aimeat 1.9.4 → 1.10.0

package/README.md

@@ -26,12 +26,12 @@ An AI agent connects to an AIMEAT node and reaches full operational readiness au
 
 [![AIMEAT Agent Hello Integration](https://img.youtube.com/vi/ncBX9BaoAWM/maxresdefault.jpg)](https://youtu.be/ncBX9BaoAWM)
 
-`0:45` Device auth with automatic polling (RFC 8628) | `2:10` Skill bundle download + boot sequence | `3:40` 11-step Hello Integration | `4:30` Test task proposed, executed, completed | `5:20` Commands + config registered, agent operational
+`0:45` Device auth with automatic polling (RFC 8628) | `2:10` Skill bundle download + boot sequence | `3:40` Hello Integration | `4:30` Test task proposed, executed, completed | `5:20` Commands + config registered, agent operational
 
 <p align="center">
-  <img src="assets/screenshots/agent_hello_integration_finished.png" alt="Agent Hello Integration completed -- 11/11 steps passed, capabilities reported, commands registered" width="70%" />
+  <img src="assets/screenshots/agent_hello_integration_finished.png" alt="Agent Hello Integration completed -- all required steps passed, capabilities reported, commands registered" width="70%" />
 </p>
-<p align="center"><em>After Hello Integration: agent detail view showing connection status, platform, skill bundle version, readiness (all 11 steps passed), identity, and delivery log.</em></p>
+<p align="center"><em>After Hello Integration: agent detail view showing connection status, platform, skill bundle version, readiness (all required steps passed), identity, and delivery log. Since 1.10.0 the system also verifies that the agent has published its slash command catalogue and runtime config before declaring it complete.</em></p>
 
 ---
 
@@ -132,7 +132,22 @@ On top of the protocol sits the application layer. Apps are self-contained HTML
 
 <img src="assets/screenshots/profile-agents.png" alt="Agent connection prompt" width="600" />
 
-From your profile, copy the connection prompt and give it to any AI agent. The agent calls one endpoint, you approve, and it's connected with its own identity and scoped permissions. Claude Pro, ChatGPT Plus, and other MCP-capable AIs connect directly as MCP clients. OpenClaw, Hermes, Claude Code, and Cursor all work. Three scope presets (readonly, standard, full) control what each agent can access.
+There are two ways to connect:
+
+**1. `aimeat connect` CLI** (recommended, added in 1.10.0). Any runtime that can run a shell command can attach to a node in seconds:
+
+```bash
+npx aimeat connect --url https://your-node --owner your-handle [--agent name]
+# you approve from your profile -> Agents tab
+# the CLI stores the token, downloads the runtime-specific skill bundle,
+# and prints a paste-ready Hello Integration instruction for your agent
+```
+
+For MCP-capable runtimes (Claude Desktop, MCP-aware IDEs), run `aimeat connect serve` afterwards to attach the AIMEAT toolset over stdio. For CLI-only runtimes that cannot do stdio, every MCP tool is also reachable via `aimeat connect call <tool-name> --json '<input>'`.
+
+**2. Copy the prompt from your profile.** If you do not want to install a CLI, your profile -> Agents tab still produces a paste-ready prompt with the device-auth flow baked in -- give it to any AI agent, the agent calls one endpoint, you approve, and it is connected with its own identity and scoped permissions.
+
+Claude Pro, ChatGPT Plus, and other MCP-capable AIs connect directly as MCP clients. OpenClaw, Hermes, Claude Code, and Cursor all work. Three scope presets (readonly, standard, full) control what each agent can access.
 
 ### Build apps with AI
 
@@ -231,6 +246,19 @@ On the left: Telegram chat with the agent. The user asks it to build things ("bu
 
 The app prompts the agent with the current world state so it can make informed decisions about what to build and where. You edit the world manually (drag objects, place shapes from the toolbar) while the agent builds alongside you. Everything syncs through AIMEAT memory.
 
+### Example: Comicland, an AI comic community (full app, built from VS Code)
+
+Comicland is a community for AI-generated comics built end-to-end from VS Code with Claude Code talking directly to a live AIMEAT node. No CI, no separate deploy step -- each iteration is `aimeat_app_publish` over MCP and the new version is live on the node within seconds. The whole 5-layer AIMEAT stack (extension, cortex, app) was scaffolded by AI, then evolved through dozens of feature passes in the same workflow.
+
+<p align="center">
+  <img src="assets/screenshots/comic-land-series-view.png" alt="Comicland series detail with episodes, follow, tip, and owner-only publish/unpublish controls" width="48%" />
+  <img src="assets/screenshots/comic-land-creation-pipeline.png" alt="Comicland creation pipeline: AI interview -> script JSON -> per-page image prompts -> overlay editor -> publish" width="48%" />
+</p>
+
+What's in there: a prompt-driven creation pipeline (AI interview produces a script, the app generates per-page Nano-Banana-style image prompts with character/environment references, the user pastes the resulting images back); a 3-step episode wizard with page or panel images; a drag-and-drop speech-bubble overlay editor with language-keyed translations; multi-tenant reading where any logged-in user can read another author's published series from their own GHII namespace; characters and environments with multiple reference images and a chosen showcase; follow/tip/comment social actions; per-series public/private toggle and per-episode draft/published toggle so authors can prepare quietly and roll out when ready; full FI/EN i18n. All of it stored in AIMEAT memory + storage with proper public/private visibility, no Comicland-specific backend code beyond one sandboxed extension with eleven router-actions.
+
+The same loop works for any sufficiently rich app: open a folder, point Claude Code at the node, and iterate. The MCP tools (`aimeat_app_publish`, `aimeat_extension_install`, `aimeat_cortex_install`, `aimeat_memory_*`, `aimeat_storage_*`) cover the entire publish/install/inspect cycle.
+
 ### Calibrate prompts
 
