@swarmclawai/swarmclaw 1.1.0 → 1.1.3

package/README.md

@@ -15,8 +15,182 @@ Docs: https://swarmclaw.ai/docs
 Website: https://swarmclaw.ai  
 Extension tutorial: https://swarmclaw.ai/docs/extension-tutorial
 
+<div align="center">
+<table>
+ <tr>
+  <td align="center"><strong>Works<br>with</strong></td>
+  <td align="center"><img src="doc/assets/logos/openclaw.svg" width="32" alt="OpenClaw"><br><sub>OpenClaw</sub></td>
+  <td align="center"><img src="doc/assets/logos/claude-code.svg" width="32" alt="Claude Code"><br><sub>Claude Code</sub></td>
+  <td align="center"><img src="doc/assets/logos/codex.svg" width="32" alt="Codex"><br><sub>Codex</sub></td>
+  <td align="center"><img src="doc/assets/logos/gemini-cli.svg" width="32" alt="Gemini CLI"><br><sub>Gemini CLI</sub></td>
+  <td align="center"><img src="doc/assets/logos/opencode.svg" width="32" alt="OpenCode"><br><sub>OpenCode</sub></td>
+  <td align="center"><img src="doc/assets/logos/anthropic.svg" width="32" alt="Anthropic"><br><sub>Anthropic</sub></td>
+  <td align="center"><img src="doc/assets/logos/openai.svg" width="32" alt="OpenAI"><br><sub>OpenAI</sub></td>
+  <td align="center"><img src="doc/assets/logos/google.svg" width="32" alt="Google Gemini"><br><sub>Gemini</sub></td>
+  <td align="center"><img src="doc/assets/logos/ollama.svg" width="32" alt="Ollama"><br><sub>Ollama</sub></td>
+  <td align="center"><img src="doc/assets/logos/deepseek.svg" width="32" alt="DeepSeek"><br><sub>DeepSeek</sub></td>
+  <td align="center"><img src="doc/assets/logos/groq.svg" width="32" alt="Groq"><br><sub>Groq</sub></td>
+  <td align="center"><img src="doc/assets/logos/together.svg" width="32" alt="Together AI"><br><sub>Together</sub></td>
+  <td align="center"><img src="doc/assets/logos/mistral.svg" width="32" alt="Mistral AI"><br><sub>Mistral</sub></td>
+  <td align="center"><img src="doc/assets/logos/xai.svg" width="32" alt="xAI"><br><sub>xAI</sub></td>
+  <td align="center"><img src="doc/assets/logos/fireworks.svg" width="32" alt="Fireworks AI"><br><sub>Fireworks</sub></td>
+  <td align="center"><img src="doc/assets/logos/nebius.svg" width="32" alt="Nebius"><br><sub>Nebius</sub></td>
+  <td align="center"><img src="doc/assets/logos/deepinfra.svg" width="32" alt="DeepInfra"><br><sub>DeepInfra</sub></td>
+ </tr>
+</table>
+</div>
+
+## Use Cases
+
+SwarmClaw is a general-purpose agent runtime. Here are some of the ways people use it.
+
+---
+
+### Personal Assistant
+
+A single agent with memory, web access, scheduling, and file tools — your always-available copilot.
+
+> *"Remember that I prefer window seats. Book research time every Monday at 9am. Summarize the articles I saved last week."*
+
+- Remembers preferences, contacts, and decisions across conversations
+- Schedules reminders, recurring check-ins, and follow-ups
+- Researches, drafts, plans, and manages your day-to-day
+- Bridges to WhatsApp or Telegram so you can message your agent on the go
+
+**Starter kit:** Personal Assistant &rarr; 1 agent, ready in under a minute.
+
+---
+
+### Virtual Company
+
+Build a full org chart of specialized agents that collaborate, delegate, and report up — a lightweight simulation of a real company.
+
+| Role | Agent | Responsibilities |
+|------|-------|-----------------|
+| **CEO** | Strategist | Sets objectives, reviews progress, delegates to department heads |
+| **CTO** | Builder | Owns technical execution, code reviews, architecture decisions |
+| **CFO** | Analyst | Tracks budgets, monitors token spend, produces cost reports |
+| **CMO** | Marketer | Drafts campaigns, manages content calendar, monitors channels |
+| **COO** | Operator | Coordinates cross-agent work, manages schedules, unblocks tasks |
+
+- Each agent has its own provider, model, personality (soul), and tool access
+- The CEO delegates via the task board; department heads pick up work autonomously
+- Heartbeat loops let agents check in on their own, surface blockers, and request approvals
+- Memory means every agent remembers past decisions and context
+- Connect the CMO to Discord/Slack so it can post updates directly
+
+---
+
+### Development Team
+
+A squad of agents mirroring a real engineering team — planning, building, reviewing, and testing in parallel.
