fix: prevent agents from duplicating delegated subagent work

Addresses user reports where Sisyphus/Hephaestus would delegate tasks
to explore/librarian subagents but then immediately perform the same
search/work themselves, wasting context and defeating the purpose of
delegation.

Changes:
- Add Anti-Duplication section to dynamic-agent-prompt-builder with
  clear rules: once you delegate, do NOT manually re-do the same search
- Update all agent prompts (sisyphus, hephaestus, sis-junior gemini/gpt)
  to use 'non-overlapping work' instead of 'keep working' after delegation
- Add buildAntiDuplicationSection() with explicit examples of forbidden
  vs allowed behavior after delegation
- Add 'Delegation Trust Rule' to explore section
- Add 'Delegation Duplication' to anti-patterns list

Atlas fixes:
- Add AUTO-CONTINUE POLICY to all Atlas variants (default, gemini, gpt)
  preventing the 'should I continue?' confirmation loop between plan steps
- Fix plan file path in default atlas (.sisyphus/tasks/ -> .sisyphus/plans/)
- Update GPT atlas uncertainty section to only ask questions during initial
  plan analysis, not during execution

Fixes: subagent delegation duplication, Atlas continuation prompting

bun.lock

@@ -1,6 +1,6 @@
 {
   "lockfileVersion": 1,
-  "configVersion": 0,
+  "configVersion": 1,
   "workspaces": {
     "": {
       "name": "oh-my-opencode",
@@ -10,8 +10,8 @@
         "@clack/prompts": "^0.11.0",
         "@code-yeongyu/comment-checker": "^0.7.0",
         "@modelcontextprotocol/sdk": "^1.25.2",
-        "@opencode-ai/plugin": "^1.1.19",
-        "@opencode-ai/sdk": "^1.1.19",
+        "@opencode-ai/plugin": "^1.2.16",
+        "@opencode-ai/sdk": "^1.2.17",
         "commander": "^14.0.2",
         "detect-libc": "^2.0.0",
         "diff": "^8.0.3",
@@ -48,42 +48,45 @@
     "@ast-grep/napi",
     "@code-yeongyu/comment-checker",
   ],
+  "overrides": {
+    "@opencode-ai/sdk": "^1.2.17",
+  },
   "packages": {
-    "@ast-grep/cli": ["@ast-grep/cli@0.40.0", "", { "dependencies": { "detect-libc": "2.1.2" }, "optionalDependencies": { "@ast-grep/cli-darwin-arm64": "0.40.0", "@ast-grep/cli-darwin-x64": "0.40.0", "@ast-grep/cli-linux-arm64-gnu": "0.40.0", "@ast-grep/cli-linux-x64-gnu": "0.40.0", "@ast-grep/cli-win32-arm64-msvc": "0.40.0", "@ast-grep/cli-win32-ia32-msvc": "0.40.0", "@ast-grep/cli-win32-x64-msvc": "0.40.0" }, "bin": { "sg": "sg", "ast-grep": "ast-grep" } }, "sha512-L8AkflsfI2ZP70yIdrwqvjR02ScCuRmM/qNGnJWUkOFck+e6gafNVJ4e4jjGQlEul+dNdBpx36+O2Op629t47A=="],
+    "@ast-grep/cli": ["@ast-grep/cli@0.40.5", "", { "dependencies": { "detect-libc": "2.1.2" }, "optionalDependencies": { "@ast-grep/cli-darwin-arm64": "0.40.5", "@ast-grep/cli-darwin-x64": "0.40.5", "@ast-grep/cli-linux-arm64-gnu": "0.40.5", "@ast-grep/cli-linux-x64-gnu": "0.40.5", "@ast-grep/cli-win32-arm64-msvc": "0.40.5", "@ast-grep/cli-win32-ia32-msvc": "0.40.5", "@ast-grep/cli-win32-x64-msvc": "0.40.5" }, "bin": { "sg": "sg", "ast-grep": "ast-grep" } }, "sha512-yVXL7Gz0WIHerQLf+MVaVSkhIhidtWReG5akNVr/JS9OVCVkSdz7gWm7H8jVv2M9OO1tauuG76K3UaRGBPu5lQ=="],
 
-    "@ast-grep/cli-darwin-arm64": ["@ast-grep/cli-darwin-arm64@0.40.0", "", { "os": "darwin", "cpu": "arm64" }, "sha512-UehY2MMUkdJbsriP7NKc6+uojrqPn7d1Cl0em+WAkee7Eij81VdyIjRsRxtZSLh440ZWQBHI3PALZ9RkOO8pKQ=="],
+    "@ast-grep/cli-darwin-arm64": ["@ast-grep/cli-darwin-arm64@0.40.5", "", { "os": "darwin", "cpu": "arm64" }, "sha512-T9CzwJ1GqQhnANdsu6c7iT1akpvTVMK+AZrxnhIPv33Ze5hrXUUkqan+j4wUAukRJDqU7u94EhXLSLD+5tcJ8g=="],
 
-    "@ast-grep/cli-darwin-x64": ["@ast-grep/cli-darwin-x64@0.40.0", "", { "os": "darwin", "cpu": "x64" }, "sha512-RFDJ2ZxUbT0+grntNlOLJx7wa9/ciVCeaVtQpQy8WJJTvXvkY0etl8Qlh2TmO2x2yr+i0Z6aMJi4IG/Yx5ghTQ=="],
+    "@ast-grep/cli-darwin-x64": ["@ast-grep/cli-darwin-x64@0.40.5", "", { "os": "darwin", "cpu": "x64" }, "sha512-ez9b2zKvXU8f4ghhjlqYvbx6tWCKJTuVlNVqDDfjqwwhGeiTYfnzMlSVat4ElYRMd21gLtXZIMy055v2f21Ztg=="],
 
-    "@ast-grep/cli-linux-arm64-gnu": ["@ast-grep/cli-linux-arm64-gnu@0.40.0", "", { "os": "linux", "cpu": "arm64" }, "sha512-4p55gnTQ1mMFCyqjtM7bH9SB9r16mkwXtUcJQGX1YgFG4WD+QG8rC4GwSuNNZcdlYaOQuTWrgUEQ9z5K06UXfg=="],
+    "@ast-grep/cli-linux-arm64-gnu": ["@ast-grep/cli-linux-arm64-gnu@0.40.5", "", { "os": "linux", "cpu": "arm64" }, "sha512-VXa2L1IEYD66AMb0GuG7VlMMbPmEGoJUySWDcwSZo/D9neiry3MJ41LQR5oTG2HyhIPBsf9umrXnmuRq66BviA=="],
 
-    "@ast-grep/cli-linux-x64-gnu": ["@ast-grep/cli-linux-x64-gnu@0.40.0", "", { "os": "linux", "cpu": "x64" }, "sha512-u2MXFceuwvrO+OQ6zFGoJ6wbATXn46HWwW79j4UPrXYJzVl97jRyjJOIQTJOzTflsk02fjP98DQkfvbXt2dl3Q=="],
+    "@ast-grep/cli-linux-x64-gnu": ["@ast-grep/cli-linux-x64-gnu@0.40.5", "", { "os": "linux", "cpu": "x64" }, "sha512-GQC5162eIOWXR2eQQ6Knzg7/8Trp5E1ODJkaErf0IubdQrZBGqj5AAcQPcWgPbbnmktjIp0H4NraPpOJ9eJ22A=="],
 
-    "@ast-grep/cli-win32-arm64-msvc": ["@ast-grep/cli-win32-arm64-msvc@0.40.0", "", { "os": "win32", "cpu": "arm64" }, "sha512-E/I1xpF/RQL2fo1CQsQfTxyDLnChsbZ+ERrQHKuF1FI4WrkaPOBibpqda60QgVmUcgOGZyZ/GRb3iKEVWPsQNQ=="],
+    "@ast-grep/cli-win32-arm64-msvc": ["@ast-grep/cli-win32-arm64-msvc@0.40.5", "", { "os": "win32", "cpu": "arm64" }, "sha512-YiZdnQZsSlXQTMsZJop/Ux9MmUGfuRvC2x/UbFgrt5OBSYxND+yoiMc0WcA3WG+wU+tt4ZkB5HUea3r/IkOLYA=="],
 
-    "@ast-grep/cli-win32-ia32-msvc": ["@ast-grep/cli-win32-ia32-msvc@0.40.0", "", { "os": "win32", "cpu": "ia32" }, "sha512-9h12OQu1BR0GxHEtT+Z4QkJk3LLWLiKwjBkjXUGlASHYDPTyLcs85KwDLeFHs4BwarF8TDdF+KySvB9WPGl/nQ=="],
+    "@ast-grep/cli-win32-ia32-msvc": ["@ast-grep/cli-win32-ia32-msvc@0.40.5", "", { "os": "win32", "cpu": "ia32" }, "sha512-MHkCxCITVTr8sY9CcVqNKbfUzMa3Hc6IilGXad0Clnw2vNmPfWqSky+hU/UTerr5YHWwWfAVURH7ANZgirtx0Q=="],
 
-    "@ast-grep/cli-win32-x64-msvc": ["@ast-grep/cli-win32-x64-msvc@0.40.0", "", { "os": "win32", "cpu": "x64" }, "sha512-n2+3WynEWFHhXg6KDgjwWQ0UEtIvqUITFbKEk5cDkUYrzYhg/A6kj0qauPwRbVMoJms49vtsNpLkzzqyunio5g=="],
+    "@ast-grep/cli-win32-x64-msvc": ["@ast-grep/cli-win32-x64-msvc@0.40.5", "", { "os": "win32", "cpu": "x64" }, "sha512-/MJ5un7yxlClaaxou9eYl+Kr2xr/yTtYtTq5aLBWjPWA6dmmJ1nAJgx5zKHVuplFXFBrFDQk3paEgAETMTGcrA=="],
 
-    "@ast-grep/napi": ["@ast-grep/napi@0.40.0", "", { "optionalDependencies": { "@ast-grep/napi-darwin-arm64": "0.40.0", "@ast-grep/napi-darwin-x64": "0.40.0", "@ast-grep/napi-linux-arm64-gnu": "0.40.0", "@ast-grep/napi-linux-arm64-musl": "0.40.0", "@ast-grep/napi-linux-x64-gnu": "0.40.0", "@ast-grep/napi-linux-x64-musl": "0.40.0", "@ast-grep/napi-win32-arm64-msvc": "0.40.0", "@ast-grep/napi-win32-ia32-msvc": "0.40.0", "@ast-grep/napi-win32-x64-msvc": "0.40.0" } }, "sha512-tq6nO/8KwUF/mHuk1ECaAOSOlz2OB/PmygnvprJzyAHGRVzdcffblaOOWe90M9sGz5MAasXoF+PTcayQj9TKKA=="],
+    "@ast-grep/napi": ["@ast-grep/napi@0.40.5", "", { "optionalDependencies": { "@ast-grep/napi-darwin-arm64": "0.40.5", "@ast-grep/napi-darwin-x64": "0.40.5", "@ast-grep/napi-linux-arm64-gnu": "0.40.5", "@ast-grep/napi-linux-arm64-musl": "0.40.5", "@ast-grep/napi-linux-x64-gnu": "0.40.5", "@ast-grep/napi-linux-x64-musl": "0.40.5", "@ast-grep/napi-win32-arm64-msvc": "0.40.5", "@ast-grep/napi-win32-ia32-msvc": "0.40.5", "@ast-grep/napi-win32-x64-msvc": "0.40.5" } }, "sha512-hJA62OeBKUQT68DD2gDyhOqJxZxycqg8wLxbqjgqSzYttCMSDL9tiAQ9abgekBYNHudbJosm9sWOEbmCDfpX2A=="],
 
-    "@ast-grep/napi-darwin-arm64": ["@ast-grep/napi-darwin-arm64@0.40.0", "", { "os": "darwin", "cpu": "arm64" }, "sha512-ZMjl5yLhKjxdwbqEEdMizgQdWH2NrWsM6Px+JuGErgCDe6Aedq9yurEPV7veybGdLVJQhOah6htlSflXxjHnYA=="],
+    "@ast-grep/napi-darwin-arm64": ["@ast-grep/napi-darwin-arm64@0.40.5", "", { "os": "darwin", "cpu": "arm64" }, "sha512-2F072fGN0WTq7KI3okuEnkGJVEHLbi56Bw1H6NAMf7j2mJJeQWsRyGOMcyNnUXZDeNdvoMH0OB2a5wwUegY/nQ=="],
 
-    "@ast-grep/napi-darwin-x64": ["@ast-grep/napi-darwin-x64@0.40.0", "", { "os": "darwin", "cpu": "x64" }, "sha512-f9Ol5oQKNRMBkvDtzBK1WiNn2/3eejF2Pn9xwTj7PhXuSFseedOspPYllxQo0gbwUlw/DJqGFTce/jarhR/rBw=="],
+    "@ast-grep/napi-darwin-x64": ["@ast-grep/napi-darwin-x64@0.40.5", "", { "os": "darwin", "cpu": "x64" }, "sha512-dJMidHZhhxuLBYNi6/FKI812jQ7wcFPSKkVPwviez2D+KvYagapUMAV/4dJ7FCORfguVk8Y0jpPAlYmWRT5nvA=="],
 
