@turmind/halo 1.1.2 → 1.1.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/admin-out/404.html +1 -1
- package/admin-out/_next/static/chunks/212-70bd2971392bde84.js +1 -0
- package/admin-out/_next/static/chunks/app/page-71c576815b4a30d9.js +1 -0
- package/admin-out/index.html +1 -1
- package/admin-out/index.txt +4 -4
- package/bundled-docs/design/agentcore.md +35 -0
- package/bundled-docs/design/cron.md +3 -3
- package/bundled-docs/design/goal-mode.md +1 -0
- package/bundled-docs/design/session.md +3 -0
- package/bundled-docs/dev/api.md +2 -2
- package/dist/index.js +207 -17
- package/package.json +1 -1
- package/templates/agents/default/agent.yaml +1 -1
- package/templates/models/aws-bedrock-claude-invoke.yaml +28 -0
- package/templates/skills/cron/SKILL.md +8 -0
- package/templates/skills/cron/manage-cron.py +27 -3
- package/templates/skills/skill/SKILL.md +1 -1
- package/templates/skills/web-search/SKILL.md +44 -0
- package/templates/skills/web-search/search.py +137 -0
- package/templates/skills/workspace/share.md +1 -1
- package/templates/skills/workspace/stage.py +1 -1
- package/admin-out/_next/static/chunks/212-8ac9dfe9c24e512c.js +0 -1
- package/admin-out/_next/static/chunks/app/page-2076ec04359bb395.js +0 -1
- package/templates/skills/nova-web-search/SKILL.md +0 -65
- /package/admin-out/_next/static/{bZcoAqHBQyOvzwS5c84EJ → PuVQROsIREQUt1b6EFWJR}/_buildManifest.js +0 -0
- /package/admin-out/_next/static/{bZcoAqHBQyOvzwS5c84EJ → PuVQROsIREQUt1b6EFWJR}/_ssgManifest.js +0 -0
package/admin-out/index.html
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
<!DOCTYPE html><!--
|
|
1
|
+
<!DOCTYPE html><!--PuVQROsIREQUt1b6EFWJR--><html lang="en" class="dark"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="preload" href="/_next/static/media/e4af272ccee01ff0-s.p.woff2" as="font" crossorigin="" type="font/woff2"/><link rel="stylesheet" href="/_next/static/css/0d0ca7b3c8cc5562.css" data-precedence="next"/><link rel="stylesheet" href="/_next/static/css/659eccb5db697b76.css" data-precedence="next"/><link rel="preload" as="script" fetchPriority="low" href="/_next/static/chunks/webpack-fc1574554e7b1108.js"/><script src="/_next/static/chunks/fb4ec4d6-3fa44f69484f91b9.js" async=""></script><script src="/_next/static/chunks/635-d7fd95bff8674116.js" async=""></script><script src="/_next/static/chunks/main-app-483b436873410ddc.js" async=""></script><script src="/_next/static/chunks/212-70bd2971392bde84.js" async=""></script><script src="/_next/static/chunks/app/layout-c2fa8035998e48d5.js" async=""></script><script src="/_next/static/chunks/1d2d5650-810a3ca1ae20cab5.js" async=""></script><script src="/_next/static/chunks/438-866a1a20e9efa78a.js" async=""></script><script src="/_next/static/chunks/app/page-71c576815b4a30d9.js" async=""></script><meta name="next-size-adjust" content=""/><title>Halo - Multi-Agent Workspace</title><meta name="description" content="Multi-agent collaboration workspace for complex project delivery"/><link rel="icon" href="/favicon.ico" type="image/x-icon" sizes="16x16"/><link rel="icon" href="/icon.svg?3a6863548daca964" type="image/svg+xml" sizes="any"/><script>try{var t=localStorage.getItem('halo_theme');if(t==='light'||t==='midnight'||t==='warm')document.documentElement.dataset.theme=t}catch(e){}</script><script src="/_next/static/chunks/polyfills-42372ed130431b0a.js" noModule=""></script></head><body class="__variable_f367f3 font-sans antialiased"><div hidden=""><!