openvisio-agent 0.14.0 → 0.15.0

package/README.md

@@ -58,7 +58,7 @@ Runs the **autonomy loop** — the agent replies to @mentions and picks up ticke
 
 Backend/BYO watchers reconcile immediately whenever the process starts or the WebSocket connects. A direct MCP session uses the backend's actual tools (`list_agents`, `list_projects`, `list_tasks`, `list_task_types`, and `list_activity`) to recover assigned tasks and recent mention activity missed while offline. The same zero-model check runs every five minutes as a safety net; a model starts only when pending work exists.
 
-Routine messages, triage, introductions, catch-up checks, and ticket movement use a lightweight model by default. Claude uses Haiku and Codex uses `gpt-5.6-luna`. Requests that clearly require repository work route to the coding model: Sonnet for Claude and `gpt-5.6-sol` for Codex. Override either lane with `--chat-model` and `--model`.
+Routine messages, triage, introductions, catch-up checks, and ticket movement use a lower-cost model by default. Claude uses Haiku and Codex uses `gpt-5.6-terra`; Luna is intentionally not used because watcher coordination depends on reliable MCP tool use. Requests that require repository work route to the coding model: Sonnet for Claude and `gpt-5.6-sol` for Codex. Override either lane with `--chat-model` and `--model`.
 
 ```bash
 openvisio-agent watch --name ada                 # run in this terminal

package/bin/cli.mjs

@@ -58,8 +58,8 @@ connect --backend
     --model <m>      coding model. Claude defaults to sonnet; Codex defaults to
                      gpt-5.6-sol; OpenCode uses its configured default.
                      Engineers can also change it live from chat: "@agent /model …".
-    --chat-model <m> lightweight coordination model for chat, triage, and board
-                     movement. Defaults: Claude haiku, Codex gpt-5.6-luna.
+    --chat-model <m> coordination model for chat, triage, and board movement.
+                     Defaults: Claude haiku, Codex gpt-5.6-terra.
                      Coding work stays on --model.
     --no-service     skip the background service — just save config + print the
                      watch commands to run yourself.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openvisio-agent",
-  "version": "0.14.0",
+  "version": "0.15.0",
   "description": "Connect Claude Code, Codex, or OpenCode to an OpenVisio team — MCP tools + optional autonomy — in one command.",
   "type": "module",
   "bin": {

package/src/watch.mjs

@@ -215,10 +215,11 @@ export async function runWatch({ flags }) {
   const workdir = chatOnly ? '' : (explicitWorkdir || (saved && (saved.workspace || saved.workdir)) || DEFAULT_WORKSPACE)
   if (workdir) { try { mkdirSync(workdir, { recursive: true }) } catch { /* best-effort; spawn will surface a real problem */ } }
 
-  // Keep routine coordination on the cheapest capable tier. Reserve the stronger
-  // default for coding cycles. Explicit flags and saved choices always win.
+  // Keep routine coordination on a balanced tool-capable tier. Luna proved too
+  // willing to narrate instead of acting in MCP-heavy watcher cycles, so Codex
+  // defaults to Terra for coordination and reserves Sol for repository work.
   const defaultModel = agent === 'claude' ? 'sonnet' : agent === 'codex' ? 'gpt-5.6-sol' : ''
-  const defaultChatModel = agent === 'claude' ? 'haiku' : agent === 'codex' ? 'gpt-5.6-luna' : ''
+  const defaultChatModel = agent === 'claude' ? 'haiku' : agent === 'codex' ? 'gpt-5.6-terra' : ''
   const model = String(flags.model || (saved && saved.model) || defaultModel)
   const chatModel = String(flags['chat-model'] || (saved && saved.chatModel) || defaultChatModel)
 
@@ -343,17 +344,35 @@ function createCodexRunner({ mcpUrl, mcpHeaders, workdir, canCode, maxCycleMs, l
         ...(m ? ['--model', m] : []),
         ...(mcpOverride ? ['-c', mcpOverride] : []),
         full]
-      let child = null, done = false, didCode = false, didMessage = false, outputText = '', jsonlBuffer = ''
-      const finish = (o) => { if (done) return; done = true; clearTimeout(timer); resolve({ ...o, didCode, didMessage, outputText }) }
+      let child = null, done = false, didCode = false, didRepoMutation = false, didMessage = false, outputText = '', jsonlBuffer = ''
+      const mcpCalls = new Set(), mcpErrors = new Set()
+      let didMcpTaskRead = false, didMcpTaskUpdate = false
+      const finish = (o) => {
+        if (done) return
+        done = true
+        clearTimeout(timer)
+        const calls = [...mcpCalls]
+        log('codex MCP calls: ' + (calls.length ? calls.join(', ') : 'none') + (mcpErrors.size ? ' (failed: ' + [...mcpErrors].join(', ') + ')' : ''))