-    "@ast-grep/napi-linux-arm64-gnu": ["@ast-grep/napi-linux-arm64-gnu@0.40.0", "", { "os": "linux", "cpu": "arm64" }, "sha512-+tO+VW5GDhT9jGkKOK+3b8+ohKjC98WTzn7wSskd/myyhK3oYL1WTKqCm07WSYBZOJvb3z+WaX+wOUrc4bvtyQ=="],
+    "@ast-grep/napi-linux-arm64-gnu": ["@ast-grep/napi-linux-arm64-gnu@0.40.5", "", { "os": "linux", "cpu": "arm64" }, "sha512-nBRCbyoS87uqkaw4Oyfe5VO+SRm2B+0g0T8ME69Qry9ShMf41a2bTdpcQx9e8scZPogq+CTwDHo3THyBV71l9w=="],
 
-    "@ast-grep/napi-linux-arm64-musl": ["@ast-grep/napi-linux-arm64-musl@0.40.0", "", { "os": "linux", "cpu": "arm64" }, "sha512-MS9qalLRjUnF2PCzuTKTvCMVSORYHxxe3Qa0+SSaVULsXRBmuy5C/b1FeWwMFnwNnC0uie3VDet31Zujwi8q6A=="],
+    "@ast-grep/napi-linux-arm64-musl": ["@ast-grep/napi-linux-arm64-musl@0.40.5", "", { "os": "linux", "cpu": "arm64" }, "sha512-/qKsmds5FMoaEj6FdNzepbmLMtlFuBLdrAn9GIWCqOIcVcYvM1Nka8+mncfeXB/MFZKOrzQsQdPTWqrrQzXLrA=="],
 
-    "@ast-grep/napi-linux-x64-gnu": ["@ast-grep/napi-linux-x64-gnu@0.40.0", "", { "os": "linux", "cpu": "x64" }, "sha512-BeHZVMNXhM3WV3XE2yghO0fRxhMOt8BTN972p5piYEQUvKeSHmS8oeGcs6Ahgx5znBclqqqq37ZfioYANiTqJA=="],
+    "@ast-grep/napi-linux-x64-gnu": ["@ast-grep/napi-linux-x64-gnu@0.40.5", "", { "os": "linux", "cpu": "x64" }, "sha512-DP4oDbq7f/1A2hRTFLhJfDFR6aI5mRWdEfKfHzRItmlKsR9WlcEl1qDJs/zX9R2EEtIDsSKRzuJNfJllY3/W8Q=="],
 
-    "@ast-grep/napi-linux-x64-musl": ["@ast-grep/napi-linux-x64-musl@0.40.0", "", { "os": "linux", "cpu": "x64" }, "sha512-rG1YujF7O+lszX8fd5u6qkFTuv4FwHXjWvt1CCvCxXwQLSY96LaCW88oVKg7WoEYQh54y++Fk57F+Wh9Gv9nVQ=="],
+    "@ast-grep/napi-linux-x64-musl": ["@ast-grep/napi-linux-x64-musl@0.40.5", "", { "os": "linux", "cpu": "x64" }, "sha512-BRZUvVBPUNpWPo6Ns8chXVzxHPY+k9gpsubGTHy92Q26ecZULd/dTkWWdnvfhRqttsSQ9Pe/XQdi5+hDQ6RYcg=="],
 
-    "@ast-grep/napi-win32-arm64-msvc": ["@ast-grep/napi-win32-arm64-msvc@0.40.0", "", { "os": "win32", "cpu": "arm64" }, "sha512-9SqmnQqd4zTEUk6yx0TuW2ycZZs2+e569O/R0QnhSiQNpgwiJCYOe/yPS0BC9HkiaozQm6jjAcasWpFtz/dp+w=="],
+    "@ast-grep/napi-win32-arm64-msvc": ["@ast-grep/napi-win32-arm64-msvc@0.40.5", "", { "os": "win32", "cpu": "arm64" }, "sha512-y95zSEwc7vhxmcrcH0GnK4ZHEBQrmrszRBNQovzaciF9GUqEcCACNLoBesn4V47IaOp4fYgD2/EhGRTIBFb2Ug=="],
 
-    "@ast-grep/napi-win32-ia32-msvc": ["@ast-grep/napi-win32-ia32-msvc@0.40.0", "", { "os": "win32", "cpu": "ia32" }, "sha512-0JkdBZi5l9vZhGEO38A1way0LmLRDU5Vos6MXrLIOVkymmzDTDlCdY394J1LMmmsfwWcyJg6J7Yv2dw41MCxDQ=="],
+    "@ast-grep/napi-win32-ia32-msvc": ["@ast-grep/napi-win32-ia32-msvc@0.40.5", "", { "os": "win32", "cpu": "ia32" }, "sha512-K/u8De62iUnFCzVUs7FBdTZ2Jrgc5/DLHqjpup66KxZ7GIM9/HGME/O8aSoPkpcAeCD4TiTZ11C1i5p5H98hTg=="],
 
-    "@ast-grep/napi-win32-x64-msvc": ["@ast-grep/napi-win32-x64-msvc@0.40.0", "", { "os": "win32", "cpu": "x64" }, "sha512-Hk2IwfPqMFGZt5SRxsoWmGLxBXxprow4LRp1eG6V8EEiJCNHxZ9ZiEaIc5bNvMDBjHVSnqZAXT22dROhrcSKQg=="],
+    "@ast-grep/napi-win32-x64-msvc": ["@ast-grep/napi-win32-x64-msvc@0.40.5", "", { "os": "win32", "cpu": "x64" }, "sha512-dqm5zg/o4Nh4VOQPEpMS23ot8HVd22gG0eg01t4CFcZeuzyuSgBlOL3N7xLbz3iH2sVkk7keuBwAzOIpTqziNQ=="],
 
     "@clack/core": ["@clack/core@0.5.0", "", { "dependencies": { "picocolors": "^1.0.0", "sisteransi": "^1.0.5" } }, "sha512-p3y0FIOwaYRUPRcMO7+dlmLh8PSRcrjuTndsiA0WAFbWES0mLZlrjVoBRZ9DzkPFJZG6KGkJmoEAY0ZcVWTkow=="],
 
@@ -91,29 +94,29 @@
 
     "@code-yeongyu/comment-checker": ["@code-yeongyu/comment-checker@0.7.0", "", { "os": [ "linux", "win32", "darwin", ], "cpu": [ "x64", "arm64", ], "bin": { "comment-checker": "bin/comment-checker" } }, "sha512-AOic1jPHY3CpNraOuO87YZHO3uRzm9eLd0wyYYN89/76Ugk2TfdUYJ6El/Oe8fzOnHKiOF0IfBeWRo0IUjrHHg=="],
 
-    "@hono/node-server": ["@hono/node-server@1.19.9", "", { "peerDependencies": { "hono": "^4" } }, "sha512-vHL6w3ecZsky+8P5MD+eFfaGTyCeOHUIFYMGpQGbrBTSmNNoxv0if69rEZ5giu36weC5saFuznL411gRX7bJDw=="],
+    "@hono/node-server": ["@hono/node-server@1.19.10", "", { "peerDependencies": { "hono": "^4" } }, "sha512-hZ7nOssGqRgyV3FVVQdfi+U4q02uB23bpnYpdvNXkYTRRyWx84b7yf1ans+dnJ/7h41sGL3CeQTfO+ZGxuO+Iw=="],
 
-    "@modelcontextprotocol/sdk": ["@modelcontextprotocol/sdk@1.26.0", "", { "dependencies": { "@hono/node-server": "^1.19.9", "ajv": "^8.17.1", "ajv-formats": "^3.0.1", "content-type": "^1.0.5", "cors": "^2.8.5", "cross-spawn": "^7.0.5", "eventsource": "^3.0.2", "eventsource-parser": "^3.0.0", "express": "^5.2.1", "express-rate-limit": "^8.2.1", "hono": "^4.11.4", "jose": "^6.1.3", "json-schema-typed": "^8.0.2", "pkce-challenge": "^5.0.0", "raw-body": "^3.0.0", "zod": "^3.25 || ^4.0", "zod-to-json-schema": "^3.25.1" }, "peerDependencies": { "@cfworker/json-schema": "^4.1.1" }, "optionalPeers": ["@cfworker/json-schema"] }, "sha512-Y5RmPncpiDtTXDbLKswIJzTqu2hyBKxTNsgKqKclDbhIgg1wgtf1fRuvxgTnRfcnxtvvgbIEcqUOzZrJ6iSReg=="],
+    "@modelcontextprotocol/sdk": ["@modelcontextprotocol/sdk@1.27.1", "", { "dependencies": { "@hono/node-server": "^1.19.9", "ajv": "^8.17.1", "ajv-formats": "^3.0.1", "content-type": "^1.0.5", "cors": "^2.8.5", "cross-spawn": "^7.0.5", "eventsource": "^3.0.2", "eventsource-parser": "^3.0.0", "express": "^5.2.1", "express-rate-limit": "^8.2.1", "hono": "^4.11.4", "jose": "^6.1.3", "json-schema-typed": "^8.0.2", "pkce-challenge": "^5.0.0", "raw-body": "^3.0.0", "zod": "^3.25 || ^4.0", "zod-to-json-schema": "^3.25.1" }, "peerDependencies": { "@cfworker/json-schema": "^4.1.1" }, "optionalPeers": ["@cfworker/json-schema"] }, "sha512-sr6GbP+4edBwFndLbM60gf07z0FQ79gaExpnsjMGePXqFcSSb7t6iscpjk9DhFhwd+mTEQrzNafGP8/iGGFYaA=="],
 
-    "@opencode-ai/plugin": ["@opencode-ai/plugin@1.1.19", "", { "dependencies": { "@opencode-ai/sdk": "1.1.19", "zod": "4.1.8" } }, "sha512-Q6qBEjHb/dJMEw4BUqQxEswTMxCCHUpFMMb6jR8HTTs8X/28XRkKt5pHNPA82GU65IlSoPRph+zd8LReBDN53Q=="],
+    "@opencode-ai/plugin": ["@opencode-ai/plugin@1.2.16", "", { "dependencies": { "@opencode-ai/sdk": "1.2.16", "zod": "4.1.8" } }, "sha512-9Kb7BQIC2P3oKCvI8K3thP5YP0vE7yLvcmBmgyACUIqc3e5UL6U+4umLpTvgQa2eQdjxtOXznuGTNwgcGMHUHg=="],
 
-    "@opencode-ai/sdk": ["@opencode-ai/sdk@1.1.19", "", {}, "sha512-XhZhFuvlLCqDpvNtUEjOsi/wvFj3YCXb1dySp+OONQRMuHlorNYnNa7P2A2ntKuhRdGT1Xt5na0nFzlUyNw+4A=="],
+    "@opencode-ai/sdk": ["@opencode-ai/sdk@1.2.17", "", {}, "sha512-HdeLeyJ2/Yl/NBHqw9pGFBnkIXuf0Id1kX1GMXDcnZwbJROUJ6TtrW/wLngTYW478E4CCm1jwknjxxmDuxzVMQ=="],
 
     "@types/js-yaml": ["@types/js-yaml@4.0.9", "", {}, "sha512-k4MGaQl5TGo/iipqb2UDG2UwjXziSWkh0uysQelTlJpX1qGlpUZYm8PnO4DxG1qBomtJUdYJ6qR6xdIah10JLg=="],
 
-    "@types/node": ["@types/node@24.10.1", "", { "dependencies": { "undici-types": "~7.16.0" } }, "sha512-GNWcUTRBgIRJD5zj+Tq0fKOJ5XZajIiBroOF0yvj2bSU1WvNdYS/dn9UxwsujGW4JX06dnHyjV2y9rRaybH0iQ=="],
+    "@types/node": ["@types/node@25.3.3", "", { "dependencies": { "undici-types": "~7.18.0" } }, "sha512-DpzbrH7wIcBaJibpKo9nnSQL0MTRdnWttGyE5haGwK86xgMOkFLp7vEyfQPGLOJh5wNYiJ3V9PmUMDhV9u8kkQ=="],
 
     "@types/picomatch": ["@types/picomatch@3.0.2", "", {}, "sha512-n0i8TD3UDB7paoMMxA3Y65vUncFJXjcUf7lQY7YyKGl6031FNjfsLs6pdLFCy2GNFxItPJG8GvvpbZc2skH7WA=="],
 
     "accepts": ["accepts@2.0.0", "", { "dependencies": { "mime-types": "^3.0.0", "negotiator": "^1.0.0" } }, "sha512-5cvg6CtKwfgdmVqY1WIiXKc3Q1bkRqGLi+2W/6ao+6Y7gu/RCwRuAhGEzh5B4KlszSuTLgZYuqFqo5bImjNKng=="],
 
-    "ajv": ["ajv@8.17.1", "", { "dependencies": { "fast-deep-equal": "^3.1.3", "fast-uri": "^3.0.1", "json-schema-traverse": "^1.0.0", "require-from-string": "^2.0.2" } }, "sha512-B/gBuNg5SiMTrPkC+A2+cW0RszwxYmn6VYxB/inlBStS5nx6xHIt/ehKRhIMhqusl7a8LjQoZnjCs5vhwxOQ1g=="],
+    "ajv": ["ajv@8.18.0", "", { "dependencies": { "fast-deep-equal": "^3.1.3", "fast-uri": "^3.0.1", "json-schema-traverse": "^1.0.0", "require-from-string": "^2.0.2" } }, "sha512-PlXPeEWMXMZ7sPYOHqmDyCJzcfNrUr3fGNKtezX14ykXOEIvyK81d+qydx89KY5O71FKMPaQ2vBfBFI5NHR63A=="],
 