--$--><!--/$--></div><div class="flex h-screen w-screen items-center justify-center bg-[var(--background)]"><div class="text-sm text-[var(--muted-foreground)]">Loading...</div></div><!--$--><!--/$--><script src="/_next/static/chunks/webpack-fc1574554e7b1108.js" id="_R_" async=""></script><script>(self.__next_f=self.__next_f||[]).push([0])</script><script>self.__next_f.push([1,"1:\"$Sreact.fragment\"\n2:I[59391,[\"212\",\"static/chunks/212-70bd2971392bde84.js\",\"177\",\"static/chunks/app/layout-c2fa8035998e48d5.js\"],\"ThemeProvider\"]\n3:I[26967,[\"212\",\"static/chunks/212-70bd2971392bde84.js\",\"177\",\"static/chunks/app/layout-c2fa8035998e48d5.js\"],\"AppI18nProvider\"]\n4:I[66048,[],\"\"]\n5:I[29926,[],\"\"]\n6:I[57917,[],\"ClientPageRoot\"]\n7:I[61089,[\"560\",\"static/chunks/1d2d5650-810a3ca1ae20cab5.js\",\"438\",\"static/chunks/438-866a1a20e9efa78a.js\",\"212\",\"static/chunks/212-70bd2971392bde84.js\",\"974\",\"static/chunks/app/page-71c576815b4a30d9.js\"],\"default\"]\na:I[11789,[],\"OutletBoundary\"]\nc:I[21528,[],\"AsyncMetadataOutlet\"]\ne:I[11789,[],\"ViewportBoundary\"]\n10:I[11789,[],\"MetadataBoundary\"]\n11:\"$Sreact.suspense\"\n13:I[79836,[],\"\"]\n:HL[\"/_next/static/media/e4af272ccee01ff0-s.p.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n:HL[\"/_next/static/css/0d0ca7b3c8cc5562.css\",\"style\"]\n:HL[\"/_next/static/css/659eccb5db697b76.css\",\"style\"]\n"])</script><script>self.__next_f.push([1,"0:{\"P\":null,\"b\":\"PuVQROsIREQUt1b6EFWJR\",\"p\":\"\",\"c\":[\"\",\"\"],\"i\":false,\"f\":[[[\"\",{\"children\":[\"__PAGE__\",{}]},\"$undefined\",\"$undefined\",true],[\"\",[\"$\",\"$1\",\"c\",{\"children\":[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/_next/static/css/0d0ca7b3c8cc5562.css\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}]],[\"$\",\"html\",null,{\"lang\":\"en\",\"className\":\"dark\",\"suppressHydrationWarning\":true,\"children\":[[\"$\",\"head\",null,{\"children\":[\"$\",\"script\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"try{var t=localStorage.getItem('halo_theme');if(t==='light'||t==='midnight'||t==='warm')document.documentElement.dataset.theme=t}catch(e){}\"}}]}],[\"$\",\"body\",null,{\"className\":\"__variable_f367f3 font-sans antialiased\",\"children\":[\"$\",\"$L2\",null,{\"children\":[\"$\",\"$L3\",null,{\"children\":[\"$\",\"$L4\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L5\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[[\"$\",\"title\",null,{\"children\":\"404: This page could not be found.