test(core): simplify command layer wiring

Co-authored-by: Aiden Cline <aidenpcline@gmail.com>

bun.lock

@@ -29,7 +29,7 @@
     },
     "packages/app": {
       "name": "@opencode-ai/app",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@kobalte/core": "catalog:",
         "@opencode-ai/core": "workspace:*",
@@ -86,7 +86,7 @@
     },
     "packages/cli": {
       "name": "@opencode-ai/cli",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "bin": {
         "lildax": "./bin/lildax.cjs",
       },
@@ -111,7 +111,7 @@
     },
     "packages/console/app": {
       "name": "@opencode-ai/console-app",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@cloudflare/vite-plugin": "1.15.2",
         "@ibm/plex": "6.4.1",
@@ -147,7 +147,7 @@
     },
     "packages/console/core": {
       "name": "@opencode-ai/console-core",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@aws-sdk/client-sts": "3.782.0",
         "@jsx-email/render": "1.1.1",
@@ -174,7 +174,7 @@
     },
     "packages/console/function": {
       "name": "@opencode-ai/console-function",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@ai-sdk/anthropic": "3.0.82",
         "@ai-sdk/openai": "3.0.48",
@@ -196,7 +196,7 @@
     },
     "packages/console/mail": {
       "name": "@opencode-ai/console-mail",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@jsx-email/all": "2.2.3",
         "@jsx-email/cli": "1.4.3",
@@ -220,7 +220,7 @@
     },
     "packages/console/support": {
       "name": "@opencode-ai/console-support",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@cloudflare/vite-plugin": "1.15.2",
         "@opencode-ai/console-core": "workspace:*",
@@ -240,7 +240,7 @@
     },
     "packages/core": {
       "name": "@opencode-ai/core",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "bin": {
         "opencode": "./bin/opencode",
       },
@@ -331,7 +331,7 @@
     },
     "packages/desktop": {
       "name": "@opencode-ai/desktop",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@zip.js/zip.js": "2.7.62",
         "effect": "catalog:",
@@ -385,7 +385,7 @@
     },
     "packages/effect-drizzle-sqlite": {
       "name": "@opencode-ai/effect-drizzle-sqlite",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "drizzle-orm": "catalog:",
         "effect": "catalog:",
@@ -399,7 +399,7 @@
     },
     "packages/effect-sqlite-node": {
       "name": "@opencode-ai/effect-sqlite-node",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "effect": "catalog:",
       },
@@ -411,7 +411,7 @@
     },
     "packages/enterprise": {
       "name": "@opencode-ai/enterprise",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@hono/standard-validator": "catalog:",
         "@opencode-ai/core": "workspace:*",
@@ -442,7 +442,7 @@
     },
     "packages/function": {
       "name": "@opencode-ai/function",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@octokit/auth-app": "8.0.1",
         "@octokit/rest": "catalog:",
@@ -458,10 +458,10 @@
     },
     "packages/http-recorder": {
       "name": "@opencode-ai/http-recorder",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
-        "@effect/platform-node": "4.0.0-beta.74",
-        "@effect/platform-node-shared": "4.0.0-beta.74",
+        "@effect/platform-node": "4.0.0-beta.83",
+        "@effect/platform-node-shared": "4.0.0-beta.83",
       },
       "devDependencies": {
         "@tsconfig/node22": "catalog:",
@@ -472,12 +472,12 @@
         "typescript": "catalog:",
       },
       "peerDependencies": {
-        "effect": "4.0.0-beta.74",
+        "effect": "4.0.0-beta.83",
       },
     },
     "packages/llm": {
       "name": "@opencode-ai/llm",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@smithy/eventstream-codec": "4.2.14",
         "@smithy/util-utf8": "4.2.2",
@@ -495,7 +495,7 @@
     },
     "packages/opencode": {
       "name": "opencode",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "bin": {
         "opencode": "./bin/opencode",
       },
@@ -623,7 +623,7 @@
     },
     "packages/plugin": {
       "name": "@opencode-ai/plugin",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@opencode-ai/sdk": "workspace:*",
         "effect": "catalog:",
@@ -661,7 +661,7 @@
     },
     "packages/sdk/js": {
       "name": "@opencode-ai/sdk",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "cross-spawn": "catalog:",
       },
@@ -676,7 +676,7 @@
     },
     "packages/server": {
       "name": "@opencode-ai/server",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@opencode-ai/core": "workspace:*",
         "drizzle-orm": "catalog:",
@@ -690,7 +690,7 @@
     },
     "packages/slack": {
       "name": "@opencode-ai/slack",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@opencode-ai/sdk": "workspace:*",
         "@slack/bolt": "^3.17.1",
@@ -703,7 +703,7 @@
     },
     "packages/stats/app": {
       "name": "@opencode-ai/stats-app",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@ibm/plex": "6.4.1",
         "@opencode-ai/stats-core": "workspace:*",
@@ -736,7 +736,7 @@
     },
     "packages/stats/core": {
       "name": "@opencode-ai/stats-core",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@aws-sdk/client-athena": "3.933.0",
         "@planetscale/database": "1.19.0",
@@ -755,7 +755,7 @@
     },
     "packages/stats/server": {
       "name": "@opencode-ai/stats-server",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@aws-sdk/client-firehose": "3.933.0",
         "@effect/platform-node": "catalog:",
@@ -795,7 +795,7 @@
     },
     "packages/tui": {
       "name": "@opencode-ai/tui",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@opencode-ai/core": "workspace:*",
         "@opencode-ai/plugin": "workspace:*",
@@ -822,7 +822,7 @@
     },
     "packages/ui": {
       "name": "@opencode-ai/ui",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@kobalte/core": "catalog:",
         "@opencode-ai/core": "workspace:*",
@@ -871,7 +871,7 @@
     },
     "packages/web": {
       "name": "@opencode-ai/web",
-      "version": "1.17.8",
+      "version": "1.17.9",
       "dependencies": {
         "@astrojs/cloudflare": "12.6.3",
         "@astrojs/markdown-remark": "6.3.1",
@@ -935,9 +935,9 @@
   },
   "catalog": {
     "@cloudflare/workers-types": "4.20251008.0",
-    "@effect/opentelemetry": "4.0.0-beta.74",
-    "@effect/platform-node": "4.0.0-beta.74",
-    "@effect/sql-sqlite-bun": "4.0.0-beta.74",
+    "@effect/opentelemetry": "4.0.0-beta.83",
+    "@effect/platform-node": "4.0.0-beta.83",
+    "@effect/sql-sqlite-bun": "4.0.0-beta.83",
     "@hono/standard-validator": "0.2.0",
     "@hono/zod-validator": "0.4.2",
     "@kobalte/core": "0.13.11",
@@ -973,7 +973,7 @@
     "dompurify": "3.3.1",
     "drizzle-kit": "1.0.0-rc.2",
     "drizzle-orm": "1.0.0-rc.2",
-    "effect": "4.0.0-beta.74",
+    "effect": "4.0.0-beta.83",
     "fuzzysort": "3.1.0",
     "hono": "4.10.7",
     "hono-openapi": "1.1.2",
@@ -1328,13 +1328,13 @@
 
     "@drizzle-team/brocli": ["@drizzle-team/brocli@0.11.0", "", {}, "sha512-hD3pekGiPg0WPCCGAZmusBBJsDqGUR66Y452YgQsZOnkdQ7ViEPKuyP4huUGEZQefp8g34RRodXYmJ2TbCH+tg=="],
 
-    "@effect/opentelemetry": ["@effect/opentelemetry@4.0.0-beta.74", "", { "peerDependencies": { "@opentelemetry/api": "^1.9", "@opentelemetry/api-logs": ">=0.203.0 <0.300.0", "@opentelemetry/resources": "^2.0.0", "@opentelemetry/sdk-logs": ">=0.203.0 <0.300.0", "@opentelemetry/sdk-metrics": "^2.0.0", "@opentelemetry/sdk-trace-base": "^2.0.0", "@opentelemetry/sdk-trace-node": "^2.0.0", "@opentelemetry/sdk-trace-web": "^2.0.0", "@opentelemetry/semantic-conventions": "^1.33.0", "effect": "^4.0.0-beta.74" }, "optionalPeers": ["@opentelemetry/api", "@opentelemetry/api-logs", "@opentelemetry/resources", "@opentelemetry/sdk-logs", "@opentelemetry/sdk-metrics", "@opentelemetry/sdk-trace-base", "@opentelemetry/sdk-trace-node", "@opentelemetry/sdk-trace-web"] }, "sha512-flpyqLPyr+THSe6ZCGRZl6hi+FqxbIXNSkslKGiRJAjbPabam9mSp7R3aC8biIMt6xE4Fd0LNfo4p2GplUkm2Q=="],
+    "@effect/opentelemetry": ["@effect/opentelemetry@4.0.0-beta.83", "", { "peerDependencies": { "@opentelemetry/api": "^1.9", "@opentelemetry/api-logs": ">=0.203.0 <0.300.0", "@opentelemetry/resources": "^2.0.0", "@opentelemetry/sdk-logs": ">=0.203.0 <0.300.0", "@opentelemetry/sdk-metrics": "^2.0.0", "@opentelemetry/sdk-trace-base": "^2.0.0", "@opentelemetry/sdk-trace-node": "^2.0.0", "@opentelemetry/sdk-trace-web": "^2.0.0", "@opentelemetry/semantic-conventions": "^1.33.0", "effect": "^4.0.0-beta.83" }, "optionalPeers": ["@opentelemetry/api", "@opentelemetry/api-logs", "@opentelemetry/resources", "@opentelemetry/sdk-logs", "@opentelemetry/sdk-metrics", "@opentelemetry/sdk-trace-base", "@opentelemetry/sdk-trace-node", "@opentelemetry/sdk-trace-web"] }, "sha512-cPfCfp/ghu0itbX6Dqjdr4N0rbjng5ON4sUpnLHV5JJySG8zZpWmuOZLWIrfrNKT2ctYR1BYmp1aYCgkItaJLw=="],
 
-    "@effect/platform-node": ["@effect/platform-node@4.0.0-beta.74", "", { "dependencies": { "@effect/platform-node-shared": "^4.0.0-beta.74", "mime": "^4.1.0", "undici": "^8.2.0" }, "peerDependencies": { "effect": "^4.0.0-beta.74", "ioredis": "^5.7.0" } }, "sha512-/W16mKqxvhWINLjufzc0log1sl57exXQfwd+em398/zKCbmU3S7snXTDMN6w0ju2TtgK35qrsoGBXEochij6Sg=="],
+    "@effect/platform-node": ["@effect/platform-node@4.0.0-beta.83", "", { "dependencies": { "@effect/platform-node-shared": "^4.0.0-beta.83", "mime": "^4.1.0", "undici": "^8.2.0" }, "peerDependencies": { "effect": "^4.0.0-beta.83", "ioredis": "^5.7.0" } }, "sha512-RmpVGu/+X/Bif3/g1Rzj8oFzTOknoVB3yHCa0b179vytPpKe+Kj9ZwKNcAnKWqHUDkbSPBq1Ca60mvOHr2/+LQ=="],
 
-    "@effect/platform-node-shared": ["@effect/platform-node-shared@4.0.0-beta.74", "", { "dependencies": { "@types/ws": "^8.18.1", "ws": "^8.20.0" }, "peerDependencies": { "effect": "^4.0.0-beta.74" } }, "sha512-C6C2hXixNcZXLaFF2u7B/FtOsqpdY7luaPuiGFBJza0P7EnYDkwaT3kB6lv7l/qctmkADc24qOsSCWIKRbC4jg=="],
+    "@effect/platform-node-shared": ["@effect/platform-node-shared@4.0.0-beta.83", "", { "dependencies": { "@types/ws": "^8.18.1", "ws": "^8.20.0" }, "peerDependencies": { "effect": "^4.0.0-beta.83" } }, "sha512-+yr/+PJmKTgmJq1QOINSBPgLu7Cjc4CZcotBXnGjyDEizOmimFgTkN2B8PBJAKIKUWYWfobjXqC+58/VhhPKAw=="],
 
-    "@effect/sql-sqlite-bun": ["@effect/sql-sqlite-bun@4.0.0-beta.74", "", { "peerDependencies": { "effect": "^4.0.0-beta.74" } }, "sha512-RVMRVY7NhSoAp9cAAyy4TT6dt6NNZjOpWeqticoho9HNBukxQSUcu/kjcz4Iq9eoQfXadmepu8kZqtdZULM/fg=="],
+    "@effect/sql-sqlite-bun": ["@effect/sql-sqlite-bun@4.0.0-beta.83", "", { "peerDependencies": { "effect": "^4.0.0-beta.83" } }, "sha512-6OaxLsWffxkh9pXYUSyj/AxjVb9URY2rG9U6atjxClWy30Jx77R9Pm3Rrc7cQ63kQurePavEw1bQbzQ/SILiQQ=="],
 
     "@electron/asar": ["@electron/asar@3.4.1", "", { "dependencies": { "commander": "^5.0.0", "glob": "^7.1.6", "minimatch": "^3.0.4" }, "bin": { "asar": "bin/asar.js" } }, "sha512-i4/rNPRS84t0vSRa2HorerGRXWyF4vThfHesw0dmcWHp+cspK743UanA0suA5Q5y8kzY2y6YKrvbIUn69BCAiA=="],
 
@@ -3366,7 +3366,7 @@
 
     "ee-first": ["ee-first@1.1.1", "", {}, "sha512-WMwm9LhRUo+WUaRN+vRuETqG89IgZphVSNkdFgeb6sS/E4OrDIN7t48CAewSHXc6C8lefD8KKfr5vY61brQlow=="],
 
-    "effect": ["effect@4.0.0-beta.74", "", { "dependencies": { "@standard-schema/spec": "^1.1.0", "fast-check": "^4.8.0", "find-my-way-ts": "^0.1.6", "ini": "^7.0.0", "kubernetes-types": "^1.30.0", "msgpackr": "^2.0.1", "multipasta": "^0.2.7", "toml": "^4.1.1", "uuid": "^14.0.0", "yaml": "^2.9.0" } }, "sha512-Yx+Kh12U+i2FmjwEfKs+ePFmpMd43RPD1oGqc/VraSS9bYzvF0Ff3PojwEFEVEewp8xc92Uxu28gTspU4qyvHA=="],
+    "effect": ["effect@4.0.0-beta.83", "", { "dependencies": { "@standard-schema/spec": "^1.1.0", "fast-check": "^4.8.0", "find-my-way-ts": "^0.1.6", "ini": "^7.0.0", "kubernetes-types": "^1.30.0", "msgpackr": "^2.0.1", "multipasta": "^0.2.7", "toml": "^4.1.1", "uuid": "^14.0.0", "yaml": "^2.9.0" } }, "sha512-0wsak8RtgGAr9UWSbVDgJHZcUqMSvicHcvaZv1MbMM7MCGgW4Rn/137J1MHQbwYPcwYGxT/IqehFd+UbYuj78w=="],
 
     "ejs": ["ejs@3.1.10", "", { "dependencies": { "jake": "^10.8.5" }, "bin": { "ejs": "bin/cli.js" } }, "sha512-UeJmFfOrAQS8OJWPZ4qtgHyWExa088/MtK5UEyoJGFH67cDEXkZSviOiKRCZ4Xij0zxI3JECgYs3oKx+AizQBA=="],
 
@@ -5898,6 +5898,10 @@
 
     "@solidjs/start/vite": ["vite@7.1.10", "", { "dependencies": { "esbuild": "^0.25.0", "fdir": "^6.5.0", "picomatch": "^4.0.3", "postcss": "^8.5.6", "rollup": "^4.43.0", "tinyglobby": "^0.2.15" }, "optionalDependencies": { "fsevents": "~2.3.3" }, "peerDependencies": { "@types/node": "^20.19.0 || >=22.12.0", "jiti": ">=1.21.0", "less": "^4.0.0", "lightningcss": "^1.21.0", "sass": "^1.70.0", "sass-embedded": "^1.70.0", "stylus": ">=0.54.8", "sugarss": "^5.0.0", "terser": "^5.16.0", "tsx": "^4.8.1", "yaml": "^2.4.2" }, "optionalPeers": ["@types/node", "jiti", "less", "lightningcss", "sass", "sass-embedded", "stylus", "sugarss", "terser", "tsx", "yaml"], "bin": { "vite": "bin/vite.js" } }, "sha512-CmuvUBzVJ/e3HGxhg6cYk88NGgTnBoOo7ogtfJJ0fefUWAxN/WDSUa50o+oVBxuIhO8FoEZW0j2eW7sfjs5EtA=="],
 
+    "@standard-community/standard-json/effect": ["effect@4.0.0-beta.74", "", { "dependencies": { "@standard-schema/spec": "^1.1.0", "fast-check": "^4.8.0", "find-my-way-ts": "^0.1.6", "ini": "^7.0.0", "kubernetes-types": "^1.30.0", "msgpackr": "^2.0.1", "multipasta": "^0.2.7", "toml": "^4.1.1", "uuid": "^14.0.0", "yaml": "^2.9.0" } }, "sha512-Yx+Kh12U+i2FmjwEfKs+ePFmpMd43RPD1oGqc/VraSS9bYzvF0Ff3PojwEFEVEewp8xc92Uxu28gTspU4qyvHA=="],
+
+    "@standard-community/standard-openapi/effect": ["effect@4.0.0-beta.74", "", { "dependencies": { "@standard-schema/spec": "^1.1.0", "fast-check": "^4.8.0", "find-my-way-ts": "^0.1.6", "ini": "^7.0.0", "kubernetes-types": "^1.30.0", "msgpackr": "^2.0.1", "multipasta": "^0.2.7", "toml": "^4.1.1", "uuid": "^14.0.0", "yaml": "^2.9.0" } }, "sha512-Yx+Kh12U+i2FmjwEfKs+ePFmpMd43RPD1oGqc/VraSS9bYzvF0Ff3PojwEFEVEewp8xc92Uxu28gTspU4qyvHA=="],
+
     "@storybook/csf-plugin/unplugin": ["unplugin@2.3.11", "", { "dependencies": { "@jridgewell/remapping": "^2.3.5", "acorn": "^8.15.0", "picomatch": "^4.0.3", "webpack-virtual-modules": "^0.6.2" } }, "sha512-5uKD0nqiYVzlmCRs01Fhs2BdkEgBS3SAVP6ndrBsuK42iC2+JHyxM05Rm9G8+5mkmRtzMZGY8Ct5+mliZxU/Ww=="],
 
     "@tailwindcss/oxide/detect-libc": ["detect-libc@2.1.2", "", {}, "sha512-Btj2BOOO83o3WyH59e8MgXsxEQVcarkUOpEYrubB0urwnN10yQ364rsiByU11nZlqWYZm05i/of7io4mzihBtQ=="],
@@ -6700,6 +6704,10 @@
 
     "@solidjs/start/shiki/@shikijs/types": ["@shikijs/types@1.29.2", "", { "dependencies": { "@shikijs/vscode-textmate": "^10.0.1", "@types/hast": "^3.0.4" } }, "sha512-VJjK0eIijTZf0QSTODEXCqinjBn0joAHQ+aPSBzrv4O2d/QSbsMw+ZeSRx03kV34Hy7NzUvV/7NqfYGRLrASmw=="],
 