+        resolve({ ...o, didCode, didRepoMutation, didMessage, didMcpTaskRead, didMcpTaskUpdate, mcpCalls: calls, outputText })
+      }
       const inspectLine = (line) => {
         const s = line.trim()
         if (!s) return
         if (/command_execution|file_change|apply_patch|shell_command|exec_command/i.test(s)) didCode = true
+        if (/file_change|apply_patch/i.test(s) || /\b(?:git\s+(?:commit|push)|gh\s+pr\s+create)\b/i.test(s)) didRepoMutation = true
         if (/post_message|comment_ticket/i.test(s)) didMessage = true
         try {
           const event = JSON.parse(s)
           const item = event.item ?? event
           if (item?.type === 'agent_message' && typeof item.text === 'string') outputText += ' ' + item.text
+          if (item?.type === 'mcp_tool_call') {
+            const tool = String(item.tool || item.name || item.method || 'unknown').replace(/^openvisio-team[.:/]/, '')
+            mcpCalls.add(tool)
+            if (/^(?:get_ticket|list_tasks|list_task_types)$/.test(tool)) didMcpTaskRead = true
+            if (tool === 'update_ticket') didMcpTaskUpdate = true
+            if (/post_message|comment_ticket/.test(tool)) didMessage = true
+            if (/fail|error/i.test(String(item.status || '')) || item.error) mcpErrors.add(tool)
+          }
         } catch { /* non-JSON diagnostic */ }
         if (debug) log('  · ' + s.slice(0, 220))
       }
@@ -578,7 +597,7 @@ function loopBackendWs({ wsUrl, apiKey, identifier, slug, claude, agent, mcpConf
   }
   const ensureMcpSession = async () => {
     if (mcpSessionId) return
-    const res = await mcpPost({ jsonrpc: '2.0', id: ++mcpRpcId, method: 'initialize', params: { protocolVersion: '2025-03-26', capabilities: {}, clientInfo: { name: 'openvisio-agent', version: '0.14.0' } } }, false)
+    const res = await mcpPost({ jsonrpc: '2.0', id: ++mcpRpcId, method: 'initialize', params: { protocolVersion: '2025-03-26', capabilities: {}, clientInfo: { name: 'openvisio-agent', version: '0.15.0' } } }, false)
     if (!res.ok) throw new Error('MCP initialize HTTP ' + res.status)
     await mcpPayload(res)
     mcpSessionId = res.headers.get('mcp-session-id') || ''
@@ -690,13 +709,15 @@ function loopBackendWs({ wsUrl, apiKey, identifier, slug, claude, agent, mcpConf
     const heartbeat = targets.length ? setInterval(() => emitStatus('working'), 9000) : null
     try {
       const result = await runCycle(prompt, useModel)
-      // Codex can exit successfully after posting only "I'll do it". For coding
-      // cycles, treat that as incomplete and give it one focused recovery turn.
-      // Do not retry a real blocker, which would only create duplicate noise.
+      // A zero exit is not proof of work. Assigned-ticket cycles must both use
+      // the task MCP and leave repository evidence. A simple `ls` no longer
+      // counts as completion. Do not retry a verified real blocker.
       const legitimateNoWork = /\b(?:no (?:open |assigned |pending )?tasks?|not assigned to (?:me|you)|assigned to (?:another|someone else)|blocked|cannot|can't|missing|need access|permission|unclear)\b/i.test(result?.outputText || '')
-      if (agent === 'codex' && kind === 'full' && result?.subtype === 'ok' && !result.didCode && !legitimateNoWork) {
-        log('coding cycle exited without repository action; running one completion recovery')
-        await runCycle('You exited the assigned coding task without performing repository work. Do not post another acknowledgement or plan. Resume the same task now: inspect the workspace, make the required changes, verify them, commit and push an agent/* branch, open the PR, then post exactly one result update with evidence. If a real blocker appears, report that blocker once.', codeModel)
+      const incomplete = !result?.didRepoMutation || !result?.didMcpTaskRead || !result?.didMcpTaskUpdate
+      if (agent === 'codex' && kind === 'full' && result?.subtype === 'ok' && incomplete && !legitimateNoWork) {
+        const missing = [!result.didMcpTaskRead && 'read the ticket through get_ticket/list_tasks', !result.didRepoMutation && 'perform and verify the repository change', !result.didMcpTaskUpdate && 'update the ticket through update_ticket'].filter(Boolean)
+        log('coding cycle incomplete; recovery requires: ' + missing.join(', '))
+        await runCycle(`The assigned task is NOT complete. Missing evidence: ${missing.join('; ')}. Do not post another acknowledgement or plan. Resume now. First use get_ticket/list_tasks and list_task_types, then do the repository work, verify it, commit and push an agent/* branch, open the PR, call update_ticket with the correct board column, and post exactly one result update with evidence. If a real blocker appears, report it once.`, codeModel)
       }
     } finally {
       if (heartbeat) clearInterval(heartbeat)