\"}],[\"$\",\"div\",null,{\"style\":{\"fontFamily\":\"system-ui,\\\"Segoe UI\\\",Roboto,Helvetica,Arial,sans-serif,\\\"Apple Color Emoji\\\",\\\"Segoe UI Emoji\\\"\",\"height\":\"100vh\",\"textAlign\":\"center\",\"display\":\"flex\",\"flexDirection\":\"column\",\"alignItems\":\"center\",\"justifyContent\":\"center\"},\"children\":[\"$\",\"div\",null,{\"children\":[[\"$\",\"style\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}\"}}],[\"$\",\"h1\",null,{\"className\":\"next-error-h1\",\"style\":{\"display\":\"inline-block\",\"margin\":\"0 20px 0 0\",\"padding\":\"0 23px 0 0\",\"fontSize\":24,\"fontWeight\":500,\"verticalAlign\":\"top\",\"lineHeight\":\"49px\"},\"children\":404}],[\"$\",\"div\",null,{\"style\":{\"display\":\"inline-block\"},\"children\":[\"$\",\"h2\",null,{\"style\":{\"fontSize\":14,\"fontWeight\":400,\"lineHeight\":\"49px\",\"margin\":0},\"children\":\"This page could not be found.\"}]}]]}]}]],[]],\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]}]}]}]]}]]}],{\"children\":[\"__PAGE__\",[\"$\",\"$1\",\"c\",{\"children\":[[\"$\",\"$L6\",null,{\"Component\":\"$7\",\"searchParams\":{},\"params\":{},\"promises\":[\"$@8\",\"$@9\"]}],[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/_next/static/css/659eccb5db697b76.css\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}]],[\"$\",\"$La\",null,{\"children\":[\"$Lb\",[\"$\",\"$Lc\",null,{\"promise\":\"$@d\"}]]}]]}],{},null,false]},null,false],[\"$\",\"$1\",\"h\",{\"children\":[null,[[\"$\",\"$Le\",null,{\"children\":\"$Lf\"}],[\"$\",\"meta\",null,{\"name\":\"next-size-adjust\",\"content\":\"\"}]],[\"$\",\"$L10\",null,{\"children\":[\"$\",\"div\",null,{\"hidden\":true,\"children\":[\"$\",\"$11\",null,{\"fallback\":null,\"children\":\"$L12\"}]}]}]]}],false]],\"m\":\"$undefined\",\"G\":[\"$13\",[]],\"s\":false,\"S\":true}\n"])</script><script>self.__next_f.push([1,"8:{}\n9:\"$0:f:0:1:2:children:1:props:children:0:props:params\"\n"])</script><script>self.__next_f.push([1,"f:[[\"$\",\"meta\",\"0\",{\"charSet\":\"utf-8\"}],[\"$\",\"meta\",\"1\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}]]\nb:null\n"])</script><script>self.__next_f.push([1,"14:I[89592,[],\"IconMark\"]\nd:{\"metadata\":[[\"$\",\"title\",\"0\",{\"children\":\"Halo - Multi-Agent Workspace\"}],[\"$\",\"meta\",\"1\",{\"name\":\"description\",\"content\":\"Multi-agent collaboration workspace for complex project delivery\"}],[\"$\",\"link\",\"2\",{\"rel\":\"icon\",\"href\":\"/favicon.ico\",\"type\":\"image/x-icon\",\"sizes\":\"16x16\"}],[\"$\",\"link\",\"3\",{\"rel\":\"icon\",\"href\":\"/icon.svg?3a6863548daca964\",\"type\":\"image/svg+xml\",\"sizes\":\"any\"}],[\"$\",\"$L14\",\"4\",{}]],\"error\":null,\"digest\":\"$undefined\"}\n"])</script><script>self.__next_f.push([1,"12:\"$d:metadata\"\n"])</script></body></html>
|
package/admin-out/index.txt
CHANGED
|
@@ -1,10 +1,10 @@
|
|
|
1
1
|
1:"$Sreact.fragment"
|
|
2
|
-
2:I[59391,["212","static/chunks/212-
|
|
3
|
-
3:I[26967,["212","static/chunks/212-
|
|
2
|
+
2:I[59391,["212","static/chunks/212-70bd2971392bde84.js","177","static/chunks/app/layout-c2fa8035998e48d5.js"],"ThemeProvider"]
|
|
3
|
+
3:I[26967,["212","static/chunks/212-70bd2971392bde84.js","177","static/chunks/app/layout-c2fa8035998e48d5.js"],"AppI18nProvider"]
|
|
4
4
|
4:I[66048,[],""]
|
|
5
5
|
5:I[29926,[],""]
|
|
6
6
|