+
+| Role | Agent | Tools |
+|------|-------|-------|
+| **Lead** | Architect | Delegation, tasks, schedules, missions |
+| **Dev** | Builder | Shell, files, Claude Code / Codex / OpenCode |
+| **QA** | Tester | Shell, browser, files, web search |
+| **Designer** | Creative | Image generation, browser, web search, files |
+| **Reviewer** | Critic | Files, web search, memory |
+
+- The Lead creates missions and breaks them into tasks on the board
+- Dev agents pick up tasks and delegate to Claude Code, Codex, or OpenCode for implementation
+- QA runs tests, takes screenshots, and files bugs back on the task board
+- The Reviewer audits PRs and flags regressions
+- Structured Sessions let you run a bounded sprint — plan → build → test → review — with durable transcripts
+
+**Starter kit:** Builder Studio &rarr; pre-configured Builder + Reviewer pair.
+
+---
+
+### Research Bureau
+
+Multiple research agents working in parallel, each with different search strategies, then synthesizing findings.
+
+- Spawn a swarm of researchers across different topics or sources
+- Each agent searches, fetches, reads, and summarizes independently
+- A lead agent collects outputs into a structured report with citations
+- Memory stores findings for future reference across conversations
+- Schedule recurring research runs (daily digest, weekly competitive scan)
+
+**Starter kit:** Research Copilot &rarr; 1 focused researcher, scale up with subagents.
+
+---
+
+### OpenClaw Fleet
+
+Distribute autonomous agents across multiple machines using OpenClaw gateways — one control plane, many runtimes.
+
+- Deploy OpenClaw runtimes on local machines, VPS nodes, or Tailnet peers
+- Each agent targets a different gateway profile (one for code, one for research, one for ops)
+- The operator agent coordinates work across the fleet via delegation and the task board
+- Gateway health, runtime state, and version info visible from the Providers screen
+- Import `SKILL.md` files from any OpenClaw instance into SwarmClaw's skill library
+
+**Starter kit:** OpenClaw Fleet &rarr; Operator + Remote Builder + Remote Researcher.
+
+---
+
+### Content Studio
+
+A writer/editor pipeline for blogs, docs, newsletters, marketing copy, or social posts.
+
+- **Writer** drafts content based on briefs, outlines, and style guides
+- **Editor** tightens structure, fixes tone, and flags missing evidence
+- Schedule daily or weekly content runs with automatic handoff
+- Connect to Slack or Discord to publish directly from the pipeline
+- Image generation agent produces visuals alongside copy
+
+**Starter kit:** Content Studio &rarr; Writer + Editor pair.
+
+---
+
+### Customer Support Desk
+
+Agents answering questions on every platform your users are on, with shared memory and escalation paths.
+
+- Bridge a support agent to Discord, Slack, Telegram, WhatsApp, and Teams simultaneously
+- The agent remembers each sender's history, preferences, and open issues
+- Unanswerable questions escalate via `ask_human` or get routed to a specialist agent
+- Schedule a nightly agent to review open threads, follow up on stale conversations, and summarize trends
+- Skills let you codify common support workflows so the agent improves over time
+
+---
+
+### Crypto Operations
+
+Agents with linked wallets for on-chain work — monitoring, trading, signing, and reporting.
+
+- Attach Solana or Ethereum wallets to any agent
+- Agents can check balances, simulate transactions, and execute swaps
+- Approval gates require human sign-off before spending above a threshold
+- Schedule periodic balance checks or price-alert sweeps
+- The operator agent coordinates across multiple wallet-holding agents
+
+---
+
+### Mix and Match
+
+These aren't exclusive templates — they're patterns you combine. A virtual company can have a dev team inside it. A personal assistant can spin up a research swarm on demand. An OpenClaw fleet can run your customer support desk.
+
+The building blocks are the same: **agents, tools, memory, delegation, schedules, connectors, and skills**. SwarmClaw just gives you the control plane to wire them together.
+
 ## Release Notes
 