+    "@standard-community/standard-json/effect/@standard-schema/spec": ["@standard-schema/spec@1.1.0", "", {}, "sha512-l2aFy5jALhniG5HgqrD6jXLi/rUWrKvqN/qJx6yoJsgKhblVd+iqqU4RCXavm/jPityDo5TCvKMnpjKnOriy0w=="],
+
+    "@standard-community/standard-openapi/effect/@standard-schema/spec": ["@standard-schema/spec@1.1.0", "", {}, "sha512-l2aFy5jALhniG5HgqrD6jXLi/rUWrKvqN/qJx6yoJsgKhblVd+iqqU4RCXavm/jPityDo5TCvKMnpjKnOriy0w=="],
+
     "@storybook/csf-plugin/unplugin/webpack-virtual-modules": ["webpack-virtual-modules@0.6.2", "", {}, "sha512-66/V2i5hQanC51vBQKPH4aI8NMAcBW59FVBs+rC7eGHupMyfn34q7rZIE+ETlJ+XTevqfUhVVBgSUNSW2flEUQ=="],
 
     "@tailwindcss/oxide-wasm32-wasi/@napi-rs/wasm-runtime/@tybys/wasm-util": ["@tybys/wasm-util@0.10.2", "", { "dependencies": { "tslib": "^2.4.0" } }, "sha512-RoBvJ2X0wuKlWFIjrwffGw1IqZHKQqzIchKaadZZfnNpsAYp2mM0h36JtPCjNDAHGgYez/15uMBpfGwchhiMgg=="],

nix/hashes.json

@@ -1,8 +1,8 @@
 {
   "nodeModules": {
-    "x86_64-linux": "sha256-LOxTad/iCquvJyonFOcz6/rDTPNDmwyBnykhWZJ5GC4=",
-    "aarch64-linux": "sha256-iO+0vYhp+2x6ACmh5lQJ/2Ac4uZTqRZE/KhG3u0o6D8=",
-    "aarch64-darwin": "sha256-tpBydRbrJ+4QxmkGUt/BhME8q6ysCW/CXrsNshYgqDU=",
-    "x86_64-darwin": "sha256-QQcI6SK7WJ7dSkX6xZuSQPoUdwfoCaimVgoHCnrO0wY="
+    "x86_64-linux": "sha256-g0tDvRf7MErZ1PEeUazEYi492ZHiRT8kYv3bPdkss/I=",
+    "aarch64-linux": "sha256-6sKgf3ftbIqlPxlFkoPzoWPsJp3IwXD+H3Y6g874xmk=",
+    "aarch64-darwin": "sha256-Se/Nls/KlkuK2ysDQ9DeAzSaX3NsL2iDdf/dsv2GIXc=",
+    "x86_64-darwin": "sha256-V9MCkqnvQ1nkD2PaaTfNFKkBZGymj6KxrSAK6+DTF8Y="
   }
 }

package.json

@@ -30,9 +30,9 @@
       "packages/slack"
     ],
     "catalog": {
-      "@effect/opentelemetry": "4.0.0-beta.74",
-      "@effect/platform-node": "4.0.0-beta.74",
-      "@effect/sql-sqlite-bun": "4.0.0-beta.74",
+      "@effect/opentelemetry": "4.0.0-beta.83",
+      "@effect/platform-node": "4.0.0-beta.83",
+      "@effect/sql-sqlite-bun": "4.0.0-beta.83",
       "@npmcli/arborist": "9.4.0",
       "@types/bun": "1.3.13",
       "@types/cross-spawn": "6.0.6",
@@ -61,7 +61,7 @@
       "dompurify": "3.3.1",
       "drizzle-kit": "1.0.0-rc.2",
       "drizzle-orm": "1.0.0-rc.2",
-      "effect": "4.0.0-beta.74",
+      "effect": "4.0.0-beta.83",
       "ai": "6.0.168",
       "cross-spawn": "7.0.6",
       "hono": "4.10.7",

packages/app/AGENTS.md

@@ -1,3 +1,8 @@
+## Priorities
+
+- Prioritise, in this order: stability, simplicity, performance.
+- Before changing session or timeline code, record a production benchmark baseline and compare it after the change.
+
 ## Debugging
 
 - NEVER try to restart the app, or the server process, EVER.

packages/app/e2e/performance/AGENTS.md

@@ -0,0 +1,13 @@
+- Prioritize stability, then simplicity, then measurement overhead.
+- Use Playwright for scenario control, isolation, and completion checks.
+- Use Chrome Performance traces for generic browser profiling.
+- Use Electron `contentTracing` for packaged multi-process profiling.
+- Keep custom probes only for product-specific measurements.
+- Do not duplicate measurements across the harness, probes, and traces.
+- Run benchmarks serially to avoid cross-test contention.
+- Run benchmarks against production builds.
+- Keep detailed profiling opt-in when it changes workload behavior.
+- Preserve raw diagnostic data or use lossless representations.
+- Do not enforce machine-dependent performance thresholds.
+- Assert scenario completion and metric collection only.
+- Keep normal test discovery free of manual benchmarks.

packages/app/e2e/performance/README.md

@@ -0,0 +1,77 @@
+# Manual app performance suite
+
+The app's high-volume performance diagnostics live under `packages/app/e2e/performance` and are excluded from normal local and CI Playwright discovery. The benchmark config builds the app and serves the production bundle before running scenarios serially.
+
+Run the suite explicitly from `packages/app`:
+
+```sh
+bun run test:bench
+```
+
+PowerShell:
+
+```powershell
+$env:PLAYWRIGHT_WORKERS = "1"
+bun run test:bench
+```
+
+The suite contains:
+
+- cold and hot session-tab timing
+- cached session repaint and mutation tracing
+- streaming timeline throughput, RAF-gap, long-task, geometry, and remount diagnostics
+
+All benchmarks import the shared `benchmark` fixture. Pages created through Playwright's `page` fixture automatically capture main-frame navigation history and emit a Chrome trace when `OPENCODE_PERFORMANCE_TRACE_DIR` is set. Benchmarks that need isolated browser contexts use `withBenchmarkPage`, which owns the context and the same diagnostics lifecycle.
+
+New benchmarks should look like normal Playwright tests:
+
+```ts
+import { benchmark, expect } from "../benchmark"
+
+benchmark("measures one interaction", async ({ page, report }) => {
+  // Only scenario-specific setup and interaction belong here.
+  report({ durationMs: 42 })
+})
+```
+
+The fixture requires every benchmark to call `report()`, automatically names and closes traces, captures navigation history, attaches that history when a test fails, and emits metrics as a consistent `BENCHMARK` JSON line.
+
+```text
+BENCHMARK {"name":"...","context":{"project":"chromium","platform":"darwin"},"metrics":{...}}
+```
+
+Every observed page also emits `BENCHMARK_PAGE` with the same run ID, navigation history, and optional trace path before the final status-bearing `BENCHMARK` record. Chrome traces are browser-wide page-lifetime diagnostics; scenario metrics use narrower explicitly named observation windows.
+
+This follows the stack's own guidance: [Electron recommends repeated Chrome DevTools and Chrome Tracing measurement](https://www.electronjs.org/docs/latest/tutorial/performance), [Chrome DevTools recommends Performance recordings for runtime work](https://developer.chrome.com/docs/devtools/performance), and [Playwright uses traces for test debugging rather than renderer profiling](https://playwright.dev/docs/trace-viewer).
+
+These Playwright benchmarks profile the shared app renderer in Chromium. A future packaged Electron benchmark that needs main-process and multi-process attribution should use Electron's official [`contentTracing`](https://www.electronjs.org/docs/latest/api/content-tracing/) API rather than extending this renderer harness with bespoke process instrumentation.
+
+CPU and high-volume visual profiling are disabled by default. Set `TIMELINE_CPU_PROFILE=1` to enable both, or additionally set `TIMELINE_VISUAL_PROFILE=0` for CPU-only profiling.
+
+The streaming scenario's 30x CPU throttle is a deterministic stress profile, not a simulated end-user device.
+
+Benchmarks do not assert machine-dependent performance budgets. Streaming processes 160 deltas by default and reports renderer-observed completion time, throughput, RAF callback-gap distributions, frame-budget equivalents, and long tasks through final geometry settlement. Delta count and delivery batch are included in result context when overridden. These are main-thread callback diagnostics, not compositor presentation or dropped-frame measurements. Visual-only and geometry metrics are `null` when their probes are disabled. Tab metrics describe sampled DOM observations. Assertions verify scenario and metric collection completion. Repeated repaint states are run-length grouped, but every original observation timestamp is retained alongside raw mutation batches and layout shifts.
+
+Committed smoke and regression tests continue to own correctness coverage for pagination, tab paint, context resize, collapse state, and composer spacing.
+
+## Chrome traces
+
+Set `OPENCODE_PERFORMANCE_TRACE_DIR` to emit a standard Chrome DevTools trace for every benchmark page automatically:
+
+```sh
+OPENCODE_PERFORMANCE_TRACE_DIR=/tmp/opencode-performance-traces \
+bunx playwright test --config e2e/performance/playwright.config.ts \
+  timeline/session-tab-switch-benchmark.spec.ts
+```
+
+The emitted JSON is a standard Chrome trace and can be loaded directly into the Chrome DevTools Performance panel. `devtools-tracing` can optionally inspect it from the command line without adding package scripts or dependencies:
+
+Trace capture mirrors [Puppeteer's official tracing defaults and lifecycle](https://pptr.dev/api/puppeteer.tracing), using Chrome's `ReturnAsStream` transfer mode and failing when Chromium reports trace data loss.
+
+```sh
+bunx devtools-tracing stats <trace-path-from-BENCHMARK_PAGE>
+```
+
+INP analysis requires a trace with a supported navigation/interaction insight. Selector statistics require a trace captured with `OPENCODE_PERFORMANCE_SELECTOR_TRACE=1`.
+
+`e2e/performance/playwright.uncapped.config.ts` disables Chromium frame-rate limiting for explicit uncapped diagnostics. Native product benchmarks should use the default Playwright configuration.

packages/app/e2e/performance/benchmark.ts

@@ -0,0 +1,144 @@
+import { expect, test as base, type Browser, type Page, type TestInfo } from "@playwright/test"
+import { startChromeTrace } from "./chrome-trace"
+
+type BenchmarkFixtures = {
+  report: (metrics: Record<string, unknown>, context?: Record<string, unknown>) => void
+  reportState: { payload?: { metrics: Record<string, unknown>; context: Record<string, unknown> } }
+  benchmarkResult: void
+}
+
+export type PerformancePageDiagnostics = {
+  navigations: string[]
+  stop: () => Promise<string | undefined>
+}
+
+const pages = new WeakMap<Page, PerformancePageDiagnostics>()
+
+export const benchmark = base.extend<BenchmarkFixtures>({
+  reportState: async ({}, use) => use({}),
+  report: async ({ reportState }, use) => {
+    await use((metrics, context = {}) => {
+      if (reportState.payload) throw new Error("Benchmark reported metrics more than once")
+      reportState.payload = { metrics, context }
+    })
+  },
+  benchmarkResult: [
+    async ({ reportState }, use, testInfo) => {
+      await use()
+      const missing = !reportState.payload
+      console.log(
+        `BENCHMARK ${JSON.stringify({
+          schemaVersion: 2,
+          runID: process.env.OPENCODE_PERFORMANCE_RUN_ID,
+          name: benchmarkName(testInfo),
+          status: missing ? "failed" : testInfo.status,
+          expectedStatus: testInfo.expectedStatus,
+          retry: testInfo.retry,
+          repeatEachIndex: testInfo.repeatEachIndex,
+          context: {
+            project: testInfo.project.name,
+            platform: process.platform,
+            ...reportState.payload?.context,
+          },
+          metrics: reportState.payload?.metrics ?? null,
+          error: missing ? "Benchmark did not report metrics" : undefined,
+        })}`,
+      )
+      if (missing && testInfo.status === testInfo.expectedStatus)
+        throw new Error(`Benchmark did not report metrics: ${benchmarkName(testInfo)}`)
+    },
+    { auto: true },
+  ],
+  page: async ({ page }, use, testInfo) => {
+    const name = benchmarkName(testInfo)
+    const diagnostics = await observePerformancePage(page, name)
+    try {
+      await use(page)
+    } finally {
+      try {
+        await reportPerformancePage(name, diagnostics, testInfo)
+      } finally {
+        if (testInfo.status !== testInfo.expectedStatus) {
+          await testInfo.attach("performance-navigations", {
+            body: JSON.stringify(diagnostics.navigations, null, 2),
+            contentType: "application/json",
+          })
+        }
+      }
+    }
+  },
+})
+
+function benchmarkName(testInfo: TestInfo) {
+  return testInfo.titlePath.slice(1).join(" > ")
+}
+
+export { expect }
+
+async function observePerformancePage(page: Page, name: string) {
+  const navigations: string[] = []
+  const onNavigation = (frame: ReturnType<Page["mainFrame"]>) => {
+    if (frame === page.mainFrame()) navigations.push(frame.url())
+  }
+  page.on("framenavigated", onNavigation)
+  const stopTrace = await startChromeTrace(page, name).catch((error) => {
+    page.off("framenavigated", onNavigation)
+    throw error
+  })
+  let stopping: Promise<string | undefined> | undefined
+  const diagnostics: PerformancePageDiagnostics = {
+    navigations,
+    stop() {
+      page.off("framenavigated", onNavigation)
+      return (stopping ??= stopTrace?.() ?? Promise.resolve(undefined))
+    },
+  }
+  pages.set(page, diagnostics)
+  return diagnostics
+}
+
+export async function withBenchmarkPage<T>(
+  browser: Browser,
+  name: string,
+  run: (page: Page) => Promise<T>,
+  testInfo?: TestInfo,
+) {
+  const context = await browser.newContext()
+  try {
+    const page = await context.newPage()
+    const diagnostics = await observePerformancePage(page, name)
+    try {
+      return await run(page)
+    } finally {
+      await reportPerformancePage(name, diagnostics, testInfo)
+    }
+  } finally {
+    await context.close()
+  }
+}
+
+async function reportPerformancePage(name: string, diagnostics: PerformancePageDiagnostics, testInfo?: TestInfo) {
+  const trace = await diagnostics.stop()
+  console.log(
+    `BENCHMARK_PAGE ${JSON.stringify({
+      schemaVersion: 2,
+      runID: process.env.OPENCODE_PERFORMANCE_RUN_ID,
+      name,
+      test: testInfo ? benchmarkName(testInfo) : undefined,
+      retry: testInfo?.retry,
+      repeatEachIndex: testInfo?.repeatEachIndex,
+      context: {
+        platform: process.platform,
+        trace,
+        selectorTrace: process.env.OPENCODE_PERFORMANCE_SELECTOR_TRACE === "1",
+      },
+      navigations: diagnostics.navigations,
+    })}`,
+  )
+}
+
+export function benchmarkDiagnostics(page: Page) {
+  const diagnostics = pages.get(page)
+  if (!diagnostics) throw new Error("Performance diagnostics are not installed for this page")
+  return diagnostics
+}

packages/app/e2e/performance/chrome-trace.ts

@@ -0,0 +1,95 @@
+import type { CDPSession, Page } from "@playwright/test"
+import path from "node:path"
+import { mkdir, open, rename } from "node:fs/promises"
+import { Buffer } from "node:buffer"
+import { createHash, randomUUID } from "node:crypto"
+
+const categories = [
+  "-*",
+  "devtools.timeline",
+  "v8.execute",
+  "disabled-by-default-devtools.timeline",
+  "disabled-by-default-devtools.timeline.frame",
+  "toplevel",
+  "blink.console",
+  "blink.user_timing",
+  "latencyInfo",
+  "disabled-by-default-devtools.timeline.stack",
+  "disabled-by-default-v8.cpu_profiler",
+]
+
+export async function startChromeTrace(page: Page, name: string) {
+  const directory = process.env.OPENCODE_PERFORMANCE_TRACE_DIR
+  if (!directory) return
+
+  const selectors = process.env.OPENCODE_PERFORMANCE_SELECTOR_TRACE === "1"
+  const file = await prepareChromeTrace(directory, name, selectors)
+  const session = await page.context().newCDPSession(page)
+  try {
+    await session.send("Tracing.start", {
+      transferMode: "ReturnAsStream",
+      traceConfig: {
+        excludedCategories: categories
+          .filter((category) => category.startsWith("-"))
+          .map((category) => category.slice(1)),
+        includedCategories: [
+          ...categories.filter((category) => !category.startsWith("-")),
+          ...(selectors
+            ? ["disabled-by-default-blink.debug", "disabled-by-default-devtools.timeline.invalidationTracking"]
+            : []),
+        ],
+      },
+    })
+  } catch (error) {
+    await Promise.allSettled([session.detach()])
+    throw error
+  }
+  let stopping: Promise<string> | undefined
+
+  return () =>
+    (stopping ??= (async () => {
+      try {
+        const complete = new Promise<{ stream?: string; dataLossOccurred: boolean }>((resolve) =>
+          session.once("Tracing.tracingComplete", resolve),
+        )
+        await session.send("Tracing.end")
+        const result = await complete
+        if (!result.stream) throw new Error(`Chrome trace stream missing: ${file}`)
+        const partial = `${file}.partial`
+        await writeProtocolStream(session, result.stream, partial)
+        if (result.dataLossOccurred) throw new Error(`Chrome trace lost data; partial capture retained: ${partial}`)
+        await rename(partial, file)
+        return file
+      } finally {
+        await Promise.allSettled([session.detach()])
+      }
+    })())
+}
+
+export async function prepareChromeTrace(
+  directory: string,
+  name: string,
+  selectors: boolean,
+  nonce = randomUUID().slice(0, 8),
+) {
+  await mkdir(directory, { recursive: true })
+  const run = process.env.OPENCODE_PERFORMANCE_RUN_ID ?? "manual"
+  const hash = createHash("sha256").update(name).digest("hex").slice(0, 8)
+  return path.join(
+    directory,
+    `${run}-${name.replace(/[^a-zA-Z0-9_-]/g, "-")}-${hash}-${nonce}${selectors ? "-selectors" : ""}.json`,
+  )
+}
+
+async function writeProtocolStream(session: CDPSession, handle: string, file: string) {
+  const output = await open(file, "wx")
+  try {
+    while (true) {
+      const chunk = await session.send("IO.read", { handle })
+      await output.write(chunk.base64Encoded ? Buffer.from(chunk.data, "base64") : chunk.data)
+      if (chunk.eof) break
+    }
+  } finally {
+    await Promise.allSettled([output.close(), session.send("IO.close", { handle })])
+  }
+}

