent per project.
+- **On a schedule.** Every hour, day, weekday or week at a time you pick ("every weekday at 9:00, triage yesterday's flaky tests"). A scheduled playbook needs a default for each `{{value}}`. A run missed while the daemon was off runs once when it is back. Budgets and the daily limit apply.
+
+Agents started by a playbook are marked **▶ <playbook>**, and the playbook lists the agents of its last run.
+
+```sh
+agentmgr playbook add "Flaky tests" "Find yesterday's flaky tests in CI and fix or quarantine them" --projects web,api --every weekday --at 09:00
+agentmgr playbook ls
+```
+
+## Repo memory
+
+Agents in the same repository share what they learn. When an agent finds out something non-obvious that would save the next one time (how to build or run the tests, a gotcha, where something lives, a convention that isn't written down), it records one line with `agentmgr learn "…"`, which it may run without asking. Every agent that starts in that repo afterwards gets the list with its instructions. Each line says which agent added it and when, and the same thing isn't added twice.
+
+**Repo memory → View and edit** on an agent's Workspace card shows the file to tidy (keep it short and true; it is capped at 16 KB), and `agentmgr memory <agent>` prints it. The files live in `~/.agentmanager/memory/`, one per repository. Turn it off with `"memory": false` in config.json.
+
 ## Decision inbox
 
 The **Inbox** tab (and `agentmgr inbox`) lists what needs you, across all agents:
@@ -739,6 +797,7 @@ An always-on Claude session that works on your behalf. **Assistant** in the top
 | It watches | What it does |
 |---|---|
 | Jira issues newly assigned to you | Starts an agent in the matching project, with the issue link first so the agent is named after the issue (`OPS-7`) |
+| Linear issues newly assigned to you (turn it on in the dialog) | The same, with the Linear link first (`ENG-42`) |
 | New comments and mentions on your Jira issues | Passes the comment to the agent on that issue (`agentmgr tell`), or starts one if the comment asks for new work |
 | GitHub pull requests waiting for your review | Starts a review agent that drafts the review for you to post |
 | Failing checks on your open pull requests | Tells the agent on that PR to fix it, or starts one |
@@ -758,6 +817,38 @@ agentmgr assistant pause                    # stop checking and close the sessio
 
 Settings live in `config.json` under `"assistant"`. A running assistant reads new watch lists and notes after **Pause** and **Turn on**.
 
+## Triggers
+
+Start agents from where the work lives, with no session watching and no tokens spent on it. **Assistant → Triggers…**, or `agentmgr triggers`:
+
+- **GitHub label.** Every few minutes, open issues with a label (`agentmgr` by default) in the repos or owners you list each get an agent in that repo, named `repo#12`, asked to open a pull request that fixes the issue. A project already on that repo reuses its clone. Each issue starts one agent, once. Labeling an issue needs triage access to the repo, so that is the go-ahead. **Comment on the issue** (off by default) says an agent is on it.
+- **Pull request comments.** A comment that starts with `/agent` on an agent's open pull request, from the repo's owners, members or collaborators, is typed into that agent: `/agent add a test for Safari`. On by default.
+- **Webhook.** `POST /api/hooks/agents` with `Authorization: Bearer <token>` and `{"intent": "…", "project": "<shortcut>"}` (or `"repo": "<git URL>"`, optional `"name"`, `"priority"`, `"url"`) creates an agent, for Jira automation, CI or scripts. Off until you make a token (**New token**, or `agentmgr triggers set --new-token`); the token is shown once. **Only these repos** limits where it may start agents. The daemon listens on this computer only, so other machines reach it through remote access.
+
+Agents started this way are marked **⚡ GitHub** or **⚡ webhook**, Slack alerts can announce them, and triggers start at most 20 agents a day (`maxPerDay`). Agents use your default permission mode; a webhook can't pick another. In config.json:
+
+```json
+"triggers": {
+  "github": { "enabled": true, "label": "agentmgr", "repos": ["acme/web"], "owners": [], "everyMin": 5, "comment": false },
+  "prCommands": { "enabled": true, "prefix": "/agent" },
+  "webhook": { "enabled": false, "repos": [] },
+  "maxPerDay": 20
+}
+```
+
+## Results and spend
+
+**Results** in the top bar shows how agents did over the last 7, 30 or 90 days (or all time): how many started and how many opened a pull request, PRs merged and closed, the merge rate, the median time from starting an agent to its first PR and to merge, and the cost per merged PR. The same by engine and model (which one gets merged more, for less), by where agents came from (you, the assistant, triggers, the backlog, teams, races) and by project. `agentmgr stats --days 30`.
+
+### Spend and budgets
+
+The same dialog shows what agents cost today, the last two weeks and the costliest agents, from the cost Claude Code records for each session (the API price, even on a subscription plan; Codex and Antigravity record none). Set limits there, with `agentmgr spend --per-agent 5 --per-day 50`, or in config.json (`"budgets": { "perAgentUsd": 5, "perDayUsd": 50 }`):
+
+- **Each agent.** At 80% of its budget you get an alert. At its budget its session is closed, and it doesn't start or resume until you raise its budget. **Edit** on an agent (or `agentmgr edit <agent> --budget 20`) gives it its own budget.
+- **All agents a day.** Once today's spend reaches it, no new agents start or resume, from the UI, the CLI, the backlog, triggers or the assistant, until tomorrow or a higher limit. Running agents go on.
+
+Alerts for both go to Slack with **Alerts → nears or reaches its budget**.
+
 ## Cleaning up old agents
 