+### v1.1.2 Highlights
+
+- **Structured Sessions expanded into richer orchestration**: ProtocolRun-based sessions now support dependency-aware step graphs, reusable step outputs, and a broader advanced execution model on the same durable runtime instead of bringing back a separate orchestrator.
+- **Explicit Ollama local/cloud routing**: agents and sessions now persist the user-selected Ollama mode directly, so local Ollama no longer flips to cloud because of model naming or leftover credentials.
+- **Chat and runtime regression hardening**: live-streamed inline media, stale streaming cleanup, exact-output handling, and chat rendering bugs were tightened again, including the recent message-row and avatar rendering regressions.
+- **Nebius and DeepInfra as built-in providers**: both are now first-class providers with setup wizard entries, model discovery, and pre-configured defaults instead of requiring the custom provider workaround.
+- **`stream_options` resilience**: the OpenAI-compatible streaming handler now retries without `stream_options` if a provider rejects it with 400, fixing connectivity for strict endpoints.
+
+### v1.1.1 Highlights
+
+- **Structured Sessions are now contextual**: start bounded structured runs from direct chats, chatrooms, tasks, missions, or schedules, including a new chatroom `/breakout` command that spins up a focused session from the current room with auto-filled participants and kickoff context.
+- **ProtocolRun orchestration matured**: structured sessions now run on the same durable engine for step-based branching, repeat loops, parallel branches, and explicit joins instead of growing a separate orchestration subsystem.
+- **Live-agent runtime hardening**: exact-output contracts, memory preflight behavior, same-channel delivery rendering, inline media, and grounded runtime inspection were all tightened through live-agent validation before release.
+
 ### v1.1.0 Highlights
 
 - **Mission controller and Missions UI**: SwarmClaw now tracks durable multi-step objectives as missions with status, phase, linked tasks, queued turns, recent runs, event history, and operator actions from the new **Missions** surface.
@@ -34,6 +208,7 @@ Extension tutorial: https://swarmclaw.ai/docs/extension-tutorial
 ## What SwarmClaw Focuses On
 
 - **Delegation and background execution**: delegated work, subagents, durable jobs, checkpointing, and background task execution.
+- **Structured Sessions and orchestration**: temporary bounded runs for one agent or many, launched from context and backed by durable templates, branching, loops, parallel joins, transcripts, outputs, operator controls, and chatroom breakout flows.
 - **Autonomy and memory**: heartbeats, schedules, long-running execution, durable memory, reflection memory, human-context learning, document recall, and project-aware context.
 - **OpenClaw integration**: named gateway profiles, external runtimes, deploy helpers, config sync, approval handling, and OpenClaw agent file editing.
 - **Runtime skills**: pinned skills, OpenClaw-compatible `SKILL.md` import, on-demand skill execution, and configurable keyword or embedding-based recommendation.
@@ -113,9 +288,11 @@ Then open `http://localhost:3456`.
 