     "ajv-formats": ["ajv-formats@3.0.1", "", { "dependencies": { "ajv": "^8.0.0" } }, "sha512-8iUql50EUR+uUcdRQ3HDqa6EVyo3docL8g5WJ3FNcWmu62IbkGUue/pEyLBW8VGKKucTPgqeks4fIU1DA4yowQ=="],
 
     "argparse": ["argparse@2.0.1", "", {}, "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="],
 
-    "body-parser": ["body-parser@2.2.1", "", { "dependencies": { "bytes": "^3.1.2", "content-type": "^1.0.5", "debug": "^4.4.3", "http-errors": "^2.0.0", "iconv-lite": "^0.7.0", "on-finished": "^2.4.1", "qs": "^6.14.0", "raw-body": "^3.0.1", "type-is": "^2.0.1" } }, "sha512-nfDwkulwiZYQIGwxdy0RUmowMhKcFVcYXUU7m4QlKYim1rUtg83xm2yjZ40QjDuc291AJjjeSc9b++AWHSgSHw=="],
+    "body-parser": ["body-parser@2.2.2", "", { "dependencies": { "bytes": "^3.1.2", "content-type": "^1.0.5", "debug": "^4.4.3", "http-errors": "^2.0.0", "iconv-lite": "^0.7.0", "on-finished": "^2.4.1", "qs": "^6.14.1", "raw-body": "^3.0.1", "type-is": "^2.0.1" } }, "sha512-oP5VkATKlNwcgvxi0vM0p/D3n2C3EReYVX+DNYs5TjZFn/oQt2j+4sVJtSMr18pdRr8wjTcBl6LoV+FUwzPmNA=="],
 
     "bun-types": ["bun-types@1.3.6", "", { "dependencies": { "@types/node": "*" } }, "sha512-OlFwHcnNV99r//9v5IIOgQ9Uk37gZqrNMCcqEaExdkVq3Avwqok1bJFmvGMCkCE0FqzdY8VMOZpfpR3lwI+CsQ=="],
 
@@ -123,7 +126,7 @@
 
     "call-bound": ["call-bound@1.0.4", "", { "dependencies": { "call-bind-apply-helpers": "^1.0.2", "get-intrinsic": "^1.3.0" } }, "sha512-+ys997U96po4Kx/ABpBCqhA9EuxJaQWDQg7295H4hBphv3IZg0boBKuwYpt4YXp6MZ5AmZQnU/tyMTlRpaSejg=="],
 
-    "commander": ["commander@14.0.2", "", {}, "sha512-TywoWNNRbhoD0BXs1P3ZEScW8W5iKrnbithIl0YH+uCmBd0QpPOA8yc82DS3BIE5Ma6FnBVUsJ7wVUDz4dvOWQ=="],
+    "commander": ["commander@14.0.3", "", {}, "sha512-H+y0Jo/T1RZ9qPP4Eh1pkcQcLRglraJaSLoyOtHxu6AapkjWVCy2Sit1QQ4x3Dng8qDlSsZEet7g5Pq06MvTgw=="],
 
     "content-disposition": ["content-disposition@1.0.1", "", {}, "sha512-oIXISMynqSqm241k6kcQ5UwttDILMK4BiurCfGEREw6+X9jkkpEe5T9FZaApyLGGOnFuyMWZpdolTXMtvEJ08Q=="],
 
@@ -133,7 +136,7 @@
 
     "cookie-signature": ["cookie-signature@1.2.2", "", {}, "sha512-D76uU73ulSXrD1UXF4KE2TMxVVwhsnCgfAyTg9k8P6KGZjlXKrOLe4dJQKI3Bxi5wjesZoFXJWElNWBjPZMbhg=="],
 
-    "cors": ["cors@2.8.5", "", { "dependencies": { "object-assign": "^4", "vary": "^1" } }, "sha512-KIHbLJqu73RGr/hnbrO9uBeixNGuvSQjul/jdFvS/KFSIH1hWVd1ng7zOHx+YrEfInLG7q4n6GHQ9cDtxv/P6g=="],
+    "cors": ["cors@2.8.6", "", { "dependencies": { "object-assign": "^4", "vary": "^1" } }, "sha512-tJtZBBHA6vjIAaF6EnIaq6laBBP9aq/Y3ouVJjEfoHbRBcHBAHYcMh/w8LDrk2PvIMMq8gmopa5D4V8RmbrxGw=="],
 
     "cross-spawn": ["cross-spawn@7.0.6", "", { "dependencies": { "path-key": "^3.1.0", "shebang-command": "^2.0.0", "which": "^2.0.1" } }, "sha512-uV2QOWP2nWzsy2aMp8aRibhi9dlzF5Hgh5SHaB9OiTGEyDTiJJyx0uy51QXdyWbtAHNua4XJzUKca3OzKUd3vA=="],
 
@@ -191,11 +194,11 @@
 
     "hasown": ["hasown@2.0.2", "", { "dependencies": { "function-bind": "^1.1.2" } }, "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ=="],
 
-    "hono": ["hono@4.12.0", "", {}, "sha512-NekXntS5M94pUfiVZ8oXXK/kkri+5WpX2/Ik+LVsl+uvw+soj4roXIsPqO+XsWrAw20mOzaXOZf3Q7PfB9A/IA=="],
+    "hono": ["hono@4.12.5", "", {}, "sha512-3qq+FUBtlTHhtYxbxheZgY8NIFnkkC/MR8u5TTsr7YZ3wixryQ3cCwn3iZbg8p8B88iDBBAYSfZDS75t8MN7Vg=="],
 
     "http-errors": ["http-errors@2.0.1", "", { "dependencies": { "depd": "~2.0.0", "inherits": "~2.0.4", "setprototypeof": "~1.2.0", "statuses": "~2.0.2", "toidentifier": "~1.0.1" } }, "sha512-4FbRdAX+bSdmo4AUFuS0WNiPz8NgFt+r8ThgNWmlrjQjt1Q7ZR9+zTlce2859x4KSXrwIsaeTqDoKQmtP8pLmQ=="],
 
-    "iconv-lite": ["iconv-lite@0.7.1", "", { "dependencies": { "safer-buffer": ">= 2.1.2 < 3.0.0" } }, "sha512-2Tth85cXwGFHfvRgZWszZSvdo+0Xsqmw8k8ZwxScfcBneNUraK+dxRxRm24nszx80Y0TVio8kKLt5sLE7ZCLlw=="],
+    "iconv-lite": ["iconv-lite@0.7.2", "", { "dependencies": { "safer-buffer": ">= 2.1.2 < 3.0.0" } }, "sha512-im9DjEDQ55s9fL4EYzOAv0yMqmMBSZp6G0VvFyTMPKWxiSBHUj9NW/qqLmXUwXrrM7AvqSlTCfvqRb0cM8yYqw=="],
 
     "inherits": ["inherits@2.0.4", "", {}, "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ=="],
 
@@ -275,7 +278,7 @@
 
     "proxy-addr": ["proxy-addr@2.0.7", "", { "dependencies": { "forwarded": "0.2.0", "ipaddr.js": "1.9.1" } }, "sha512-llQsMLSUDUPT44jdrU/O37qlnifitDP+ZwrmmZcoSKyLKvtZxpyV0n2/bD/N4tBAAZ/gJEdZU7KMraoK1+XYAg=="],
 
-    "qs": ["qs@6.14.1", "", { "dependencies": { "side-channel": "^1.1.0" } }, "sha512-4EK3+xJl8Ts67nLYNwqw/dsFVnCf+qR7RgXSK9jEEm9unao3njwMDdmsdvoKBKHzxd7tCYz5e5M+SnMjdtXGQQ=="],
+    "qs": ["qs@6.15.0", "", { "dependencies": { "side-channel": "^1.1.0" } }, "sha512-mAZTtNCeetKMH+pSjrb76NAM8V9a05I9aBZOHztWy/UqcJdQYNsf59vrRKWnojAT9Y+GbIvoTBC++CPHqpDBhQ=="],
 
     "range-parser": ["range-parser@1.2.1", "", {}, "sha512-Hrgsx+orqoygnmhFbKaHE6c296J+HTAQXoxEF6gNupROmmGJRoyzfG3ccAveqCBrwr/2yxQ5BVd/GTl5agOwSg=="],
 
@@ -315,7 +318,7 @@
 
     "typescript": ["typescript@5.9.3", "", { "bin": { "tsc": "bin/tsc", "tsserver": "bin/tsserver" } }, "sha512-jl1vZzPDinLr9eUt3J/t7V6FgNEw9QjvBPdysz9KfQDD41fQrC2Y4vKQdiaUpFT4bXlb1RHhLpp8wtm6M5TgSw=="],
 
-    "undici-types": ["undici-types@7.16.0", "", {}, "sha512-Zz+aZWSj8LE6zoxD+xrjh4VfkIG8Ya6LvYkZqtUQGJPZjYl53ypCaUwWqo7eI0x66KBGeRo+mlBEkMSeSZ38Nw=="],
+    "undici-types": ["undici-types@7.18.2", "", {}, "sha512-AsuCzffGHJybSaRrmr5eHr81mwJU3kjw6M+uprWvCXiNeN9SOGwQ3Jn8jb8m3Z6izVgknn1R0FTCEAP2QrLY/w=="],
 
     "unpipe": ["unpipe@1.0.0", "", {}, "sha512-pjy2bYhSsufwWlKwPc+l3cN7+wuJlK6uz0YdJEOlQDbl6jo/YlPi4mb8agUkVC8BF7V8NuzeyPNqRksA3hztKQ=="],
 
@@ -327,8 +330,10 @@
 
     "wrappy": ["wrappy@1.0.2", "", {}, "sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ=="],
 
-    "zod": ["zod@4.1.8", "", {}, "sha512-5R1P+WwQqmmMIEACyzSvo4JXHY5WiAFHRMg+zBZKgKS+Q1viRa0C1hmUKtHltoIFKtIdki3pRxkmpP74jnNYHQ=="],
+    "zod": ["zod@4.3.6", "", {}, "sha512-rftlrkhHZOcjDwkGlnUtZZkvaPHCsDATp4pGpuOOMDaTdDDXF91wuVDJoWoPsKX/3YPQ5fHuF3STjcYyKr+Qhg=="],
 
     "zod-to-json-schema": ["zod-to-json-schema@3.25.1", "", { "peerDependencies": { "zod": "^3.25 || ^4" } }, "sha512-pM/SU9d3YAggzi6MtR4h7ruuQlqKtad8e9S0fmxcMi+ueAK5Korys/aWcV9LIIHTVbj01NdzxcnXSN+O74ZIVA=="],
+
+    "@opencode-ai/plugin/zod": ["zod@4.1.8", "", {}, "sha512-5R1P+WwQqmmMIEACyzSvo4JXHY5WiAFHRMg+zBZKgKS+Q1viRa0C1hmUKtHltoIFKtIdki3pRxkmpP74jnNYHQ=="],
   }
 }

package.json

@@ -56,8 +56,8 @@
     "@clack/prompts": "^0.11.0",
     "@code-yeongyu/comment-checker": "^0.7.0",
     "@modelcontextprotocol/sdk": "^1.25.2",
-    "@opencode-ai/plugin": "^1.1.19",
-    "@opencode-ai/sdk": "^1.1.19",
+    "@opencode-ai/plugin": "^1.2.16",
+    "@opencode-ai/sdk": "^1.2.17",
     "commander": "^14.0.2",
     "detect-libc": "^2.0.0",
     "diff": "^8.0.3",
@@ -87,6 +87,9 @@
     "oh-my-opencode-windows-x64": "3.10.0",
     "oh-my-opencode-windows-x64-baseline": "3.10.0"
   },
+  "overrides": {
+    "@opencode-ai/sdk": "^1.2.17"
+  },
   "trustedDependencies": [
     "@ast-grep/cli",
     "@ast-grep/napi",

signatures/cla.json

@@ -1895,6 +1895,94 @@
       "created_at": "2026-03-04T00:43:53Z",
       "repoId": 1108837393,
       "pullRequestNo": 2277
+    },
+    {
+      "name": "chan1103",
+      "id": 241870013,
+      "comment_id": 3996082243,
+      "created_at": "2026-03-04T08:40:54Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2288
+    },
+    {
+      "name": "SeeYouCowboi",
+      "id": 103308766,
+      "comment_id": 3996126396,
+      "created_at": "2026-03-04T08:50:32Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2291
+    },
+    {
+      "name": "guazi04",
+      "id": 134621827,
+      "comment_id": 3996644267,
+      "created_at": "2026-03-04T10:31:44Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2293
+    },
+    {
+      "name": "brandonwebb-vista",
+      "id": 237281185,
+      "comment_id": 3998901238,
+      "created_at": "2026-03-04T17:07:00Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2299
+    },
+    {
+      "name": "RaviTharuma",
+      "id": 25951435,
+      "comment_id": 4000536638,
+      "created_at": "2026-03-04T21:53:38Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2302
+    },
+    {
+      "name": "Romanok2805",
+      "id": 37216910,
+      "comment_id": 4001032410,
+      "created_at": "2026-03-04T23:51:02Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2306
+    },
+    {
+      "name": "Vacbo",
+      "id": 53411412,
+      "comment_id": 4002083771,
+      "created_at": "2026-03-05T04:19:50Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2310
+    },
+    {
+      "name": "Wangmerlyn",
+      "id": 29993182,
+      "comment_id": 4004271570,
+      "created_at": "2026-03-05T11:08:09Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2318
+    },
+    {
+      "name": "mInrOz",
+      "id": 14320143,
+      "comment_id": 4004791744,
+      "created_at": "2026-03-05T12:42:30Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2321
+    },
+    {
+      "name": "hkc5",
+      "id": 142545736,
+      "comment_id": 4006670642,
+      "created_at": "2026-03-05T17:49:07Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2327
+    },
+    {
+      "name": "mrosnerr",
+      "id": 3758430,
+      "comment_id": 4006707281,
+      "created_at": "2026-03-05T17:55:33Z",
+      "repoId": 1108837393,
+      "pullRequestNo": 2328
     }
   ]
 }