6:I[57917,[],"ClientPageRoot"]
|
|
7
|
-
7:I[61089,["560","static/chunks/1d2d5650-810a3ca1ae20cab5.js","438","static/chunks/438-866a1a20e9efa78a.js","212","static/chunks/212-
|
|
7
|
+
7:I[61089,["560","static/chunks/1d2d5650-810a3ca1ae20cab5.js","438","static/chunks/438-866a1a20e9efa78a.js","212","static/chunks/212-70bd2971392bde84.js","974","static/chunks/app/page-71c576815b4a30d9.js"],"default"]
|
|
8
8
|
a:I[11789,[],"OutletBoundary"]
|
|
9
9
|
c:I[21528,[],"AsyncMetadataOutlet"]
|
|
10
10
|
e:I[11789,[],"ViewportBoundary"]
|
|
@@ -14,7 +14,7 @@ e:I[11789,[],"ViewportBoundary"]
|
|
|
14
14
|
:HL["/_next/static/media/e4af272ccee01ff0-s.p.woff2","font",{"crossOrigin":"","type":"font/woff2"}]
|
|
15
15
|
:HL["/_next/static/css/0d0ca7b3c8cc5562.css","style"]
|
|
16
16
|
:HL["/_next/static/css/659eccb5db697b76.css","style"]
|
|
17
|
-
0:{"P":null,"b":"
|
|
17
|
+
0:{"P":null,"b":"PuVQROsIREQUt1b6EFWJR","p":"","c":["",""],"i":false,"f":[[["",{"children":["__PAGE__",{}]},"$undefined","$undefined",true],["",["$","$1","c",{"children":[[["$","link","0",{"rel":"stylesheet","href":"/_next/static/css/0d0ca7b3c8cc5562.css","precedence":"next","crossOrigin":"$undefined","nonce":"$undefined"}]],["$","html",null,{"lang":"en","className":"dark","suppressHydrationWarning":true,"children":[["$","head",null,{"children":["$","script",null,{"dangerouslySetInnerHTML":{"__html":"try{var t=localStorage.getItem('halo_theme');if(t==='light'||t==='midnight'||t==='warm')document.documentElement.dataset.theme=t}catch(e){}"}}]}],["$","body",null,{"className":"__variable_f367f3 font-sans antialiased","children":["$","$L2",null,{"children":["$","$L3",null,{"children":["$","$L4",null,{"parallelRouterKey":"children","error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":404}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],[]],"forbidden":"$undefined","unauthorized":"$undefined"}]}]}]}]]}]]}],{"children":["__PAGE__",["$","$1","c",{"children":[["$","$L6",null,{"Component":"$7","searchParams":{},"params":{},"promises":["$@8","$@9"]}],[["$","link","0",{"rel":"stylesheet","href":"/_next/static/css/659eccb5db697b76.css","precedence":"next","crossOrigin":"$undefined","nonce":"$undefined"}]],["$","$La",null,{"children":["$Lb",["$","$Lc",null,{"promise":"$@d"}]]}]]}],{},null,false]},null,false],["$","$1","h",{"children":[null,[["$","$Le",null,{"children":"$Lf"}],["$","meta",null,{"name":"next-size-adjust","content":""}]],["$","$L10",null,{"children":["$","div",null,{"hidden":true,"children":["$","$11",null,{"fallback":null,"children":"$L12"}]}]}]]}],false]],"m":"$undefined","G":["$13",[]],"s":false,"S":true}
|
|
18
18
|
8:{}
|
|
19
19
|
9:"$0:f:0:1:2:children:1:props:children:0:props:params"
|
|
20
20
|
f:[["$","meta","0",{"charSet":"utf-8"}],["$","meta","1",{"name":"viewport","content":"width=device-width, initial-scale=1"}]]
|
|
@@ -76,6 +76,41 @@ whole lifetime (audit B-L3). Every command is `accessLevel: 'full'` by design:
|
|
|
76
76
|
auth terminated upstream at AgentCore, so whoever reached this socket already
|
|
77
77
|
owns the isolated per-user workspace behind it.