 <img src="assets/screenshots/profile-generator.png" alt="Generator and calibrator" width="600" />
@@ -276,9 +304,13 @@ Each node runs independently with its own identity and portal. Operators customi
 Requires Node.js 24+. Runs without cloning the repo:
 
 ```bash
+# Run a node
 npx aimeat init     # interactive setup, generates .env
 npx aimeat start    # start the server
 npx aimeat seed     # seed example packages (in another terminal, server must be running)
+
+# Or just connect an agent to someone else's node
+npx aimeat connect --url https://your-node --owner your-handle
 ```
 
 ### From source
@@ -320,21 +352,25 @@ If the AI reads the docs and explains the protocol, everything works. Admin dash
 
 The `aimeat/` directory contains a full reference implementation in TypeScript (Express 5.2, Node 24). It implements the entire RFC and adds production features: GHII human identities, TOTP 2FA, V8 extensions, package marketplace, push notifications, WebRTC, and a comprehensive admin UI.
 
-Three storage backends: in-memory (fast dev), SQLite (personal nodes), MongoDB (production).
+Two storage backends: SQLite (personal nodes, local dev; can run `:memory:` for true in-RAM speed) and MongoDB (production). The legacy in-memory backend is deprecated -- SQLite `:memory:` covers the same fast-iteration role using the actual production code path.
 
 See the [Implementation Guide v3.0](docs/AIMEAT-IO-Implementation-Guide-v3.0.md) for full details.
 
 ### Testing
 
 ```bash
-pnpm test:e2e               # fastest (memory backend)
-pnpm test:e2e:sqlite
-pnpm test:e2e:mongodb
-pnpm test:playwright        # browser tests
+pnpm test:e2e:sqlite        # fast iteration default
+pnpm test:e2e:mongodb       # most realistic; run before a PR
+pnpm test:playwright:sqlite # browser tests, scoped
 pnpm test                   # unit tests
 pnpm typecheck && pnpm lint
+
+# Run a single E2E suite (preferred during iteration -- much faster than the full sweep)
+cd aimeat && pnpm exec node --env-file=.env.test.sqlite --import tsx test/run-e2e-ci.ts --test=<suite>
 ```
 
+> The legacy `pnpm test:e2e` (in-memory backend) is deprecated and produces stale failures. Use the SQLite or MongoDB commands instead.
+
 ---
 
 ## Documentation
@@ -367,7 +403,8 @@ See [CONTRIBUTING.md](CONTRIBUTING.md). Before opening a PR:
 ```bash
 pnpm typecheck
 pnpm lint
-pnpm test:e2e
+pnpm test:e2e:sqlite
+pnpm test:e2e:mongodb
 ```
 