packages/app/e2e/performance/playwright.config.ts

@@ -0,0 +1,20 @@
+import config from "../../playwright.config"
+
+const port = Number(process.env.PLAYWRIGHT_PORT ?? 3000)
+process.env.PLAYWRIGHT_SERVER_PORT = String(port)
+process.env.OPENCODE_PERFORMANCE_RUN_ID ??= `${new Date().toISOString().replace(/[:.]/g, "-")}-${process.pid}`
+
+export default {
+  ...config,
+  testDir: ".",
+  testIgnore: "unit/**",
+  outputDir: "../test-results/performance",
+  fullyParallel: false,
+  workers: 1,
+  reporter: [["html", { outputFolder: "../playwright-report/performance", open: "never" }], ["line"]],
+  webServer: {
+    ...config.webServer,
+    command: `bun run build && bun run serve -- --host 0.0.0.0 --port ${port} --strictPort`,
+    reuseExistingServer: false,
+  },
+}

packages/app/e2e/performance/playwright.uncapped.config.ts

@@ -0,0 +1,13 @@
+import config from "./playwright.config"
+
+export default {
+  ...config,
+  outputDir: "../test-results/performance-uncapped",
+  reporter: [["html", { outputFolder: "../playwright-report/performance-uncapped", open: "never" }], ["line"]],
+  use: {
+    ...config.use,
+    launchOptions: {
+      args: ["--disable-frame-rate-limit", "--disable-gpu-vsync"],
+    },
+  },
+}

packages/app/e2e/performance/timeline/session-tab-flash.spec.ts

@@ -0,0 +1,49 @@
+import { benchmark, expect } from "../benchmark"
+import { expectSessionTitle } from "../../utils/waits"
+import { fixture } from "./session-timeline-stress.fixture"
+import {
+  collectCachedRepaintTrace,
+  compressCachedRepaintTrace,
+  installCachedRepaintProbe,
+  waitForCachedRepaintWindow,
+} from "./session-tab-repaint-probe"
+import { waitForStableTimeline } from "./session-tab-switch-probe"
+import {
+  installStressSessionTabs,
+  installTimelineSettings,
+  mockStressTimeline,
+  stressSessionHref,
+} from "./timeline-test-helpers"
+
+benchmark("samples cached session repaint after the click", async ({ page, report }) => {
+  benchmark.setTimeout(120_000)
+  await mockStressTimeline(page)
+  await installStressSessionTabs(page)
+  await installTimelineSettings(page)
+  await page.goto(stressSessionHref(fixture.targetID))
+  await expectSessionTitle(page, fixture.expected.targetTitle)
+  await waitForStableTimeline(page, fixture.expected.targetMessageIDs.at(-1)!)
+  await page
+    .locator(`[data-slot="titlebar-tabs"] a[href="${stressSessionHref(fixture.sourceID)}"]`)
+    .first()
+    .click()
+  await expectSessionTitle(page, fixture.expected.sourceTitle)
+  await waitForStableTimeline(page, fixture.expected.sourceMessageIDs.at(-1)!)
+
+  await installCachedRepaintProbe(page, {
+    targetHref: stressSessionHref(fixture.targetID),
+    destination: fixture.messages[fixture.targetID].map((message) => message.info.id),
+    source: fixture.messages[fixture.sourceID].map((message) => message.info.id),
+    last: fixture.expected.targetMessageIDs.at(-1)!,
+    windowMs: 1_000,
+  })
+
+  await page
+    .locator(`[data-slot="titlebar-tabs"] a[href="${stressSessionHref(fixture.targetID)}"]`)
+    .first()
+    .click()
+  await Promise.all([expectSessionTitle(page, fixture.expected.targetTitle), waitForCachedRepaintWindow(page, 1_000)])
+  const result = await collectCachedRepaintTrace(page)
+  report(compressCachedRepaintTrace(result))
+  expect(result.samples.length).toBeGreaterThan(0)
+})

packages/app/e2e/performance/timeline/session-tab-repaint-probe.ts

@@ -0,0 +1,251 @@
+import type { Page } from "@playwright/test"
+
+type CachedRepaintTrace = {
+  timeOriginEpochMs: number
+  startedAtPerformanceMs: number
+  samples: {
+    observedAtMs: number
+    root: number | undefined
+    scrollTop: number
+    scrollHeight: number
+    bottomErrorPx: number | undefined
+    last: boolean
+    rows: { key: string | undefined; node: number; top: number; bottom: number }[]
+    mounted: number
+    center: string | undefined
+    destination: string[]
+    source: string[]
+  }[]
+  mutations: { observedAtMs: number; changed: { type: string; node: number }[] }[]
+  shifts: { occurredAtMs: number; value: number }[]
+  windowMs: number
+  running: boolean
+  stop: () => void
+}
+
+export async function installCachedRepaintProbe(
+  page: Page,
+  input: { targetHref: string; destination: string[]; source: string[]; last: string; windowMs: number },
+) {
+  await page.evaluate(({ targetHref, destination, source, last, windowMs }) => {
+    const destinationIDs = new Set(destination)
+    const sourceIDs = new Set(source)
+    const nodeIDs = new WeakMap<Node, number>()
+    let nextNodeID = 1
+    const id = (node: Node) => {
+      const current = nodeIDs.get(node)
+      if (current) return current
+      nodeIDs.set(node, nextNodeID)
+      return nextNodeID++
+    }
+    const state: CachedRepaintTrace = {
+      timeOriginEpochMs: performance.timeOrigin,
+      startedAtPerformanceMs: 0,
+      samples: [],
+      mutations: [],
+      shifts: [],
+      windowMs,
+      running: false,
+      stop: () => {},
+    }
+    const recordShifts = (entries: PerformanceEntry[]) => {
+      if (!state.running) return
+      state.shifts.push(
+        ...entries
+          .map((entry) => {
+            if (
+              entry.startTime < state.startedAtPerformanceMs ||
+              entry.startTime > state.startedAtPerformanceMs + state.windowMs
+            )
+              return
+            return {
+              occurredAtMs: entry.startTime - state.startedAtPerformanceMs,
+              value: (entry as PerformanceEntry & { value: number }).value,
+            }
+          })
+          .filter((entry): entry is { occurredAtMs: number; value: number } => entry !== undefined),
+      )
+    }
+    const shiftObserver = new PerformanceObserver((entries) => recordShifts(entries.getEntries()))
+    shiftObserver.observe({ type: "layout-shift" })
+    const recordMutations = (entries: MutationRecord[]) => {
+      if (!state.running) return
+      const observedAtMs = performance.now() - state.startedAtPerformanceMs
+      if (observedAtMs > state.windowMs) return
+      const changed = entries.flatMap((entry) => [
+        ...[...entry.addedNodes].map((node) => ({ type: "add", node: id(node) })),
+        ...[...entry.removedNodes].map((node) => ({ type: "remove", node: id(node) })),
+      ])
+      if (changed.length) state.mutations.push({ observedAtMs, changed })
+    }
+    const mutationObserver = new MutationObserver(recordMutations)
+    mutationObserver.observe(document.documentElement, { childList: true, subtree: true })
+    state.stop = () => {
+      recordShifts(shiftObserver.takeRecords())
+      recordMutations(mutationObserver.takeRecords())
+      state.running = false
+      shiftObserver.disconnect()
+      mutationObserver.disconnect()
+    }
+    const sample = () => {
+      if (!state.running) return
+      setTimeout(() => {
+        if (!state.running) return
+        const observedAtMs = performance.now() - state.startedAtPerformanceMs
+        if (observedAtMs > state.windowMs) return
+        const root = [...document.querySelectorAll<HTMLElement>(".scroll-view__viewport")].find((element) =>
+          element.querySelector("[data-timeline-row]"),
+        )
+        if (root) {
+          const view = root.getBoundingClientRect()
+          const rows = [...root.querySelectorAll<HTMLElement>("[data-timeline-key]")]
+            .map((element) => ({
+              key: element.dataset.timelineKey,
+              node: id(element),
+              rect: element.getBoundingClientRect(),
+            }))
+            .filter((item) => item.rect.bottom > view.top && item.rect.top < view.bottom)
+            .map((item) => ({
+              key: item.key,
+              node: item.node,
+              top: item.rect.top - view.top,
+              bottom: item.rect.bottom - view.top,
+            }))
+          const messages = [...root.querySelectorAll<HTMLElement>("[data-message-id]")]
+            .filter((element) => {
+              const rect = element.getBoundingClientRect()
+              return rect.bottom > view.top && rect.top < view.bottom
+            })
+            .map((element) => element.dataset.messageId!)
+          const spacer = root.querySelector<HTMLElement>('[data-timeline-row="bottom-spacer"]')?.getBoundingClientRect()
+          state.samples.push({
+            observedAtMs,
+            root: id(root),
+            scrollTop: root.scrollTop,
+            scrollHeight: root.scrollHeight,
+            bottomErrorPx: spacer ? spacer.bottom - view.bottom : undefined,
+            last: messages.includes(last),
+            rows,
+            mounted: root.querySelectorAll("[data-timeline-key]").length,
+            center: document
+              .elementFromPoint(view.left + view.width / 2, view.top + view.height / 2)
+              ?.textContent?.slice(0, 80),
+            destination: messages.filter((messageID) => destinationIDs.has(messageID)),
+            source: messages.filter((messageID) => sourceIDs.has(messageID)),
+          })
+        } else {
+          state.samples.push({
+            observedAtMs,
+            root: undefined,
+            scrollTop: 0,
+            scrollHeight: 0,
+            bottomErrorPx: undefined,
+            last: false,
+            rows: [],
+            mounted: 0,
+            center: document.elementFromPoint(innerWidth / 2, innerHeight / 2)?.textContent?.slice(0, 80),
+            destination: [],
+            source: [],
+          })
+        }
+        requestAnimationFrame(sample)
+      }, 0)
+    }
+    document.addEventListener(
+      "click",
+      (event) => {
+        const link = event.target instanceof Element ? event.target.closest("a") : undefined
+        if (link?.getAttribute("href") !== targetHref) return
+        state.startedAtPerformanceMs = performance.now()
+        state.running = true
+        requestAnimationFrame(sample)
+      },
+      { capture: true, once: true },
+    )
+    ;(window as Window & { __cachedFlash?: CachedRepaintTrace }).__cachedFlash = state
+  }, input)
+}
+
+export function layoutShiftSample(entry: Pick<PerformanceEntry, "startTime"> & { value: number }, started: number) {
+  if (entry.startTime < started) return
+  return { occurredAtMs: entry.startTime - started, value: entry.value }
+}
+
+export async function waitForCachedRepaintWindow(page: Page, durationMs: number) {
+  await page.waitForFunction((durationMs) => {
+    const state = (window as Window & { __cachedFlash?: CachedRepaintTrace }).__cachedFlash
+    return !!state?.running && performance.now() - state.startedAtPerformanceMs >= durationMs
+  }, durationMs)
+}
+
+export async function collectCachedRepaintTrace(page: Page) {
+  return page.evaluate(() => {
+    const state = (window as Window & { __cachedFlash?: CachedRepaintTrace }).__cachedFlash!
+    state.stop()
+    return state
+  })
+}
+
+export function summarizeCachedRepaintTrace(trace: CachedRepaintTrace) {
+  const roots = trace.samples.map((sample) => sample.root)
+  const bottomErrors = trace.samples.flatMap((sample) =>
+    sample.bottomErrorPx === undefined ? [] : [Math.abs(sample.bottomErrorPx)],
+  )
+  const category = (sample: CachedRepaintTrace["samples"][number]) => {
+    if (sample.source.length) return "source"
+    if (sample.root === undefined || sample.rows.length === 0) return "blank"
+    if (!sample.destination.length) return "unknown"
+    if (sample.last && Math.abs(sample.bottomErrorPx ?? Infinity) <= 1) return "correct"
+    return "wrongDestination"
+  }
+  return {
+    samples: trace.samples.length,
+    durationMs: trace.samples.at(-1)?.observedAtMs ?? 0,
+    firstSampleObservedMs: trace.samples[0]?.observedAtMs,
+    firstSampleCorrect: trace.samples[0] ? category(trace.samples[0]) === "correct" : false,
+    blankSamples: trace.samples.filter((sample) => category(sample) === "blank").length,
+    sourceSamples: trace.samples.filter((sample) => category(sample) === "source").length,
+    wrongDestinationSamples: trace.samples.filter((sample) => category(sample) === "wrongDestination").length,
+    unknownSamples: trace.samples.filter((sample) => category(sample) === "unknown").length,
+    rootChanges: roots.slice(1).filter((root, index) => root !== roots[index]).length,
+    mountedMin: trace.samples.length ? Math.min(...trace.samples.map((sample) => sample.mounted)) : 0,
+    mountedMax: Math.max(...trace.samples.map((sample) => sample.mounted)),
+    maxBottomErrorPx: Math.max(0, ...bottomErrors),
+    mutationBatches: trace.mutations.length,
+    addedNodes: trace.mutations.reduce(
+      (sum, batch) => sum + batch.changed.filter((change) => change.type === "add").length,
+      0,
+    ),
+    removedNodes: trace.mutations.reduce(
+      (sum, batch) => sum + batch.changed.filter((change) => change.type === "remove").length,
+      0,
+    ),
+    layoutShiftValueSum: trace.shifts.reduce((sum, shift) => sum + shift.value, 0),
+    maxLayoutShiftValue: Math.max(0, ...trace.shifts.map((shift) => shift.value)),
+  }
+}
+
+export function compressCachedRepaintTrace(trace: CachedRepaintTrace) {
+  const samples: {
+    observedAtMs: number[]
+    state: Omit<CachedRepaintTrace["samples"][number], "observedAtMs">
+  }[] = []
+  for (const sample of trace.samples) {
+    const { observedAtMs, ...state } = sample
+    const previous = samples.at(-1)
+    if (previous && JSON.stringify(previous.state) === JSON.stringify(state)) {
+      previous.observedAtMs.push(observedAtMs)
+      continue
+    }
+    samples.push({ observedAtMs: [observedAtMs], state })
+  }
+  return {
+    timeOriginEpochMs: trace.timeOriginEpochMs,
+    startedAtPerformanceMs: trace.startedAtPerformanceMs,
+    windowMs: trace.windowMs,
+    summary: summarizeCachedRepaintTrace(trace),
+    samples,
+    mutations: trace.mutations,
+    shifts: trace.shifts,
+  }
+}

packages/app/e2e/performance/timeline/session-tab-switch-benchmark.spec.ts

@@ -0,0 +1,79 @@
+import type { Page } from "@playwright/test"
+import { expectSessionTitle } from "../../utils/waits"
+import { benchmark, expect, withBenchmarkPage } from "../benchmark"
+import { fixture } from "./session-timeline-stress.fixture"
+import { installStressSessionTabs, mockStressTimeline, stressSessionHref } from "./timeline-test-helpers"
+import { measureSessionSwitch, waitForStableTimeline } from "./session-tab-switch-probe"
+
+type Result = Awaited<ReturnType<typeof measureSessionSwitch>>
+
+benchmark("benchmarks cold and hot session tab switching", async ({ browser, report }, testInfo) => {
+  benchmark.setTimeout(180_000)
+  const results = { cold: [] as Result[], hot: [] as Result[] }
+  for (const mode of ["cold", "hot"] as const) {
+    for (let run = 0; run < 5; run++) {
+      results[mode].push(
+        await withBenchmarkPage(browser, `session-tab-switch-${mode}-${run}`, (page) => trial(page, mode), testInfo),
+      )
+    }
+  }
+  report({ results, summary: summarize(results) })
+})
+
+async function trial(page: Page, mode: "cold" | "hot") {
+  await mockStressTimeline(page)
+  await installStressSessionTabs(page)
+  if (mode === "hot") {
+    await page.goto(stressSessionHref(fixture.targetID))
+    await expectSessionTitle(page, fixture.expected.targetTitle)
+    await waitForStableTimeline(page, fixture.expected.targetMessageIDs.at(-1)!)
+    await switchSession(page, fixture.sourceID, fixture.expected.sourceTitle)
+  } else {
+    await page.goto(stressSessionHref(fixture.sourceID))
+    await expectSessionTitle(page, fixture.expected.sourceTitle)
+  }
+  await waitForStableTimeline(page, fixture.expected.sourceMessageIDs.at(-1)!)
+
+  const destinationIDs = fixture.messages[fixture.targetID].map((message) => message.info.id)
+  const sourceIDs = fixture.messages[fixture.sourceID].map((message) => message.info.id)
+  const lastID = fixture.expected.targetMessageIDs.at(-1)!
+  const href = stressSessionHref(fixture.targetID)
+  const result = await measureSessionSwitch(page, {
+    destinationIDs,
+    sourceIDs,
+    lastID,
+    href,
+    switch: () => switchSession(page, fixture.targetID, fixture.expected.targetTitle),
+  })
+  return result
+}
+
+function summarize(results: Record<"cold" | "hot", Result[]>) {
+  const stats = (values: (number | null)[]) => {
+    const sorted = values.filter((value): value is number => value !== null).sort((a, b) => a - b)
+    return {
+      min: sorted[0] ?? null,
+      median: sorted[Math.floor(sorted.length / 2)] ?? null,
+      max: sorted.at(-1) ?? null,
+      missing: values.length - sorted.length,
+    }
+  }
+  return Object.fromEntries(
+    Object.entries(results).map(([mode, values]) => [
+      mode,
+      {
+        firstDestinationObservedMs: stats(values.map((value) => value.firstDestinationObservedMs)),
+        firstCorrectObservedMs: stats(values.map((value) => value.firstCorrectObservedMs)),
+        stableObservedMs: stats(values.map((value) => value.stableObservedMs)),
+      },
+    ]),
+  )
+}
+
+async function switchSession(page: Page, sessionID: string, title: string) {
+  const href = stressSessionHref(sessionID)
+  const tab = page.locator(`[data-slot="titlebar-tabs"] a[href="${href}"]`).first()
+  await expect(tab).toBeVisible()
+  await tab.click()
+  await expectSessionTitle(page, title)
+}

packages/app/e2e/performance/timeline/session-tab-switch-metrics.ts

@@ -0,0 +1,46 @@
+export type SessionSwitchSample = {
+  observedAtMs: number
+  destination: string[]
+  source: string[]
+  hasVisibleRows: boolean
+  last: boolean
+  bottomErrorPx?: number
+}
+
+export function classifySessionSwitch(samples: SessionSwitchSample[]) {
+  const firstDestination = samples.findIndex((sample) => sample.destination.length > 0)
+  const firstCorrect = samples.findIndex(isCorrectDestination)
+  const stable = samples.findIndex((_, index) => isStableSessionSwitch(samples.slice(index, index + 3)))
+  return {
+    firstDestinationObservedMs: samples[firstDestination]?.observedAtMs ?? null,
+    firstCorrectObservedMs: samples[firstCorrect]?.observedAtMs ?? null,
+    stableObservedMs: samples[stable + 2]?.observedAtMs ?? null,
+    wrongDestinationSamples: samples
+      .slice(firstDestination)
+      .filter((sample) => sample.destination.length > 0 && !sample.last).length,
+    blankSamples: samples.filter((sample) => !sample.hasVisibleRows).length,
+    unknownSamples: samples.filter(
+      (sample) => sample.hasVisibleRows && sample.destination.length === 0 && sample.source.length === 0,
+    ).length,
+    sourceSamples: samples.filter((sample) => sample.source.length > 0).length,
+  }
+}
+
+export function isCorrectDestination(sample: SessionSwitchSample) {
+  return (
+    sample.destination.length > 0 &&
+    sample.source.length === 0 &&
+    sample.last &&
+    Math.abs(sample.bottomErrorPx ?? Infinity) <= 1
+  )
+}
+
+export function isStableSessionSwitch(samples: SessionSwitchSample[]) {
+  return samples.length === 3 && samples.every(isCorrectDestination)
+}
+
+export function isStableDestination(samples: Pick<SessionSwitchSample, "last" | "bottomErrorPx">[]) {
+  return (
+    samples.length === 3 && samples.every((sample) => sample.last && Math.abs(sample.bottomErrorPx ?? Infinity) <= 1)
+  )
+}