 Agents you no longer use keep a session open and a worktree on disk. **Clean up** (in the top bar, or `agentmgr cleanup`) closes agents with no activity for a while and deletes agents that stayed closed long after that. Pick a strategy:

package/docs/plugins.md

@@ -53,6 +53,9 @@ Policies are synchronous so every code path can call them. Keep them fast; do sl
 | `agent.start` | Before an agent's engine is launched or resumed (including after a restart) | `agent`, `fresh` |
 | `agent.message` | Before a message is typed into an agent (`tell`, inbox replies) | `agent`, `text`, `source` |
 | `agent.remove` | Before an agent is deleted | `agent`, `deleteWorkspace` |
+| `agent.commit` | Before Commit in the review screen commits an agent's worktree | `agent`, `message` |
+| `agent.pr` | Before the review screen pushes an agent's branch and opens a pull request | `agent`, `title`, `draft` |
+| `agent.merge` | Before Merge (or auto-merge) in the Land tab merges an agent's pull request | `agent`, `url`, `method`, `auto` |
 | `terminal.open` | Before a live terminal is attached (browser, CLI `attach`, hub) | `agent`, `kind` (`claude` or `shell:N`) |
 | `hub.action` | Before an action the hub asked for, after this machine's own `hub.allow` check | `action`, `agent` |
 
@@ -60,7 +63,7 @@ Policies are synchronous so every code path can call them. Keep them fast; do sl
 
 ## Daemon events (listeners)
 
-`agent.created`, `agent.starting`, `agent.stopping`, `agent.message`, `agent.removed`, `hub.action`, each with the same `agent` summary and an `at` timestamp.
+`agent.created`, `agent.starting`, `agent.stopping`, `agent.message`, `agent.removed`, `agent.commit` (with `sha`), `agent.pr` (with `url`), `agent.merge`, `hub.action`, each with the same `agent` summary and an `at` timestamp.
 
 ## Engines
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai-agentmanager",
-  "version": "1.2.1",
+  "version": "1.3.0",
   "description": "Run background coding agents (Claude Code, Codex) per intent, and keep track of them from a web UI, your phone or the CLI",
   "keywords": [
     "claude",

package/public/app.js

@@ -4,6 +4,12 @@ import { marked } from '/vendor/marked/marked.esm.js';
 import DOMPurify from '/vendor/dompurify/purify.es.mjs';
 import { touchScroll } from '/touchscroll.js';
 import { openStream, post, REMOTE } from '/transport.js';
+import { initReview } from '/review.js';
+import { initLand, prChips } from '/land.js';
+import { initTriggers } from '/triggers.js';
+import { initSpend } from '/spend.js';
+import { initPlaybooks } from '/playbooks.js';
+import { initSetup } from '/setup.js';
 
 const $ = (sel) => document.querySelector(sel);
 const agents = new Map();
@@ -93,6 +99,19 @@ async function act(fn, okMsg) {
   }
 }
 