 ## License

package/dist/locales/en.json

@@ -12,7 +12,9 @@
     "noData": "No data available",
     "id": "ID",
     "name": "Name",
-    "add": "Add"
+    "add": "Add",
+    "yes": "Yes",
+    "no": "No"
   },
   "nav": {
     "try": "Try it",
@@ -259,15 +261,24 @@
     },
     "agents": {
       "title": "Your Agents",
-      "desc": "Agents are AI identities registered under your account, each with their own memory, wallet, and skills. Think of them as your personal AI team — they act on your behalf across the network.",
+      "desc": "Agents are AI identities registered under your account, each with their own identity, scopes, tools, tasks, and memory access. Think of them as your personal AI team — they act on your behalf across the network.",
       "connect": "Connect an Automation Agent",
-      "connectDesc": "Connect an AI agent to your account using the AIMEAT connector CLI or by pasting a prompt to your AI chat:",
+      "connectDesc": "Connect an AI agent to your account using the AIMEAT connector CLI or an agent-capable runtime. The connector is the easiest path because it gives the agent a persistent identity, approved scopes, local skill bundle, and MCP access to AIMEAT tools:",
+      "connectOptionsTitle": "Choose how the agent connects to AIMEAT first:",
+      "connectOptionConnectorTitle": "Recommended: use the AIMEAT connector.",
+      "connectOptionConnectorDesc": "It handles device authentication, stores the agent token locally, downloads the skill bundle, and exposes AIMEAT tools through MCP so the agent can use tasks, messages, memory, telemetry, and Hello Integration across sessions.",
+      "connectOptionFallbackTitle": "Fallback: use the API prompt.",
+      "connectOptionFallbackDesc": "Use this when the connector or MCP tools are not available. It still lets an HTTPS-capable agent connect, but the agent must make API calls itself instead of receiving local tools.",
       "cliInstall": "Install the AIMEAT connector and authenticate:",
       "cliServe": "After connecting, start the MCP server:",
-      "cliDesc": "The connector handles authentication, downloads your agent’s configuration, and provides all AIMEAT tools as an MCP server.",
+      "cliDesc": "Keep this server running while your AI runtime is attached. It turns AIMEAT into local tools so the agent can do useful work without manually composing every API call.",
+      "agentInstructionTitle": "Tell the connected agent what to do next:",
+      "agentInstructionDesc": "After the MCP server is attached to your agent runtime, paste this instruction to start Hello Integration:",
       "noNodejs": "Don’t have Node.js?",
-      "pasteAlt": "Or paste to your AI chat",
-      "pasteDesc": "For environments without terminal access, copy this prompt and paste it into your AI chat:",
+      "pasteAlt": "Fallback: connect an AI agent with APIs",
+      "pasteDesc": "If the connector or MCP tools are not available, copy this prompt for an agent that can make HTTPS requests. It explains how to connect to AIMEAT and start Hello Integration through the API:",
+      "copyCommand": "Copy command",
+      "copyAgentInstruction": "Copy agent instruction",
       "copyPrompt": "Copy Prompt",
       "copied": "Copied!",
       "copyGaii": "Copy GAII",
@@ -637,6 +648,12 @@
         },
         "integration": {
           "checklistTitle": "Hello Integration",
+          "postOnboardingSetup": "Post-Onboarding Setup",
+          "commandsRegistered": "Commands registered",
+          "configPublished": "Config published",
+          "sharedTagsInUse": "Shared tags in use",
+          "knowledgePackages": "Knowledge packages",
+          "notApplicable": "Not applicable",
           "progress": "Progress",
           "rerun": "Re-run Hello Integration",
           "rerunStarted": "Hello Integration re-started",
@@ -699,7 +716,7 @@
           "memoryAreasTitle": "Agent Memory Areas",
           "knowledgeTitle": "Knowledge Packages",
           "effectiveScope": "Effective data scope for this agent",
-          "tagsHelp": "Tags create shared memory areas. All agents with the same tag can read and write to agents.tag.{name}.* -- they discover each other automatically.",
+          "tagsHelp": "Tags mark same-owner shared memory areas. Agents with the same tag should use agents.tag.{name}.* with visibility owner and the matching tag filter.",
           "addArea": "Add area",
           "areaKeyPlaceholder": "Key prefix (e.g., agents.mydata.)",
           "areaDescPlaceholder": "Description",
@@ -2782,7 +2799,7 @@
     "usernamePlaceholder": "Username",
     "passwordPlaceholder": "Password (min 4 chars)",
     "displayNamePlaceholder": "Display Name (optional, for new accounts)",
-    "signInBtn": "Sign In",
+    "signInBtn": "Sign In / Register",
     "cancelBtn": "Cancel",
     "working": "Working...",
     "errUserShort": "Username must be at least 3 characters",
@@ -5417,6 +5434,8 @@
       "report_telemetry": "Report Telemetry",
       "accept_test_task": "Accept Test Task",
       "complete_test_task": "Complete Test Task",
+      "publish_commands": "Publish Slash Commands",
+      "publish_config": "Publish Runtime Config",
       "declare_services": "Declare Services"
     },
     "stepDescriptions": {
@@ -5430,6 +5449,8 @@
       "report_telemetry": "At least one telemetry event with non-zero data",
       "accept_test_task": "Agent proposes todos for the test task",
       "complete_test_task": "Agent executes and completes the test task",
+      "publish_commands": "agents.{name}.commands memory has a non-empty array of { name, description, category }",
+      "publish_config": "At least one agents.config.{name}.* memory entry exists describing this runtime",
       "declare_services": "Agent declares offered services (optional)"
     },
     "errors": {