 ## Core Capabilities
 
-- **Providers**: OpenClaw, OpenAI, Anthropic, Ollama, Google, DeepSeek, Groq, Together, Mistral, xAI, Fireworks, plus compatible custom endpoints.
+- **Providers**: OpenClaw, OpenAI, Anthropic, Ollama, Google, DeepSeek, Groq, Together, Mistral, xAI, Fireworks, Nebius, DeepInfra, plus compatible custom endpoints.
 - **Delegation**: built-in delegation to Claude Code, Codex CLI, OpenCode CLI, Gemini CLI, and native SwarmClaw subagents.
 - **Autonomy**: heartbeat loops, schedules, background jobs, task execution, supervisor recovery, mission control, and agent wakeups.
+- **Orchestration**: durable structured execution with branching, repeat loops, parallel branches, explicit joins, restart-safe run state, and contextual launch from chats, chatrooms, tasks, missions, schedules, and API flows.
+- **Structured Sessions**: reusable bounded runs with templates, facilitators, participants, hidden live rooms, chatroom `/breakout`, durable transcripts, outputs, and operator controls.
 - **Memory**: hybrid recall, graph traversal, journaling, durable documents, project-scoped context, automatic reflection memory, communication preferences, profile and boundary memory, significant events, and open follow-up loops.
 - **Wallets**: balances, transfers, signatures, EVM call/quote/swap flows, and approval-gated execution.
 - **Connectors**: Discord, Slack, Telegram, WhatsApp, Teams, Matrix, OpenClaw, and more.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@swarmclawai/swarmclaw",
-  "version": "1.1.0",
+  "version": "1.1.3",
   "description": "Self-hosted AI runtime for OpenClaw, delegation, autonomy, runtime skills, crypto wallets, and chat platform connectors.",
   "license": "MIT",
   "publishConfig": {

package/src/app/api/agents/[id]/route.ts

@@ -44,6 +44,9 @@ export async function PUT(req: Request, { params }: { params: Promise<{ id: stri
         body.apiEndpoint,
       )
     }
+    if (body.provider !== undefined && body.provider !== 'ollama' && body.ollamaMode === undefined) {
+      agent.ollamaMode = null
+    }
     if (body.sandboxConfig !== undefined) {
       agent.sandboxConfig = normalizeAgentSandboxConfig(body.sandboxConfig)
     }
@@ -64,6 +67,9 @@ export async function PUT(req: Request, { params }: { params: Promise<{ id: stri
         role: target.role,
         provider: (typeof target.provider === 'string' && target.provider.trim() ? target.provider : agent.provider),
         model: typeof target.model === 'string' ? target.model : '',
+        ollamaMode: (typeof target.provider === 'string' ? target.provider : agent.provider) === 'ollama'
+          ? (target.ollamaMode === 'cloud' ? 'cloud' : 'local')
+          : null,
         credentialId: target.credentialId ?? null,
         fallbackCredentialIds: Array.isArray(target.fallbackCredentialIds) ? target.fallbackCredentialIds : [],
         apiEndpoint: normalizeProviderEndpoint(

package/src/app/api/agents/route.ts

@@ -79,6 +79,7 @@ export async function POST(req: Request) {
     systemPrompt: body.systemPrompt,
     provider: body.provider,
     model: body.model,
+    ollamaMode: body.provider === 'ollama' ? (body.ollamaMode || 'local') : null,
     credentialId: body.credentialId,
     fallbackCredentialIds: body.fallbackCredentialIds,
     apiEndpoint: normalizeProviderEndpoint(body.provider, body.apiEndpoint || null),
@@ -88,6 +89,7 @@ export async function POST(req: Request) {
     routingStrategy: body.routingStrategy,
     routingTargets: body.routingTargets?.map((target) => ({
       ...target,
+      ollamaMode: target.provider === 'ollama' ? (target.ollamaMode || 'local') : null,
       apiEndpoint: normalizeProviderEndpoint(target.provider, target.apiEndpoint || null),
     })),
     delegationEnabled: body.delegationEnabled ?? false,

package/src/app/api/agents/thread-route.test.ts

@@ -25,7 +25,7 @@ function seedAgent(id: string, overrides: Record<string, unknown> = {}) {
     fallbackCredentialIds: [],
     apiEndpoint: null,
     gatewayProfileId: null,
-    plugins: ['memory'],
+    extensions: ['memory'],
     createdAt: now,
     updatedAt: now,
     ...overrides,
@@ -84,7 +84,7 @@ test('POST /api/agents/[id]/thread reuses an existing thread for a disabled agen
     sessionType: 'human',
     agentId: 'agent-thread-disabled-existing',
     parentSessionId: null,
-    plugins: ['memory'],
+    extensions: ['memory'],
     tools: ['memory'],
     heartbeatEnabled: false,
     heartbeatIntervalSec: null,
@@ -104,7 +104,7 @@ test('POST /api/agents/[id]/thread reuses an existing thread for a disabled agen
     connectorIdleTimeoutSec: null,
     connectorMaxAgeSec: null,
     mailbox: null,
-    connectorContext: null,
+    connectorContext: undefined,
     lastAutoMemoryAt: null,
     lastHeartbeatText: null,
     lastHeartbeatSentAt: null,