|
|
78
78
|
|
|
79
|
+
## WS image upload protocol (chunking)
|
|
80
|
+
|
|
81
|
+
The AgentCore WS proxy hard-caps a single frame at **64KB** — send more and
|
|
82
|
+
the connection is cut with close code 1009 ("Policy violated: message size
|
|
83
|
+
limit of 64 KB for a message frame is exceeded", verified against the Tokyo
|
|
84
|
+
prod runtime). An inline base64 image blows past that instantly, so images
|
|
85
|
+
ride as chunked `image_chunk` frames, assembled server-side, then referenced
|
|
86
|
+
by id from the actual message frame:
|
|
87
|
+
|
|
88
|
+
```jsonc
|
|
89
|
+
// 1..N chunk frames per image (inputText empty string is required — the
|
|
90
|
+
// proxy only forwards client frames that carry an inputText key at all)
|
|
91
|
+
{"inputText":"", "type":"image_chunk", "uploadId":"u1", "seq":0, "total":8,
|
|
92
|
+
"mimeType":"image/jpeg", "data":"<base64 slice, ≤48KB>"}
|
|
93
|
+
|
|
94
|
+
// message frame referencing the finished upload(s)
|
|
95
|
+
{"inputText":"describe this", "imageRefs":["u1"]}
|
|
96
|
+
```
|
|
97
|
+
|
|
98
|
+
Limits (all enforced in `acceptChunk` / `claimImageRefs`): ≤4 images per
|
|
99
|
+
message, ≤8MB of base64 per image, ≤4 concurrent pending uploads per
|
|
100
|
+
connection, ≤256 chunks per upload. Assembly state (`Map<uploadId,
|
|
101
|
+
PendingUpload>`) is **per-connection, in-memory only** — a dropped socket
|
|
102
|
+
discards any partial uploads and the client just re-sends; there is no
|
|
103
|
+
cross-reconnect persistence by design. The server doesn't ack individual
|
|
104
|
+
chunks (that'd add N round-trips for no benefit since the proxy forwards
|
|
105
|
+
mid-stream frames fine) — it only replies with an `error` frame when a chunk
|
|
106
|
+
or `imageRefs` fails validation.
|
|
107
|
+
|
|
108
|
+
On a completed reference, the image is decoded and persisted via
|
|
109
|
+
`saveInboundMedia` into the user's workspace — the same storage path
|
|
110
|
+
telegram uses — and the message text gets a `[图片已保存: <path>]` marker
|
|
111
|
+
appended so history replay can show the image was there without re-sending
|
|
112
|
+
the bytes.
|
|
113
|
+
|
|
79
114
|
## Session lifecycle (the part everyone gets wrong)
|
|
80
115
|
|
|
81
116
|
- Idle timeout (`idleRuntimeSessionTimeout`) terminates a session whose
|
|
@@ -52,9 +52,9 @@ Each fire:
|
|
|
52
52
|
1. **Concurrency guard**: if the same `jobId` is already running in this process (in-memory `_inflight` set), insert a `cron_runs` row with `status='skipped'`, `failureReason='previous run still in progress'`, broadcast, and bail without spawning. Applies to both scheduled fires and manual run-now clicks. Two overlapping cli children would double-write the same `cron-<jobId>` on-disk session state; SessionManager's per-session lock is in-process and can't see across cli children, so this set is the cheapest place to enforce serialization. The set itself is in-memory, but its restart blind spot is covered: the boot-time orphan sweep (below) re-enters stale jobIds before croner re-arms.
|
|
53
53
|
2. Insert a `cron_runs` row with `status='running'` up front (UI sees it mid-flight); broadcast `cron:run_changed`.
|
|
54
54
|
3. Check `job.workspacePath` exists — fail loudly if the workspace was moved/deleted.
|
|
55
|
-
4. Spawn `halo cli -a <agent> -s cron-<jobId> -w <workspace>`, prompt on **stdin** (avoids Windows argv length limits). The stable `cron-<jobId>` session id means each fire *resumes the same session*, so the conversation accumulates and is reviewable in the admin Sessions tab. The child's pid is written back onto the `running` row (`cron_runs.pid`, nullable) — this is what makes the orphan sweep possible after a server crash.
|
|
55
|
+
4. Spawn `halo cli -a <agent> -s cron-<jobId> -w <workspace>`, prompt on **stdin** (avoids Windows argv length limits). The stable `cron-<jobId>` session id means each fire *resumes the same session*, so the conversation accumulates and is reviewable in the admin Sessions tab. The child's pid is written back onto the `running` row (`cron_runs.pid`, nullable) — this is what makes the orphan sweep possible after a server crash. Note the **dual-writer layout** this creates: the cli child and the server share the workspace's session files. The server side is view-only for these sessions — admin subscribes seed a UIState from disk, and the WS detach-save skips it via the dirty gate (see [session.md](session.md#ws-disconnect-resilience)); without that gate a frozen server snapshot would overwrite the cli child's newer messages (the cron-session UI-log truncation incident). Live streaming of a cli-driven session into the admin is out of scope — events don't cross processes; the Sessions tab re-reads the file on open.