+const reviewUi = initReview({ api, esc, toast, agents, $ });
+const triggersUi = initTriggers({ api, esc, toast, $ });
+initSpend({ api, esc, toast, $ });
+initSetup({ api, esc, $ });
+const playbooksUi = initPlaybooks({ api, esc, toast, $, select: (id) => (showTab('agents'), select(id)) });
+$('#new-playbook').onclick = () => {
+  const f = $('#new-form');
+  $('#new-dialog').close();
+  playbooksUi.open({ intent: f.intents.value.trim(), projects: f.project.value.trim() ? [f.project.value.trim()] : [], model: f.model.value.trim(), permissionMode: f.permissionMode.value });
+};
+$('#triggers-open').onclick = () => triggersUi.open();
+const landUi = initLand({ api, esc, toast, agents, $, select: (id) => (showTab('agents'), select(id)), openReview: (id) => reviewUi.open(id), isOpen: () => sideTab === 'land' });
+
 function statusOf(a) {
   if (a.runtime.planning) return a.runtime.attention ? 'attention' : 'planning';
   if (a.status === 'running') {
@@ -605,7 +624,7 @@ function agentItem(a) {
   const idle = !isActive(a);
   return `<li data-id="${a.id}" class="agent pr${a.priority ?? 2} ${a.id === selectedId ? 'selected' : ''} ${idle ? 'idle' : ''}">
     <div class="line1">${prioChip(a.priority ?? 2)}${a.results?.outcome === 'blocked' ? '<span class="outcome-mark" title="Blocked">⛔</span>' : a.results?.outcome === 'done' ? '<span class="outcome-mark" title="Done">✅</span>' : ''}<span class="name">${esc(a.name)}</span>${flags(a)}<span class="pill ${st}">${pillText(st)}</span></div>
-    <div class="intent">${a.kind === 'general' ? '<span class="tag">general</span> ' : a.kind === 'assistant' ? '<span class="tag assistant">assistant</span> ' : a.startedBy ? '<span class="tag assistant" title="Started by the assistant">🤖 by assistant</span> ' : ''}${a.engine && a.engine !== 'claude' ? `<span class="tag engine">${esc(ENGINE_LABEL[a.engine] ?? a.engine)}</span> ` : ''}${esc(a.intent || (a.kind === 'assistant' ? 'Finds new work and starts agents for it' : 'General session'))}</div>
+    <div class="intent">${a.kind === 'general' ? '<span class="tag">general</span> ' : a.kind === 'assistant' ? '<span class="tag assistant">assistant</span> ' : a.startedBy ? '<span class="tag assistant" title="Started by the assistant">🤖 by assistant</span> ' : a.trigger ? `<span class="tag assistant" title="Started from ${a.trigger.source === 'github' ? 'a labeled GitHub issue' : 'the webhook'}${a.trigger.url ? `: ${esc(a.trigger.url)}` : ''}">⚡ ${a.trigger.source === 'github' ? 'GitHub' : 'webhook'}</span> ` : a.playbook ? `<span class="tag assistant" title="Started by the playbook ${esc(a.playbook.name)}">▶ ${esc(a.playbook.name)}</span> ` : ''}${a.engine && a.engine !== 'claude' ? `<span class="tag engine">${esc(ENGINE_LABEL[a.engine] ?? a.engine)}</span> ` : ''}${esc(a.intent || (a.kind === 'assistant' ? 'Finds new work and starts agents for it' : 'General session'))}</div>
     ${a.status === 'preparing' && a.progress ? `<div class="progress-line">${esc(progressText(a.progress))}</div>` : ''}
     <div class="meta">
       <span class="mono">${a.id}</span>
@@ -759,6 +778,7 @@ function renderBacklog() {
       <span class="spacer"></span>
       <button class="link" data-bl="toggle-run" title="${backlogState.autoRun ? 'Stop starting new items (running ones continue)' : 'Start picking up queued items again'}">${backlogState.autoRun ? '⏸ Pause' : '▶ Resume'}</button>
       <button class="link" data-bl="add">+ Add</button>
+      <button class="link" data-bl="playbooks" title="Saved requests you run again, by hand or on a schedule">Playbooks</button>
     </div>
     ${!backlogState.autoRun ? '<p class="hint bl-paused">Paused: queued items wait until you resume.</p>' : ''}
     ${items.length
@@ -807,7 +827,9 @@ function showTab(tab) {
   $('#agents-view').hidden = tab !== 'agents';
   $('#backlog-view').hidden = tab !== 'backlog';
   $('#inbox-view').hidden = tab !== 'inbox';
+  $('#land-view').hidden = tab !== 'land';
   if (tab === 'inbox') loadJudge();
+  if (tab === 'land') landUi.load();
   renderBacklog();
   renderInbox();
 }
@@ -830,6 +852,8 @@ $('#backlog-view').addEventListener('click', async (e) => {
       return blApi('POST', '/backlog/settings', { autoRun: !backlogState.autoRun });
     case 'add':
       return openNewDialog('backlog');
+    case 'playbooks':
+      return playbooksUi.open();
     case 'limit': {
       const n = prompt(`How many "${el.dataset.name}" items should agents work on at once?`, el.textContent.split(' ')[0]);
       if (n === null) return;
@@ -1508,6 +1532,7 @@ function prRow(a, p) {
     <a class="grow" href="${esc(p.url)}" target="_blank" rel="noopener" title="${esc(p.url)}">${label} ${esc(p.title ?? p.repo ?? p.url)}</a>
     <span class="tag" title="How this was found">${esc(p.source)}</span>
     <button class="link" data-unlink="pr" data-key="${esc(p.url)}" title="Remove">✕</button>
+    ${p.state === 'OPEN' && (p.checks || p.review || p.mergeState) ? `<div class="pr-chips">${prChips(p, esc)}</div>` : ''}
   </li>`;
 }
 