packages/app/e2e/performance/timeline/session-tab-switch-probe.ts

@@ -0,0 +1,152 @@
+import { expect, type Page } from "@playwright/test"
+import { classifySessionSwitch, isStableDestination, type SessionSwitchSample } from "./session-tab-switch-metrics"
+
+type SessionSwitchProbe = {
+  samples: SessionSwitchSample[]
+  stop: () => void
+}
+
+async function installSessionSwitchProbe(
+  page: Page,
+  input: { destinationIDs: string[]; sourceIDs: string[]; lastID: string; href: string },
+) {
+  await page.evaluate(({ destinationIDs, sourceIDs, lastID, href }) => {
+    const destination = new Set(destinationIDs)
+    const source = new Set(sourceIDs)
+    const samples: SessionSwitchSample[] = []
+    let started: number | undefined
+    let running = true
+    const sample = () => {
+      if (!running || started === undefined) return
+      setTimeout(() => {
+        if (!running || started === undefined) return
+        const observedAtMs = performance.now() - started
+        const root = [...document.querySelectorAll<HTMLElement>(".scroll-view__viewport")].find((element) =>
+          element.querySelector("[data-timeline-row]"),
+        )
+        if (root) {
+          const view = root.getBoundingClientRect()
+          const visible = [...root.querySelectorAll<HTMLElement>("[data-message-id]")]
+            .filter((element) => {
+              const rect = element.getBoundingClientRect()
+              return rect.bottom > view.top && rect.top < view.bottom
+            })
+            .map((element) => element.dataset.messageId!)
+          const hasVisibleRows = [...root.querySelectorAll<HTMLElement>("[data-timeline-key]")].some((element) => {
+            const rect = element.getBoundingClientRect()
+            return rect.bottom > view.top && rect.top < view.bottom
+          })
+          const spacer = root.querySelector<HTMLElement>('[data-timeline-row="bottom-spacer"]')?.getBoundingClientRect()
+          samples.push({
+            observedAtMs,
+            destination: visible.filter((id) => destination.has(id)),
+            source: visible.filter((id) => source.has(id)),
+            hasVisibleRows,
+            last: visible.includes(lastID),
+            bottomErrorPx: spacer ? spacer.bottom - view.bottom : undefined,
+          })
+        } else {
+          samples.push({ observedAtMs, destination: [], source: [], hasVisibleRows: false, last: false })
+        }
+        requestAnimationFrame(sample)
+      }, 0)
+    }
+    document.addEventListener(
+      "click",
+      (event) => {
+        const link = event.target instanceof Element ? event.target.closest("a") : undefined
+        if (link?.getAttribute("href") !== href) return
+        started = performance.now()
+        requestAnimationFrame(sample)
+      },
+      { capture: true, once: true },
+    )
+    ;(window as Window & { __sessionSwitchProbe?: SessionSwitchProbe }).__sessionSwitchProbe = {
+      samples,
+      stop: () => {
+        running = false
+      },
+    }
+  }, input)
+}
+
+async function waitForStableSessionSwitch(page: Page) {
+  await page.waitForFunction(() => {
+    const samples = (window as Window & { __sessionSwitchProbe?: SessionSwitchProbe }).__sessionSwitchProbe?.samples
+    if (!samples) return false
+    return samples.some((_, index) => {
+      const stable = samples.slice(index, index + 3)
+      return (
+        stable.length === 3 &&
+        stable.every(
+          (sample) =>
+            sample.destination.length > 0 &&
+            sample.source.length === 0 &&
+            sample.last &&
+            Math.abs(sample.bottomErrorPx ?? Infinity) <= 1,
+        )
+      )
+    })
+  })
+}
+
+async function collectSessionSwitchResult(page: Page) {
+  const samples = await page.evaluate(() => {
+    const probe = (window as Window & { __sessionSwitchProbe?: SessionSwitchProbe }).__sessionSwitchProbe!
+    probe.stop()
+    return probe.samples
+  })
+  return classifySessionSwitch(samples)
+}
+
+export async function measureSessionSwitch(
+  page: Page,
+  input: { destinationIDs: string[]; sourceIDs: string[]; lastID: string; href: string; switch: () => Promise<void> },
+) {
+  const { switch: run, ...probe } = input
+  await installSessionSwitchProbe(page, probe)
+  await run()
+  await waitForStableSessionSwitch(page)
+  return collectSessionSwitchResult(page)
+}
+
+export async function waitForStableTimeline(page: Page, lastID: string) {
+  const samples: Pick<SessionSwitchSample, "last" | "bottomErrorPx">[] = []
+  await expect
+    .poll(
+      async () => {
+        samples.push(
+          await page.evaluate(
+            (lastID) =>
+              new Promise<Pick<SessionSwitchSample, "last" | "bottomErrorPx">>((resolve) => {
+                requestAnimationFrame(() =>
+                  setTimeout(() => {
+                    const root = [...document.querySelectorAll<HTMLElement>(".scroll-view__viewport")].find((element) =>
+                      element.querySelector("[data-timeline-row]"),
+                    )
+                    if (!root) {
+                      resolve({ last: false })
+                      return
+                    }
+                    const view = root.getBoundingClientRect()
+                    const last = [...root.querySelectorAll<HTMLElement>("[data-message-id]")].some((element) => {
+                      if (element.dataset.messageId !== lastID) return false
+                      const rect = element.getBoundingClientRect()
+                      return rect.bottom > view.top && rect.top < view.bottom
+                    })
+                    const spacer = root
+                      .querySelector<HTMLElement>('[data-timeline-row="bottom-spacer"]')
+                      ?.getBoundingClientRect()
+                    resolve({ last, bottomErrorPx: spacer ? spacer.bottom - view.bottom : undefined })
+                  }, 0),
+                )
+              }),
+            lastID,
+          ),
+        )
+        return isStableDestination(samples.slice(-3))
+      },
+      { timeout: 30_000, intervals: [0] },
+    )
+    .toBe(true)
+}

packages/app/e2e/performance/timeline/session-timeline-benchmark.fixture.ts

@@ -0,0 +1,488 @@
+import { base64Encode } from "@opencode-ai/core/util/encode"
+import type { Page } from "@playwright/test"
+import { mockOpenCodeServer } from "../../utils/mock-server"
+import { expectAppVisible, expectSessionTitle } from "../../utils/waits"
+import { expect } from "../benchmark"
+
+const directory = "C:/OpenCode/TimelineStateRegression"
+const projectID = "proj_timeline_state_regression"
+const sessionID = "ses_timeline_state_regression"
+const userMessageID = "msg_user_regression"
+const assistantMessageID = "msg_assistant_regression"
+const editPartID = "prt_0001_edit"
+export const textPartID = "prt_9999_text"
+const title = "Timeline collapse state regression"
+const model = { providerID: "opencode", modelID: "claude-opus-4-6", variant: "max" }
+
+type EventPayload = {
+  directory: string
+  payload: Record<string, unknown>
+}
+
+const userMessage = {
+  info: {
+    id: userMessageID,
+    sessionID,
+    role: "user",
+    time: { created: 1700000000000 },
+    summary: { diffs: [] },
+    agent: "build",
+    model,
+  },
+  parts: [
+    {
+      id: "prt_user_text",
+      sessionID,
+      messageID: userMessageID,
+      type: "text",
+      text: "Please edit the file.",
+    },
+  ],
+}
+
+const editPart = {
+  id: editPartID,
+  sessionID,
+  messageID: assistantMessageID,
+  type: "tool",
+  callID: "call_edit_regression",
+  tool: "edit",
+  state: {
+    status: "completed",
+    input: { filePath: "src/regression.ts" },
+    output: "Edited src/regression.ts",
+    title: "src/regression.ts",
+    metadata: {
+      filediff: {
+        file: "src/regression.ts",
+        additions: 1,
+        deletions: 1,
+        before: "export const value = 'before'\n",
+        after: "export const value = 'after'\n",
+      },
+      diff: "diff --git a/src/regression.ts b/src/regression.ts\n-export const value = 'before'\n+export const value = 'after'\n",
+    },
+    time: { start: 1700000001000, end: 1700000002000 },
+  },
+}
+
+const streamedTextPart = {
+  id: textPartID,
+  sessionID,
+  messageID: assistantMessageID,
+  type: "text",
+  text: "Streaming added a later assistant text part.",
+}
+
+const assistantMessage = {
+  info: {
+    id: assistantMessageID,
+    sessionID,
+    role: "assistant",
+    time: { created: 1700000001000 },
+    parentID: userMessageID,
+    modelID: model.modelID,
+    providerID: model.providerID,
+    mode: "build",
+    agent: "build",
+    path: { cwd: directory, root: directory },
+    cost: 0.01,
+    tokens: { input: 100, output: 200, reasoning: 0, cache: { read: 0, write: 0 } },
+    variant: "max",
+  },
+  parts: [editPart],
+}
+
+export async function setupTimelineBenchmark(page: Page, options: { historyTurns: number; eventBatch: number }) {
+  const events: EventPayload[] = []
+  let eventBatch = options.eventBatch
+  await mockOpenCodeServer(page, {
+    directory,
+    project: project(),
+    provider: provider(),
+    sessions: [session()],
+    pageMessages: () => ({
+      items: [
+        ...Array.from({ length: options.historyTurns }, (_, index) => performanceTurn(index)).flat(),
+        userMessage,
+        assistantMessage,
+      ],
+    }),
+    events: () => events.splice(0, eventBatch),
+    eventRetry: 16,
+  })
+  await page.addInitScript(() => {
+    localStorage.setItem(
+      "settings.v3",
+      JSON.stringify({
+        general: {
+          editToolPartsExpanded: true,
+          shellToolPartsExpanded: true,
+          showReasoningSummaries: true,
+          showSessionProgressBar: true,
+        },
+      }),
+    )
+  })
+  await page.setViewportSize({ width: 1366, height: 768 })
+  const scroller = page.locator(".scroll-view__viewport", { has: page.locator("[data-timeline-row]") })
+  const text = page.locator(`[data-timeline-part-id="${textPartID}"]`).first()
+  await page.goto(`/${base64Encode(directory)}/session/${sessionID}`)
+  await expectSessionTitle(page, title)
+  await expectAppVisible(scroller)
+  return {
+    scroller,
+    text,
+    transport: {
+      enqueue(payload: EventPayload | EventPayload[]) {
+        events.push(...(Array.isArray(payload) ? payload : [payload]))
+      },
+      pendingCount() {
+        return events.length
+      },
+      releaseAll() {
+        eventBatch = events.length
+      },
+    },
+    async scrollToBottom() {
+      await scroller.evaluate((element) => {
+        element.scrollTop = element.scrollHeight
+      })
+    },
+    async waitForStableGeometry() {
+      await expect
+        .poll(() => scroller.evaluate((element) => element.scrollHeight - element.clientHeight - element.scrollTop))
+        .toBeLessThanOrEqual(1)
+      await page.waitForFunction((partID) => {
+        const root = [...document.querySelectorAll<HTMLElement>(".scroll-view__viewport")].find((element) =>
+          element.querySelector(`[data-timeline-part-id="${partID}"]`),
+        )
+        if (!root) return false
+        return new Promise<boolean>((resolve) => {
+          const height = root.scrollHeight
+          requestAnimationFrame(() =>
+            requestAnimationFrame(() =>
+              resolve(root.scrollHeight === height && root.scrollHeight - root.clientHeight - root.scrollTop <= 1),
+            ),
+          )
+        })
+      }, textPartID)
+    },
+  }
+}
+
+export function buildInitialStreamEvent(deltaCount: number): EventPayload {
+  return {
+    directory,
+    payload: {
+      type: "message.part.updated",
+      properties: {
+        part: {
+          ...streamedTextPart,
+          text: `Streaming${streamChunk(0, deltaCount + 1)}\n\n\`\`\`ts\nconst initial = true\n\`\`\``,
+        },
+      },
+    },
+  }
+}
+
+export function buildStreamDeltaEvents(deltaCount: number): EventPayload[] {
+  return Array.from({ length: deltaCount }, (_, index) => ({
+    directory,
+    payload: {
+      type: "message.part.delta",
+      properties: {
+        messageID: assistantMessageID,
+        partID: textPartID,
+        field: "text",
+        delta: streamChunk(index + 1, deltaCount + 1),
+      },
+    },
+  }))
+}
+
+function performanceTurn(index: number) {
+  const suffix = String(index).padStart(4, "0")
+  const userID = `msg_0000_${suffix}_a_user`
+  const assistantID = `msg_0000_${suffix}_b_assistant`
+  const before = historicalSource(index, false)
+  const after = historicalSource(index, true)
+  const parts = [
+    ...(index % 5 === 0
+      ? [
+          {
+            id: `prt_0000_${suffix}_reasoning`,
+            sessionID,
+            messageID: assistantID,
+            type: "reasoning",
+            text: `Reviewing the existing implementation. ${"constraint analysis ".repeat(20)}`,
+            time: { start: 1690000001000 + index * 2_000, end: 1690000001200 + index * 2_000 },
+          },
+        ]
+      : []),
+    {
+      id: `prt_0000_${suffix}_assistant`,
+      sessionID,
+      messageID: assistantID,
+      type: "text",
+      text: historicalMarkdown(index),
+    },
+    ...(index % 8 === 0
+      ? [
+          {
+            id: `prt_0000_${suffix}_edit`,
+            sessionID,
+            messageID: assistantID,
+            type: "tool",
+            callID: `call_0000_${suffix}_edit`,
+            tool: "edit",
+            state: {
+              status: "completed",
+              input: { filePath: `src/history-${index}.ts` },
+              output: `Edited src/history-${index}.ts`,
+              title: `src/history-${index}.ts`,
+              metadata: {
+                filediff: { file: `src/history-${index}.ts`, additions: 48, deletions: 48, before, after },
+              },
+              time: { start: 1690000001200 + index * 2_000, end: 1690000001400 + index * 2_000 },
+            },
+          },
+        ]
+      : []),
+    ...(index % 12 === 0
+      ? [
+          {
+            id: `prt_0000_${suffix}_write`,
+            sessionID,
+            messageID: assistantID,
+            type: "tool",
+            callID: `call_0000_${suffix}_write`,
+            tool: "write",
+            state: {
+              status: "completed",
+              input: { filePath: `src/generated-${index}.tsx`, content: after },
+              output: `Wrote src/generated-${index}.tsx`,
+              title: `src/generated-${index}.tsx`,
+              metadata: {
+                filediff: { file: `src/generated-${index}.tsx`, additions: 32, deletions: 0, before: "", after },
+              },
+              time: { start: 1690000001400 + index * 2_000, end: 1690000001500 + index * 2_000 },
+            },
+          },
+        ]
+      : []),
+    ...(index % 16 === 0
+      ? [
+          {
+            id: `prt_0000_${suffix}_patch`,
+            sessionID,
+            messageID: assistantID,
+            type: "tool",
+            callID: `call_0000_${suffix}_patch`,
+            tool: "apply_patch",
+            state: {
+              status: "completed",
+              input: { patchText: realisticPatch(index) },
+              output: "Success. Updated src/components/SessionCard.tsx",
+              title: "src/components/SessionCard.tsx",
+              metadata: {
+                files: [
+                  {
+                    filePath: "src/components/SessionCard.tsx",
+                    relativePath: "src/components/SessionCard.tsx",
+                    type: "update",
+                    additions: 8,
+                    deletions: 3,
+                    patch: realisticPatch(index),
+                    before,
+                    after,
+                  },
+                ],
+              },
+              time: { start: 1690000001500 + index * 2_000, end: 1690000001700 + index * 2_000 },
+            },
+          },
+        ]
+      : []),
+  ]
+  return [
+    {
+      info: {
+        id: userID,
+        sessionID,
+        role: "user",
+        time: { created: 1690000000000 + index * 2_000 },
+        summary: { diffs: [] },
+        agent: "build",
+        model,
+      },
+      parts: [
+        {
+          id: `prt_0000_${suffix}_user`,
+          sessionID,
+          messageID: userID,
+          type: "text",
+          text: `Historical prompt ${index}`,
+        },
+      ],
+    },
+    {
+      info: {
+        id: assistantID,
+        sessionID,
+        role: "assistant",
+        time: { created: 1690000001000 + index * 2_000, completed: 1690000001500 + index * 2_000 },
+        parentID: userID,
+        modelID: model.modelID,
+        providerID: model.providerID,
+        mode: "build",
+        agent: "build",
+        path: { cwd: directory, root: directory },
+        cost: 0.01,
+        tokens: { input: 100, output: 200, reasoning: 0, cache: { read: 0, write: 0 } },
+        variant: "max",
+        finish: "stop",
+      },
+      parts,
+    },
+  ]
+}
+
+function historicalMarkdown(index: number) {
+  const code = `import { For, Show, createSignal } from "solid-js"
+
+type SessionRow = { id: string; title: string; active: boolean }
+
+export function SessionList(props: { rows: SessionRow[] }) {
+  const [selected, setSelected] = createSignal<string>()
+  return (
+    <section aria-label="Sessions">
+      <For each={props.rows}>{(row) => (
+        <button classList={{ active: row.active }} onClick={() => setSelected(row.id)}>
+          <Show when={selected() === row.id} fallback={row.title}>{row.title.toUpperCase()}</Show>
+        </button>
+      )}</For>
+    </section>
+  )
+}`
+  return `## Session renderer review ${index}
+
+The active session keeps **semantic row identity** while reconciling measured content. See [Solid documentation](https://docs.solidjs.com/) and the inline \`measureElement(node)\` call.
+
+| Concern | Current behavior | Verification |
+| --- | --- | --- |
+| streaming | appends Markdown blocks | painted frames |
+| geometry | anchors visible rows | DOM coordinates |
+| tools | preserves expanded state | keyed remount probe |
+
+> Long sessions combine Markdown, syntax highlighting, tool output, and asynchronously rendered diffs.
+
+${index % 4 === 0 ? `\`\`\`tsx\n${code}\n\`\`\`\n\n\`\`\`bash\nbun typecheck\nbun test --preload ./happydom.ts ./src/pages/session\ngit diff --check\n\`\`\`` : "- preserve the viewport anchor\n- avoid replacing stable Markdown nodes\n- process provider deltas without blocking input"}`
+}
+
+function historicalSource(index: number, updated: boolean) {
+  const method = updated ? "toLocaleUpperCase(props.locale)" : "toUpperCase()"
+  const limit = updated ? 24 : 20
+  return `import { createMemo, For } from "solid-js"
+
+type Message = {
+  id: string
+  role: "user" | "assistant"
+  text: string
+  tokens: { input: number; output: number }
+}
+
+export function MessageSummary(props: { messages: Message[]; locale: string }) {
+  const visible = createMemo(() => props.messages.filter((message) => message.text.trim()).slice(-${limit}))
+  const total = createMemo(() => visible().reduce((sum, message) => sum + message.tokens.output, 0))
+  return (
+    <article data-session-index="${index}">
+      <header>{total().toLocaleString(props.locale)} output tokens</header>
+      <For each={visible()}>{(message) => <p data-role={message.role}>{message.text.${method}}</p>}</For>
+    </article>
+  )
+}
+`
+}
+
+function realisticPatch(index: number) {
+  return `*** Begin Patch
+*** Update File: src/components/SessionCard.tsx
+@@
+-const title = props.session.title.toUpperCase()
+-const messages = props.messages.slice(-20)
++const title = props.session.title.toLocaleUpperCase(props.locale)
++const messages = props.messages.filter((message) => message.text.trim()).slice(-24)
++const outputTokens = messages.reduce((sum, message) => sum + message.tokens.output, 0)
+@@
+-  <h2>{title}</h2>
++  <h2 data-session-index="${index}">{title}</h2>
++  <span>{outputTokens.toLocaleString(props.locale)} output tokens</span>
+*** End Patch`
+}
+
+export function streamChunk(index: number, count: number) {
+  if (index === 0) return `\n\n## Implementation plan\n\nStreaming **bold analysis`
+  if (index === count - 1)
+    return `\n\`\`\`\n\n## Verification\n\n- **Typecheck:** passed\n- **Timeline geometry:** stable\n- **Streaming output:** benchmark-complete <!-- stream-${index} -->`
+
+  const section = Math.floor(index / 18) + 1
+  const fragments = [
+    ` continues across three`,
+    ` or four word`,
+    ` provider deltas and`,
+    ` closes in this fragment**. <!-- stream-${index} -->\n\n`,
+    `| Concern | State`,
+    ` | Verification |\n|`,
+    ` --- | ---`,
+    ` | --- |\n|`,
+    ` markdown | incremental |`,
+    ` painted frames | <!-- stream-${index} -->\n\n`,
+    `\`\`\`tsx\nconst row: SessionRow`,
+    ` = rows[index] ??`,
+    ` fallback\nconst title =`,
+    ` row.title.toLocaleUpperCase(locale)\n`,
+    `const selected = createMemo(()`,
+    ` => row.id ===`,
+    ` activeID()) // stream-${index}\n`,
+    `// stream-${index}\n\`\`\`\n\n### Iteration ${section}\n\nStreaming **bold analysis`,
+  ]
+  return fragments[(index - 1) % fragments.length]!
+}
+
+function project() {
+  return {
+    id: projectID,
+    worktree: directory,
+    vcs: "git",
+    name: "timeline-state-regression",
+    time: { created: 1700000000000, updated: 1700000000000 },
+    sandboxes: [],
+  }
+}
+
+function session() {
+  return {
+    id: sessionID,
+    slug: "timeline-state-regression",
+    projectID,
+    directory,
+    title,
+    version: "dev",
+    time: { created: 1700000000000, updated: 1700000000000 },
+  }
+}
+
+function provider() {
+  return {
+    all: [
+      {
+        id: "opencode",
+        name: "OpenCode",
+        models: { "claude-opus-4-6": { id: "claude-opus-4-6", name: "Claude Opus 4.6", limit: { context: 200_000 } } },
+      },
+    ],
+    connected: ["opencode"],
+    default: { providerID: "opencode", modelID: "claude-opus-4-6" },
+  }
+}