package/dist/locales/fi.json

@@ -12,7 +12,9 @@
     "noData": "Ei tietoja saatavilla",
     "id": "ID",
     "name": "Nimi",
-    "add": "Lisää"
+    "add": "Lisää",
+    "yes": "Kyllä",
+    "no": "Ei"
   },
   "nav": {
     "try": "Kokeile",
@@ -259,15 +261,24 @@
     },
     "agents": {
       "title": "Agenttisi",
-      "desc": "Agentit ovat tilillesi rekisteröityjä AI-identiteettejä, joilla jokaisella on oma muisti, lompakko ja taidot. Ajattele heitä henkilökohtaisena AI-tiiminsi — ne toimivat puolestasi verkossa.",
+      "desc": "Agentit ovat tilillesi rekisteröityjä AI-identiteettejä, joilla on oma identiteetti, rajaukset, työkalut, tehtävät ja muistipääsy. Ajattele heitä henkilökohtaisena AI-tiiminäsi - ne toimivat puolestasi verkossa.",
       "connect": "Yhdistä automaatioagentti",
-      "connectDesc": "Yhdista tekoalyagentti tilillesi AIMEAT-liittimen avulla tai liittamalla kehote tekoalykeskusteluun:",
+      "connectDesc": "Yhdistä tekoälyagentti tilillesi AIMEAT-liittimellä tai agenttia ajavassa ympäristössä. Liitin on helpoin polku, koska se antaa agentille pysyvän identiteetin, hyväksytyt rajaukset, paikallisen taitopaketin ja MCP-pääsyn AIMEAT-työkaluihin:",
+      "connectOptionsTitle": "Valitse ensin, miten agentti yhdistetään AIMEATiin:",
+      "connectOptionConnectorTitle": "Suositus: käytä AIMEAT-liitintä.",
+      "connectOptionConnectorDesc": "Se hoitaa laitetunnistautumisen, tallentaa agentin tunnuksen paikallisesti, lataa taitopaketin ja tarjoaa AIMEAT-työkalut MCP:n kautta, jotta agentti voi käyttää tehtäviä, viestejä, muistia, telemetriaa ja Hello Integrationia istuntojen välillä.",
+      "connectOptionFallbackTitle": "Varapolku: käytä API-kehotetta.",
+      "connectOptionFallbackDesc": "Käytä tätä, kun liitin tai MCP-työkalut eivät ole käytettävissä. HTTPS-pyyntöjä tekevä agentti voi silti yhdistää, mutta sen täytyy tehdä API-kutsut itse paikallisten työkalujen sijaan.",
       "cliInstall": "Asenna AIMEAT-liitin ja tunnistaudu:",
-      "cliServe": "Yhdistamisen jalkeen kaynnista MCP-palvelin:",
-      "cliDesc": "Liitin hoitaa tunnistautumisen, lataa agentin asetukset ja tarjoaa kaikki AIMEAT-tyokalut MCP-palvelimena.",
-      "noNodejs": "Eiko Node.js:aa ole asennettuna?",
-      "pasteAlt": "Tai liita tekoalykeskusteluun",
-      "pasteDesc": "Jos terminaalia ei ole saatavilla, kopioi tama kehote ja liita se tekoalykeskusteluun:",
+      "cliServe": "Yhdistämisen jälkeen käynnistä MCP-palvelin:",
+      "cliDesc": "Pidä tämä palvelin käynnissä, kun AI-ympäristö on liitetty. Se muuttaa AIMEATin paikallisiksi työkaluiksi, jotta agentti voi tehdä hyödyllistä työtä ilman jokaisen API-kutsun käsin rakentamista.",
+      "agentInstructionTitle": "Kerro yhdistetylle agentille mitä tehdä seuraavaksi:",
+      "agentInstructionDesc": "Kun MCP-palvelin on liitetty agenttiympäristöön, liitä tämä ohje Hello Integration -prosessin aloittamiseen:",
+      "noNodejs": "Eikö Node.js:aa ole asennettuna?",
+      "pasteAlt": "Varapolku: yhdistä AI-agentti API-kutsuilla",
+      "pasteDesc": "Jos liitin tai MCP-työkalut eivät ole käytettävissä, kopioi tämä kehote agentille, joka voi tehdä HTTPS-pyyntöjä. Se kertoo, miten AIMEATiin yhdistetään ja Hello Integration aloitetaan API:n kautta:",
+      "copyCommand": "Kopioi komento",
+      "copyAgentInstruction": "Kopioi agentin ohje",
       "copyPrompt": "Kopioi kehote",
       "copied": "Kopioitu!",
       "copyGaii": "Kopioi GAII",
@@ -499,7 +510,7 @@
       "services": {
         "title": "Julkaistut palvelut",
         "empty": "Ei julkaistuja palveluita",
-        "info": "Muut agentit voivat kutsua naita palveluita tyonvaihdon kautta",
+        "info": "Muut agentit voivat kutsua näitä palveluita työnvaihdon kautta",
         "calls": "kutsut",
         "unpublish": "Poista julkaisu",
         "unpublished": "Palvelun julkaisu poistettu",
@@ -517,19 +528,19 @@
       },
       "messages": {
         "title": "Viestit",
-        "empty": "Ei viesteja viela. Laheta viesti aloittaaksesi keskustelun.",
-        "send": "Laheta",
+        "empty": "Ei viestejä vielä. Lähetä viesti aloittaaksesi keskustelun.",
+        "send": "Lähetä",
         "placeholder": "Kirjoita viesti...",
         "online": "online",
         "offline": "offline",
         "threads": "Keskustelut",
-        "proposedTask": "Ehdotettu tehtava",
-        "createTask": "Luo tama tehtava",
+        "proposedTask": "Ehdotettu tehtävä",
+        "createTask": "Luo tämä tehtävä",
         "adjustTask": "Muokkaan ensin",
         "tokensUsed": "tokenia",
-        "proposedTaskDefault": "Agentin ehdottama tehtava",
-        "createTaskError": "Tehtavan luonti epaonnistui",
-        "sendError": "Viestin lahetys epaonnistui",
+        "proposedTaskDefault": "Agentin ehdottama tehtävä",
+        "createTaskError": "Tehtävän luonti epäonnistui",
+        "sendError": "Viestin lähetys epäonnistui",
         "inboxLabel": "saapuneet",
         "deliveredLabel": "toimitettu",
         "errorsLabel": "virheet"
@@ -637,6 +648,12 @@
         },
         "integration": {
           "checklistTitle": "Hello-integraatio",
+          "postOnboardingSetup": "Perehdytyksen jälkeiset toimet",
+          "commandsRegistered": "Komennot rekisteröity",
+          "configPublished": "Konfiguraatio julkaistu",
+          "sharedTagsInUse": "Jaetut tagit käytössä",
+          "knowledgePackages": "Tietopaketit",
+          "notApplicable": "Ei sovellu",
           "progress": "Edistyminen",
           "rerun": "Suorita Hello-integraatio uudelleen",
           "rerunStarted": "Hello-integraatio aloitettu uudelleen",
@@ -699,7 +716,7 @@
           "memoryAreasTitle": "Agentin muistialueet",
           "knowledgeTitle": "Tietopaketit",
           "effectiveScope": "Agentin tehokas datan laajuus",
-          "tagsHelp": "Tagit luovat jaettuja muistialueita. Kaikki agentit samalla tagilla voivat lukea ja kirjoittaa agents.tag.{name}.* -- ne löytävät toisensa automaattisesti.",
+          "tagsHelp": "Tunnisteet merkitsevät saman omistajan jaettuja muistialueita. Samalla tunnisteella olevien agenttien kannattaa käyttää agents.tag.{name}.*-avaimia, näkyvyyttä owner ja samaa tunnistesuodatinta.",
           "addArea": "Lisää alue",
           "areaKeyPlaceholder": "Avainprefiksi (esim. agents.tietoni.)",
           "areaDescPlaceholder": "Kuvaus",
@@ -2782,7 +2799,7 @@
     "usernamePlaceholder": "Käyttäjänimi",
     "passwordPlaceholder": "Salasana (vähintään 4 merkkiä)",
     "displayNamePlaceholder": "Näyttönimi (valinnainen, uusille tileille)",
-    "signInBtn": "Kirjaudu",
+    "signInBtn": "Kirjaudu / Rekisteröidy",
     "cancelBtn": "Peruuta",
     "working": "Käsitellään...",
     "errUserShort": "Käyttäjänimen tulee olla vähintään 3 merkkiä",
@@ -5417,6 +5434,8 @@
       "report_telemetry": "Raportoi telemetria",
       "accept_test_task": "Hyväksy testitehtävä",
       "complete_test_task": "Suorita testitehtävä",
+      "publish_commands": "Julkaise slash-komennot",
+      "publish_config": "Julkaise runtime-konfiguraatio",
       "declare_services": "Ilmoita palvelut"
     },
     "stepDescriptions": {
@@ -5430,6 +5449,8 @@
       "report_telemetry": "Vähintään yksi telemetriatapahtuma nollasta poikkeavalla datalla",
       "accept_test_task": "Agentti ehdottaa todoja testitehtävälle",
       "complete_test_task": "Agentti suorittaa ja viimeistelee testitehtävän",
+      "publish_commands": "agents.{name}.commands -muistissa on epätyhjä { name, description, category } -taulu",
+      "publish_config": "Vähintään yksi agents.config.{name}.* -muistitietue kuvaa tätä runtimea",
       "declare_services": "Agentti ilmoittaa tarjoamansa palvelut (valinnainen)"
     },
     "errors": {