@@ -1563,6 +1588,7 @@ function renderDetail() {
             : `<button data-act="start" ${a.status === 'preparing' ? 'disabled' : ''}>Resume in background</button>`}
         <button data-act="fresh" ${running || a.status === 'preparing' ? 'disabled' : ''} title="Start over with a new session ID (old ones are kept)">New session</button>
         <button data-act="shell" ${a.workdir && a.status !== 'preparing' ? '' : 'disabled'} title="A separate terminal in this agent's folder for running commands by hand">Open shell</button>
+        ${noRepo(a) ? '' : `<button data-act="changes" ${a.workdir && a.status !== 'preparing' ? '' : 'disabled'} title="Read its changes, comment on lines for the agent, commit and open a pull request">Review changes${a.git?.dirtyFiles ? ` <span class="count">${a.git.dirtyFiles}</span>` : ''}</button>`}
         <button data-act="fork" ${a.workdir && a.git?.branch ? '' : 'disabled'} title="A new agent with this one's code and conversation, in its own worktree, to try another approach">Fork</button>
         <button data-act="edit" title="Change its name, request, project, priority, permission mode or model">Edit</button>
         <button data-act="refresh" title="Re-scan git, PRs and transcripts">Refresh</button>
@@ -1620,7 +1646,7 @@ function renderDetail() {
                     <br>${fmtTokens(u.total)} total incl. cache · ${u.requests} requests</div>`
                  : ''}`
             : '—'}</dd>
-          <dt>Cost</dt><dd>${totalCost ? `$${totalCost.toFixed(2)} <span class="hint">(reported by Claude Code)</span>` : '—'}</dd>
+          <dt>Cost</dt><dd>${totalCost ? `$${totalCost.toFixed(2)}${a.budgetUsd ? ` of its $${a.budgetUsd.toFixed(2)} budget` : ''} <span class="hint">(reported by Claude Code)</span>` : a.budgetUsd ? `— <span class="hint">budget $${a.budgetUsd.toFixed(2)}</span>` : '—'}${a.budgetHit ? ' <span class="tag fail" title="Its session was closed at its budget; raise it in Edit to continue">budget reached</span>' : ''}</dd>
           <dt>Mode</dt><dd>${esc(a.permissionMode)}${a.model ? ` · ${esc(a.model)}` : ''}</dd>
         </dl>
       </div>
@@ -1635,6 +1661,7 @@ function renderDetail() {
           <dt>Head</dt><dd>${a.git?.head ? `<code>${esc(a.git.head.sha)}</code> ${esc(a.git.head.subject)}` : '—'}</dd>
           ${a.baseRef ? `<dt>Branched from</dt><dd><code>${esc(a.baseRef)}</code></dd>` : ''}
           ${a.worktree ? `<dt>Worktree of</dt><dd><code>${esc(a.sourceDir)}</code></dd>` : ''}
+          ${noRepo(a) ? '' : `<dt>Repo memory</dt><dd><button class="link" data-act="memory" title="What agents learned working in this repo; every agent here gets it">View and edit</button></dd>`}
         </dl>
       </div>
 