src/agents/anti-duplication.test.ts

@@ -0,0 +1,92 @@
+/// <reference types="bun-types" />
+
+import { describe, it, expect } from "bun:test"
+import { buildAntiDuplicationSection } from "./dynamic-agent-prompt-builder"
+
+describe("buildAntiDuplicationSection", () => {
+  it("#given no arguments #when building anti-duplication section #then returns comprehensive rule section", () => {
+    //#given: no special configuration needed
+
+    //#when: building the anti-duplication section
+    const result = buildAntiDuplicationSection()
+
+    //#then: should contain the anti-duplication rule with all key concepts
+    expect(result).toContain("Anti-Duplication Rule")
+    expect(result).toContain("CRITICAL")
+    expect(result).toContain("DO NOT perform the same search yourself")
+  })
+
+  it("#given no arguments #when building #then explicitly forbids manual re-search after delegation", () => {
+    //#given: no special configuration
+
+    //#when: building the section
+    const result = buildAntiDuplicationSection()
+
+    //#then: should explicitly list forbidden behaviors
+    expect(result).toContain("FORBIDDEN")
+    expect(result).toContain("manually grep/search for the same information")
+    expect(result).toContain("Re-doing the research")
+  })
+
+  it("#given no arguments #when building #then allows non-overlapping work", () => {
+    //#given: no special configuration
+
+    //#when: building the section
+    const result = buildAntiDuplicationSection()
+
+    //#then: should explicitly allow non-overlapping work
+    expect(result).toContain("ALLOWED")
+    expect(result).toContain("non-overlapping work")
+    expect(result).toContain("work that doesn't depend on the delegated research")
+  })
+
+  it("#given no arguments #when building #then includes wait-for-results instructions", () => {
+    //#given: no special configuration
+
+    //#when: building the section
+    const result = buildAntiDuplicationSection()
+
+    //#then: should include instructions for waiting properly
+    expect(result).toContain("Wait for Results Properly")
+    expect(result).toContain("End your response")
+    expect(result).toContain("Wait for the completion notification")
+    expect(result).toContain("background_output")
+  })
+
+  it("#given no arguments #when building #then explains why this matters", () => {
+    //#given: no special configuration
+
+    //#when: building the section
+    const result = buildAntiDuplicationSection()
+
+    //#then: should explain the purpose
+    expect(result).toContain("Why This Matters")
+    expect(result).toContain("Wasted tokens")
+    expect(result).toContain("Confusion")
+    expect(result).toContain("Efficiency")
+  })
+
+  it("#given no arguments #when building #then provides code examples", () => {
+    //#given: no special configuration
+
+    //#when: building the section
+    const result = buildAntiDuplicationSection()
+
+    //#then: should include examples
+    expect(result).toContain("Example")
+    expect(result).toContain("WRONG")
+    expect(result).toContain("CORRECT")
+    expect(result).toContain("task(subagent_type=")
+  })
+
+  it("#given no arguments #when building #then uses proper markdown formatting", () => {
+    //#given: no special configuration
+
+    //#when: building the section
+    const result = buildAntiDuplicationSection()
+
+    //#then: should be wrapped in Anti_Duplication tag
+    expect(result).toContain("<Anti_Duplication>")
+    expect(result).toContain("</Anti_Duplication>")
+  })
+})

src/agents/atlas/atlas-prompt.test.ts

@@ -0,0 +1,118 @@
+import { describe, test, expect } from "bun:test"
+import { ATLAS_SYSTEM_PROMPT } from "./default"
+import { ATLAS_GPT_SYSTEM_PROMPT } from "./gpt"
+import { ATLAS_GEMINI_SYSTEM_PROMPT } from "./gemini"
+
+describe("Atlas prompts auto-continue policy", () => {
+  test("default variant should forbid asking user for continuation confirmation", () => {
+    // given
+    const prompt = ATLAS_SYSTEM_PROMPT
+
+    // when
+    const lowerPrompt = prompt.toLowerCase()
+
+    // then
+    expect(lowerPrompt).toContain("auto-continue policy")
+    expect(lowerPrompt).toContain("never ask the user")
+    expect(lowerPrompt).toContain("should i continue")
+    expect(lowerPrompt).toContain("proceed to next task")
+    expect(lowerPrompt).toContain("approval-style")
+    expect(lowerPrompt).toContain("auto-continue immediately")
+  })
+
+  test("gpt variant should forbid asking user for continuation confirmation", () => {
+    // given
+    const prompt = ATLAS_GPT_SYSTEM_PROMPT
+
+    // when
+    const lowerPrompt = prompt.toLowerCase()
+
+    // then
+    expect(lowerPrompt).toContain("auto-continue policy")
+    expect(lowerPrompt).toContain("never ask the user")
+    expect(lowerPrompt).toContain("should i continue")
+    expect(lowerPrompt).toContain("proceed to next task")
+    expect(lowerPrompt).toContain("approval-style")
+    expect(lowerPrompt).toContain("auto-continue immediately")
+  })
+
+  test("gemini variant should forbid asking user for continuation confirmation", () => {
+    // given
+    const prompt = ATLAS_GEMINI_SYSTEM_PROMPT
+
+    // when
+    const lowerPrompt = prompt.toLowerCase()
+
+    // then
+    expect(lowerPrompt).toContain("auto-continue policy")
+    expect(lowerPrompt).toContain("never ask the user")
+    expect(lowerPrompt).toContain("should i continue")
+    expect(lowerPrompt).toContain("proceed to next task")
+    expect(lowerPrompt).toContain("approval-style")
+    expect(lowerPrompt).toContain("auto-continue immediately")
+  })
+
+  test("all variants should require immediate continuation after verification passes", () => {
+    // given
+    const prompts = [ATLAS_SYSTEM_PROMPT, ATLAS_GPT_SYSTEM_PROMPT, ATLAS_GEMINI_SYSTEM_PROMPT]
+
+    // when / then
+    for (const prompt of prompts) {
+      const lowerPrompt = prompt.toLowerCase()
+      expect(lowerPrompt).toMatch(/auto-continue immediately after verification/)
+      expect(lowerPrompt).toMatch(/immediately delegate next task/)
+    }
+  })
+
+  test("all variants should define when user interaction is actually needed", () => {
+    // given
+    const prompts = [ATLAS_SYSTEM_PROMPT, ATLAS_GPT_SYSTEM_PROMPT, ATLAS_GEMINI_SYSTEM_PROMPT]
+
+    // when / then
+    for (const prompt of prompts) {
+      const lowerPrompt = prompt.toLowerCase()
+      expect(lowerPrompt).toMatch(/only pause.*truly blocked/)
+      expect(lowerPrompt).toMatch(/plan needs clarification|blocked by external/)
+    }
+  })
+})
+
+describe("Atlas prompts plan path consistency", () => {
+  test("default variant should use .sisyphus/plans/{plan-name}.md path", () => {
+    // given
+    const prompt = ATLAS_SYSTEM_PROMPT
+
+    // when / then
+    expect(prompt).toContain(".sisyphus/plans/{plan-name}.md")
+    expect(prompt).not.toContain(".sisyphus/tasks/{plan-name}.yaml")
+    expect(prompt).not.toContain(".sisyphus/tasks/")
+  })
+
+  test("gpt variant should use .sisyphus/plans/{plan-name}.md path", () => {
+    // given
+    const prompt = ATLAS_GPT_SYSTEM_PROMPT
+
+    // when / then
+    expect(prompt).toContain(".sisyphus/plans/{plan-name}.md")
+    expect(prompt).not.toContain(".sisyphus/tasks/")
+  })
+
+  test("gemini variant should use .sisyphus/plans/{plan-name}.md path", () => {
+    // given
+    const prompt = ATLAS_GEMINI_SYSTEM_PROMPT
+
+    // when / then
+    expect(prompt).toContain(".sisyphus/plans/{plan-name}.md")
+    expect(prompt).not.toContain(".sisyphus/tasks/")
+  })
+
+  test("all variants should read plan file after verification", () => {
+    // given
+    const prompts = [ATLAS_SYSTEM_PROMPT, ATLAS_GPT_SYSTEM_PROMPT, ATLAS_GEMINI_SYSTEM_PROMPT]
+
+    // when / then
+    for (const prompt of prompts) {
+      expect(prompt).toMatch(/read[\s\S]*?\.sisyphus\/plans\//)
+    }
+  })
+})

src/agents/atlas/default.ts

@@ -99,6 +99,29 @@ Every \`task()\` prompt MUST include ALL 6 sections:
 **If your prompt is under 30 lines, it's TOO SHORT.**
 </delegation_system>
 
+<auto_continue>
+## AUTO-CONTINUE POLICY (STRICT)
+
+**CRITICAL: NEVER ask the user "should I continue", "proceed to next task", or any approval-style questions between plan steps.**
+
+**You MUST auto-continue immediately after verification passes:**
+- After any delegation completes and passes verification → Immediately delegate next task
+- Do NOT wait for user input, do NOT ask "should I continue"
+- Only pause or ask if you are truly blocked by missing information, an external dependency, or a critical failure
+
+**The only time you ask the user:**
+- Plan needs clarification or modification before execution
+- Blocked by an external dependency beyond your control
+- Critical failure prevents any further progress
+
+**Auto-continue examples:**
+- Task A done → Verify → Pass → Immediately start Task B
+- Task fails → Retry 3x → Still fails → Document → Move to next independent task
+- NEVER: "Should I continue to the next task?"
+
+**This is NOT optional. This is core to your role as orchestrator.**
+</auto_continue>
+
 <workflow>
 ## Step 0: Register Tracking
 
@@ -214,7 +237,7 @@ After EVERY delegation, complete ALL of these steps — no shortcuts:
 
 After verification, READ the plan file directly — every time, no exceptions:
 \`\`\`
-Read(".sisyphus/tasks/{plan-name}.yaml")
+Read(".sisyphus/plans/{plan-name}.md")
 \`\`\`
 Count remaining \`- [ ]\` tasks. This is your ground truth for what comes next.
 

src/agents/atlas/gemini.ts

@@ -116,6 +116,29 @@ Every \`task()\` prompt MUST include ALL 6 sections:
 **Minimum 30 lines per delegation prompt. Under 30 lines = the subagent WILL fail.**
 </delegation_system>
 
+<auto_continue>
+## AUTO-CONTINUE POLICY (STRICT)
+
+**CRITICAL: NEVER ask the user "should I continue", "proceed to next task", or any approval-style questions between plan steps.**
+
+**You MUST auto-continue immediately after verification passes:**
+- After any delegation completes and passes verification → Immediately delegate next task
+- Do NOT wait for user input, do NOT ask "should I continue"
+- Only pause or ask if you are truly blocked by missing information, an external dependency, or a critical failure
+
+**The only time you ask the user:**
+- Plan needs clarification or modification before execution
+- Blocked by an external dependency beyond your control
+- Critical failure prevents any further progress
+
+**Auto-continue examples:**
+- Task A done → Verify → Pass → Immediately start Task B
+- Task fails → Retry 3x → Still fails → Document → Move to next independent task
+- NEVER: "Should I continue to the next task?"
+
+**This is NOT optional. This is core to your role as orchestrator.**
+</auto_continue>
+
 <workflow>
 ## Step 0: Register Tracking
 

src/agents/atlas/gpt.ts

@@ -48,9 +48,10 @@ Complete ALL tasks in a work plan via \`task()\` until fully done.
 </scope_and_design_constraints>
 
 <uncertainty_and_ambiguity>
-- If a task is ambiguous or underspecified:
+- During initial plan analysis, if a task is ambiguous or underspecified:
   - Ask 1-3 precise clarifying questions, OR
   - State your interpretation explicitly and proceed with the simplest approach.
+- Once execution has started, do NOT stop to ask for continuation or approval between steps.
 - Never fabricate task details, file paths, or requirements.
 - Prefer language like "Based on the plan..." instead of absolute claims.
 - When unsure about parallelization, default to sequential execution.
@@ -134,6 +135,29 @@ Every \`task()\` prompt MUST include ALL 6 sections:
 **Minimum 30 lines per delegation prompt.**
 </delegation_system>
 