packages/app/e2e/performance/timeline/session-timeline-benchmark.spec.ts

@@ -0,0 +1,85 @@
+import { benchmark, benchmarkDiagnostics, expect } from "../benchmark"
+import {
+  buildInitialStreamEvent,
+  buildStreamDeltaEvents,
+  setupTimelineBenchmark,
+  textPartID,
+} from "./session-timeline-benchmark.fixture"
+import { startTimelineProfile } from "./session-timeline-profile"
+import {
+  collectTimelineStreamMetrics,
+  installTimelineStreamProbe,
+  startTimelineStreamProbe,
+} from "./session-timeline-stream-probe"
+
+benchmark.describe("performance: session timeline streaming", () => {
+  benchmark("streams assistant text without remounting or oscillating", async ({ page, report }) => {
+    benchmark.setTimeout(480_000)
+    const cpuThrottle = Number(process.env.TIMELINE_CPU_THROTTLE ?? 30)
+    const deltaCount = Number(process.env.TIMELINE_DELTA_COUNT ?? 160)
+    const historyTurns = Number(process.env.TIMELINE_HISTORY_TURNS ?? 320)
+    const eventBatch = Number(process.env.TIMELINE_EVENT_BATCH ?? 1)
+    const minimal = process.env.TIMELINE_MINIMAL === "1"
+    const profileCPU = process.env.TIMELINE_CPU_PROFILE === "1"
+    const profileVisual = !minimal && profileCPU && process.env.TIMELINE_VISUAL_PROFILE !== "0"
+    const fixture = await setupTimelineBenchmark(page, {
+      historyTurns,
+      eventBatch,
+    })
+
+    fixture.transport.enqueue(buildInitialStreamEvent(deltaCount))
+    const contentStart = performance.now()
+    await expect(fixture.text).toBeVisible()
+    await expect(fixture.text).toContainText("Implementation plan")
+    const initialContentObservedMs = performance.now() - contentStart
+    await fixture.scrollToBottom()
+    await fixture.waitForStableGeometry()
+
+    const profile = await startTimelineProfile(page, { cpuThrottle, profileCPU })
+    await installTimelineStreamProbe(page, { textPartID, finalIndex: deltaCount, profileVisual, minimal })
+    const deltas = buildStreamDeltaEvents(deltaCount)
+    await startTimelineStreamProbe(page)
+    fixture.transport.enqueue(deltas)
+
+    await page.waitForFunction(
+      (finalIndex) =>
+        (
+          window as Window & {
+            __timelineStreamBenchmark?: { applied: { index: number }[] }
+          }
+        ).__timelineStreamBenchmark?.applied.some((value) => value.index === finalIndex),
+      deltaCount,
+      { timeout: 420_000 },
+    )
+    await expect(fixture.text).toContainText("benchmark-complete")
+    await expect(fixture.text).toContainText("Streaming")
+    await fixture.waitForStableGeometry()
+    const metrics = await collectTimelineStreamMetrics(page, {
+      textPartID,
+      finalIndex: deltaCount,
+      navigations: benchmarkDiagnostics(page).navigations,
+    })
+    const delivered = deltas.length - fixture.transport.pendingCount()
+    await profile.stop()
+
+    report(
+      {
+        endToEndInitialContentObservedMs: initialContentObservedMs,
+        ...metrics,
+        deliveredDeltas: delivered,
+        pendingDeltas: fixture.transport.pendingCount(),
+      },
+      {
+        cpuThrottle,
+        profileCPU,
+        profileVisual,
+        minimal,
+        queuedDeltas: deltas.length,
+        historyTurns,
+        eventBatch,
+      },
+    )
+
+    await profile.reset()
+  })
+})

packages/app/e2e/performance/timeline/session-timeline-profile.ts

@@ -0,0 +1,40 @@
+import type { CDPSession, Page } from "@playwright/test"
+
+export async function startTimelineProfile(page: Page, options: { cpuThrottle: number; profileCPU: boolean }) {
+  const cdp = await page.context().newCDPSession(page)
+  if (options.cpuThrottle > 1) await cdp.send("Emulation.setCPUThrottlingRate", { rate: options.cpuThrottle })
+  if (options.profileCPU) {
+    await cdp.send("Profiler.enable")
+    await cdp.send("Profiler.setSamplingInterval", { interval: 100 })
+    await cdp.send("Profiler.start")
+  }
+  return {
+    async stop() {
+      if (!options.profileCPU) return
+      const result = await cdp.send("Profiler.stop")
+      const self = new Map<number, number>()
+      result.profile.samples?.forEach((id, index) => {
+        const duration = (result.profile.timeDeltas?.[index] ?? 0) / 1_000
+        self.set(id, (self.get(id) ?? 0) + duration)
+      })
+      console.log(
+        "timeline cpu profile",
+        JSON.stringify(
+          result.profile.nodes
+            .map((node) => ({
+              function: node.callFrame.functionName || "(anonymous)",
+              url: node.callFrame.url,
+              line: node.callFrame.lineNumber + 1,
+              selfMs: self.get(node.id) ?? 0,
+            }))
+            .filter((node) => node.selfMs > 1)
+            .sort((a, b) => b.selfMs - a.selfMs)
+            .slice(0, 40),
+        ),
+      )
+    },
+    async reset() {
+      if (options.cpuThrottle > 1) await cdp.send("Emulation.setCPUThrottlingRate", { rate: 1 })
+    },
+  }
+}