@@ -1699,6 +1726,7 @@ function renderDetail() {
 function render() {
   renderList();
   renderBacklog();
+  landUi.render();
   renderInbox();
   renderRace();
   renderTeam();
@@ -2906,6 +2934,10 @@ $('#detail-body').addEventListener('click', async (e) => {
     case 'shell':
       term.open(a.id, 'shell:1');
       break;
+    case 'changes':
+      return reviewUi.open(a.id);
+    case 'memory':
+      return openMemory(a);
     case 'fork':
       forkAgent(a.id);
       break;
@@ -3511,6 +3543,34 @@ let enginesCache = null;
 // The project picked in the dialog: "" while it is listed under its own repo or folder.
 const editProject = (a) => (a.projectMove || a.project ? (a.projectInfo?.shortcut ?? '') : '');
 
+let memoryAgent = null;
+async function openMemory(a) {
+  memoryAgent = a.id;
+  const f = $('#memory-form');
+  $('#memory-error').hidden = true;
+  try {
+    const m = await api('GET', `/agents/${a.id}/memory`);
+    $('#memory-repo').textContent = a.projectInfo?.full || a.projectInfo?.name || a.repo || 'this repo';
+    f.text.value = m.text;
+    $('#memory-meta').textContent = `${m.entries} learning${m.entries === 1 ? '' : 's'} · ${(m.bytes / 1000).toFixed(1)} of ${m.max / 1000} KB`;
+    $('#memory-dialog').showModal();
+  } catch (err) {
+    toast(`Error: ${err.message}`, 5000);
+  }
+}
+$('#memory-form').addEventListener('submit', async (e) => {
+  e.preventDefault();
+  try {
+    await api('PUT', `/agents/${memoryAgent}/memory`, { text: $('#memory-form').text.value });
+    $('#memory-dialog').close();
+    toast('Saved; agents get it from their next start');
+  } catch (err) {
+    $('#memory-error').hidden = false;
+    $('#memory-error').textContent = err.message;
+  }
+});
+$('#memory-close').onclick = () => $('#memory-dialog').close();
+
 async function openEdit(a, focus) {
   editing = a;
   const f = $('#edit-form');
@@ -3519,6 +3579,7 @@ async function openEdit(a, focus) {
   f.tell.checked = false;
   f.priority.value = String(a.priority ?? 2);
   f.model.value = a.model ?? '';
+  f.budgetUsd.value = a.budgetUsd ?? '';
   $('#edit-project-row').hidden = noRepo(a);
   $('#edit-tell-row').hidden = !a.intent;
   // Its own repo or folder, every known project, or a new name.
@@ -3554,6 +3615,7 @@ $('#edit-form').addEventListener('submit', async (e) => {
   if (Number(f.priority.value) !== (a.priority ?? 2)) patch.priority = Number(f.priority.value);
   if ((f.permissionMode.value || null) !== (a.permissionMode ?? null)) patch.permissionMode = f.permissionMode.value || null;
   if ((f.model.value.trim() || null) !== (a.model ?? null)) patch.model = f.model.value.trim() || null;
+  if ((f.budgetUsd.value === '' ? null : Number(f.budgetUsd.value)) !== (a.budgetUsd ?? null)) patch.budgetUsd = f.budgetUsd.value === '' ? null : Number(f.budgetUsd.value);
   if (!noRepo(a)) {
     const target = f.project.value === '__new' ? f.newProject.value.trim() : f.project.value;
     const was = editProject(a);
@@ -3578,7 +3640,7 @@ $('#edit-form').addEventListener('submit', async (e) => {
 
 // ------------------------------------------------------------------ assistant
 
-const ASSISTANT_SOURCES = ['jira', 'comments', 'reviews', 'ci', 'slack'];
+const ASSISTANT_SOURCES = ['jira', 'comments', 'reviews', 'ci', 'slack', 'linear'];
 let assistantState = null;
 