+<auto_continue>
+## AUTO-CONTINUE POLICY (STRICT)
+
+**CRITICAL: NEVER ask the user "should I continue", "proceed to next task", or any approval-style questions between plan steps.**
+
+**You MUST auto-continue immediately after verification passes:**
+- After any delegation completes and passes verification → Immediately delegate next task
+- Do NOT wait for user input, do NOT ask "should I continue"
+- Only pause or ask if you are truly blocked by missing information, an external dependency, or a critical failure
+
+**The only time you ask the user:**
+- Plan needs clarification or modification before execution
+- Blocked by an external dependency beyond your control
+- Critical failure prevents any further progress
+
+**Auto-continue examples:**
+- Task A done → Verify → Pass → Immediately start Task B
+- Task fails → Retry 3x → Still fails → Document → Move to next independent task
+- NEVER: "Should I continue to the next task?"
+
+**This is NOT optional. This is core to your role as orchestrator.**
+</auto_continue>
+
 <workflow>
 ## Step 0: Register Tracking
 

src/agents/delegation-trust-prompt.test.ts

@@ -0,0 +1,88 @@
+import { describe, expect, test } from "bun:test"
+import { createSisyphusAgent } from "./sisyphus"
+import { createHephaestusAgent } from "./hephaestus"
+import { buildSisyphusJuniorPrompt } from "./sisyphus-junior/agent"
+import {
+  buildAntiDuplicationSection,
+  buildExploreSection,
+  type AvailableAgent,
+} from "./dynamic-agent-prompt-builder"
+
+const exploreAgent = {
+  name: "explore",
+  description: "Contextual grep specialist",
+  metadata: {
+    category: "advisor",
+    cost: "FREE",
+    promptAlias: "Explore",
+    triggers: [],
+    useWhen: ["Multiple search angles needed"],
+    avoidWhen: ["Single keyword search is enough"],
+  },
+} satisfies AvailableAgent
+
+describe("delegation trust prompt rules", () => {
+  test("buildAntiDuplicationSection explains overlap is forbidden", () => {
+    // given
+    const section = buildAntiDuplicationSection()
+
+    // when / then
+    expect(section).toContain("DO NOT perform the same search yourself")
+    expect(section).toContain("non-overlapping work")
+    expect(section).toContain("End your response")
+  })
+
+  test("buildExploreSection includes delegation trust rule", () => {
+    // given
+    const agents = [exploreAgent]
+
+    // when
+    const section = buildExploreSection(agents)
+
+    // then
+    expect(section).toContain("Delegation Trust Rule")
+    expect(section).toContain("do **not** manually perform that same search yourself")
+  })
+
+  test("Sisyphus prompt forbids duplicate delegated exploration", () => {
+    // given
+    const agent = createSisyphusAgent("anthropic/claude-sonnet-4-6", [exploreAgent])
+
+    // when
+    const prompt = agent.prompt
+
+    // then
+    expect(prompt).toContain("Continue only with non-overlapping work")
+    expect(prompt).toContain("DO NOT perform the same search yourself")
+  })
+
+  test("Hephaestus prompt forbids duplicate delegated exploration", () => {
+    // given
+    const agent = createHephaestusAgent("openai/gpt-5.2", [exploreAgent])
+
+    // when
+    const prompt = agent.prompt
+
+    // then
+    expect(prompt).toContain("Continue only with non-overlapping work after launching background agents")
+    expect(prompt).toContain("DO NOT perform the same search yourself")
+  })
+
+  test("Sisyphus-Junior GPT prompt forbids duplicate delegated exploration", () => {
+    // given
+    const prompt = buildSisyphusJuniorPrompt("openai/gpt-5.2", false)
+
+    // when / then
+    expect(prompt).toContain("continue only with non-overlapping work while they search")
+    expect(prompt).toContain("DO NOT perform the same search yourself")
+  })
+
+  test("Sisyphus-Junior Gemini prompt forbids duplicate delegated exploration", () => {
+    // given
+    const prompt = buildSisyphusJuniorPrompt("google/gemini-3.1-pro", false)
+
+    // when / then
+    expect(prompt).toContain("continue only with non-overlapping work while they search")
+    expect(prompt).toContain("DO NOT perform the same search yourself")
+  })
+})

src/agents/dynamic-agent-prompt-builder.ts

@@ -118,6 +118,8 @@ export function buildExploreSection(agents: AvailableAgent[]): string {
 
 Use it as a **peer tool**, not a fallback. Fire liberally.
 
+**Delegation Trust Rule:** Once you fire an explore agent for a search, do **not** manually perform that same search yourself. Use direct tools only for non-overlapping work or when you intentionally skipped delegation.
+
 **Use Direct Tools when:**
 ${avoidWhen.map((w) => `- ${w}`).join("\n")}
 
@@ -308,6 +310,7 @@ export function buildAntiPatternsSection(): string {
     "- **Search**: Firing agents for single-line typos or obvious syntax errors",
     "- **Debugging**: Shotgun debugging, random changes",
     "- **Background Tasks**: Polling `background_output` on running tasks — end response and wait for notification",
+    "- **Delegation Duplication**: Delegating exploration to explore/librarian and then manually doing the same search yourself",
     "- **Oracle**: Delivering answer without collecting Oracle results",
   ]
 
@@ -409,3 +412,52 @@ export function buildUltraworkSection(
 
   return lines.join("\n")
 }
+
+// Anti-duplication section for agent prompts
+export function buildAntiDuplicationSection(): string {
+  return `<Anti_Duplication>
+## Anti-Duplication Rule (CRITICAL)
+
+Once you delegate exploration to explore/librarian agents, **DO NOT perform the same search yourself**.
+
+### What this means:
+
+**FORBIDDEN:**
+- After firing explore/librarian, manually grep/search for the same information
+- Re-doing the research the agents were just tasked with
+- "Just quickly checking" the same files the background agents are checking
+
+**ALLOWED:**
+- Continue with **non-overlapping work** — work that doesn't depend on the delegated research
+- Work on unrelated parts of the codebase
+- Preparation work (e.g., setting up files, configs) that can proceed independently
+
+### Wait for Results Properly:
+
+When you need the delegated results but they're not ready:
+
+1. **End your response** — do NOT continue with work that depends on those results
+2. **Wait for the completion notification** — the system will trigger your next turn
+3. **Then** collect results via \`background_output(task_id="...")\`
+4. **Do NOT** impatiently re-search the same topics while waiting
+
+### Why This Matters:
+
+- **Wasted tokens**: Duplicate exploration wastes your context budget
+- **Confusion**: You might contradict the agent's findings
+- **Efficiency**: The whole point of delegation is parallel throughput
+
+### Example:
+
+\`\`\`typescript
+// WRONG: After delegating, re-doing the search
+task(subagent_type="explore", run_in_background=true, ...)
+// Then immediately grep for the same thing yourself — FORBIDDEN
+
+// CORRECT: Continue non-overlapping work
+task(subagent_type="explore", run_in_background=true, ...)
+// Work on a different, unrelated file while they search
+// End your response and wait for the notification
+\`\`\`
+</Anti_Duplication>`
+}

src/agents/hephaestus.ts

@@ -16,6 +16,7 @@ import {
   buildOracleSection,
   buildHardBlocksSection,
   buildAntiPatternsSection,
+  buildAntiDuplicationSection,
   categorizeTools,
 } from "./dynamic-agent-prompt-builder";
 
@@ -290,11 +291,13 @@ Prompt structure for each agent:
 - Fire 2-5 explore agents in parallel for any non-trivial codebase question
 - Parallelize independent file reads — don't read files one at a time
 - NEVER use \`run_in_background=false\` for explore/librarian
-- Continue your work immediately after launching background agents
+- Continue only with non-overlapping work after launching background agents
 - Collect results with \`background_output(task_id="...")\` when needed
 - BEFORE final answer, cancel DISPOSABLE tasks individually: \`background_cancel(taskId="bg_explore_xxx")\`, \`background_cancel(taskId="bg_librarian_xxx")\`
 - **NEVER use \`background_cancel(all=true)\`** — it kills tasks whose results you haven't collected yet
 
+${buildAntiDuplicationSection()}
+
 ### Search Stop Conditions
 
 STOP searching when:

src/agents/sisyphus-junior/gemini.ts

@@ -9,6 +9,7 @@
  */
 
 import { resolvePromptAppend } from "../builtin-agents/resolve-file-uri"
+import { buildAntiDuplicationSection } from "../dynamic-agent-prompt-builder"
 
 export function buildGeminiSisyphusJuniorPrompt(
   useTaskSystem: boolean,
@@ -58,7 +59,7 @@ Before responding, ask yourself: What tools do I need to call? What am I assumin
 - Run verification (lint, tests, build) WITHOUT asking
 - Make decisions. Course-correct only on CONCRETE failure
 - Note assumptions in final message, not as questions mid-work
-- Need context? Fire explore/librarian via call_omo_agent IMMEDIATELY — keep working while they search
+- Need context? Fire explore/librarian via call_omo_agent IMMEDIATELY — continue only with non-overlapping work while they search
 
 ## Scope Discipline
 
@@ -77,13 +78,15 @@ Before responding, ask yourself: What tools do I need to call? What am I assumin
 
 <tool_usage_rules>
 - Parallelize independent tool calls: multiple file reads, grep searches, agent fires — all at once
-- Explore/Librarian via call_omo_agent = background research. Fire them and keep working
+- Explore/Librarian via call_omo_agent = background research. Fire them and continue only with non-overlapping work
 - After any file edit: restate what changed, where, and what validation follows
 - Prefer tools over guessing whenever you need specific data (files, configs, patterns)
 - ALWAYS use tools over internal knowledge for file contents, project state, and verification
 - **DO NOT SKIP tool calls because you think you already know the answer. You DON'T.**
 </tool_usage_rules>
 
+${buildAntiDuplicationSection()}
+
 ${taskDiscipline}
 
 ## Progress Updates

src/agents/sisyphus-junior/gpt.ts

@@ -7,6 +7,7 @@
  */
 
 import { resolvePromptAppend } from "../builtin-agents/resolve-file-uri"
+import { buildAntiDuplicationSection } from "../dynamic-agent-prompt-builder"
 
 export function buildGptSisyphusJuniorPrompt(
   useTaskSystem: boolean,
@@ -40,7 +41,7 @@ When blocked: try a different approach → decompose the problem → challenge a
 - Run verification (lint, tests, build) WITHOUT asking
 - Make decisions. Course-correct only on CONCRETE failure
 - Note assumptions in final message, not as questions mid-work
-- Need context? Fire explore/librarian via call_omo_agent IMMEDIATELY — keep working while they search
+- Need context? Fire explore/librarian via call_omo_agent IMMEDIATELY — continue only with non-overlapping work while they search
 
 ## Scope Discipline
 
@@ -58,12 +59,14 @@ When blocked: try a different approach → decompose the problem → challenge a
 
 <tool_usage_rules>
 - Parallelize independent tool calls: multiple file reads, grep searches, agent fires — all at once
-- Explore/Librarian via call_omo_agent = background research. Fire them and keep working
+- Explore/Librarian via call_omo_agent = background research. Fire them and continue only with non-overlapping work
 - After any file edit: restate what changed, where, and what validation follows
 - Prefer tools over guessing whenever you need specific data (files, configs, patterns)
 - ALWAYS use tools over internal knowledge for file contents, project state, and verification
 </tool_usage_rules>
 
+${buildAntiDuplicationSection()}
+
 ${taskDiscipline}
 
 ## Progress Updates

src/agents/sisyphus.ts

@@ -35,6 +35,7 @@ import {
   buildAntiPatternsSection,
   buildDeepParallelSection,
   buildNonClaudePlannerSection,
+  buildAntiDuplicationSection,
   categorizeTools,
 } from "./dynamic-agent-prompt-builder";
 
@@ -333,7 +334,7 @@ task(subagent_type="explore", run_in_background=true, load_skills=[], descriptio
 // Reference Grep (external)
 task(subagent_type="librarian", run_in_background=true, load_skills=[], description="Find JWT security docs", prompt="I'm implementing JWT auth and need current security best practices to choose token storage (httpOnly cookies vs localStorage) and set expiration policy. Find: OWASP auth guidelines, recommended token lifetimes, refresh token rotation strategies, common JWT vulnerabilities. Skip 'what is JWT' tutorials — production security guidance only.")
 task(subagent_type="librarian", run_in_background=true, load_skills=[], description="Find Express auth patterns", prompt="I'm building Express auth middleware and need production-quality patterns to structure my middleware chain. Find how established Express apps (1000+ stars) handle: middleware ordering, token refresh, role-based access control, auth error propagation. Skip basic tutorials — I need battle-tested patterns with proper error handling.")
-// Continue working immediately. System notifies on completion — collect with background_output then.
+// Continue only with non-overlapping work. System notifies on completion — collect with background_output then.
 