packages/app/e2e/performance/timeline/session-timeline-stream-probe.ts

@@ -0,0 +1,547 @@
+import type { Page } from "@playwright/test"
+
+const STREAM_MARKER_PATTERN = "stream-(\\d+)"
+const STREAM_FRAGMENT_COUNT = 18
+
+type TimelineProbeState = {
+  started: number
+  ended: number
+  profileVisual: boolean
+  minimal: boolean
+  frames: number[]
+  frameAt: number[]
+  applied: { at: number; index: number }[]
+  geometry: {
+    scrollTop: number
+    scrollHeight: number
+    clientHeight: number
+    distance: number
+    virtualHeight: number
+    headerHeight: number
+  }[]
+  blanks: number
+  longTasks: number[]
+  layoutShifts: number[]
+  visibleMounts: number
+  visibleUnmounts: number
+  visibleRows: Set<Element>
+  visibleSubtreeMounts: string[]
+  visibleSubtreeUnmounts: string[]
+  visibleSubtreeReplacements: number
+  visibleSubtreeDropouts: string[]
+  visibleSubtrees: Map<string, Element>
+  subtreeKeys: WeakMap<Element, string>
+  maxOverlap: number
+  maxGap: number
+  maxPartTopMovement: number
+  previousPartTop: number
+  slowFrames: {
+    duration: number
+    index: number
+    phase: "stream" | "boundary" | "complete" | "unknown"
+    tokenSpans: number
+    blocks: number
+    codeBlocks: number
+    height: number
+    distance: number
+  }[]
+  scroll: {
+    calls: number
+    callNoops: number
+    sameFrameCalls: number
+    assignments: number
+    assignmentNoops: number
+    lastCallFrame: number
+    frame: number
+  }
+  row: HTMLElement
+  markdown: HTMLElement
+  running: boolean
+  previous: number
+  cleanup: () => void
+  start: () => void
+}
+
+export async function installTimelineStreamProbe(
+  page: Page,
+  options: { textPartID: string; finalIndex: number; profileVisual: boolean; minimal: boolean },
+) {
+  await page.evaluate(
+    ({ textPartID, finalIndex, profileVisual, minimal, markerPattern, fragmentCount }) => {
+      const part = document.querySelector<HTMLElement>(`[data-timeline-part-id="${textPartID}"]`)
+      const row = part?.closest<HTMLElement>("[data-timeline-row]")
+      const markdown = part?.querySelector<HTMLElement>('[data-component="markdown"]')
+      const root = part?.closest<HTMLElement>(".scroll-view__viewport")
+      if (!part || !row || !markdown || !root) throw new Error("missing streaming benchmark nodes")
+      const viewport = root.getBoundingClientRect()
+      const state: TimelineProbeState = {
+        started: 0,
+        ended: Infinity,
+        profileVisual,
+        minimal,
+        frames: [],
+        frameAt: [],
+        applied: [],
+        geometry: [],
+        blanks: 0,
+        longTasks: [],
+        layoutShifts: [],
+        visibleMounts: 0,
+        visibleUnmounts: 0,
+        visibleRows: new Set(
+          [...root.querySelectorAll("[data-timeline-key]")].filter((element) => {
+            const rect = element.getBoundingClientRect()
+            return rect.bottom > viewport.top && rect.top < viewport.bottom
+          }),
+        ),
+        visibleSubtreeMounts: [],
+        visibleSubtreeUnmounts: [],
+        visibleSubtreeReplacements: 0,
+        visibleSubtreeDropouts: [],
+        visibleSubtrees: new Map<string, Element>(),
+        subtreeKeys: new WeakMap<Element, string>(),
+        maxOverlap: 0,
+        maxGap: 0,
+        maxPartTopMovement: 0,
+        previousPartTop: part.getBoundingClientRect().top,
+        slowFrames: [],
+        scroll: {
+          calls: 0,
+          callNoops: 0,
+          sameFrameCalls: 0,
+          assignments: 0,
+          assignmentNoops: 0,
+          lastCallFrame: -1,
+          frame: 0,
+        },
+        row,
+        markdown,
+        running: false,
+        previous: 0,
+        cleanup: () => {},
+        start: () => {},
+      }
+      ;(window as Window & { __timelineStreamBenchmark?: TimelineProbeState }).__timelineStreamBenchmark = state
+      const scrollTo = Element.prototype.scrollTo
+      const scrollTop = Object.getOwnPropertyDescriptor(Element.prototype, "scrollTop")!
+      if (profileVisual) {
+        Element.prototype.scrollTo = function (...args) {
+          state.scroll.calls += 1
+          const top = typeof args[0] === "object" ? args[0]?.top : args[1]
+          if (typeof top === "number") {
+            const target = Math.min(top, this.scrollHeight - this.clientHeight)
+            if (Math.abs(this.scrollTop - target) < 1) state.scroll.callNoops += 1
+          }
+          if (state.scroll.lastCallFrame === state.scroll.frame) state.scroll.sameFrameCalls += 1
+          state.scroll.lastCallFrame = state.scroll.frame
+          return scrollTo.apply(this, args)
+        }
+        Object.defineProperty(Element.prototype, "scrollTop", {
+          configurable: true,
+          get: scrollTop.get,
+          set(value) {
+            state.scroll.assignments += 1
+            if (Math.abs(this.scrollTop - value) < 1) state.scroll.assignmentNoops += 1
+            scrollTop.set!.call(this, value)
+          },
+        })
+      }
+
+      const recordLongTasks = (entries: PerformanceEntry[]) => {
+        if (!state.running) return
+        state.longTasks.push(
+          ...entries
+            .filter((entry) => entry.startTime >= state.started && entry.startTime <= state.ended)
+            .map((entry) => entry.duration),
+        )
+      }
+      const longTaskObserver = new PerformanceObserver((list) => recordLongTasks(list.getEntries()))
+      longTaskObserver.observe({ type: "longtask" })
+      const recordLayoutShifts = (entries: PerformanceEntry[]) => {
+        if (!state.running) return
+        state.layoutShifts.push(
+          ...entries
+            .map((entry) => {
+              const shift = entry as LayoutShiftEntry
+              if (shift.startTime < state.started || shift.hadRecentInput) return
+              return shift.value
+            })
+            .filter((value): value is number => value !== undefined),
+        )
+      }
+      const layoutShiftObserver = profileVisual
+        ? new PerformanceObserver((list) => recordLayoutShifts(list.getEntries()))
+        : undefined
+      layoutShiftObserver?.observe({ type: "layout-shift", buffered: true })
+
+      const visible = (element: Element) => {
+        const rect = element.getBoundingClientRect()
+        const viewport = root.getBoundingClientRect()
+        const style = getComputedStyle(element)
+        return (
+          element.isConnected &&
+          rect.width > 0 &&
+          rect.height > 0 &&
+          rect.bottom > viewport.top &&
+          rect.top < viewport.bottom &&
+          style.display !== "none" &&
+          style.visibility !== "hidden" &&
+          Number(style.opacity) > 0
+        )
+      }
+      const critical = [
+        "[data-timeline-part-id]",
+        '[data-component="edit-content"]',
+        '[data-component="apply-patch-file-diff"]',
+        '[data-component="file"]',
+        '[data-component="markdown-code"]',
+        "[data-markdown-block]",
+      ].join(",")
+      const describe = (element: Element) => {
+        const cached = state.subtreeKeys.get(element)
+        if (!element.isConnected && cached) return cached
+        const part = element.closest<HTMLElement>("[data-timeline-part-id]")?.dataset.timelinePartId ?? "unknown"
+        const block = element
+          .closest<HTMLElement>("[data-markdown-key]")
+          ?.dataset.markdownKey?.replace(/:(?:code|full|live)$/, "")
+        const component =
+          element.getAttribute("data-component") ?? element.getAttribute("data-markdown-block") ?? element.tagName
+        const key = `${part}:${block ?? "root"}:${component}`
+        state.subtreeKeys.set(element, key)
+        return key
+      }
+      const recordMutations = (records: MutationRecord[]) => {
+        if (!state.running) return
+        records.forEach((record) => {
+          record.addedNodes.forEach((node) => {
+            if (node instanceof HTMLElement && node.matches("[data-timeline-key]") && visible(node)) {
+              state.visibleMounts += 1
+              state.visibleRows.add(node)
+            }
+            if (!(node instanceof Element)) return
+            const added = [node, ...node.querySelectorAll(critical)].filter((element) => element.matches(critical))
+            added.forEach((element) => {
+              if (visible(element)) state.visibleSubtreeMounts.push(describe(element))
+            })
+          })
+          record.removedNodes.forEach((node) => {
+            if (node instanceof HTMLElement && node.matches("[data-timeline-key]") && state.visibleRows.delete(node))
+              state.visibleUnmounts += 1
+            if (!(node instanceof Element)) return
+            const removed = [node, ...node.querySelectorAll(critical)].filter((element) => element.matches(critical))
+            removed.forEach((element) => {
+              const key = describe(element)
+              if (state.visibleSubtrees.get(key) === element) state.visibleSubtreeUnmounts.push(key)
+            })
+          })
+        })
+      }
+      const mutationObserver = profileVisual ? new MutationObserver(recordMutations) : undefined
+      mutationObserver?.observe(root, { childList: true, subtree: true })
+      const currentPart = () => root.querySelector<HTMLElement>(`[data-timeline-part-id="${textPartID}"]`)
+      const observeProgress = (at: number) => {
+        if (!state.running) return
+        const content = currentPart()?.textContent ?? ""
+        const index = content.includes("benchmark-complete")
+          ? finalIndex
+          : Number(content.match(new RegExp(markerPattern, "g"))?.at(-1)?.match(/\d+/)?.[0] ?? -1)
+        if (index >= 0 && index !== state.applied.at(-1)?.index) state.applied.push({ at, index })
+      }
+      const progressObserver = new MutationObserver(() => observeProgress(performance.now()))
+      progressObserver.observe(root, { characterData: true, childList: true, subtree: true })
+      state.cleanup = () => {
+        recordLongTasks(longTaskObserver.takeRecords())
+        recordLayoutShifts(layoutShiftObserver?.takeRecords() ?? [])
+        recordMutations(mutationObserver?.takeRecords() ?? [])
+        if (progressObserver.takeRecords().length) observeProgress(performance.now())
+        longTaskObserver.disconnect()
+        layoutShiftObserver?.disconnect()
+        mutationObserver?.disconnect()
+        progressObserver.disconnect()
+        if (!profileVisual) return
+        Element.prototype.scrollTo = scrollTo
+        Object.defineProperty(Element.prototype, "scrollTop", scrollTop)
+      }
+
+      const sample = (now: number) => {
+        if (!state.running) return
+        state.frameAt.push(now)
+        observeProgress(now)
+        if (minimal) {
+          state.frames.push(now - state.previous)
+          state.previous = now
+          requestAnimationFrame(sample)
+          return
+        }
+        setTimeout(() => {
+          if (!state.running) return
+          state.scroll.frame += 1
+          const duration = now - state.previous
+          state.frames.push(duration)
+          state.previous = now
+          const virtualRoot = root.querySelector<HTMLElement>("[data-timeline-virtual-content]")
+          const header = root.querySelector<HTMLElement>("[data-session-title]")
+          state.geometry.push({
+            scrollTop: root.scrollTop,
+            scrollHeight: root.scrollHeight,
+            clientHeight: root.clientHeight,
+            distance: root.scrollHeight - root.clientHeight - root.scrollTop,
+            virtualHeight: virtualRoot?.getBoundingClientRect().height ?? 0,
+            headerHeight: header?.getBoundingClientRect().height ?? 0,
+          })
+          const viewport = root.getBoundingClientRect()
+          if (profileVisual) {
+            const visibleRows = [...root.querySelectorAll<HTMLElement>("[data-timeline-key]")]
+              .map((element) => ({ element, rect: element.getBoundingClientRect() }))
+              .filter((item) => item.rect.bottom > viewport.top && item.rect.top < viewport.bottom)
+              .sort((a, b) => a.rect.top - b.rect.top)
+            state.visibleRows = new Set(visibleRows.map((item) => item.element))
+            const rows = visibleRows.map((item) => item.rect)
+            rows.slice(1).forEach((rect, index) => {
+              const previous = rows[index]!
+              state.maxOverlap = Math.max(state.maxOverlap, previous.bottom - rect.top)
+              state.maxGap = Math.max(state.maxGap, rect.top - previous.bottom)
+            })
+            const partTop = part.getBoundingClientRect().top
+            state.maxPartTopMovement = Math.max(state.maxPartTopMovement, Math.abs(partTop - state.previousPartTop))
+            state.previousPartTop = partTop
+          }
+          const visibleRow = [...root.querySelectorAll<HTMLElement>("[data-timeline-row]")].some((element) => {
+            const rect = element.getBoundingClientRect()
+            return rect.bottom > viewport.top && rect.top < viewport.bottom
+          })
+          if (!visibleRow) state.blanks += 1
+          if (profileVisual) {
+            const subtrees = new Map<string, { element: Element; rendered: boolean }>()
+            const visibleSubtrees = new Map<string, Element>()
+            root.querySelectorAll(critical).forEach((element) => {
+              const key = describe(element)
+              const rect = element.getBoundingClientRect()
+              const style = getComputedStyle(element)
+              const rendered =
+                element.isConnected &&
+                rect.width > 0 &&
+                rect.height > 0 &&
+                style.display !== "none" &&
+                style.visibility !== "hidden" &&
+                Number(style.opacity) > 0
+              subtrees.set(key, { element, rendered })
+              if (rendered && rect.bottom > viewport.top && rect.top < viewport.bottom) {
+                const previous = state.visibleSubtrees.get(key)
+                if (previous && previous !== element && key.startsWith(`${textPartID}:`))
+                  state.visibleSubtreeReplacements += 1
+                visibleSubtrees.set(key, element)
+              }
+            })
+            state.visibleSubtrees.forEach((element, key) => {
+              const current = subtrees.get(key)
+              if (key.startsWith(`${textPartID}:`) && !current?.rendered) {
+                const markdown = part.querySelector<HTMLElement>('[data-component="markdown"]')
+                state.visibleSubtreeDropouts.push(
+                  `${key}:projection=${markdown?.dataset.markdownProjectionLength}/${markdown?.dataset.markdownProjectionBlocks}:result=${markdown?.dataset.markdownResultLength}/${markdown?.dataset.markdownResultBlocks}:applied=${markdown?.dataset.markdownAppliedBlocks}:dom=${markdown?.children.length}`,
+                )
+              }
+              if (element.matches('[data-component="file"]')) {
+                const hadLines = element.hasAttribute("data-profiler-had-lines")
+                const hasLines = element.shadowRoot?.querySelector("[data-line]") != null
+                if (hasLines) element.setAttribute("data-profiler-had-lines", "")
+                if (hadLines && !hasLines) state.visibleSubtreeDropouts.push(`${key}:shadow-lines`)
+              }
+            })
+            state.visibleSubtrees = visibleSubtrees
+          }
+          if (profileVisual && duration > 33.34) {
+            const livePart = currentPart()
+            const content = livePart?.textContent ?? ""
+            const complete = content.includes("benchmark-complete")
+            const index = complete
+              ? finalIndex
+              : Number(content.match(new RegExp(markerPattern, "g"))?.at(-1)?.match(/\d+/)?.[0] ?? -1)
+            state.slowFrames.push({
+              duration,
+              index,
+              phase: complete
+                ? "complete"
+                : index >= 0 && index % fragmentCount === 0
+                  ? "boundary"
+                  : index >= 0
+                    ? "stream"
+                    : "unknown",
+              tokenSpans: livePart?.querySelectorAll(".shiki span").length ?? 0,
+              blocks: livePart?.querySelectorAll("[data-markdown-block]").length ?? 0,
+              codeBlocks: livePart?.querySelectorAll('[data-component="markdown-code"]').length ?? 0,
+              height: livePart?.getBoundingClientRect().height ?? 0,
+              distance: root.scrollHeight - root.clientHeight - root.scrollTop,
+            })
+          }
+          requestAnimationFrame(sample)
+        }, 0)
+      }
+      state.start = () => {
+        state.started = performance.now()
+        state.previous = state.started
+        state.running = true
+        requestAnimationFrame(sample)
+      }
+    },
+    { ...options, markerPattern: STREAM_MARKER_PATTERN, fragmentCount: STREAM_FRAGMENT_COUNT },
+  )
+}
+
+export function startTimelineStreamProbe(page: Page) {
+  return page.evaluate(() => {
+    const state = (window as Window & { __timelineStreamBenchmark?: TimelineProbeState }).__timelineStreamBenchmark
+    if (!state) throw new Error("missing streaming benchmark state")
+    state.start()
+  })
+}
+
+type LayoutShiftEntry = PerformanceEntry & { value: number; hadRecentInput?: boolean }
+
+export function layoutShiftValue(
+  entry: Pick<LayoutShiftEntry, "startTime" | "value" | "hadRecentInput">,
+  start: number,
+) {
+  if (entry.startTime < start || entry.hadRecentInput) return
+  return entry.value
+}
+
+export function removeVisibleRow<T>(visible: Set<T>, row: T) {
+  return visible.delete(row)
+}
+
+export function streamProgress(content: string) {
+  const index = Number(content.match(new RegExp(STREAM_MARKER_PATTERN, "g"))?.at(-1)?.match(/\d+/)?.[0] ?? -1)
+  return {
+    index,
+    phase: content.includes("benchmark-complete")
+      ? ("complete" as const)
+      : index >= 0 && index % STREAM_FRAGMENT_COUNT === 0
+        ? ("boundary" as const)
+        : index >= 0
+          ? ("stream" as const)
+          : ("unknown" as const),
+  }
+}
+
+export async function collectTimelineStreamMetrics(
+  page: Page,
+  options: { textPartID: string; finalIndex: number; navigations: string[] },
+) {
+  return page.evaluate(({ textPartID, finalIndex, navigations }) => {
+    const state = (window as Window & { __timelineStreamBenchmark?: TimelineProbeState }).__timelineStreamBenchmark
+    if (!state) throw new Error(`missing streaming benchmark state after navigation: ${JSON.stringify(navigations)}`)
+    state.ended = performance.now()
+    state.cleanup()
+    state.running = false
+    const part = document.querySelector<HTMLElement>(`[data-timeline-part-id="${textPartID}"]`)
+    const row = part?.closest<HTMLElement>("[data-timeline-row]")
+    const markdown = part?.querySelector<HTMLElement>('[data-component="markdown"]')
+    const sorted = state.frames.slice().sort((a, b) => a - b)
+    const duration = state.frames.reduce((sum, value) => sum + value, 0)
+    const longestSlowStreak = state.frames.reduce(
+      (result, value) => {
+        const current = value > 33.34 ? result.current + 1 : 0
+        return { current, longest: Math.max(result.longest, current) }
+      },
+      { current: 0, longest: 0 },
+    ).longest
+    const busyStart = state.applied.at(0)?.at
+    const completion = state.applied.find((value) => value.index === finalIndex)
+    const busyEnd = completion?.at
+    const busyFrames =
+      busyStart === undefined || busyEnd === undefined
+        ? []
+        : state.frames.filter((_, index) => state.frameAt[index]! >= busyStart && state.frameAt[index]! <= busyEnd)
+    const busySorted = busyFrames.slice().sort((a, b) => a - b)
+    const busyDuration = busyFrames.reduce((sum, value) => sum + value, 0)
+    const completionObservedMs = (completion?.at ?? NaN) - state.started
+    const visual = state.profileVisual
+      ? {
+          layoutShiftValueSum: state.layoutShifts.reduce((sum, value) => sum + value, 0),
+          maxLayoutShiftValue: Math.max(0, ...state.layoutShifts),
+          visibleMounts: state.visibleMounts,
+          visibleUnmounts: state.visibleUnmounts,
+          visibleSubtreeMounts: state.visibleSubtreeMounts,
+          visibleSubtreeUnmounts: [...new Set(state.visibleSubtreeUnmounts)],
+          visibleSubtreeReplacements: state.visibleSubtreeReplacements,
+          visibleSubtreeDropouts: [...new Set(state.visibleSubtreeDropouts)],
+          maxOverlapPx: state.maxOverlap,
+          maxGapPx: state.maxGap,
+          maxPartTopMovementPx: state.maxPartTopMovement,
+          slowestRafGaps: state.slowFrames
+            .sort((a, b) => b.duration - a.duration)
+            .slice(0, 20)
+            .map((frame) => ({
+              durationMs: frame.duration,
+              index: frame.index,
+              phase: frame.phase,
+              tokenSpans: frame.tokenSpans,
+              blocks: frame.blocks,
+              codeBlocks: frame.codeBlocks,
+              heightPx: frame.height,
+              distancePx: frame.distance,
+            })),
+          slowRafGapPhases: Object.fromEntries(
+            ["stream", "boundary", "complete", "unknown"].map((phase) => {
+              const frames = state.slowFrames.filter((frame) => frame.phase === phase)
+              return [
+                phase,
+                {
+                  count: frames.length,
+                  totalMs: frames.reduce((sum, frame) => sum + frame.duration, 0),
+                  maxMs: Math.max(0, ...frames.map((frame) => frame.duration)),
+                },
+              ]
+            }),
+          ),
+          scroll: state.scroll,
+        }
+      : null
+    const geometry = state.minimal
+      ? null
+      : {
+          maxDistancePx: Math.max(0, ...state.geometry.map((sample) => sample.distance)),
+          finalDistancePx: state.geometry.at(-1)?.distance ?? 0,
+          final: state.geometry.at(-1),
+          distanceTransitionsPx: state.geometry
+            .map((sample) => Math.round(sample.distance))
+            .filter((value, index, values) => index === 0 || value !== values[index - 1]),
+          bottomDriftTransitions: state.geometry.slice(1).filter((value, index) => {
+            const previous = state.geometry[index]?.distance ?? 0
+            return previous <= 1 && value.distance > 1
+          }).length,
+          blankSamples: state.blanks,
+        }
+    return {
+      capabilities: { visual: state.profileVisual, geometry: !state.minimal },
+      completionObservedMs,
+      deltasPerSecond: Number.isFinite(completionObservedMs) ? finalIndex / (completionObservedMs / 1_000) : null,
+      rafGapSamples: state.frames.length,
+      rafCallbackRate: duration ? (state.frames.length * 1000) / duration : 0,
+      observedProgressWindowRafCallbackRate: busyDuration ? (busyFrames.length * 1000) / busyDuration : null,
+      observedProgressWindowRafGapP95Ms: busySorted[Math.floor(busySorted.length * 0.95)] ?? null,
+      observedProgressWindowRafGaps: busyFrames.length,
+      maxObservedProgressIndex: Math.max(-1, ...state.applied.map((value) => value.index)),
+      observedProgressTransitions: state.applied.length,
+      rafGapP50Ms: sorted[Math.floor(sorted.length * 0.5)] ?? 0,
+      rafGapP95Ms: sorted[Math.floor(sorted.length * 0.95)] ?? 0,
+      rafGapP99Ms: sorted[Math.floor(sorted.length * 0.99)] ?? 0,
+      maxRafGapMs: sorted.at(-1) ?? 0,
+      rafGapsOver33Ms: state.frames.filter((value) => value > 33.34).length,
+      rafGapsOver50Ms: state.frames.filter((value) => value > 50).length,
+      missedFrameBudgetEquivalents: state.frames.reduce(
+        (sum, value) => sum + Math.max(0, Math.round(value / 16.67) - 1),
+        0,
+      ),
+      longestRafGapOver33MsStreak: longestSlowStreak,
+      longTaskCount: state.longTasks.length,
+      longTaskTimeMs: state.longTasks.reduce((sum, value) => sum + value, 0),
+      visual,
+      geometry,
+      rowReplaced: row !== state.row,
+      markdownReplaced: markdown !== state.markdown,
+      domTextCharacters: part?.textContent?.length ?? 0,
+    }
+  }, options)
+}