|
|
56
56
|
5. Tee stdout + stderr live to `~/.halo/global/logs/cron/<runId>.log`; capture stdout to memory for dispatch.
|
|
57
|
-
6. Enforce a **
|
|
57
|
+
6. Enforce a **per-job timeout** (`job.timeoutSec ?? 3600`, the nullable `cron_jobs.timeout_sec` validated 60–21600 at every write surface; a change takes effect on the job's next fire, no croner re-instantiation needed) via a Node timer (cross-platform, not the Linux-only `timeout(1)`), with a **two-phase kill**: SIGTERM the direct child first — the cli has a SIGTERM handler that stops the harness, repairs + flushes the session, kills its own shell_exec process groups, and exits 143 — then, if it's still alive after a 30s grace, SIGKILL the entire descendant tree (POSIX ppid-walk over one `ps` snapshot; `taskkill /T /F` on Windows) so no grandchild survives to double-write the workspace on the next fire. A ppid walk, not a process-group kill: the cli sandbox spawns shell_exec workers `detached` into their own groups, so `kill(-pid)` would miss them. Timed-out runs still report exit code 124. Generous because overlap-of-the-same-job is already blocked up-front in step 1; this is just the long-stop reaper for a truly stuck child.
|
|
58
58
|
7. Classify: exit 124 → `timeout`; non-zero → `failed`; zero but empty stdout → `failed` ("nothing to dispatch"); else `succeeded`.
|
|
59
59
|
8. On success only, `dispatchToTargets(stdout, targets, job.workspacePath)` — the raw stdout goes down as-is; `MEDIA:` extraction happens per-target inside the dispatcher (see Dispatch model). If every target fails, downgrade to `failed`.
|
|
60
60
|
9. `finalize`: write the terminal `cron_runs` row, update `cron_jobs.lastRun*`, disable one-shot jobs, broadcast. The `_inflight` entry is released in `finally`, regardless of outcome.
|
|
@@ -111,6 +111,6 @@ interface CronChannelDispatcher {
|
|
|
111
111
|
|
|
112
112
|
## Scope
|
|
113
113
|
|
|
114
|
-
Supported: recurring (cron expr) + one-shot (`runAt`) schedules; per-timezone; multi-target fan-out; stable accumulating session per job; run-now (manual trigger); admin UI history with per-run logs + dispatch results.
|
|
114
|
+
Supported: recurring (cron expr) + one-shot (`runAt`) schedules; per-timezone; per-job configurable timeout (`timeoutSec`, 60–21600s, default 3600); multi-target fan-out; stable accumulating session per job; run-now (manual trigger); admin UI history with per-run logs + dispatch results.
|
|
115
115
|
|
|
116
116
|
Not supported: sub-minute schedules below croner's resolution; in-process job execution (always a fresh cli child); conversation context carried *between different jobs* (each job has its own `cron-<jobId>` session).
|
|
@@ -69,6 +69,7 @@ Gates, in order:
|
|
|
69
69
|
|
|
70
70
|
1. Root only (`parentId === null`), row carries `goalSessionId`, goal status is `running`.
|
|
71
71
|
2. **Subtree-quiet gate** (inherited from `tryReportToParent`): no active children in the db **and** an empty message queue. A W that dispatched executors and idled while they run does NOT end the round — their reports wake W first.
|
|
72
|
+
- **Aborted-round marker**: the report body is `finalOutput || output || '(no output)'`; when W's turn was killed by an unrecoverable error (`turnError` set — retry budget exhausted / account error), it is prefixed with `[WORKER ABORTED: … Error: <text> … judge this as an interrupted round, do not score it as a completed result …]`. Without it G scored mid-turn fragments (or a literal "(no output)") as real rounds — same defect as the sub-agent auto-report, same prescription (see [session.md](session.md#session-lifecycle)): prefix, don't suppress (skipping delivery would stall the loop), prepended *before* the truncation cap so it always survives. The marker rides every downstream delivery path (question-stop / halt headers describe the stop, the marker describes the round's shape — both true), and an aborted round still counts toward round accounting and the no-progress hash: three identical aborts trip the breaker, which is the right read for a worker dying the same way thrice.