 function renderAssistantDot() {

package/public/index.html

@@ -23,6 +23,7 @@
       <div class="top-actions">
         <input id="filter" type="search" placeholder="Filter agents" aria-label="Filter agents" />
         <button id="assistant-btn" title="An always-on session that finds new work and starts agents for it">Assistant <span id="assistant-dot" class="assistant-dot" hidden></span></button>
+        <button id="spend-btn" title="Results across agents (merge rate, time to PR, cost per merged PR), what they cost, and spending limits">Results <span id="spend-today" class="spend-today"></span></button>
         <button id="cleanup-btn" title="Close agents idle for a while, and delete old closed ones">Clean up</button>
         <button id="alerts-btn" class="local-only" title="Slack alerts when an agent needs you">Alerts</button>
         <button id="remote-btn" class="local-only" title="Open AI Agent Manager from your phone">Remote access</button>
@@ -37,6 +38,7 @@
           <button class="side-tab active" data-tab="agents" role="tab">Agents</button>
           <button class="side-tab" data-tab="inbox" role="tab" title="Everything waiting on you: prompts, questions, stuck agents, overlaps">Inbox <span id="inbox-count" class="badge"></span></button>
           <button class="side-tab" data-tab="backlog" role="tab">Backlog <span id="backlog-count" class="badge"></span></button>
+          <button class="side-tab" data-tab="land" role="tab" title="Agents' open pull requests: what each needs to get merged">Land <span id="land-count" class="badge"></span></button>
         </div>
         <div id="agents-view">
           <div class="counts" id="counts"></div>
@@ -51,6 +53,7 @@
         </div>
         <div id="backlog-view" hidden></div>
         <div id="inbox-view" hidden></div>
+        <div id="land-view" hidden></div>
         <div id="empty" class="empty" hidden>
           <p>No agents yet.</p>
           <p>Add one or more intents and a repo or folder to get started.</p>
@@ -269,6 +272,8 @@
         </label>
         <p id="new-error" class="error" hidden></p>
         <div class="dialog-actions">
+          <button type="button" id="new-playbook" class="ghost" title="Keep this request to run again, in several projects or on a schedule">Save as playbook…</button>
+          <span class="spacer"></span>
           <button type="button" id="new-cancel" class="ghost">Cancel</button>
           <button type="submit" class="primary">Create agents</button>
         </div>
@@ -355,6 +360,15 @@
       <div id="team-body" class="race-body team-body"></div>
     </dialog>
 
+    <dialog id="review-dialog" class="doc-dialog review-dialog">
+      <div class="doc-head">
+        <h2 id="review-title">Review</h2>
+        <span class="spacer"></span>
+        <button type="button" id="review-close" class="small ghost">Close</button>
+      </div>
+      <div id="review-body" class="review-body"></div>
+    </dialog>
+
     <dialog id="race-dialog" class="doc-dialog">
       <div class="doc-head">
         <h2 id="race-title">Race</h2>
@@ -384,7 +398,8 @@
           <label class="check"><input type="checkbox" name="ev_stuck" /> seems stuck (same failure, undoing its edits, no progress)</label>
           <label class="check"><input type="checkbox" name="ev_conflict" /> changes the same files as another agent</label>
           <label class="check"><input type="checkbox" name="ev_question" /> asks a question in the inbox</label>
-          <label class="check"><input type="checkbox" name="ev_assistant" /> is started by the assistant for new work</label>
+          <label class="check"><input type="checkbox" name="ev_assistant" /> is started for new work (by the assistant, a GitHub label or a webhook)</label>
+          <label class="check"><input type="checkbox" name="ev_budget" /> nears or reaches its budget, or today's spend reaches the daily limit</label>
           <label class="check"><input type="checkbox" name="ev_waiting" /> finished its turn and is idle after <input name="waitingDelaySec" type="number" min="0" class="num" />s</label>
           <label class="check"><input type="checkbox" name="skipWhenWatching" /> not while I have its terminal open</label>
           <label class="check"><input type="checkbox" name="includeIntent" /> include the intent text in the message</label>
@@ -420,6 +435,7 @@
           <label>Permission mode <select name="permissionMode"></select></label>
           <label>Model <input name="model" placeholder="as configured" /></label>
         </div>
+        <label>Budget <span class="hint">US dollars; empty for the default limit</span><input name="budgetUsd" type="number" min="0.01" step="0.01" placeholder="default" /></label>
         <p class="hint" id="edit-hint">Moving changes only where the agent is listed; its code stays in its own repo and branch. Permission mode and model apply from its next launch.</p>
         <p id="edit-error" class="error" hidden></p>
         <div class="dialog-actions">
@@ -442,6 +458,7 @@
           <label class="check"><input type="checkbox" name="src_reviews" /> GitHub pull requests waiting for my review</label>
           <label class="check"><input type="checkbox" name="src_ci" /> Failing checks on my open pull requests</label>
           <label class="check"><input type="checkbox" name="src_slack" /> Slack messages to me that ask for work</label>
+          <label class="check"><input type="checkbox" name="src_linear" /> Linear issues newly assigned to me</label>
         </fieldset>
         <div class="row three">
           <label>Check every <span class="hint">minutes</span><input name="everyMin" type="number" min="1" /></label>
@@ -458,6 +475,7 @@
           <button type="button" id="assistant-check">Check now</button>
           <button type="button" id="assistant-pause">Pause</button>
           <button type="button" id="assistant-open" class="ghost">Open its session</button>
+          <button type="button" id="triggers-open" class="ghost" title="Start agents from GitHub labels, /agent PR comments and a webhook, with no session watching">Triggers…</button>
           <span class="spacer"></span>
           <button type="button" id="assistant-close" class="ghost">Close</button>
           <button id="assistant-save">Save</button>
@@ -465,6 +483,120 @@
       </form>
     </dialog>
 