packages/app/e2e/performance/timeline/session-timeline-stress.fixture.ts

@@ -0,0 +1,335 @@
+const words = [
+  "alpha",
+  "bravo",
+  "charlie",
+  "delta",
+  "echo",
+  "foxtrot",
+  "golf",
+  "hotel",
+  "india",
+  "juliet",
+  "kilo",
+  "lima",
+  "metro",
+  "nova",
+  "orbit",
+  "pixel",
+  "quartz",
+  "river",
+  "signal",
+  "vector",
+]
+
+const sourceID = "ses_smoke_source"
+const targetID = "ses_smoke_target"
+const directory = "C:/OpenCode/SmokeProject"
+const projectID = "proj_smoke_timeline"
+const model = { providerID: "opencode", modelID: "claude-opus-4-6", variant: "max" }
+
+type MessageInfo = Record<string, unknown> & { id: string; role: "user" | "assistant" }
+type MessagePart = Record<string, unknown> & { id: string; type: string; text?: string; tool?: string }
+type Message = { info: MessageInfo; parts: MessagePart[] }
+
+function lorem(seed: number, length: number) {
+  let out = ""
+  let i = seed
+  while (out.length < length) {
+    const word = words[i % words.length]
+    out += (out ? " " : "") + word
+    if (i % 17 === 0) out += ".\n\n"
+    i += 7
+  }
+  return out.slice(0, length)
+}
+
+function id(prefix: string, value: number) {
+  return `${prefix}_smoke_${String(value).padStart(4, "0")}`
+}
+
+function userMessage(sessionID: string, index: number, textLength: number, diffs: unknown[] = []): Message {
+  const messageID = id("msg_user", index)
+  return {
+    info: {
+      id: messageID,
+      sessionID,
+      role: "user",
+      time: { created: 1700000000000 + index * 10_000 },
+      summary: { diffs },
+      agent: "build",
+      model,
+    },
+    parts: [
+      {
+        id: id("prt_user_text", index),
+        sessionID,
+        messageID,
+        type: "text",
+        text: lorem(index, textLength),
+      },
+    ],
+  }
+}
+
+function assistantMessage(sessionID: string, index: number, parentID: string, parts: MessagePart[]): Message {
+  const messageID = id("msg_assistant", index)
+  return {
+    info: {
+      id: messageID,
+      sessionID,
+      role: "assistant",
+      time: { created: 1700000000000 + index * 10_000 + 1_000, completed: 1700000000000 + index * 10_000 + 8_000 },
+      parentID,
+      modelID: model.modelID,
+      providerID: model.providerID,
+      mode: "build",
+      agent: "build",
+      path: { cwd: directory, root: directory },
+      cost: 0.01,
+      tokens: { input: 100, output: 200, reasoning: 0, cache: { read: 0, write: 0 } },
+      variant: "max",
+      finish: "stop",
+    },
+    parts: parts.map((part) => ({
+      ...part,
+      sessionID,
+      messageID,
+    })),
+  }
+}
+
+function textPart(index: number, partIndex: number, length: number): MessagePart {
+  const prose = lorem(index * 13 + partIndex, length)
+  const text =
+    index % 12 === 0
+      ? `${prose}\n\n\`\`\`ts\n${code(index, 80)}\n\`\`\``
+      : index % 5 === 0
+        ? `${prose}\n\n\`\`\`ts\nexport const value = "${lorem(index, 220)}"\n\`\`\``
+        : index % 7 === 0
+          ? `${prose}\n\nThe wrapped inline value is \`${lorem(index, 180)}\`.`
+          : prose
+  return { id: id(`prt_text_${partIndex}`, index), type: "text", text }
+}
+
+function reasoningPart(index: number, partIndex: number, length: number): MessagePart {
+  return {
+    id: id(`prt_reasoning_${partIndex}`, index),
+    type: "reasoning",
+    text: lorem(index * 19 + partIndex, length),
+    time: { start: 1700000000000 + index * 10_000, end: 1700000000000 + index * 10_000 + 500 },
+  }
+}
+
+function toolPart(
+  index: number,
+  partIndex: number,
+  tool: string,
+  input: Record<string, unknown>,
+  outputLength = 160,
+): MessagePart {
+  const metadata =
+    tool === "apply_patch"
+      ? { files: [patchFile(index, "update"), patchFile(index + 1, index % 2 === 0 ? "add" : "delete")] }
+      : tool === "edit" || tool === "write"
+        ? {
+            filediff: fileDiff(String(input.filePath ?? `src/generated/file-${index}.ts`), index),
+            diff: patch(index, outputLength),
+            preview: patch(index + 1, 420),
+          }
+        : tool === "question"
+          ? { answers: [["Proceed"], ["Keep sample output"]] }
+          : {}
+  return {
+    id: id(`prt_tool_${tool}_${partIndex}`, index),
+    type: "tool",
+    callID: id("call", index * 10 + partIndex),
+    tool,
+    state: {
+      status: "completed",
+      input,
+      output: lorem(index * 23 + partIndex, outputLength),
+      title: tool === "bash" ? "Verify generated output" : input.filePath || input.path || input.pattern || "completed",
+      metadata,
+      time: { start: 1700000000000 + index * 10_000, end: 1700000000000 + index * 10_000 + 400 },
+    },
+  }
+}
+
+function patchFile(seed: number, type: "add" | "update" | "delete") {
+  return {
+    filePath: `src/generated/patch-${seed}.ts`,
+    relativePath: `src/generated/patch-${seed}.ts`,
+    type,
+    additions: (seed % 7) + 1,
+    deletions: type === "add" ? 0 : seed % 4,
+    patch: patch(seed, 520),
+    before: type === "add" ? undefined : code(seed, 18),
+    after: type === "delete" ? undefined : code(seed + 1, 24),
+  }
+}
+
+function fileDiff(file: string, seed: number) {
+  const lines = seed % 12 === 0 ? 300 : seed % 8 === 0 ? 2 : 38
+  const before = code(seed, lines, seed % 10 === 0 ? 280 : 32)
+  const after =
+    lines === 2
+      ? before.replace("value1", "updatedValue1")
+      : lines === 300
+        ? code(seed + 1, lines, seed % 10 === 0 ? 280 : 32)
+        : before.replace("value4", "updatedValue4").replace("value20", "updatedValue20")
+  return {
+    file,
+    additions: lines === 300 ? 300 : lines === 2 ? 1 : 2,
+    deletions: lines === 300 ? 300 : lines === 2 ? 1 : 2,
+    before,
+    after,
+  }
+}
+
+function patch(seed: number, length: number) {
+  return `diff --git a/src/generated/file-${seed}.ts b/src/generated/file-${seed}.ts\n+${lorem(seed, length).replace(/\n/g, "\n+")}`
+}
+
+function code(seed: number, lines: number, width = 32) {
+  return Array.from(
+    { length: lines },
+    (_, index) => `export const value${index} = "${lorem(seed + index, width)}"`,
+  ).join("\n")
+}
+
+function turn(index: number): Message[] {
+  const diff = index % 9 === 0 ? [fileDiff(`src/generated/summary-${index}.ts`, index)] : []
+  const user = userMessage(targetID, index, 100 + (index % 4) * 80, diff)
+  const parts = [
+    ...(index % 5 === 0 ? [reasoningPart(index, 0, 420)] : []),
+    ...(index % 3 === 0
+      ? [
+          toolPart(index, 0, "read", { filePath: `src/generated/file-${index}.ts`, offset: 0, limit: 80 }, 220),
+          toolPart(index, 5, "glob", { path: directory, pattern: `**/*sample-${index}*.ts` }, 140),
+          toolPart(index, 1, "grep", { path: directory, pattern: `sample-${index}`, include: "*.ts" }, 180),
+          toolPart(index, 6, "list", { path: `src/generated/${index}` }, 120),
+        ]
+      : []),
+    textPart(index, 2, 160 + (index % 6) * 90),
+    ...(index % 4 === 0 ? [toolPart(index, 3, "edit", { filePath: `src/generated/file-${index}.ts` }, 700)] : []),
+    ...(index % 6 === 0
+      ? [toolPart(index, 7, "write", { filePath: `src/generated/write-${index}.ts`, content: code(index, 28) }, 560)]
+      : []),
+    ...(index % 8 === 0
+      ? [toolPart(index, 8, "apply_patch", { files: [`src/generated/patch-${index}.ts`] }, 620)]
+      : []),
+    ...(index % 7 === 0
+      ? [toolPart(index, 4, "bash", { command: "bun typecheck", description: "Verify generated output" }, 620)]
+      : []),
+    ...(index % 10 === 0 ? [toolPart(index, 9, "webfetch", { url: "https://example.com/docs/sample" }, 120)] : []),
+    ...(index % 11 === 0 ? [toolPart(index, 10, "websearch", { query: "sample movement notes" }, 240)] : []),
+    ...(index % 13 === 0
+      ? [
+          toolPart(
+            index,
+            11,
+            "question",
+            { questions: [{ question: "Use generated fixture?" }, { question: "Keep same row shape?" }] },
+            120,
+          ),
+        ]
+      : []),
+    ...(index % 17 === 0
+      ? [toolPart(index, 12, "task", { description: "Inspect generated fixture", subagent_type: "explore" }, 160)]
+      : []),
+  ]
+  return [user, assistantMessage(targetID, index, user.info.id, parts)]
+}
+
+const targetMessages = Array.from({ length: 72 }, (_, index) => turn(index)).flat()
+const sourceMessages = Array.from({ length: 12 }, (_, index) => [
+  userMessage(sourceID, index + 1000, 120),
+  assistantMessage(sourceID, index + 1000, id("msg_user", index + 1000), [textPart(index + 1000, 0, 240)]),
+]).flat()
+
+function renderable(part: MessagePart) {
+  if (part.type === "tool" && part.tool === "todowrite") return false
+  if (part.type === "text") return !!part.text.trim()
+  if (part.type === "reasoning") return !!part.text.trim()
+  return part.type !== "step-start" && part.type !== "step-finish" && part.type !== "patch"
+}
+
+function orderedParts(message: Message) {
+  return message.parts.slice().sort((a, b) => a.id.localeCompare(b.id))
+}
+
+export const fixture = {
+  directory,
+  project: {
+    id: projectID,
+    worktree: directory,
+    vcs: "git",
+    name: "smoke-project",
+    time: { created: 1700000000000, updated: 1700000000000 },
+    sandboxes: [],
+  },
+  provider: {
+    all: [
+      {
+        id: "opencode",
+        name: "OpenCode",
+        models: { "claude-opus-4-6": { id: "claude-opus-4-6", name: "Claude Opus 4.6", limit: { context: 200_000 } } },
+      },
+    ],
+    connected: ["opencode"],
+    default: { providerID: "opencode", modelID: "claude-opus-4-6" },
+  },
+  sessions: [
+    {
+      id: sourceID,
+      slug: "source",
+      projectID,
+      directory,
+      title: "Uncommitted changes inquiry",
+      version: "dev",
+      time: { created: 1700000000000, updated: 1700000000000 },
+    },
+    {
+      id: targetID,
+      slug: "target",
+      projectID,
+      directory,
+      title: "Example Game: sample jump movement & sample physics analysis",
+      version: "dev",
+      time: { created: 1700000001000, updated: 1700000001000 },
+    },
+  ],
+  sourceID,
+  targetID,
+  messages: { [sourceID]: sourceMessages, [targetID]: targetMessages },
+  expected: {
+    sourceTitle: "Uncommitted changes inquiry",
+    targetTitle: "Example Game: sample jump movement & sample physics analysis",
+    sourceMessageIDs: sourceMessages
+      .filter((message) => message.info.role === "user")
+      .map((message) => message.info.id),
+    targetMessageIDs: targetMessages
+      .filter((message) => message.info.role === "user")
+      .map((message) => message.info.id),
+    targetPartIDs: targetMessages.flatMap((message) =>
+      orderedParts(message)
+        .filter(renderable)
+        .map((part) => part.id),
+    ),
+  },
+}
+
+export function pageMessages(sessionID: string, limit: number, before?: string) {
+  const messages = fixture.messages[sessionID as keyof typeof fixture.messages] ?? []
+  const end = before
+    ? Math.max(
+        0,
+        messages.findIndex((message) => message.info.id === before),
+      )
+    : messages.length
+  const start = Math.max(0, end - limit)
+  return {
+    items: messages.slice(start, end),
+    cursor: start > 0 ? messages[start]!.info.id : undefined,
+  }
+}

packages/app/e2e/performance/timeline/timeline-test-helpers.ts

@@ -0,0 +1,67 @@
+import type { Page } from "@playwright/test"
+import { base64Encode } from "@opencode-ai/core/util/encode"
+import { mockOpenCodeServer } from "../../utils/mock-server"
+import { fixture } from "./session-timeline-stress.fixture"
+
+export async function installTimelineSettings(page: Page) {
+  await page.addInitScript(() => {
+    localStorage.setItem(
+      "settings.v3",
+      JSON.stringify({
+        general: {
+          editToolPartsExpanded: true,
+          shellToolPartsExpanded: true,
+          showReasoningSummaries: true,
+          showSessionProgressBar: true,
+        },
+      }),
+    )
+  })
+}
+
+export function mockStressTimeline(page: Page) {
+  return mockOpenCodeServer(page, {
+    sessions: fixture.sessions,
+    provider: fixture.provider,
+    directory: fixture.directory,
+    project: fixture.project,
+    pageMessages: (sessionID) => ({ items: fixture.messages[sessionID as keyof typeof fixture.messages] ?? [] }),
+  })
+}
+
+export async function installStressSessionTabs(page: Page) {
+  const server = `http://${process.env.PLAYWRIGHT_SERVER_HOST ?? "127.0.0.1"}:${process.env.PLAYWRIGHT_SERVER_PORT ?? "4096"}`
+  await page.addInitScript(
+    ({ directory, sourceID, targetID, dirBase64, server }) => {
+      localStorage.setItem(
+        "opencode.global.dat:server",
+        JSON.stringify({
+          projects: { local: [{ worktree: directory, expanded: true }] },
+          lastProject: { local: directory },
+        }),
+      )
+      localStorage.setItem(
+        "opencode.global.dat:tabs",
+        JSON.stringify(
+          [sourceID, targetID].map((sessionId) => ({
+            type: "session",
+            server,
+            dirBase64,
+            sessionId,
+          })),
+        ),
+      )
+    },
+    {
+      directory: fixture.directory,
+      sourceID: fixture.sourceID,
+      targetID: fixture.targetID,
+      dirBase64: base64Encode(fixture.directory),
+      server,
+    },
+  )
+}
+
+export function stressSessionHref(sessionID: string) {
+  return `/${base64Encode(fixture.directory)}/session/${sessionID}`
+}

packages/app/e2e/performance/unit/chrome-trace-write.test.ts

@@ -0,0 +1,15 @@
+import { expect, test } from "bun:test"
+import { mkdtemp, rm } from "node:fs/promises"
+import path from "node:path"
+import os from "node:os"
+import { prepareChromeTrace } from "../chrome-trace"
+
+test("creates the configured trace directory", async () => {
+  const root = await mkdtemp(path.join(os.tmpdir(), "opencode-trace-"))
+  try {
+    const file = await prepareChromeTrace(path.join(root, "nested", "traces"), "session/tab", false, "test")
+    expect(file).toEndWith("-session-tab-458ed9e3-test.json")
+  } finally {
+    await rm(root, { recursive: true, force: true })
+  }
+})

packages/app/e2e/performance/unit/session-tab-repaint-probe.test.ts

@@ -0,0 +1,42 @@
+import { expect, test } from "bun:test"
+import { compressCachedRepaintTrace, layoutShiftSample } from "../timeline/session-tab-repaint-probe"
+
+test("compresses repeated repaint states without losing frame samples", () => {
+  const state = {
+    root: 1,
+    scrollTop: 10,
+    scrollHeight: 20,
+    bottomErrorPx: 0,
+    last: true,
+    rows: [{ key: "row", node: 2, top: 0, bottom: 10 }],
+    mounted: 1,
+    center: "content",
+  }
+  const trace = {
+    timeOriginEpochMs: 1_000,
+    startedAtPerformanceMs: 100,
+    samples: [
+      { observedAtMs: 16, ...state, destination: ["target"], source: [] },
+      { observedAtMs: 32, ...state, destination: ["target"], source: [] },
+      { observedAtMs: 48, ...state, scrollTop: 11, destination: ["target"], source: [] },
+    ],
+    mutations: [{ observedAtMs: 20, changed: [{ type: "add", node: 2 }] }],
+    shifts: [{ occurredAtMs: 24, value: 0.1 }],
+    windowMs: 1_000,
+    running: false,
+    stop() {},
+  }
+  const compressed = compressCachedRepaintTrace(trace)
+  const samples = compressed.samples.flatMap((group) =>
+    group.observedAtMs.map((observedAtMs) => ({ observedAtMs, ...group.state })),
+  )
+
+  expect(samples).toEqual(trace.samples)
+  expect(compressed.mutations).toEqual(trace.mutations)
+  expect(compressed.shifts).toEqual(trace.shifts)
+})
+
+test("records layout shifts at occurrence time within the probe window", () => {
+  expect(layoutShiftSample({ startTime: 99, value: 0.1 }, 100)).toBeUndefined()
+  expect(layoutShiftSample({ startTime: 124, value: 0.2 }, 100)).toEqual({ occurredAtMs: 24, value: 0.2 })
+})

packages/app/e2e/performance/unit/session-tab-switch-metrics.test.ts

@@ -0,0 +1,54 @@
+import { expect, test } from "bun:test"
+import { classifySessionSwitch } from "../timeline/session-tab-switch-metrics"
+
+test("counts source and blank samples before the destination is observed", () => {
+  const result = classifySessionSwitch([
+    { observedAtMs: 16, destination: [], source: ["source"], hasVisibleRows: true, last: false },
+    { observedAtMs: 32, destination: [], source: [], hasVisibleRows: false, last: false },
+    { observedAtMs: 48, destination: ["destination"], source: [], hasVisibleRows: true, last: true, bottomErrorPx: 0 },
+    { observedAtMs: 64, destination: ["destination"], source: [], hasVisibleRows: true, last: true, bottomErrorPx: 0 },
+    { observedAtMs: 80, destination: ["destination"], source: [], hasVisibleRows: true, last: true, bottomErrorPx: 0 },
+  ])
+
+  expect(result.blankSamples).toBe(1)
+  expect(result.sourceSamples).toBe(1)
+  expect(result.unknownSamples).toBe(0)
+  expect(result.firstDestinationObservedMs).toBe(48)
+  expect(result.stableObservedMs).toBe(80)
+})
+
+test("does not classify mixed source and destination content as correct", () => {
+  const result = classifySessionSwitch([
+    {
+      observedAtMs: 16,
+      destination: ["destination"],
+      source: ["source"],
+      hasVisibleRows: true,
+      last: true,
+      bottomErrorPx: 0,
+    },
+    { observedAtMs: 32, destination: ["destination"], source: [], hasVisibleRows: true, last: true, bottomErrorPx: 0 },
+    { observedAtMs: 48, destination: ["destination"], source: [], hasVisibleRows: true, last: true, bottomErrorPx: 0 },
+    { observedAtMs: 64, destination: ["destination"], source: [], hasVisibleRows: true, last: true, bottomErrorPx: 0 },
+  ])
+
+  expect(result.firstCorrectObservedMs).toBe(32)
+  expect(result.stableObservedMs).toBe(64)
+})
+
+test("reports missing correctness without throwing", () => {
+  const result = classifySessionSwitch([
+    {
+      observedAtMs: 16,
+      destination: ["destination"],
+      source: ["source"],
+      hasVisibleRows: true,
+      last: true,
+      bottomErrorPx: 0,
+    },
+  ])
+
+  expect(result.firstDestinationObservedMs).toBe(16)
+  expect(result.firstCorrectObservedMs).toBeNull()
+  expect(result.stableObservedMs).toBeNull()
+})

packages/app/e2e/performance/unit/session-timeline-stream-probe.test.ts

@@ -0,0 +1,14 @@
+import { expect, test } from "bun:test"
+import { streamChunk } from "../timeline/session-timeline-benchmark.fixture"
+import { streamProgress } from "../timeline/session-timeline-stream-probe"
+
+test("classifies emitted stream markers using the fixture cycle", () => {
+  expect(streamProgress("before stream-17 after stream-18")).toEqual({ index: 18, phase: "boundary" })
+  expect(streamProgress("before stream-18 after stream-19")).toEqual({ index: 19, phase: "stream" })
+  expect(streamProgress("benchmark-complete stream-36")).toEqual({ index: 36, phase: "complete" })
+  expect(streamProgress("no marker")).toEqual({ index: -1, phase: "unknown" })
+})
+
+test("emits progress markers at fixture boundaries", () => {
+  expect(streamProgress(streamChunk(18, 160))).toEqual({ index: 18, phase: "boundary" })
+})

packages/app/e2e/performance/unit/session-timeline-visual-tracking.test.ts

@@ -0,0 +1,16 @@
+import { expect, test } from "bun:test"
+import { layoutShiftValue, removeVisibleRow } from "../timeline/session-timeline-stream-probe"
+
+test("excludes layout shifts before the probe window and recent input", () => {
+  expect(layoutShiftValue({ startTime: 9, value: 0.1 }, 10)).toBeUndefined()
+  expect(layoutShiftValue({ startTime: 10, value: 0.2, hadRecentInput: true }, 10)).toBeUndefined()
+  expect(layoutShiftValue({ startTime: 11, value: 0.3 }, 10)).toBe(0.3)
+})
+
+test("classifies removed rows from their last painted visibility", () => {
+  const row = {}
+  const visible = new Set([row])
+
+  expect(removeVisibleRow(visible, row)).toBe(true)
+  expect(removeVisibleRow(visible, row)).toBe(false)
+})

packages/app/e2e/smoke/session-timeline.fixture.ts

@@ -139,7 +139,7 @@ function toolPart(
       status: "completed",
       input,
       output: lorem(index * 23 + partIndex, outputLength),
-      title: tool === "bash" ? input.command : input.filePath || input.path || input.pattern || "completed",
+      title: tool === "bash" ? "Verify generated output" : input.filePath || input.path || input.pattern || "completed",
       metadata,
       time: { start: 1700000000000 + index * 10_000, end: 1700000000000 + index * 10_000 + 400 },
     },
@@ -201,7 +201,7 @@ function turn(index: number): Message[] {
       ? [toolPart(index, 8, "apply_patch", { files: [`src/generated/patch-${index}.ts`] }, 620)]
       : []),
     ...(index % 7 === 0
-      ? [toolPart(index, 4, "bash", { command: "bun typecheck" }, 620)]
+      ? [toolPart(index, 4, "bash", { command: "bun typecheck", description: "Verify generated output" }, 620)]
       : []),
     ...(index % 10 === 0 ? [toolPart(index, 9, "webfetch", { url: "https://example.com/docs/sample" }, 120)] : []),
     ...(index % 11 === 0 ? [toolPart(index, 10, "websearch", { query: "sample movement notes" }, 240)] : []),

packages/app/e2e/utils/mock-server.ts

@@ -44,7 +44,10 @@ export async function mockOpenCodeServer(page: Page, config: MockServerConfig) {
   await page.route("**/*", async (route) => {
     const url = new URL(route.request().url())
     const targetPort = process.env.PLAYWRIGHT_SERVER_PORT ?? "4096"
-    if (url.port !== targetPort) return route.fallback()
+    const appPort = new URL(
+      process.env.PLAYWRIGHT_BASE_URL ?? `http://127.0.0.1:${process.env.PLAYWRIGHT_PORT ?? "3000"}`,
+    ).port
+    if (url.port !== targetPort && url.port !== appPort) return route.fallback()
 
     const path = url.pathname
     if (path === "/global/event" || path === "/event") return sse(route, config.events?.(), config.eventRetry)
@@ -72,7 +75,8 @@ export async function mockOpenCodeServer(page: Page, config: MockServerConfig) {
       return json(route, pageData.items, pageData.cursor ? { "x-next-cursor": pageData.cursor } : undefined)
     }
 