|
|
72
73
|
3. **Spec tamper gate**: sha256 of `GOAL_SPEC.md` must equal the `specHash` stamped at attach. Changed or missing → halt (`spec-tampered`), back-pointer cleared, G instructed to write a halt diagnosis. Never silently restore.
|
|
73
74
|
4. **Question-stop**: a report containing `<NEED_INPUT>` is delivered with a question-stop header and consumes **neither** the round counter nor the no-progress budget — the worker is waiting, not failing. G triages: answerable from spec + scene → `goal_decide` + relay; genuine user-sovereignty fork → park to the user.
|
|
74
75
|
5. **Round accounting**: `round++`; `noProgress` increments when the report hash is unchanged from last round, else resets (a deterministic proxy for hard-stuck — semantic no-progress is G's judging duty).
|
|
@@ -139,6 +139,8 @@ Hierarchical encoding: `root_id>child_segment>grandchild_segment`.
|
|
|
139
139
|
|
|
140
140
|
Both true → sets `stoppedAt` + emits `agent_done` + `querySession`s the result back to the parent. The parent's `querySession` clears its own `stoppedAt`, handles the report, and may trigger its own `tryReportToParent` — bubbling up.
|
|
141
141
|
|
|
142
|
+
**Abnormal-termination marker**: when the reported turn was killed by an unrecoverable error (retry budget exhausted / account-level failure), the session's `turnError` field holds the error text and the auto-report is prefixed with an explicit `[SUB-AGENT ABORTED: … Error: <text> … Re-dispatch with query_session(…) to resume.]` block. Without it the parent LLM consumed mid-turn fragments (or a literal "(no output)") as completed reports — the cron-era "sub-agent reported without finishing" incident, root-caused to a Bedrock h2 hang (`TimeoutError: http2 request did not get a response`, now also in the transient-transport retry list). Prefix, don't suppress: skipping the report would leave the parent waiting forever, the partial trace has diagnostic value, and `stoppedAt` is stamped as usual so the child never shows as falsely running. The marker is prepended *before* the truncation cap so it can never be sliced off. (`deliverGoalRound` has the same `finalOutput || output` shape without an error dimension — known gap, unfixed.)
|
|
143
|
+
|
|
142
144
|
The full finally-chain order is `tryReportToParent → deliverGoalRound → releaseSession`: after the parent-report check, goal-bound **root** sessions get their round report delivered to the goal session (fire-and-forget; a no-op for everyone else — see [goal-mode.md](goal-mode.md#the-delivery-point-delivergoalround)), then the session is released.
|
|
143
145
|
|
|
144
146
|
- **Sibling-status injection for root** (`siblingStatusSuffix`): `tryReportToParent` early-returns for root (`parentId === null`) since there's no parent to bubble up to — so root never learns whether its *other* children are still running, and the root LLM could wrap up early after consuming just one child's report. When root consumes a child report (`querySession` idle branch + `drainQueue`), a sibling-status line is appended to the message fed to the LLM. "All sub-agents done" requires **both** no sibling running in the DB (`parentId = root AND stoppedAt IS NULL`) **and** an empty in-memory `messageQueue` — a child can be stopped while its report is still queued, so the DB check alone would falsely declare completion. The reporting child needs no identity exclusion: it stamped `stoppedAt` before the report was delivered, so `stoppedAt IS NULL` already excludes it (unless re-dispatched a new task, which clears `stoppedAt` — then it correctly counts as running). The line carries per-child `created` + `last active` timestamps so a capable model can tell a freshly dispatched sibling from an original-batch leftover. Mid-tier parents are excluded by design — their `tryReportToParent` bubble-up already gates them on a fully-drained subtree.
|
|
@@ -303,6 +305,7 @@ Frontend network issues don't affect the backend:
|
|
|
303
305
|
2. **Grace period**: fixed `config.timeout.sessionGrace` (5 min default) — a single `setTimeout`, no auto-extension
|
|
304
306
|
3. **Event buffering**: the detached handler uses `bufferDetachedNotification` to buffer structural events in `pendingEvents[]`. All state (messageLog / tokens / etc.) lives in SessionManager's UIState, not duplicated in the handler.