package/src/app/api/autonomy/estop/route.ts

@@ -37,7 +37,7 @@ export async function POST(req: Request) {
         reason: typeof body.reason === 'string' ? body.reason : null,
         engagedBy: typeof body.engagedBy === 'string' ? body.engagedBy : 'user',
       })
-      stopDaemon({ source: `api/autonomy/estop:${level}` })
+      await stopDaemon({ source: `api/autonomy/estop:${level}` })
       const cancelled = level === 'all'
         ? cancelAllRuns('Cancelled because all estop is engaged.')
         : { cancelledQueued: 0, abortedRunning: 0 }

package/src/app/api/chatrooms/[id]/chat/route.test.ts

@@ -35,7 +35,7 @@ test('chatroom route prevents duplicate chained replies when an already-queued a
         name: 'Alpha',
         provider: 'chatroom-provider',
         model: 'room-model',
-        plugins: [],
+        extensions: [],
         createdAt: now,
         updatedAt: now,
       },
@@ -44,7 +44,7 @@ test('chatroom route prevents duplicate chained replies when an already-queued a
         name: 'Beta',
         provider: 'chatroom-provider',
         model: 'room-model',
-        plugins: [],
+        extensions: [],
         createdAt: now,
         updatedAt: now,
       },
@@ -183,7 +183,7 @@ test('chatroom route forwards tool activity and records one reply per participat
         name: 'Alpha',
         provider: 'chatroom-tool-provider',
         model: 'room-tool-model',
-        plugins: ['shell'],
+        extensions: ['shell'],
         createdAt: now,
         updatedAt: now,
       },
@@ -192,7 +192,7 @@ test('chatroom route forwards tool activity and records one reply per participat
         name: 'Beta',
         provider: 'chatroom-tool-provider',
         model: 'room-tool-model',
-        plugins: ['shell'],
+        extensions: ['shell'],
         createdAt: now,
         updatedAt: now,
       },
@@ -256,7 +256,7 @@ test('chatroom route forwards tool activity and records one reply per participat
         return { fullText: reply, finalResponse: reply }
       }
       if (agentId === 'beta') {
-        const reply = 'Beta reviewed the plugin path and agrees with Alpha.'
+        const reply = 'Beta reviewed the extension path and agrees with Alpha.'
         opts.write('data: ' + JSON.stringify({ t: 'r', text: reply }) + '\\n')
         return { fullText: reply, finalResponse: reply }
       }
@@ -268,7 +268,7 @@ test('chatroom route forwards tool activity and records one reply per participat
         new Request('http://local/api/chatrooms/room_1/chat', {
           method: 'POST',
           headers: { 'content-type': 'application/json' },
-          body: JSON.stringify({ senderId: 'user', text: 'Please inspect the workspace and plugin path.' }),
+          body: JSON.stringify({ senderId: 'user', text: 'Please inspect the workspace and extension path.' }),
         }),
         { params: Promise.resolve({ id: 'room_1' }) },
       )

package/src/app/api/chatrooms/route.ts

@@ -10,7 +10,12 @@ export const dynamic = 'force-dynamic'
 
 export async function GET() {
   const chatrooms = loadChatrooms()
-  return NextResponse.json(chatrooms)
+  const filtered: typeof chatrooms = {}
+  for (const [id, chatroom] of Object.entries(chatrooms)) {
+    if (chatroom.hidden === true || chatroom.archivedAt) continue
+    filtered[id] = chatroom
+  }
+  return NextResponse.json(filtered)
 }
 
 export async function POST(req: Request) {

package/src/app/api/chats/[id]/chat/route.test.ts

@@ -48,7 +48,7 @@ test('chat route keeps long-lived user runs alive after stream disconnect and re
         name: 'Workbench Agent',
         provider: 'workbench-provider',
         model: 'wb-model',
-        plugins: [],
+        extensions: [],
         createdAt: now,
         updatedAt: now,
       },
@@ -67,7 +67,7 @@ test('chat route keeps long-lived user runs alive after stream disconnect and re
         lastActiveAt: now,
         sessionType: 'human',
         agentId: 'agent_1',
-        plugins: [],
+        extensions: [],
       },
     })
 