package/dist/public/llms-template.txt

@@ -886,13 +886,14 @@ Some steps auto-validate when you GET /v1/agents/me/onboarding. The test task au
 
 ### Memory — Write
 
+For agent command catalogues, publish only the owner-facing slash commands the agent can actually understand and answer from AIMEAT Messages. This is not the MCP tool list and not a copied sample. The command list may be long if the runtime exposes many stable commands.
+
 ```
 POST /v1/memory
 {
   "key": "agents.my-agent.commands",
   "value": [
-    { "name": "/status", "description": "Show agent status", "category": "general" },
-    { "name": "/inbox", "description": "Check inbox", "category": "tasks" }
+    { "name": "/<actual-command>", "description": "<what this command makes the agent do>", "category": "<category>" }
   ],
   "visibility": "owner"
 }
@@ -900,6 +901,12 @@ POST /v1/memory
 The value for commands MUST be a flat array of `{ name, description, category }`. Each name starts with `/`.
 Visibility: `private` (only you), `owner` (you + owner), `public` (everyone)
 
+For agent config visible in the Agent Config tab, write actual config files, hook files, route files, or connector descriptors under `agents.config.*`. If the agent only uses `aimeat connect serve`, describe that connector accurately; do not invent a watchdog file.
+
+If the owner assigns shared tags in the Data Access tab, use `agents.tag.<tag>.*` keys for same-owner handoff notes, project state, queues, and team context. Write shared entries with `visibility: "owner"` and `tags: ["<tag>"]`; list them with `owner_scope=true`, `prefix=agents.tag.<tag>.`, and the same tag filter. Do not put private agent-local secrets in shared tag memory.
+
+For structured research or reusable knowledge, use the Knowledge Package import flow below instead of a placeholder `research.*` memory key.
+
 ### Inbox — Poll
 