|
|
305
307
|
4. **Reconnect**: a `subscribe` with the same sessionId loads UIState from SessionManager, replays `pendingEvents`, and — if still running — resumes live streaming
|
|
308
|
+
5. **Detach-save dirty gate**: every WS write-back path (disconnect cleanup, grace expiry, session switch/clear, backgroundSaves) funnels through `saveSession()`, which skips any UIState that isn't **dirty** — i.e. this process never reduced an event / appended a notification / replaced the log since the last successful persist (`SessionUIStore.isUIStateDirty`). A clean state is either a pure disk seed (built by `prepareForView` to *view* a session another process is driving — e.g. a cron `halo cli` child appending to the same file) or already flushed; writing it back would clobber the fresher file with a frozen snapshot. This was the cron-session UI-log truncation incident: admin viewed a cron session, closed the tab, and the grace-expiry save erased the cli child's final minutes of messages (`rawMessages`/`output` survived only via `saveSessionToFile`'s read-merge). The flag is cleared on successful `persistUIState` (kept on failure so a later save retries) and on `dropUIState`/purge/`prepareForView` re-seed so a stale flag never leaks onto a fresh disk copy.
|
|
306
309
|
|
|
307
310
|
## Resilient execution loop
|
|
308
311
|
|
package/bundled-docs/dev/api.md
CHANGED
|
@@ -170,8 +170,8 @@ File: `packages/server/src/routes/cron.ts`. Admin cookie auth. REST CRUD over `c
|
|
|
170
170
|
| Method | Path | Purpose |
|
|
171
171
|
|---|---|---|
|
|
172
172
|
| GET | `/api/cron/jobs?limit=&before=` | Cursor-paginated newest-first by `createdAt`. Default `limit` 20, max 100; `before` is a `createdAt` cursor. Returns `{jobs, hasMore, nextCursor}`. Each job has `targets` decoded and a live `nextRunAt` (computed from schedule/runAt) |
|
|
173
|
-
| POST | `/api/cron/jobs` | Create a job. Body: `{label?, workspacePath, agentId, userPrompt, schedule, runAt?, timezone?, targets?, enabled?}`. Exactly one of `schedule` (5-field cron) or `runAt` (epoch ms, future) is required; mutually exclusive. Returns `{ok, id}` |
|
|
174
|
-
| PUT | `/api/cron/jobs/:id` | Partial update over the same fields. Re-validates `schedule` / `runAt` and enforces trigger-mode exclusivity on the **merged** row: both in one body → 400 `schedule and runAt are mutually exclusive`; supplying one side is a mode switch that implicitly clears the other; a body that clears the active side without supplying a replacement → 400 `schedule or runAt required`. `runAt` must be a finite future epoch-ms number or `null`. Flips schedule/unschedule on `enabled`. Returns `{ok}` |
|
|
173
|
+
| POST | `/api/cron/jobs` | Create a job. Body: `{label?, workspacePath, agentId, userPrompt, schedule, runAt?, timezone?, timeoutSec?, targets?, enabled?}`. Exactly one of `schedule` (5-field cron) or `runAt` (epoch ms, future) is required; mutually exclusive. `timeoutSec` must be an integer 60–21600 (else 400); unset = runner default 3600. Returns `{ok, id}` |
|
|
174
|
+
| PUT | `/api/cron/jobs/:id` | Partial update over the same fields. Re-validates `schedule` / `runAt` and enforces trigger-mode exclusivity on the **merged** row: both in one body → 400 `schedule and runAt are mutually exclusive`; supplying one side is a mode switch that implicitly clears the other; a body that clears the active side without supplying a replacement → 400 `schedule or runAt required`. `runAt` must be a finite future epoch-ms number or `null`. `timeoutSec` follows the same partial-body contract: omitted = unchanged, `null` = clear back to the default, a number is range-validated (60–21600) same as create. Flips schedule/unschedule on `enabled`. Returns `{ok}` |
|
|
175
175
|
| DELETE | `/api/cron/jobs/:id` | Unschedule, delete every `cron_runs` row for the job, then delete the job. Returns `{ok}` |
|
|
176
176
|
| POST | `/api/cron/jobs/:id/run-now` | Fire the job immediately (fire-and-forget). Returns `{ok}` |
|
|
177
177
|
| POST | `/api/cron/reload` | Re-read every job from db and rebuild schedules. Returns `{ok}` |
|