@@ -159,7 +159,7 @@ test('chat route heartbeat runs stay internal and do not persist terminal ack te
         name: 'Heartbeat Agent',
         provider: 'heartbeat-provider',
         model: 'hb-model',
-        plugins: [],
+        extensions: [],
         heartbeatEnabled: true,
         createdAt: now,
         updatedAt: now,
@@ -180,7 +180,7 @@ test('chat route heartbeat runs stay internal and do not persist terminal ack te
         sessionType: 'human',
         agentId: 'agent_1',
         heartbeatEnabled: true,
-        plugins: [],
+        extensions: [],
       },
     })
 
@@ -279,7 +279,7 @@ test('chat route queues a second user message behind the first run and completes
         name: 'Queue Agent',
         provider: 'queue-provider',
         model: 'queue-model',
-        plugins: [],
+        extensions: [],
         createdAt: now,
         updatedAt: now,
       },
@@ -298,7 +298,7 @@ test('chat route queues a second user message behind the first run and completes
         lastActiveAt: now,
         sessionType: 'human',
         agentId: 'agent_1',
-        plugins: [],
+        extensions: [],
       },
     })
 
@@ -356,7 +356,7 @@ test('chat route queues a second user message behind the first run and completes
       assistantReplies,
       runStatuses: runs.listRuns({ sessionId: 'sess_1' }).map((entry) => entry.status),
     }))
-  `, { prefix: 'swarmclaw-chat-route-plugins-' })
+  `, { prefix: 'swarmclaw-chat-route-extensions-' })
 
   assert.match(output.firstRunMeta, /"position":0/)
   assert.match(output.secondRunMeta, /"position":1/)
@@ -367,7 +367,7 @@ test('chat route queues a second user message behind the first run and completes
   assert.deepEqual(output.runStatuses, ['completed', 'completed'])
 })
 
-test('chat route forwards plugin-path tool activity when a plugin-enabled run uses streamAgentChat', () => {
+test('chat route forwards extension-path tool activity when an extension-enabled run uses streamAgentChat', () => {
   const output = runWithTempDataDir<{
     toolCalls: string[]
     toolResults: string[]
@@ -382,10 +382,10 @@ test('chat route forwards plugin-path tool activity when a plugin-enabled run us
     const route = routeMod.default || routeMod
     const stream = streamMod.default || streamMod
 
-    providers.PROVIDERS['plugin-provider'] = {
-      id: 'plugin-provider',
-      name: 'Plugin Provider',
-      models: ['plugin-model'],
+    providers.PROVIDERS['extension-provider'] = {
+      id: 'extension-provider',
+      name: 'Extension Provider',
+      models: ['extension-model'],
       requiresApiKey: false,
       requiresEndpoint: false,
       handler: { streamChat: async () => '' },
@@ -395,10 +395,10 @@ test('chat route forwards plugin-path tool activity when a plugin-enabled run us
     storage.saveAgents({
       agent_1: {
         id: 'agent_1',
-        name: 'Plugin Agent',
-        provider: 'plugin-provider',
-        model: 'plugin-model',
-        plugins: ['web'],
+        name: 'Extension Agent',
+        provider: 'extension-provider',
+        model: 'extension-model',
+        extensions: ['web'],
         createdAt: now,
         updatedAt: now,
       },
@@ -406,18 +406,18 @@ test('chat route forwards plugin-path tool activity when a plugin-enabled run us
     storage.saveSessions({
       sess_1: {
         id: 'sess_1',
-        name: 'Plugin Session',
+        name: 'Extension Session',
         cwd: process.env.WORKSPACE_DIR,
         user: 'workbench',
-        provider: 'plugin-provider',
-        model: 'plugin-model',
+        provider: 'extension-provider',
+        model: 'extension-model',
         claudeSessionId: null,
         messages: [],
         createdAt: now,
         lastActiveAt: now,
         sessionType: 'human',
         agentId: 'agent_1',
-        plugins: ['web'],
+        extensions: ['web'],
       },
     })
 