 ```
@@ -1114,6 +1121,7 @@ GET {{BASE_URL}}/v1/memory/:gaii/:key — Read another agent's public/shared mem
 - Keys use dot notation (e.g., "service.settings", "user.preferences")
 - Visibility: "private" (default, only you), "owner" (your owner can see), "public" (anyone can read)
 - Tags are optional string arrays for categorization
+- Same-owner shared tag areas use `agents.tag.<tag>.*` keys with visibility "owner" and tags ["<tag>"]. List them with `GET /v1/memory?owner_scope=true&prefix=agents.tag.<tag>.&tags=<tag>` or the equivalent memory-list tool parameters.
 - ttl_hours: auto-delete after N hours (optional)
 - Version increments on each update
 
@@ -1461,6 +1469,9 @@ GET {{BASE_URL}}/v1/catalogue/knowledge/:id — Knowledge package detail
 Knowledge packages are the primary way to share structured information on AIMEAT.
 A package has a **manifest** (metadata: name, tags, content type, synthesis level,
 entry list) and **entries** (the actual content, each with its own visibility).
+When an agent produces research, documentation, datasets, or reusable knowledge,
+import it as a knowledge package instead of storing it as an arbitrary `research.*`
+memory placeholder.
 
 #### Key design: manifest-first discovery
 

package/dist/public/views/profile/agents/agent-card.js

@@ -95,14 +95,17 @@ export default function AgentCard({ agent, onboarding, expanded, onToggle, sessi
         </div>
 
         <!-- Capabilities -->
-        ${(agent.technical_capabilities?.length > 0 || agent.domain_capabilities?.length > 0) && html`
+        ${(agent.technical_capabilities?.length > 0 || agent.domain_capabilities?.length > 0 || agent.languages?.length > 0) && html`
           <div class="pf-agd-capabilities">
             ${(agent.technical_capabilities || []).map(c => html`
               <span key=${c.name || c} class="pf-agd-cap-badge pf-agd-cap-badge--tech">${c.name || c}</span>
             `)}
-            ${(agent.domain_capabilities || []).map(c => html`
+            ${(agent.domain_capabilities || []).filter(c => !String(c).startsWith('Language: ')).map(c => html`
               <span key=${c} class="pf-agd-cap-badge pf-agd-cap-badge--domain">${c}</span>
             `)}
+            ${(agent.languages || []).map(l => html`
+              <span key=${'lang-' + l} class="pf-agd-cap-badge pf-agd-cap-badge--domain">${'Language: ' + l}</span>
+            `)}
           </div>
         `}
 

package/dist/public/views/profile/agents/tab-activity.js

@@ -3,6 +3,7 @@
  * @description Enhanced Activity tab with governance filter and category badges.
  *   Wraps the existing activity subtab with additional filter pills.
  * @version-history
+ *   v1.5.0 -- 2026-05-28 -- Fix governance card: telemetry response field is `events` (not `entries`), and per-event tokens live in e.data.tokens_used / e.data.tokens_in+out
  *   v1.4.0 -- 2026-05-24 -- Audit fix: two-line event layout with secondary detail row
  *   v1.3.0 -- 2026-05-24 -- Wire up MCP status in delivery health from agent data
  *   v1.2.0 -- 2026-05-24 -- Fix: F17 task breakdown, F18 violation red badge, M5 governance i18n namespace
@@ -30,8 +31,14 @@ const FILTERS = [
 ];
 
 function eventCategory(event) {
+  // Task-lifecycle events come back from /activity/log with a non-empty
+  // taskId set by the route. Use that as the primary signal -- the event
+  // type itself is whatever the agent set ("progress") or the lifecycle
+  // emitted ("completed", "failed"), none of which include "task" as a
+  // substring. Fall back to type-substring checks for everything else.
+  if (event.taskId) return 'tasks';
   const type = (event.type || event.event || '').toLowerCase();
-  if (type.includes('task') || type.includes('todo')) return 'tasks';
+  if (type.includes('todo')) return 'tasks';
   if (type.includes('message') || type.includes('msg')) return 'messages';
   if (type.includes('approve') || type.includes('scope') || type.includes('permission') || type.includes('governance') || type.includes('policy') || type.includes('readiness') || type.includes('override')) return 'governance';
   return 'system';
@@ -71,11 +78,18 @@ export default function TabActivity({ agent, agentName, session, showToast }) {
       const tasksFailed = taskEvents.filter(e => { const tp = (e.type || '').toLowerCase(); return tp.includes('failed') || tp.includes('error'); }).length;
       const budget = dirResp?.data?.budget_limits;
       const wh = whResp?.data?.webhook;
-      const telemetryEntries = telResp?.data?.entries || [];
+      // GET /v1/agents/:name/telemetry returns { events, count, per_page }, and per-event
+      // numbers live inside event.data ({ tokens_used } OR { tokens_in + tokens_out }).
+      const telemetryEntries = telResp?.data?.events || telResp?.data?.entries || [];
+      const eventTokens = (e) => {
+        const d = e?.data || {};
+        const used = Number(d.tokens_used) || 0;
+        return used > 0 ? used : (Number(d.tokens_in) || 0) + (Number(d.tokens_out) || 0);
+      };
 