 // WRONG: Sequential or blocking
 result = task(..., run_in_background=false)  // Never wait synchronously for explore/librarian
@@ -341,11 +342,13 @@ result = task(..., run_in_background=false)  // Never wait synchronously for exp
 
 ### Background Result Collection:
 1. Launch parallel agents \u2192 receive task_ids
-2. Continue immediate work
+2. Continue only with non-overlapping work
 3. System sends \`<system-reminder>\` on each task completion — then call \`background_output(task_id="...")\`
 4. Need results not yet ready? **End your response.** The notification will trigger your next turn.
 5. Cleanup: Cancel disposable tasks individually via \`background_cancel(taskId="...")\`
 
+${buildAntiDuplicationSection()}
+
 ### Search Stop Conditions
 
 STOP searching when:

src/cli/__snapshots__/model-fallback.test.ts.snap

@@ -83,7 +83,7 @@ exports[`generateModelConfig single native provider uses Claude models when only
       "variant": "max",
     },
     "multimodal-looker": {
-      "model": "anthropic/claude-haiku-4-5",
+      "model": "opencode/glm-4.7-free",
     },
     "oracle": {
       "model": "anthropic/claude-opus-4-6",
@@ -145,7 +145,7 @@ exports[`generateModelConfig single native provider uses Claude models with isMa
       "variant": "max",
     },
     "multimodal-looker": {
-      "model": "anthropic/claude-haiku-4-5",
+      "model": "opencode/glm-4.7-free",
     },
     "oracle": {
       "model": "anthropic/claude-opus-4-6",
@@ -212,7 +212,8 @@ exports[`generateModelConfig single native provider uses OpenAI models when only
       "variant": "medium",
     },
     "multimodal-looker": {
-      "model": "openai/gpt-5.2",
+      "model": "openai/gpt-5.3-codex",
+      "variant": "medium",
     },
     "oracle": {
       "model": "openai/gpt-5.2",
@@ -279,7 +280,8 @@ exports[`generateModelConfig single native provider uses OpenAI models with isMa
       "variant": "medium",
     },
     "multimodal-looker": {
-      "model": "openai/gpt-5.2",
+      "model": "openai/gpt-5.3-codex",
+      "variant": "medium",
     },
     "oracle": {
       "model": "openai/gpt-5.2",
@@ -468,7 +470,8 @@ exports[`generateModelConfig all native providers uses preferred models from fal
       "variant": "medium",
     },
     "multimodal-looker": {
-      "model": "google/gemini-3-flash-preview",
+      "model": "openai/gpt-5.3-codex",
+      "variant": "medium",
     },
     "oracle": {
       "model": "openai/gpt-5.2",
@@ -542,7 +545,8 @@ exports[`generateModelConfig all native providers uses preferred models with isM
       "variant": "medium",
     },
     "multimodal-looker": {
-      "model": "google/gemini-3-flash-preview",
+      "model": "openai/gpt-5.3-codex",
+      "variant": "medium",
     },
     "oracle": {
       "model": "openai/gpt-5.2",
@@ -596,7 +600,7 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models when on
   "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/dev/assets/oh-my-opencode.schema.json",
   "agents": {
     "atlas": {
-      "model": "opencode/kimi-k2.5-free",
+      "model": "opencode/claude-sonnet-4-5",
     },
     "explore": {
       "model": "opencode/claude-haiku-4-5",
@@ -617,7 +621,8 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models when on
       "variant": "medium",
     },
     "multimodal-looker": {
-      "model": "opencode/gemini-3-flash",
+      "model": "opencode/gpt-5.3-codex",
+      "variant": "medium",
     },
     "oracle": {
       "model": "opencode/gpt-5.2",
@@ -670,7 +675,7 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models with is
   "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/dev/assets/oh-my-opencode.schema.json",
   "agents": {
     "atlas": {
-      "model": "opencode/kimi-k2.5-free",
+      "model": "opencode/claude-sonnet-4-5",
     },
     "explore": {
       "model": "opencode/claude-haiku-4-5",
@@ -691,7 +696,8 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models with is
       "variant": "medium",
     },
     "multimodal-looker": {
-      "model": "opencode/gemini-3-flash",
+      "model": "opencode/gpt-5.3-codex",
+      "variant": "medium",
     },
     "oracle": {
       "model": "opencode/gpt-5.2",
@@ -988,7 +994,7 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + OpenCode Zen
   "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/dev/assets/oh-my-opencode.schema.json",
   "agents": {
     "atlas": {
-      "model": "opencode/kimi-k2.5-free",
+      "model": "anthropic/claude-sonnet-4-5",
     },
     "explore": {
       "model": "anthropic/claude-haiku-4-5",
@@ -1009,7 +1015,8 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + OpenCode Zen
       "variant": "medium",
     },
     "multimodal-looker": {
-      "model": "opencode/gemini-3-flash",
+      "model": "opencode/gpt-5.3-codex",
+      "variant": "medium",
     },
     "oracle": {
       "model": "opencode/gpt-5.2",
@@ -1083,7 +1090,8 @@ exports[`generateModelConfig mixed provider scenarios uses OpenAI + Copilot comb
       "variant": "medium",
     },
     "multimodal-looker": {
-      "model": "github-copilot/gemini-3-flash-preview",
+      "model": "openai/gpt-5.3-codex",
+      "variant": "medium",
     },
     "oracle": {
       "model": "openai/gpt-5.2",
@@ -1263,7 +1271,7 @@ exports[`generateModelConfig mixed provider scenarios uses all fallback provider
   "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/dev/assets/oh-my-opencode.schema.json",
   "agents": {
     "atlas": {
-      "model": "opencode/kimi-k2.5-free",
+      "model": "github-copilot/claude-sonnet-4.5",
     },
     "explore": {
       "model": "opencode/claude-haiku-4-5",
@@ -1284,7 +1292,8 @@ exports[`generateModelConfig mixed provider scenarios uses all fallback provider
       "variant": "medium",
     },
     "multimodal-looker": {
-      "model": "github-copilot/gemini-3-flash-preview",
+      "model": "opencode/gpt-5.3-codex",
+      "variant": "medium",
     },
     "oracle": {
       "model": "github-copilot/gpt-5.2",
@@ -1337,7 +1346,7 @@ exports[`generateModelConfig mixed provider scenarios uses all providers togethe
   "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/dev/assets/oh-my-opencode.schema.json",
   "agents": {
     "atlas": {
-      "model": "opencode/kimi-k2.5-free",
+      "model": "anthropic/claude-sonnet-4-5",
     },
     "explore": {
       "model": "anthropic/claude-haiku-4-5",
@@ -1358,7 +1367,8 @@ exports[`generateModelConfig mixed provider scenarios uses all providers togethe
       "variant": "medium",
     },
     "multimodal-looker": {
-      "model": "google/gemini-3-flash-preview",
+      "model": "openai/gpt-5.3-codex",
+      "variant": "medium",
     },
     "oracle": {
       "model": "openai/gpt-5.2",
@@ -1411,7 +1421,7 @@ exports[`generateModelConfig mixed provider scenarios uses all providers with is
   "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/dev/assets/oh-my-opencode.schema.json",
   "agents": {
     "atlas": {
-      "model": "opencode/kimi-k2.5-free",
+      "model": "anthropic/claude-sonnet-4-5",
     },
     "explore": {
       "model": "anthropic/claude-haiku-4-5",
@@ -1432,7 +1442,8 @@ exports[`generateModelConfig mixed provider scenarios uses all providers with is
       "variant": "medium",
     },
     "multimodal-looker": {
-      "model": "google/gemini-3-flash-preview",
+      "model": "openai/gpt-5.3-codex",
+      "variant": "medium",
     },
     "oracle": {
       "model": "openai/gpt-5.2",

src/cli/config-manager.test.ts

@@ -323,8 +323,8 @@ describe("generateOmoConfig - model fallback system", () => {
     expect((result.agents as Record<string, { model: string }>).sisyphus).toBeUndefined()
     // #then Oracle should use native OpenAI (first fallback entry)
     expect((result.agents as Record<string, { model: string }>).oracle.model).toBe("openai/gpt-5.2")
-    // #then multimodal-looker should use native OpenAI (fallback within native tier)
-    expect((result.agents as Record<string, { model: string }>)["multimodal-looker"].model).toBe("openai/gpt-5.2")
+    // #then multimodal-looker should use native OpenAI (first fallback entry is gpt-5.3-codex)
+    expect((result.agents as Record<string, { model: string }>)["multimodal-looker"].model).toBe("openai/gpt-5.3-codex")
   })
 
   test("uses haiku for explore when Claude max20", () => {

src/cli/model-fallback-requirements.ts

@@ -9,7 +9,6 @@ export const CLI_AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
     fallbackChain: [
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
       { providers: ["kimi-for-coding"], model: "k2p5" },
-      { providers: ["opencode"], model: "kimi-k2.5-free" },
       { providers: ["zai-coding-plan"], model: "glm-4.7" },
       { providers: ["opencode"], model: "glm-4.7-free" },
     ],
@@ -44,12 +43,10 @@ export const CLI_AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   },
   "multimodal-looker": {
     fallbackChain: [
-      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash" },
-      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2" },
-      { providers: ["zai-coding-plan"], model: "glm-4.6v" },
+      { providers: ["openai", "opencode"], model: "gpt-5.3-codex", variant: "medium" },
       { providers: ["kimi-for-coding"], model: "k2p5" },
-      { providers: ["opencode"], model: "kimi-k2.5-free" },
-      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-haiku-4-5" },
+      { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash" },
+      { providers: ["zai-coding-plan"], model: "glm-4.6v" },
       { providers: ["opencode"], model: "gpt-5-nano" },
     ],
   },
@@ -57,7 +54,6 @@ export const CLI_AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
     fallbackChain: [
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
       { providers: ["kimi-for-coding"], model: "k2p5" },
-      { providers: ["opencode"], model: "kimi-k2.5-free" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
       { providers: ["google", "github-copilot", "opencode"], model: "gemini-3.1-pro" },
     ],
@@ -66,7 +62,6 @@ export const CLI_AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
     fallbackChain: [
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
       { providers: ["kimi-for-coding"], model: "k2p5" },
-      { providers: ["opencode"], model: "kimi-k2.5-free" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
       { providers: ["google", "github-copilot", "opencode"], model: "gemini-3.1-pro", variant: "high" },
     ],
@@ -81,7 +76,6 @@ export const CLI_AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   atlas: {
     fallbackChain: [
       { providers: ["kimi-for-coding"], model: "k2p5" },
-      { providers: ["opencode"], model: "kimi-k2.5-free" },
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-sonnet-4-5" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2" },
       { providers: ["google", "github-copilot", "opencode"], model: "gemini-3.1-pro" },

src/hooks/model-fallback/hook.test.ts

@@ -134,8 +134,8 @@ describe("model fallback hook", () => {
 
     //#then - chain should progress to entry[1], not repeat entry[0]
     expect(secondOutput.message["model"]).toEqual({
-      providerID: "opencode",
-      modelID: "kimi-k2.5-free",
+      providerID: "zai-coding-plan",
+      modelID: "glm-5",
     })
     expect(secondOutput.message["variant"]).toBeUndefined()
   })

src/plugin/event.model-fallback.test.ts

@@ -334,8 +334,8 @@ describe("createEventHandler - model fallback", () => {
 
     //#then - second fallback entry applied (chain advanced)
     expect(second.message["model"]).toEqual({
-      providerID: "opencode",
-      modelID: "kimi-k2.5-free",
+      providerID: "zai-coding-plan",
+      modelID: "glm-5",
     })
     expect(second.message["variant"]).toBeUndefined()
     expect(abortCalls).toEqual([sessionID, sessionID])

src/plugin/system-transform.ts

@@ -1,5 +1,5 @@
 export function createSystemTransformHandler(): (
-  input: { sessionID: string },
+  input: { sessionID?: string; model: { id: string; providerID: string; [key: string]: unknown } },
   output: { system: string[] },
 ) => Promise<void> {
   return async (): Promise<void> => {}

src/shared/model-requirements.test.ts

@@ -31,7 +31,7 @@ describe("AGENT_MODEL_REQUIREMENTS", () => {
     // #then - fallbackChain has claude-opus-4-6 first, big-pickle last
     expect(sisyphus).toBeDefined()
     expect(sisyphus.fallbackChain).toBeArray()
-    expect(sisyphus.fallbackChain).toHaveLength(4)
+    expect(sisyphus.fallbackChain).toHaveLength(3)
     expect(sisyphus.requiresAnyModel).toBe(true)
 
     const primary = sisyphus.fallbackChain[0]
@@ -39,7 +39,7 @@ describe("AGENT_MODEL_REQUIREMENTS", () => {
     expect(primary.model).toBe("claude-opus-4-6")
     expect(primary.variant).toBe("max")
 
-    const last = sisyphus.fallbackChain[3]
+    const last = sisyphus.fallbackChain[2]
     expect(last.providers[0]).toBe("opencode")
     expect(last.model).toBe("big-pickle")
   })
@@ -86,19 +86,27 @@ describe("AGENT_MODEL_REQUIREMENTS", () => {
     expect(quaternary.model).toBe("gpt-5-nano")
   })
 
-  test("multimodal-looker has valid fallbackChain with kimi-k2.5-free as primary", () => {
+  test("multimodal-looker has valid fallbackChain with gpt-5.3-codex as primary", () => {
     // given - multimodal-looker agent requirement
     const multimodalLooker = AGENT_MODEL_REQUIREMENTS["multimodal-looker"]
 