@@ -460,7 +460,7 @@ test('chat route forwards plugin-path tool activity when a plugin-enabled run us
         toolOutput: 'Fetched queue health summary',
         toolCallId: 'tool-1',
       }) + '\\n')
-      const reply = 'Queue looks healthy and no plugin errors were observed.'
+      const reply = 'Queue looks healthy and no extension errors were observed.'
       opts.write('data: ' + JSON.stringify({ t: 'r', text: reply }) + '\\n')
       return { fullText: reply, finalResponse: reply }
     })
@@ -488,9 +488,9 @@ test('chat route forwards plugin-path tool activity when a plugin-enabled run us
     } finally {
       stream.setStreamAgentChatForTest(null)
     }
-  `, { prefix: 'swarmclaw-chat-route-plugin-events-' })
+  `, { prefix: 'swarmclaw-chat-route-extension-events-' })
 
   assert.deepEqual(output.toolCalls, ['web'])
   assert.deepEqual(output.toolResults, ['Fetched queue health summary'])
-  assert.deepEqual(output.assistantReplies, ['Queue looks healthy and no plugin errors were observed.'])
+  assert.deepEqual(output.assistantReplies, ['Queue looks healthy and no extension errors were observed.'])
 })

package/src/app/api/chats/[id]/messages/route.ts

@@ -1,7 +1,6 @@
 import { NextResponse } from 'next/server'
-import { active, loadStoredItem, upsertStoredItem } from '@/lib/server/storage'
+import { loadStoredItem, upsertStoredItem } from '@/lib/server/storage'
 import { notFound } from '@/lib/server/collection-helpers'
-import { getSessionRunState } from '@/lib/server/runtime/session-run-manager'
 import { materializeStreamingAssistantArtifacts } from '@/lib/chat/chat-streaming-state'
 import { appendSessionNote } from '@/lib/server/session-note'
 import type { Message, Session } from '@/types'
@@ -12,9 +11,9 @@ export async function GET(req: Request, { params }: { params: Promise<{ id: stri
   if (!session) return notFound()
   session.messages = Array.isArray(session.messages) ? session.messages : []
 
-  const run = getSessionRunState(id)
-  const hasLiveRun = active.has(id) || !!run.runningRunId
-  if (!hasLiveRun && materializeStreamingAssistantArtifacts(session.messages)) {
+  const sessionClaimsActive = session.active === true
+    || (typeof session.currentRunId === 'string' && session.currentRunId.trim().length > 0)
+  if (!sessionClaimsActive && materializeStreamingAssistantArtifacts(session.messages)) {
     upsertStoredItem('sessions', id, session)
   }
 

package/src/app/api/chats/[id]/route.ts

@@ -64,6 +64,11 @@ export async function PUT(req: Request, { params }: { params: Promise<{ id: stri
   else if (agentIdUpdateProvided && linkedRoute?.model) session.model = linkedRoute.model
   else if (agentIdUpdateProvided && linkedAgent?.model !== undefined) session.model = linkedAgent.model
 
+  if (updates.ollamaMode !== undefined) session.ollamaMode = updates.ollamaMode
+  else if (updates.provider !== undefined && updates.provider !== 'ollama') session.ollamaMode = null
+  else if (agentIdUpdateProvided && linkedRoute) session.ollamaMode = linkedRoute.ollamaMode ?? null
+  else if (agentIdUpdateProvided && linkedAgent) session.ollamaMode = linkedAgent.ollamaMode ?? null
+
   if (updates.credentialId !== undefined) session.credentialId = updates.credentialId
   else if (agentIdUpdateProvided && linkedRoute) session.credentialId = linkedRoute.credentialId ?? null
   else if (agentIdUpdateProvided && linkedAgent) session.credentialId = linkedAgent.credentialId ?? null