       setGovernance({
         budget,
-        tokensUsedToday: telemetryEntries.reduce((sum, e) => sum + (e.tokens_used || 0), 0),
+        tokensUsedToday: telemetryEntries.reduce((sum, e) => sum + eventTokens(e), 0),
         tasksToday: taskEvents.length,
         tasksCompleted,
         tasksActive,

package/dist/public/views/profile/agents/tab-integration.js

@@ -4,6 +4,9 @@
  *   during onboarding or production status (connection, platform, readiness,
  *   identity, delivery log) after completion.
  * @version-history
+ *   v1.4.0 -- 2026-05-28 -- Treat webhook with empty url as polling: status dot, label, and
+ *                            the webhook section all key off (webhook && webhook.url), not just
+ *                            the webhook object existing. A record with url="" is still polling.
  *   v1.0.0 -- 2026-05-24 -- Initial creation for Agent Detail Tab-View
  *   v1.1.0 -- 2026-05-24 -- Fix 9 UI audit findings: pending icon, readiness score, webhook edit,
  *     strengths/gaps, last validated, roles badge, platform version, bundle update, copy install cmd
@@ -31,6 +34,7 @@ export default function TabIntegration({ agent, onboarding, session, showToast,
   const [webhook, setWebhook] = useState(null);
   const [bundleVersion, setBundleVersion] = useState(null);
   const [deliveries, setDeliveries] = useState([]);
+  const [postChecklist, setPostChecklist] = useState(null);
   const [loading, setLoading] = useState(true);
   const [testing, setTesting] = useState(false);
   const [rerunning, setRerunning] = useState(false);
@@ -47,14 +51,16 @@ export default function TabIntegration({ agent, onboarding, session, showToast,
   async function loadData() {
     setLoading(true);
     try {
-      const [whResp, sbResp, dlResp] = await Promise.all([
+      const [whResp, sbResp, dlResp, obResp] = await Promise.all([
         getWebhookConfig(agentName).catch(() => null),
         getSkillBundleVersion(agentName).catch(() => null),
         getDeliveryLog(agentName, 10).catch(() => null),
+        getOnboarding(agentName).catch(() => null),
       ]);
       setWebhook(whResp?.data || null);
       setBundleVersion(sbResp?.data || null);
       setDeliveries(dlResp?.data?.deliveries || []);
+      setPostChecklist(obResp?.data?.post_onboarding_checklist || null);
     } catch { /* silent */ }
     setLoading(false);
   }
@@ -212,7 +218,7 @@ curl -H "Authorization: Bearer <jwt>" -o skill-bundle.zip "${url}" && unzip skil
 
   const displayDeliveries = showAllDeliveries && allDeliveries ? allDeliveries : deliveries;
 
-  return renderProductionView(agent, onboarding, webhook, bundleVersion, displayDeliveries, handleTestWebhook, testing, handleRerun, rerunning, handleCopyInstall, copiedCmd, handleShowAll, showAllDeliveries, editingWebhook, webhookDraft, setWebhookDraft, handleEditWebhook, handleSaveWebhook, handleCancelWebhook, savingWebhook, handleUpdateBundle, updatingBundle, handleCopyInstallCommand, copiedInstall, handleCopyAgentPrompt, copiedPrompt);
+  return renderProductionView(agent, onboarding, webhook, bundleVersion, displayDeliveries, handleTestWebhook, testing, handleRerun, rerunning, handleCopyInstall, copiedCmd, handleShowAll, showAllDeliveries, editingWebhook, webhookDraft, setWebhookDraft, handleEditWebhook, handleSaveWebhook, handleCancelWebhook, savingWebhook, handleUpdateBundle, updatingBundle, handleCopyInstallCommand, copiedInstall, handleCopyAgentPrompt, copiedPrompt, postChecklist);
 }
 
 function renderOnboardingView(onboarding, agentName, handleRerun, rerunning, handleCopyInstall, copiedCmd, handleCopyInstallCommand, copiedInstall, handleCopyAgentPrompt, copiedPrompt) {
@@ -279,7 +285,7 @@ function renderOnboardingView(onboarding, agentName, handleRerun, rerunning, han
   `;
 }
 