     // when - accessing multimodal-looker requirement
-    // then - fallbackChain exists with kimi-k2.5-free first, gpt-5-nano last
+    // then - fallbackChain: gpt-5.3-codex -> k2p5 -> gemini-3-flash -> glm-4.6v -> gpt-5-nano
     expect(multimodalLooker).toBeDefined()
     expect(multimodalLooker.fallbackChain).toBeArray()
     expect(multimodalLooker.fallbackChain).toHaveLength(5)
 
     const primary = multimodalLooker.fallbackChain[0]
-    expect(primary.providers[0]).toBe("opencode")
-    expect(primary.model).toBe("kimi-k2.5-free")
+    expect(primary.providers).toEqual(["openai", "opencode"])
+    expect(primary.model).toBe("gpt-5.3-codex")
+    expect(primary.variant).toBe("medium")
+
+    const secondary = multimodalLooker.fallbackChain[1]
+    expect(secondary.providers).toEqual(["kimi-for-coding"])
+    expect(secondary.model).toBe("k2p5")
+
+    const tertiary = multimodalLooker.fallbackChain[2]
+    expect(tertiary.model).toBe("gemini-3-flash")
 
     const last = multimodalLooker.fallbackChain[4]
     expect(last.providers).toEqual(["openai", "github-copilot", "opencode"])
@@ -153,19 +161,19 @@ describe("AGENT_MODEL_REQUIREMENTS", () => {
     expect(primary.providers[0]).toBe("openai")
   })
 
-  test("atlas has valid fallbackChain with kimi-k2.5-free as primary", () => {
+  test("atlas has valid fallbackChain with claude-sonnet-4-6 as primary", () => {
     // given - atlas agent requirement
     const atlas = AGENT_MODEL_REQUIREMENTS["atlas"]
 
     // when - accessing Atlas requirement
-    // then - fallbackChain exists with kimi-k2.5-free as first entry
+    // then - fallbackChain exists with claude-sonnet-4-6 as first entry
     expect(atlas).toBeDefined()
     expect(atlas.fallbackChain).toBeArray()
     expect(atlas.fallbackChain.length).toBeGreaterThan(0)
 
     const primary = atlas.fallbackChain[0]
-    expect(primary.model).toBe("kimi-k2.5-free")
-    expect(primary.providers[0]).toBe("opencode")
+    expect(primary.model).toBe("claude-sonnet-4-6")
+    expect(primary.providers[0]).toBe("anthropic")
   })
 
   test("hephaestus supports openai, github-copilot, venice, and opencode providers", () => {
@@ -335,27 +343,23 @@ describe("CATEGORY_MODEL_REQUIREMENTS", () => {
     expect(primary.providers[0]).toBe("google")
   })
 
-  test("writing has valid fallbackChain with kimi-k2.5-free as primary", () => {
+  test("writing has valid fallbackChain with gemini-3-flash as primary", () => {
     // given - writing category requirement
     const writing = CATEGORY_MODEL_REQUIREMENTS["writing"]
 
     // when - accessing writing requirement
-    // then - fallbackChain: kimi-k2.5-free -> gemini-3-flash -> claude-sonnet-4-6
+    // then - fallbackChain: gemini-3-flash -> claude-sonnet-4-6
     expect(writing).toBeDefined()
     expect(writing.fallbackChain).toBeArray()
-    expect(writing.fallbackChain).toHaveLength(3)
+    expect(writing.fallbackChain).toHaveLength(2)
 
     const primary = writing.fallbackChain[0]
-    expect(primary.model).toBe("kimi-k2.5-free")
-    expect(primary.providers[0]).toBe("opencode")
+    expect(primary.model).toBe("gemini-3-flash")
+    expect(primary.providers[0]).toBe("google")
 
     const second = writing.fallbackChain[1]
-    expect(second.model).toBe("gemini-3-flash")
-    expect(second.providers[0]).toBe("google")
-
-    const third = writing.fallbackChain[2]
-    expect(third.model).toBe("claude-sonnet-4-6")
-    expect(third.providers[0]).toBe("anthropic")
+    expect(second.model).toBe("claude-sonnet-4-6")
+    expect(second.providers[0]).toBe("anthropic")
   })
 
   test("all 8 categories have valid fallbackChain arrays", () => {

src/shared/model-requirements.ts

@@ -16,7 +16,6 @@ export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   sisyphus: {
     fallbackChain: [
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
-      { providers: ["opencode"], model: "kimi-k2.5-free" },
       { providers: ["zai-coding-plan", "opencode"], model: "glm-5" },
       { providers: ["opencode"], model: "big-pickle" },
     ],
@@ -53,9 +52,9 @@ export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   },
   "multimodal-looker": {
     fallbackChain: [
-      { providers: ["opencode"], model: "kimi-k2.5-free" },
+      { providers: ["openai", "opencode"], model: "gpt-5.3-codex", variant: "medium" },
+      { providers: ["kimi-for-coding"], model: "k2p5" },
       { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash" },
-      { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2" },
       { providers: ["zai-coding-plan"], model: "glm-4.6v" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5-nano" },
     ],
@@ -64,14 +63,12 @@ export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
     fallbackChain: [
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
-      { providers: ["opencode"], model: "kimi-k2.5-free" },
       { providers: ["google", "github-copilot", "opencode"], model: "gemini-3.1-pro" },
     ],
   },
   metis: {
     fallbackChain: [
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-6", variant: "max" },
-      { providers: ["opencode"], model: "kimi-k2.5-free" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
       { providers: ["google", "github-copilot", "opencode"], model: "gemini-3.1-pro", variant: "high" },
     ],
@@ -85,7 +82,6 @@ export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   },
   atlas: {
     fallbackChain: [
-      { providers: ["opencode"], model: "kimi-k2.5-free" },
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-sonnet-4-6" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2" },
     ],
@@ -146,7 +142,6 @@ export const CATEGORY_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   },
   writing: {
     fallbackChain: [
-      { providers: ["opencode"], model: "kimi-k2.5-free" },
       { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash" },
       { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-sonnet-4-6" },
     ],

src/tools/background-task/constants.ts

@@ -2,6 +2,6 @@ export const BACKGROUND_TASK_DESCRIPTION = `Run agent task in background. Return
 
 Use \`background_output\` to get results. Prompts MUST be in English.`
 
-export const BACKGROUND_OUTPUT_DESCRIPTION = `Get output from background task. Use full_session=true to fetch session messages with filters. System notifies on completion, so block=true rarely needed.`
+export const BACKGROUND_OUTPUT_DESCRIPTION = `Get output from background task. Use full_session=true to fetch session messages with filters. System notifies on completion, so block=true rarely needed. - Timeout values are in milliseconds (ms), NOT seconds.`
 
 export const BACKGROUND_CANCEL_DESCRIPTION = `Cancel running background task(s). Use all=true to cancel ALL before final answer.`

src/tools/background-task/create-background-output.ts

@@ -87,7 +87,6 @@ export function createBackgroundOutput(manager: BackgroundOutputManager, client:
 
         const shouldBlock = args.block === true
         const timeoutMs = Math.min(args.timeout ?? 60000, 600000)
-        const fullSession = args.full_session ?? true
 
         let resolvedTask = task
 
@@ -123,6 +122,10 @@ export function createBackgroundOutput(manager: BackgroundOutputManager, client:
         }
 
         const isActive = isTaskActiveStatus(resolvedTask.status)
+        const fullSessionProvided = args.full_session !== undefined
+        const fullSession = fullSessionProvided
+          ? (args.full_session ?? true)
+          : !isActive
         const includeThinking = isActive || (args.include_thinking ?? false)
         const includeToolResults = isActive || (args.include_tool_results ?? false)
 

src/tools/delegate-task/background-continuation.ts

@@ -33,6 +33,7 @@ export async function executeBackgroundContinuation(
         run_in_background: args.run_in_background,
         sessionId: task.sessionID,
         command: args.command,
+        model: task.model ? { providerID: task.model.providerID, modelID: task.model.modelID } : undefined,
       },
     }
     await ctx.metadata?.(bgContMeta)

src/tools/delegate-task/background-task.test.ts

@@ -0,0 +1,158 @@
+const bunTest = require("bun:test")
+const describeFn = bunTest.describe
+const testFn = bunTest.test
+const expectFn = bunTest.expect
+const beforeEachFn = bunTest.beforeEach
+const afterEachFn = bunTest.afterEach
+
+const { executeBackgroundTask } = require("./background-task")
+const { __setTimingConfig, __resetTimingConfig } = require("./timing")
+
+describeFn("executeBackgroundTask output/session metadata compatibility", () => {
+  beforeEachFn(() => {
+    //#given - reduce waiting to keep tests fast
+    __setTimingConfig({
+      WAIT_FOR_SESSION_INTERVAL_MS: 1,
+      WAIT_FOR_SESSION_TIMEOUT_MS: 2,
+    })
+  })
+
+  afterEachFn(() => {
+    __resetTimingConfig()
+  })
+
+  testFn("does not emit synthetic pending session metadata when session id is unresolved", async () => {
+    //#given - launched task without resolved subagent session id
+    const metadataCalls: any[] = []
+    const manager = {
+      launch: async () => ({
+        id: "bg_unresolved",
+        sessionID: undefined,
+        description: "Unresolved session",
+        agent: "explore",
+        status: "running",
+      }),
+      getTask: () => undefined,
+    }
+
+    const result = await executeBackgroundTask(
+      {
+        description: "Unresolved session",
+        prompt: "check",
+        run_in_background: true,
+        load_skills: [],
+      },
+      {
+        sessionID: "ses_parent",
+        callID: "call_1",
+        metadata: async (value: any) => metadataCalls.push(value),
+        abort: new AbortController().signal,
+      },
+      { manager },
+      { sessionID: "ses_parent", messageID: "msg_1" },
+      "explore",
+      undefined,
+      undefined,
+      undefined,
+    )
+
+    //#then - output and metadata should avoid fake session markers
+    expectFn(result).not.toContain("<task_metadata>")
+    expectFn(result).not.toContain("session_id: undefined")
+    expectFn(result).not.toContain("session_id: pending")
+    expectFn(metadataCalls).toHaveLength(1)
+    expectFn("sessionId" in metadataCalls[0].metadata).toBe(false)
+  })
+
+  testFn("emits task metadata session_id when real session id is available", async () => {
+    //#given - launched task with resolved subagent session id
+    const metadataCalls: any[] = []
+    const manager = {
+      launch: async () => ({
+        id: "bg_resolved",
+        sessionID: "ses_sub_123",
+        description: "Resolved session",
+        agent: "explore",
+        status: "running",
+      }),
+      getTask: () => ({ sessionID: "ses_sub_123" }),
+    }
+
+    const result = await executeBackgroundTask(
+      {
+        description: "Resolved session",
+        prompt: "check",
+        run_in_background: true,
+        load_skills: [],
+      },
+      {
+        sessionID: "ses_parent",
+        callID: "call_2",
+        metadata: async (value: any) => metadataCalls.push(value),
+        abort: new AbortController().signal,
+      },
+      { manager },
+      { sessionID: "ses_parent", messageID: "msg_2" },
+      "explore",
+      undefined,
+      undefined,
+      undefined,
+    )
+
+    //#then - output and metadata should include canonical session linkage
+    expectFn(result).toContain("<task_metadata>")
+    expectFn(result).toContain("session_id: ses_sub_123")
+    expectFn(result).toContain("task_id: ses_sub_123")
+    expectFn(result).toContain("background_task_id: bg_resolved")
+    expectFn(result).toContain("Background Task ID: bg_resolved")
+    expectFn(metadataCalls).toHaveLength(1)
+    expectFn(metadataCalls[0].metadata.sessionId).toBe("ses_sub_123")
+  })
+
+  testFn("captures late-resolved session id and emits synced metadata", async () => {
+    //#given - background task session id appears after launch via manager polling
+    const metadataCalls: any[] = []
+    let reads = 0
+    const manager = {
+      launch: async () => ({
+        id: "bg_late",
+        sessionID: undefined,
+        description: "Late session",
+        agent: "explore",
+        status: "running",
+      }),
+      getTask: () => {
+        reads += 1
+        return reads >= 2 ? { sessionID: "ses_late_123" } : undefined
+      },
+    }
+
+    const result = await executeBackgroundTask(
+      {
+        description: "Late session",
+        prompt: "check",
+        run_in_background: true,
+        load_skills: [],
+      },
+      {
+        sessionID: "ses_parent",
+        callID: "call_3",
+        metadata: async (value: any) => metadataCalls.push(value),
+        abort: new AbortController().signal,
+      },
+      { manager },
+      { sessionID: "ses_parent", messageID: "msg_3" },
+      "explore",
+      undefined,
+      undefined,
+      undefined,
+    )
+
+    //#then - late session id still propagates to task metadata contract
+    expectFn(result).toContain("session_id: ses_late_123")
+    expectFn(result).toContain("task_id: ses_late_123")
+    expectFn(result).toContain("background_task_id: bg_late")
+    expectFn(metadataCalls).toHaveLength(1)
+    expectFn(metadataCalls[0].metadata.sessionId).toBe("ses_late_123")
+  })
+})

src/tools/delegate-task/background-task.ts

@@ -56,36 +56,39 @@ export async function executeBackgroundTask(
       SessionCategoryRegistry.register(sessionId, args.category)
     }
 
+    const metadata = {
+      prompt: args.prompt,
+      agent: task.agent,
+      category: args.category,
+      load_skills: args.load_skills,
+      description: args.description,
+      run_in_background: args.run_in_background,
+      command: args.command,
+      ...(sessionId ? { sessionId } : {}),
+      ...(categoryModel ? { model: { providerID: categoryModel.providerID, modelID: categoryModel.modelID } } : {}),
+    }
+
     const unstableMeta = {
       title: args.description,
-      metadata: {
-        prompt: args.prompt,
-        agent: task.agent,
-        category: args.category,
-        load_skills: args.load_skills,
-        description: args.description,
-        run_in_background: args.run_in_background,
-        sessionId: sessionId ?? "pending",
-        command: args.command,
-      },
+      metadata,
     }
     await ctx.metadata?.(unstableMeta)
     if (ctx.callID) {
       storeToolMetadata(ctx.sessionID, ctx.callID, unstableMeta)
     }
 
+    const taskMetadataBlock = sessionId
+      ? `\n\n<task_metadata>\nsession_id: ${sessionId}\ntask_id: ${sessionId}\nbackground_task_id: ${task.id}\n</task_metadata>`
+      : ""
+
     return `Background task launched.
 