package/src/app/api/chats/messages-route.test.ts

@@ -0,0 +1,65 @@
+import assert from 'node:assert/strict'
+import test from 'node:test'
+
+import { runWithTempDataDir } from '@/lib/server/test-utils/run-with-temp-data-dir'
+
+test('chat messages route materializes stale streaming artifacts even if runtime memory is stale', () => {
+  const output = runWithTempDataDir<{
+    status: number
+    returnedStreaming: boolean | null
+    returnedText: string | null
+    persistedStreaming: boolean | null
+    persistedText: string | null
+  }>(`
+    const storageMod = await import('./src/lib/server/storage')
+    const routeMod = await import('./src/app/api/chats/[id]/messages/route')
+    const storage = storageMod.default || storageMod
+    const route = routeMod.default || routeMod
+
+    storage.upsertStoredItem('sessions', 'session-stale', {
+      id: 'session-stale',
+      name: 'Stale session',
+      provider: 'ollama',
+      model: 'test-model',
+      createdAt: 1,
+      updatedAt: 1,
+      active: false,
+      currentRunId: null,
+      messages: [
+        { role: 'user', text: 'hello', time: 1 },
+        {
+          role: 'assistant',
+          text: 'partial reply',
+          time: 2,
+          streaming: true,
+          toolEvents: [{ name: 'http_request', input: '{}', output: '{"ok":true}' }],
+        },
+      ],
+    })
+
+    storage.active.set('session-stale', { kill() {} })
+
+    const response = await route.GET(
+      new Request('http://local/api/chats/session-stale/messages'),
+      { params: Promise.resolve({ id: 'session-stale' }) },
+    )
+    const payload = await response.json()
+    const persisted = storage.loadSession('session-stale')
+    const returned = Array.isArray(payload) ? payload[payload.length - 1] : null
+    const saved = Array.isArray(persisted?.messages) ? persisted.messages[persisted.messages.length - 1] : null
+
+    console.log(JSON.stringify({
+      status: response.status,
+      returnedStreaming: returned?.streaming === true,
+      returnedText: returned?.text || null,
+      persistedStreaming: saved?.streaming === true,
+      persistedText: saved?.text || null,
+    }))
+  `, { prefix: 'swarmclaw-chat-messages-route-' })
+
+  assert.equal(output.status, 200)
+  assert.equal(output.returnedStreaming, false)
+  assert.equal(output.persistedStreaming, false)
+  assert.equal(output.returnedText, 'partial reply')
+  assert.equal(output.persistedText, 'partial reply')
+})

package/src/app/api/chats/route.ts

@@ -131,6 +131,7 @@ export async function POST(req: Request) {
     user: body.user || 'user',
     provider: body.provider || agent?.provider || 'claude-cli',
     model: body.model || agent?.model || '',
+    ollamaMode: body.ollamaMode ?? agent?.ollamaMode ?? ((body.provider || agent?.provider) === 'ollama' ? 'local' : null),
     credentialId: body.credentialId || agent?.credentialId || null,
     fallbackCredentialIds: body.fallbackCredentialIds || agent?.fallbackCredentialIds || [],
     apiEndpoint: normalizeProviderEndpoint(

package/src/app/api/credentials/[id]/route.ts

@@ -1,5 +1,5 @@
 import { NextResponse } from 'next/server'
-import { loadCredentials, saveCredentials } from '@/lib/server/storage'
+import { loadCredentials, deleteCredential } from '@/lib/server/storage'
 import { notFound } from '@/lib/server/collection-helpers'
 
 export async function DELETE(_req: Request, { params }: { params: Promise<{ id: string }> }) {
@@ -8,8 +8,7 @@ export async function DELETE(_req: Request, { params }: { params: Promise<{ id:
   if (!creds[credId]) {
     return notFound()
   }
-  delete creds[credId]
-  saveCredentials(creds)
+  deleteCredential(credId)
   console.log(`[credentials] deleted ${credId}`)
   return new NextResponse('OK')
 }

package/src/app/api/daemon/route.ts

@@ -19,7 +19,7 @@ export async function POST(req: Request) {
     return NextResponse.json({ ok: true, status: 'running' })
   } else if (action === 'stop') {
     const { stopDaemon } = await import('@/lib/server/runtime/daemon-state')
-    stopDaemon({ source: 'api/daemon:post:stop', manualStop: true })
+    await stopDaemon({ source: 'api/daemon:post:stop', manualStop: true })
     notify('daemon')
     return NextResponse.json({ ok: true, status: 'stopped' })
   }