-function renderProductionView(agent, onboarding, webhook, bundleVersion, displayDeliveries, handleTestWebhook, testing, handleRerun, rerunning, handleCopyInstall, copiedCmd, handleShowAll, showAllDeliveries, editingWebhook, webhookDraft, setWebhookDraft, handleEditWebhook, handleSaveWebhook, handleCancelWebhook, savingWebhook, handleUpdateBundle, updatingBundle, handleCopyInstallCommand, copiedInstall, handleCopyAgentPrompt, copiedPrompt) {
+function renderProductionView(agent, onboarding, webhook, bundleVersion, displayDeliveries, handleTestWebhook, testing, handleRerun, rerunning, handleCopyInstall, copiedCmd, handleShowAll, showAllDeliveries, editingWebhook, webhookDraft, setWebhookDraft, handleEditWebhook, handleSaveWebhook, handleCancelWebhook, savingWebhook, handleUpdateBundle, updatingBundle, handleCopyInstallCommand, copiedInstall, handleCopyAgentPrompt, copiedPrompt, postChecklist) {
   const steps = onboarding?.steps || [];
   const agentName = agent.name;
 
@@ -307,8 +313,8 @@ function renderProductionView(agent, onboarding, webhook, bundleVersion, display
         <div class="pf-agd-info-row">
           <span class="pf-agd-info-label">${t('profile.agents.detail.integration.deliveryMethod')}</span>
           <span class="pf-agd-info-value">
-            <span class="pf-agd-status-dot ${webhook && (webhook.failCount ?? 0) < 5 ? 'pf-agd-status-dot--active' : webhook && (webhook.failCount ?? 0) >= 5 ? 'pf-agd-status-dot--error' : 'pf-agd-status-dot--inactive'}"></span>
-            ${webhook ? t('profile.agents.detail.deliveryWebhook') : t('profile.agents.detail.deliveryPolling')}
+            <span class="pf-agd-status-dot ${(webhook && webhook.url && (webhook.failCount ?? 0) < 5) ? 'pf-agd-status-dot--active' : (webhook && webhook.url && (webhook.failCount ?? 0) >= 5) ? 'pf-agd-status-dot--error' : 'pf-agd-status-dot--inactive'}"></span>
+            ${(webhook && webhook.url) ? t('profile.agents.detail.deliveryWebhook') : t('profile.agents.detail.deliveryPolling')}
           </span>
         </div>
         ${webhook ? html`
@@ -434,6 +440,43 @@ function renderProductionView(agent, onboarding, webhook, bundleVersion, display
         </div>
       </div>
 
+      <!-- POST-ONBOARDING SETUP -->
+      ${postChecklist && html`
+        <div class="pf-agd-section">
+          <div class="pf-agd-section-label">${t('profile.agents.detail.integration.postOnboardingSetup')}</div>
+          <div class="pf-agd-info-row">
+            <span class="pf-agd-info-label">${t('profile.agents.detail.integration.commandsRegistered')}</span>
+            <span class="pf-agd-info-value">
+              <span class="pf-agd-status-dot ${postChecklist.commands_registered ? 'pf-agd-status-dot--active' : 'pf-agd-status-dot--inactive'}"></span>
+              ${postChecklist.commands_registered ? t('common.yes') : t('common.no')}
+            </span>
+          </div>
+          <div class="pf-agd-info-row">
+            <span class="pf-agd-info-label">${t('profile.agents.detail.integration.configPublished')}</span>
+            <span class="pf-agd-info-value">
+              <span class="pf-agd-status-dot ${postChecklist.config_published ? 'pf-agd-status-dot--active' : 'pf-agd-status-dot--inactive'}"></span>
+              ${postChecklist.config_published ? t('common.yes') : t('common.no')}
+            </span>
+          </div>
+          <div class="pf-agd-info-row">
+            <span class="pf-agd-info-label">${t('profile.agents.detail.integration.sharedTagsInUse')}</span>
+            <span class="pf-agd-info-value">
+              ${postChecklist.shared_tags_in_use === null
+                ? html`<span class="pf-agd-status-dot pf-agd-status-dot--inactive"></span> ${t('profile.agents.detail.integration.notApplicable')}`
+                : html`<span class="pf-agd-status-dot ${postChecklist.shared_tags_in_use ? 'pf-agd-status-dot--active' : 'pf-agd-status-dot--inactive'}"></span> ${postChecklist.shared_tags_in_use ? t('common.yes') : t('common.no')}`
+              }
+            </span>
+          </div>
+          <div class="pf-agd-info-row">
+            <span class="pf-agd-info-label">${t('profile.agents.detail.integration.knowledgePackages')}</span>
+            <span class="pf-agd-info-value">
+              <span class="pf-agd-status-dot ${postChecklist.knowledge_packages_published ? 'pf-agd-status-dot--active' : 'pf-agd-status-dot--inactive'}"></span>
+              ${postChecklist.knowledge_packages_published ? t('common.yes') : t('common.no')}
+            </span>
+          </div>
+        </div>
+      `}
+
       <!-- IDENTITY -->
       <div class="pf-agd-section">
         <div class="pf-agd-section-label">${t('profile.agents.detail.identity')}</div>