-Task ID: ${task.id}
+Background Task ID: ${task.id}
 Description: ${task.description}
 Agent: ${task.agent}${args.category ? ` (category: ${args.category})` : ""}
 Status: ${task.status}
 
-System notifies on completion. Use \`background_output\` with task_id="${task.id}" to check.
-
-<task_metadata>
-session_id: ${sessionId}
-</task_metadata>`
+System notifies on completion. Use \`background_output\` with task_id="${task.id}" to check.${taskMetadataBlock}`
   } catch (error) {
     return formatDetailedError(error, {
       operation: "Launch background task",

src/tools/delegate-task/metadata-model-unification.test.ts

@@ -0,0 +1,172 @@
+const { describe, test, expect, mock } = require("bun:test")
+
+import type { DelegateTaskArgs, ToolContextWithMetadata } from "./types"
+import type { ParentContext } from "./executor-types"
+
+const MODEL = { providerID: "anthropic", modelID: "claude-sonnet-4-6" }
+
+function makeMockCtx(): ToolContextWithMetadata & { captured: any[] } {
+  const captured: any[] = []
+  return {
+    sessionID: "ses_parent",
+    messageID: "msg_parent",
+    agent: "sisyphus",
+    abort: new AbortController().signal,
+    callID: "call_001",
+    metadata: async (input: any) => { captured.push(input) },
+    captured,
+  }
+}
+
+const parentContext: ParentContext = {
+  sessionID: "ses_parent",
+  messageID: "msg_parent",
+  agent: "sisyphus",
+  model: MODEL,
+}
+
+describe("metadata model unification", () => {
+  describe("#given delegate-task executors", () => {
+    describe("#when metadata is set during execution", () => {
+
+      test("#then sync-task metadata includes model", async () => {
+        const { executeSyncTask } = require("./sync-task")
+        const ctx = makeMockCtx()
+        const deps = {
+          createSyncSession: async () => ({ ok: true, sessionID: "ses_sync" }),
+          sendSyncPrompt: async () => null,
+          pollSyncSession: async () => null,
+          fetchSyncResult: async () => ({ ok: true as const, textContent: "done" }),
+        }
+        const args: DelegateTaskArgs = {
+          description: "test", prompt: "do it",
+          category: "quick", load_skills: [], run_in_background: false,
+        }
+
+        await executeSyncTask(args, ctx, {
+          client: { session: { create: async () => ({ data: { id: "ses_sync" } }) } },
+          directory: "/tmp",
+          onSyncSessionCreated: null,
+        }, parentContext, "explore", MODEL, undefined, undefined, undefined, deps)
+
+        const meta = ctx.captured.find((m: any) => m.metadata?.sessionId)
+        expect(meta).toBeDefined()
+        expect(meta.metadata.model).toEqual(MODEL)
+      })
+
+      test("#then background-task metadata includes model", async () => {
+        const { executeBackgroundTask } = require("./background-task")
+        const ctx = makeMockCtx()
+        const args: DelegateTaskArgs = {
+          description: "test", prompt: "do it",
+          load_skills: [], run_in_background: true, subagent_type: "explore",
+        }
+
+        await executeBackgroundTask(args, ctx, {
+          manager: {
+            launch: async () => ({
+              id: "bg_1", description: "test", agent: "explore",
+              status: "pending", sessionID: "ses_bg", model: MODEL,
+            }),
+            getTask: () => undefined,
+          },
+        } as any, parentContext, "explore", MODEL, undefined)
+
+        const meta = ctx.captured.find((m: any) => m.metadata?.sessionId)
+        expect(meta).toBeDefined()
+        expect(meta.metadata.model).toEqual(MODEL)
+      })
+
+      test("#then unstable-agent-task metadata includes model", async () => {
+        const { executeUnstableAgentTask } = require("./unstable-agent-task")
+        const ctx = makeMockCtx()
+        const args: DelegateTaskArgs = {
+          description: "test", prompt: "do it",
+          category: "quick", load_skills: [], run_in_background: false,
+        }
+
+        const launchedTask = {
+          id: "bg_unstable", description: "test", agent: "explore",
+          status: "completed", sessionID: "ses_unstable", model: MODEL,
+        }
+        const result = await executeUnstableAgentTask(
+          args, ctx,
+          {
+            manager: {
+              launch: async () => launchedTask,
+              getTask: () => launchedTask,
+            },
+            client: {
+              session: {
+                status: async () => ({ data: { ses_unstable: { type: "idle" } } }),
+                messages: async () => ({
+                  data: [{
+                    info: { role: "assistant", time: { created: 1 } },
+                    parts: [{ type: "text", text: "done" }],
+                  }],
+                }),
+              },
+            },
+            syncPollTimeoutMs: 100,
+          } as any,
+          parentContext, "explore", MODEL, undefined, "anthropic/claude-sonnet-4-6",
+        )
+
+        const meta = ctx.captured.find((m: any) => m.metadata?.sessionId)
+        expect(meta).toBeDefined()
+        expect(meta.metadata.model).toEqual(MODEL)
+      })
+
+      test("#then background-continuation metadata includes model from task", async () => {
+        const { executeBackgroundContinuation } = require("./background-continuation")
+        const ctx = makeMockCtx()
+        const args: DelegateTaskArgs = {
+          description: "continue", prompt: "keep going",
+          load_skills: [], run_in_background: true, session_id: "ses_resumed",
+        }
+
+        await executeBackgroundContinuation(args, ctx, {
+          manager: {
+            resume: async () => ({
+              id: "bg_2", description: "continue", agent: "explore",
+              status: "running", sessionID: "ses_resumed", model: MODEL,
+            }),
+          },
+        } as any, parentContext)
+
+        const meta = ctx.captured.find((m: any) => m.metadata?.sessionId)
+        expect(meta).toBeDefined()
+        expect(meta.metadata.model).toEqual(MODEL)
+      })
+
+      test("#then sync-continuation metadata includes model from resumed session", async () => {
+        const { executeSyncContinuation } = require("./sync-continuation")
+        const ctx = makeMockCtx()
+        const args: DelegateTaskArgs = {
+          description: "continue", prompt: "keep going",
+          load_skills: [], run_in_background: false, session_id: "ses_cont",
+        }
+
+        const deps = {
+          pollSyncSession: async () => null,
+          fetchSyncResult: async () => ({ ok: true as const, textContent: "done" }),
+        }
+
+        await executeSyncContinuation(args, ctx, {
+          client: {
+            session: {
+              messages: async () => ({
+                data: [{ info: { agent: "explore", model: MODEL, providerID: "anthropic", modelID: "claude-sonnet-4-6" } }],
+              }),
+              prompt: async () => ({}),
+            },
+          },
+        } as any, deps)
+
+        const meta = ctx.captured.find((m: any) => m.metadata?.sessionId)
+        expect(meta).toBeDefined()
+        expect(meta.metadata.model).toEqual(MODEL)
+      })
+    })
+  })
+})

src/tools/delegate-task/sync-continuation.ts

@@ -32,22 +32,7 @@ export async function executeSyncContinuation(
     })
   }
 
-  const syncContMeta = {
-    title: `Continue: ${args.description}`,
-    metadata: {
-      prompt: args.prompt,
-      load_skills: args.load_skills,
-      description: args.description,
-      run_in_background: args.run_in_background,
-      sessionId: args.session_id,
-      sync: true,
-      command: args.command,
-    },
-  }
-  await ctx.metadata?.(syncContMeta)
-  if (ctx.callID) {
-    storeToolMetadata(ctx.sessionID, ctx.callID, syncContMeta)
-  }
+  let syncContMeta: { title: string; metadata: Record<string, unknown> } | undefined
 
   let resumeAgent: string | undefined
   let resumeModel: { providerID: string; modelID: string } | undefined
@@ -78,6 +63,24 @@ export async function executeSyncContinuation(
       resumeVariant = resumeMessage?.model?.variant
     }
 
+    syncContMeta = {
+      title: `Continue: ${args.description}`,
+      metadata: {
+        prompt: args.prompt,
+        load_skills: args.load_skills,
+        description: args.description,
+        run_in_background: args.run_in_background,
+        sessionId: args.session_id,
+        sync: true,
+        command: args.command,
+        model: resumeModel,
+      },
+    }
+    await ctx.metadata?.(syncContMeta)
+    if (ctx.callID) {
+      storeToolMetadata(ctx.sessionID, ctx.callID, syncContMeta)
+    }
+
     const allowTask = isPlanFamily(resumeAgent)
     const tools = {
       ...(resumeAgent ? getAgentToolRestrictions(resumeAgent) : {}),

src/tools/delegate-task/sync-task.ts

@@ -91,6 +91,7 @@ export async function executeSyncTask(
         sessionId: sessionID,
         sync: true,
         command: args.command,
+        model: categoryModel ? { providerID: categoryModel.providerID, modelID: categoryModel.modelID } : undefined,
       },
     }
     await ctx.metadata?.(syncTaskMeta)

src/tools/delegate-task/unstable-agent-task.ts

@@ -66,6 +66,7 @@ export async function executeUnstableAgentTask(
         run_in_background: args.run_in_background,
         sessionId: sessionID,
         command: args.command,
+        model: categoryModel ? { providerID: categoryModel.providerID, modelID: categoryModel.modelID } : undefined,
       },
     }
     await ctx.metadata?.(bgTaskMeta)

src/tools/look-at/tools.test.ts

@@ -456,6 +456,96 @@ describe("look-at tool", () => {
     })
   })
 
+  describe("createLookAt unhandled error resilience", () => {
+    const createToolContext = (): ToolContext => ({
+      sessionID: "parent-session",
+      messageID: "parent-message",
+      agent: "sisyphus",
+      directory: "/project",
+      worktree: "/project",
+      abort: new AbortController().signal,
+      metadata: () => {},
+      ask: async () => {},
+    })
+
+    // given session.create throws (network error, not error response)
+    // when LookAt tool executed
+    // then returns error string instead of crashing
+    test("catches session.create throw and returns error string", async () => {
+      const mockClient = {
+        session: {
+          get: async () => ({ data: { directory: "/project" } }),
+          create: async () => { throw new Error("ECONNREFUSED: connection refused") },
+        },
+      }
+
+      const tool = createLookAt({
+        client: mockClient,
+        directory: "/project",
+      } as any)
+
+      const result = await tool.execute(
+        { file_path: "/test/file.png", goal: "analyze" },
+        createToolContext(),
+      )
+      expect(result).toContain("Error")
+      expect(result).toContain("ECONNREFUSED")
+    })
+
+    // given session.messages throws unexpectedly
+    // when LookAt tool executed
+    // then returns error string instead of crashing
+    test("catches session.messages throw and returns error string", async () => {
+      const mockClient = {
+        app: {
+          agents: async () => ({ data: [] }),
+        },
+        session: {
+          get: async () => ({ data: { directory: "/project" } }),
+          create: async () => ({ data: { id: "ses_msg_throw" } }),
+          prompt: async () => ({}),
+          messages: async () => { throw new Error("Unexpected server error") },
+        },
+      }
+
+      const tool = createLookAt({
+        client: mockClient,
+        directory: "/project",
+      } as any)
+
+      const result = await tool.execute(
+        { file_path: "/test/file.png", goal: "analyze" },
+        createToolContext(),
+      )
+      expect(result).toContain("Error")
+      expect(result).toContain("Unexpected server error")
+    })
+
+    // given a non-Error object is thrown
+    // when LookAt tool executed
+    // then still returns error string
+    test("handles non-Error thrown objects gracefully", async () => {
+      const mockClient = {
+        session: {
+          get: async () => ({ data: { directory: "/project" } }),
+          create: async () => { throw "string error thrown" },
+        },
+      }
+
+      const tool = createLookAt({
+        client: mockClient,
+        directory: "/project",
+      } as any)
+
+      const result = await tool.execute(
+        { file_path: "/test/file.png", goal: "analyze" },
+        createToolContext(),
+      )
+      expect(result).toContain("Error")
+      expect(result).toContain("string error thrown")
+    })
+  })
+
   describe("createLookAt with image_data", () => {
     // given base64 image data is provided
     // when LookAt tool executed

src/tools/look-at/tools.ts

@@ -217,6 +217,10 @@ Original error: ${createResult.error}`
 
         log(`[look_at] Got response, length: ${responseText.length}`)
         return responseText
+      } catch (error) {
+        const errorMessage = error instanceof Error ? error.message : String(error)
+        log(`[look_at] Unexpected error analyzing ${sourceDescription}:`, error)
+        return `Error: Failed to analyze ${sourceDescription}: ${errorMessage}`
       } finally {
         if (tempConversionPath) {
           cleanupConvertedImage(tempConversionPath)