+    <dialog id="triggers-dialog">
+      <form id="triggers-form" method="dialog" class="alerts-body">
+        <h2>Triggers</h2>
+        <p class="hint">Start agents from where the work is, with no model watching (no tokens spent on it). Agents started this way are marked <b>⚡ GitHub</b> or <b>⚡ webhook</b>.</p>
+        <fieldset>
+          <legend>GitHub label</legend>
+          <label class="check"><input type="checkbox" name="gh_enabled" /> Start an agent for each open issue with this label</label>
+          <div class="row">
+            <label>Label <input name="gh_label" placeholder="agentmgr" /></label>
+            <label>Check every <span class="hint">minutes</span><input name="gh_everyMin" type="number" min="1" /></label>
+          </div>
+          <label>In these repos <span class="hint">owner/name, comma or space separated</span><input name="gh_repos" placeholder="acme/web acme/api" /></label>
+          <label>Or any repo of these owners <input name="gh_owners" placeholder="acme" /></label>
+          <label class="check"><input type="checkbox" name="gh_comment" /> Comment on the issue that an agent is on it</label>
+        </fieldset>
+        <fieldset>
+          <legend>Pull request comments</legend>
+          <label class="check"><input type="checkbox" name="pc_enabled" /> Pass comments that start with <input name="pc_prefix" class="inline" placeholder="/agent" /> on an agent's pull request to that agent</label>
+          <p class="hint">Only from the repo's owners, members and collaborators.</p>
+        </fieldset>
+        <fieldset>
+          <legend>Webhook</legend>
+          <label class="check"><input type="checkbox" name="wh_enabled" /> Accept <code>POST /api/hooks/agents</code> with the token</label>
+          <div id="triggers-token" class="hint"></div>
+          <button type="button" id="triggers-newtoken" class="small">New token</button>
+          <label>Only these repos <span class="hint">optional</span><input name="wh_repos" /></label>
+        </fieldset>
+        <label>Agents started by triggers a day <span class="hint">at most</span><input name="maxPerDay" type="number" min="0" /></label>
+        <div id="triggers-status" class="hint"></div>
+        <p id="triggers-error" class="error" hidden></p>
+        <div class="dialog-actions">
+          <button type="button" id="triggers-poll">Check now</button>
+          <span class="spacer"></span>
+          <button type="button" id="triggers-close" class="ghost">Close</button>
+          <button class="primary">Save</button>
+        </div>
+      </form>
+    </dialog>
+
+    <dialog id="memory-dialog">
+      <form id="memory-form" method="dialog" class="alerts-body">
+        <h2>Repo memory</h2>
+        <p class="hint">What agents learned working in <b id="memory-repo"></b>. Every agent in this repo gets it when it starts, and adds to it with <code>agentmgr learn</code>. Tidy it here: keep it short and true.</p>
+        <textarea name="text" rows="14" class="memory-text" placeholder="- npm test needs a running Postgres: docker compose up db (you, 2026-10-31)"></textarea>
+        <p id="memory-meta" class="hint"></p>
+        <p id="memory-error" class="error" hidden></p>
+        <div class="dialog-actions">
+          <span class="spacer"></span>
+          <button type="button" id="memory-close" class="ghost">Cancel</button>
+          <button class="primary">Save</button>
+        </div>
+      </form>
+    </dialog>
+
+    <dialog id="playbooks-dialog" class="doc-dialog">
+      <div class="doc-head">
+        <h2>Playbooks</h2>
+        <span class="spacer"></span>
+        <button type="button" id="pb-new" class="small">+ New playbook</button>
+        <button type="button" id="pb-close" class="small ghost">Close</button>
+      </div>
+      <div class="race-body">
+        <p class="hint">Saved requests you run again, in one or more projects (one agent each), by hand or on a schedule. Write <code>{{name}}</code> for a value you fill in when it runs.</p>
+        <div id="pb-list"></div>
+        <form id="pb-form" class="alerts-body pb-form" hidden>
+          <input type="hidden" name="id" />
+          <label>Name <input name="name" required maxlength="80" placeholder="Upgrade a dependency" /></label>
+          <label>Request <textarea name="intent" rows="4" required placeholder="Upgrade {{package}} to the latest version, fix what breaks, run the tests and open a pull request."></textarea></label>
+          <label>Run in these projects <span class="hint">shortcuts, comma or space separated; one agent each</span><input name="projects" placeholder="web api" list="project-options" /></label>
+          <div id="pb-defaults"></div>
+          <div class="row three">
+            <label>Model <input name="model" placeholder="as configured" /></label>
+            <label>Permission mode <select name="permissionMode"><option value="">As configured</option><option value="acceptEdits">Accept edits</option><option value="plan">Plan</option><option value="auto">Auto</option><option value="bypassPermissions">Bypass permissions</option></select></label>
+            <label>Priority <select name="priority"><option value="0">P0</option><option value="1">P1</option><option value="2" selected>P2</option><option value="3">P3</option></select></label>
+          </div>
+          <div class="row three">
+            <label>Schedule <select name="every"><option value="">By hand only</option><option value="hour">Every hour</option><option value="day">Every day</option><option value="weekday">Every weekday</option><option value="week">Every week</option></select></label>
+            <label>At <input name="at" type="time" value="09:00" /></label>
+            <label>On <select name="day"><option value="mon">Monday</option><option value="tue">Tuesday</option><option value="wed">Wednesday</option><option value="thu">Thursday</option><option value="fri">Friday</option><option value="sat">Saturday</option><option value="sun">Sunday</option></select></label>
+          </div>
+          <label class="check"><input type="checkbox" name="enabled" checked /> Schedule on</label>
+          <p id="pb-error" class="error" hidden></p>
+          <div class="dialog-actions">
+            <button type="button" id="pb-delete" class="danger ghost">Delete</button>
+            <span class="spacer"></span>
+            <button type="button" id="pb-cancel" class="ghost">Cancel</button>
+            <button class="primary">Save</button>
+          </div>
+        </form>
+      </div>
+    </dialog>
+
+    <dialog id="spend-dialog">
+      <form id="spend-form" method="dialog" class="alerts-body">
+        <h2>Results <select id="stats-days" class="inline-select"><option value="7">last 7 days</option><option value="30" selected>last 30 days</option><option value="90">last 90 days</option><option value="0">all time</option></select></h2>
+        <div id="stats-body"></div>
+        <h3 class="spend-h">Spend</h3>
+        <div id="spend-summary"></div>
+        <div class="row">
+          <label>Each agent at most <span class="hint">US dollars; empty for no limit</span><input name="perAgentUsd" type="number" min="0.01" step="0.01" placeholder="no limit" /></label>
+          <label>All agents a day at most <span class="hint">US dollars</span><input name="perDayUsd" type="number" min="0.01" step="0.01" placeholder="no limit" /></label>
+        </div>
+        <p class="hint">At 80% of an agent's budget you get an alert; at its budget its session is closed until you raise it (Edit on the agent). At the daily limit no new agents start or resume until tomorrow; running ones go on.</p>
+        <div id="spend-agents"></div>
+        <p id="spend-note" class="hint"></p>
+        <p id="spend-error" class="error" hidden></p>
+        <div class="dialog-actions">
+          <span class="spacer"></span>
+          <button type="button" id="spend-close" class="ghost">Close</button>
+          <button class="primary">Save limits</button>
+        </div>
+      </form>
+    </dialog>
+
     <dialog id="cleanup-dialog">
       <form id="cleanup-form" method="dialog" class="alerts-body">
         <h2>Clean up old agents</h2>