-    return json(route, {})
+    if (url.port === targetPort && targetPort !== appPort) return json(route, {})
+    return route.fallback()
   })
 }
 

packages/app/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@opencode-ai/app",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "description": "",
   "type": "module",
   "exports": {
@@ -24,7 +24,8 @@
     "test:e2e": "playwright test",
     "test:e2e:local": "playwright test",
     "test:e2e:ui": "playwright test --ui",
-    "test:e2e:report": "playwright show-report e2e/playwright-report"
+    "test:e2e:report": "playwright show-report e2e/playwright-report",
+    "test:bench": "bun test ./e2e/performance/unit && playwright test --config e2e/performance/playwright.config.ts"
   },
   "license": "MIT",
   "devDependencies": {

packages/app/playwright.config.ts

@@ -9,6 +9,7 @@ const reuse = !process.env.CI
 const workers = Number(process.env.PLAYWRIGHT_WORKERS ?? (process.env.CI ? 5 : 0)) || undefined
 export default defineConfig({
   testDir: "./e2e",
+  testIgnore: process.env.OPENCODE_PERFORMANCE === "1" ? "performance/**/*.test.ts" : "performance/**",
   outputDir: "./e2e/test-results",
   timeout: 60_000,
   expect: {

packages/cli/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "@opencode-ai/cli",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "type": "module",
   "license": "MIT",
   "bin": {

packages/console/app/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@opencode-ai/console-app",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "type": "module",
   "license": "MIT",
   "scripts": {

packages/console/core/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "@opencode-ai/console-core",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "private": true,
   "type": "module",
   "license": "MIT",

packages/console/function/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@opencode-ai/console-function",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "$schema": "https://json.schemastore.org/package.json",
   "private": true,
   "type": "module",

packages/console/mail/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@opencode-ai/console-mail",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "dependencies": {
     "@jsx-email/all": "2.2.3",
     "@jsx-email/cli": "1.4.3",

packages/console/support/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@opencode-ai/console-support",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "type": "module",
   "license": "MIT",
   "scripts": {

packages/core/package.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "name": "@opencode-ai/core",
   "type": "module",
   "license": "MIT",

packages/core/src/account.ts

@@ -35,19 +35,19 @@ export class Org extends Schema.Class<Org>("Org")({
 
 export class AccountRepoError extends Schema.TaggedErrorClass<AccountRepoError>()("AccountRepoError", {
   message: Schema.String,
-  cause: Schema.optional(Schema.Defect),
+  cause: Schema.optional(Schema.Defect()),
 }) {}
 
 export class AccountServiceError extends Schema.TaggedErrorClass<AccountServiceError>()("AccountServiceError", {
   message: Schema.String,
-  cause: Schema.optional(Schema.Defect),
+  cause: Schema.optional(Schema.Defect()),
 }) {}
 
 export class AccountTransportError extends Schema.TaggedErrorClass<AccountTransportError>()("AccountTransportError", {
   method: Schema.String,
   url: Schema.String,
   description: Schema.optional(Schema.String),
-  cause: Schema.optional(Schema.Defect),
+  cause: Schema.optional(Schema.Defect()),
 }) {
   static fromHttpClientError(error: HttpClientError.TransportError): AccountTransportError {
     return new AccountTransportError({
@@ -94,7 +94,7 @@ export class PollExpired extends Schema.TaggedClass<PollExpired>()("PollExpired"
 export class PollDenied extends Schema.TaggedClass<PollDenied>()("PollDenied", {}) {}
 
 export class PollError extends Schema.TaggedClass<PollError>()("PollError", {
-  cause: Schema.Defect,
+  cause: Schema.Defect(),
 }) {}
 
 export const PollResult = Schema.Union([PollSuccess, PollPending, PollSlow, PollExpired, PollDenied, PollError])

packages/core/src/aisdk.ts

@@ -109,7 +109,7 @@ function prepareOptions(model: ModelV2.Info, pkg: string) {
 
 export class InitError extends Schema.TaggedErrorClass<InitError>()("AISDK.InitError", {
   providerID: ProviderV2.ID,
-  cause: Schema.Defect,
+  cause: Schema.Defect(),
 }) {}
 
 function initError(providerID: ProviderV2.ID) {

packages/core/src/command.ts

@@ -2,6 +2,7 @@ export * as CommandV2 from "./command"
 
 import { Context, Effect, Layer, Schema } from "effect"
 import { castDraft, type Draft } from "immer"
+import { LayerNode } from "./effect/layer-node"
 import { ModelV2 } from "./model"
 import { State } from "./state"
 
@@ -68,3 +69,4 @@ export const layer = Layer.effect(
 )
 
 export const locationLayer = layer
+export const node = LayerNode.make(layer, [])

packages/core/src/control-plane/move-session.ts

@@ -48,7 +48,7 @@ export class ResetSourceChangesError extends Schema.TaggedErrorClass<ResetSource
   {
     directory: AbsolutePath,
     message: Schema.String,
-    cause: Schema.optional(Schema.Defect),
+    cause: Schema.optional(Schema.Defect()),
   },
 ) {}
 

packages/core/src/fs-util.ts

@@ -13,7 +13,7 @@ import { filesystem } from "./effect/layer-node-platform"
 export namespace FSUtil {
   export class FileSystemError extends Schema.TaggedErrorClass<FileSystemError>()("FileSystemError", {
     method: Schema.String,
-    cause: Schema.optional(Schema.Defect),
+    cause: Schema.optional(Schema.Defect()),
   }) {}
 
   export type Error = PlatformError | FileSystemError

packages/core/src/git.ts

@@ -32,14 +32,14 @@ export class WorktreeError extends Schema.TaggedErrorClass<WorktreeError>()("Git
   message: Schema.String,
   directory: Schema.optional(AbsolutePath),
   forceRequired: Schema.optional(Schema.Boolean),
-  cause: Schema.optional(Schema.Defect),
+  cause: Schema.optional(Schema.Defect()),
 }) {}
 
 export class PatchError extends Schema.TaggedErrorClass<PatchError>()("Git.PatchError", {
   operation: Schema.Literals(["capture", "apply", "reset"]),
   directory: AbsolutePath,
   message: Schema.String,
-  cause: Schema.optional(Schema.Defect),
+  cause: Schema.optional(Schema.Defect()),
 }) {}
 
 export interface Interface {

packages/core/src/integration.ts

@@ -154,7 +154,7 @@ export class CodeRequiredError extends Schema.TaggedErrorClass<CodeRequiredError
 }) {}
 
 export class AuthorizationError extends Schema.TaggedErrorClass<AuthorizationError>()("Integration.Authorization", {
-  cause: Schema.Defect,
+  cause: Schema.Defect(),
 }) {}
 
 export type Error = CodeRequiredError | AuthorizationError

packages/core/src/npm.ts

@@ -15,7 +15,7 @@ import { NpmConfig } from "./npm-config"
 export class InstallFailedError extends Schema.TaggedErrorClass<InstallFailedError>()("NpmInstallFailedError", {
   add: Schema.Array(Schema.String).pipe(Schema.optional),
   dir: Schema.String,
-  cause: Schema.optional(Schema.Defect),
+  cause: Schema.optional(Schema.Defect()),
 }) {}
 
 export interface EntryPoint {

packages/core/src/plugin/skill.ts

@@ -23,7 +23,7 @@ export const Plugin = PluginV2.define({
           skill: new SkillV2.Info({
             name: "customize-opencode",
             description:
-              "Use ONLY when the user is editing or creating opencode's own configuration: opencode.json, opencode.jsonc, files under .opencode/, or files under ~/.config/opencode/. Also use when creating or fixing opencode agents, subagents, skills, plugins, MCP servers, or permission rules. Do not use for the user's own application code, or for any project that is not configuring opencode itself.",
+              "Use ONLY when the user is editing or creating opencode's own configuration: opencode.json, opencode.jsonc, files under .opencode/, or files under ~/.config/opencode/. Also use when creating or fixing opencode agents, subagents, commands, skills, plugins, MCP servers, or permission rules. Do not use for the user's own application code, or for any project that is not configuring opencode itself.",
             location: AbsolutePath.make("/builtin/customize-opencode.md"),
             content: CustomizeOpencodeContent,
           }),

packages/core/src/plugin/skill/customize-opencode.md

@@ -43,6 +43,8 @@ already-loaded config until then.
 | Global config                 | `~/.config/opencode/opencode.json` (NOT `~/.opencode/`)                                                                   |
 | Project agents                | `.opencode/agent/<name>.md` or `.opencode/agents/<name>.md`                                                               |
 | Global agents                 | `~/.config/opencode/agent(s)/<name>.md`                                                                                   |
+| Project commands              | `.opencode/command/<name>.md` or `.opencode/commands/<name>.md`                                                           |
+| Global commands               | `~/.config/opencode/command(s)/<name>.md`                                                                                 |
 | Project skills                | `.opencode/skill(s)/<name>/SKILL.md`                                                                                      |
 | Global skills                 | `~/.config/opencode/skill(s)/<name>/SKILL.md`                                                                             |
 | External skills (auto-loaded) | `~/.claude/skills/<name>/SKILL.md`, `~/.agents/skills/<name>/SKILL.md`                                                    |
@@ -96,7 +98,7 @@ Every field is optional.
   },
 
   "command": {
-    "deploy": { "description": "...", "prompt": "..." }
+    "deploy": { "description": "...", "template": "..." }
   },
 
   "provider": {
@@ -151,6 +153,7 @@ Shape notes worth being explicit about:
 - `skills` is an object with `paths` and/or `urls`, not an array.
 - `references` is an object keyed by alias. Each value is a local path, Git repository, or string shorthand.
 - `agent` is an object keyed by agent name, not an array.
+- `command` is an object keyed by command name, not an array.
 - `plugin` is an array of strings or `[name, options]` tuples, not an object.
 - `mcp[name].command` is an array of strings, never a single string. `type` is required.
 - `permission` is either a string action or an object keyed by tool name.
@@ -277,6 +280,31 @@ opencode ships with `build`, `plan`, `general`, `explore`. Hidden internal agent
 `compaction`, `title`, `summary`. To override a built-in's fields, define the
 same key in `agent: { <name>: { ... } }`.
 
+## Commands
+
+opencode's command loader scans for `**/*.md` inside command directories. The
+file is named after the command, and lives directly inside the `command` folder:
+
+```
+.opencode/command/deploy.md
+```
+
+Frontmatter:
+
+```markdown
+---
+description: One sentence describing what the command does.
+agent: build
+model: anthropic/claude-sonnet-4-6
+---
+
+(command body in markdown: the prompt opencode runs, with $ARGUMENTS for the user's input)
+```
+
+- `template` is the command body — everything below the frontmatter — and is required: it is the prompt opencode runs when the command is invoked. Do not also put a `template:` key in the frontmatter.
+- `$ARGUMENTS` is replaced with everything the user typed after the command; `$1`, `$2`, … pull individual positional arguments.
+- Optional: `description`, `agent`, `model`, `variant`, `subtask`.
+
 ## Plugins
 
 `plugin:` is an array. Each entry is one of:
@@ -415,8 +443,8 @@ When a user's config is broken and opencode won't start, these env vars help:
   exact shape, or the field is not covered in this skill, fetch
   `https://opencode.ai/config.json` and read the schema rather than guessing.
 - Preserve `$schema` and any existing fields the user did not ask to change.
-- For agent, skill, and plugin definitions, prefer creating new files in the
-  correct location over inlining everything in `opencode.json`.
+- For agent, command, skill, and plugin definitions, prefer creating new files
+  in the correct location over inlining everything in `opencode.json`.
 - If the user's existing config is malformed, point them at the env-var escape
   hatches above so they can edit from inside opencode without breaking their
   session.

packages/core/src/process.ts

@@ -9,7 +9,7 @@ export class AppProcessError extends Schema.TaggedErrorClass<AppProcessError>()(
   command: Schema.String,
   exitCode: Schema.optional(Schema.Number),
   stderr: Schema.optional(Schema.String),
-  cause: Schema.optional(Schema.Defect),
+  cause: Schema.optional(Schema.Defect()),
 }) {}
 
 export interface RunOptions {

packages/core/src/ripgrep.ts

@@ -42,7 +42,7 @@ type RawMatchData = (typeof RawMatch.Type)["data"]
 
 export class Error extends Schema.TaggedErrorClass<Error>()("Ripgrep.Error", {
   message: Schema.String,
-  cause: Schema.optional(Schema.Defect),
+  cause: Schema.optional(Schema.Defect()),
 }) {}
 
 export class InvalidPatternError extends Schema.TaggedErrorClass<InvalidPatternError>()("Ripgrep.InvalidPatternError", {

packages/core/src/session/runner/index.ts

@@ -1,7 +1,7 @@
 export * as SessionRunner from "./index"
 
 import type { LLMError } from "@opencode-ai/llm"
-import { Context, Effect, Schema } from "effect"
+import { Context, Effect } from "effect"
 import { SessionSchema } from "../schema"
 import type { ContextSnapshotDecodeError, MessageDecodeError } from "../error"
 import { SessionRunnerModel } from "./model"
@@ -9,20 +9,11 @@ import type { SystemContext } from "../../system-context/index"
 import type { SessionContextEpoch } from "../context-epoch"
 import type { ToolOutputStore } from "../../tool-output-store"
 
-export class StepLimitExceededError extends Schema.TaggedErrorClass<StepLimitExceededError>()(
-  "SessionRunner.StepLimitExceededError",
-  {
-    sessionID: SessionSchema.ID,
-    limit: Schema.Int,
-  },
-) {}
-
 export type RunError =
   | LLMError
   | SessionRunnerModel.Error
   | MessageDecodeError
   | ContextSnapshotDecodeError
-  | StepLimitExceededError
   | SystemContext.InitializationBlocked
   | SessionContextEpoch.AgentReplacementBlocked
   | ToolOutputStore.Error

packages/core/src/session/runner/llm.ts

@@ -3,6 +3,7 @@ import {
   LLMClient,
   LLMError,
   LLMEvent,
+  Message,
   SystemPart,
   isContextOverflowFailure,
   type ProviderErrorEvent,
@@ -29,10 +30,11 @@ import { SessionHistory } from "../history"
 import { SessionInput } from "../input"
 import { SessionSchema } from "../schema"
 import { SessionStore } from "../store"
-import { type RunError, Service, StepLimitExceededError } from "./index"
+import { type RunError, Service } from "./index"
 import { SessionRunnerModel } from "./model"
 import { createLLMEventPublisher } from "./publish-llm-event"
 import { toLLMMessages } from "./to-llm-message"
+import { MAX_STEPS_PROMPT } from "./max-steps"
 
 /**
  * Runs one durable coding-agent Session until it settles.
@@ -45,7 +47,7 @@ import { toLLMMessages } from "./to-llm-message"
  *   - [ ] Replace local ownership with durable multi-node ownership when clustered.
  *   - [ ] Mark busy, retrying, idle, interrupted, or terminal-failure status durably.
  *   - [ ] Honor interruption and reject stale work after runtime attachment replacement.
- *   - [x] Bound model steps.
+ *   - [x] Honor optional agent step limits.
  *   - [ ] Bound provider retries and repeated identical tool calls.
  *
  * - Runtime context assembly
@@ -80,13 +82,10 @@ import { toLLMMessages } from "./to-llm-message"
  * Durable activity recovery remains a separate future slice with an explicit retry policy.
  *
  * The current slice loads V2 history, translates it, resolves a model through a core service, and persists one
- * provider turn. Registry definitions are advertised, local tool calls are settled durably, and a
- * bounded explicit loop starts the next provider turn after local settlement.
+ * provider turn. Registry definitions are advertised, local tool calls are settled durably, and an
+ * explicit loop starts the next provider turn after local settlement. Configured agent step limits bound the loop.
  */
 
-// QUESTION: Did this exist previously, or did we add this limit? Does it make sense?
-const MAX_STEPS = 25
-
 export const layer = Layer.effect(
   Service,
   Effect.gen(function* () {
@@ -175,6 +174,7 @@ export const layer = Layer.effect(
     const runTurnAttempt = Effect.fn("SessionRunner.runTurn")(function* (
       sessionID: SessionSchema.ID,
       promotion: SessionInput.Delivery | undefined,
+      step: number,
       recoverOverflow?: typeof compaction.compactAfterOverflow,
     ) {
       const session = yield* getSession(sessionID)
@@ -214,7 +214,8 @@ export const layer = Layer.effect(
       const model = yield* models.resolve(session)
       const entries = yield* SessionHistory.entriesForRunner(db, session.id, system.baselineSeq)
       const context = entries.map((entry) => entry.message)
-      const toolMaterialization = yield* tools.materialize(agent.info?.permissions)
+      const isLastStep = agent.info?.steps !== undefined && step >= agent.info.steps
+      const toolMaterialization = isLastStep ? undefined : yield* tools.materialize(agent.info?.permissions)
       const promptCacheKey = /^ses_[0-9a-f]{64}$/.test(session.id) ? session.id.slice(4) : session.id
       const request = LLM.request({
         model,
@@ -222,8 +223,9 @@ export const layer = Layer.effect(
         system: [agent.info?.system, system.baseline]
           .filter((part): part is string => part !== undefined && part.length > 0)
           .map(SystemPart.make),
-        messages: toLLMMessages(context, model),
-        tools: toolMaterialization.definitions,
+        messages: [...toLLMMessages(context, model), ...(isLastStep ? [Message.assistant(MAX_STEPS_PROMPT)] : [])],
+        tools: toolMaterialization?.definitions ?? [],
+        toolChoice: isLastStep ? "none" : undefined,
       })
       if (yield* compaction.compactIfNeeded({ sessionID: session.id, entries, model, request }))
         return yield* Effect.die(rebuildPreparedTurn())
@@ -254,6 +256,10 @@ export const layer = Layer.effect(
             }
             yield* publish(event)
             if (event.type !== "tool-call" || event.providerExecuted) return
+            if (!toolMaterialization) {
+              yield* withPublication(publisher.failUnsettledTools("Tools are disabled after the maximum agent steps"))
+              return
+            }
             needsContinuation = true
             const assistantMessageID = yield* publisher.assistantMessageID(event.id)
             yield* Effect.uninterruptibleMask((restore) =>
@@ -340,31 +346,32 @@ export const layer = Layer.effect(
     type RunTurn = (
       sessionID: SessionSchema.ID,
       promotion: SessionInput.Delivery | undefined,
+      step: number,
     ) => Effect.Effect<boolean, RunError>
 
-    const runAfterOverflowCompaction: RunTurn = Effect.fnUntraced(function* (sessionID, promotion) {
-      return yield* runTurnAttempt(sessionID, promotion).pipe(
+    const runAfterOverflowCompaction: RunTurn = Effect.fnUntraced(function* (sessionID, promotion, step) {
+      return yield* runTurnAttempt(sessionID, promotion, step).pipe(
         Effect.catchDefect(
           Effect.fnUntraced(function* (defect) {
             if (!(defect instanceof TurnTransitionError)) return yield* Effect.die(defect)
             if (defect.transition._tag === "ContinueAfterOverflowCompaction")
               return yield* Effect.die("Post-compaction provider attempt cannot recover another overflow")
             yield* Effect.yieldNow
-            return yield* runAfterOverflowCompaction(sessionID, defect.transition.promotion)
+            return yield* runAfterOverflowCompaction(sessionID, defect.transition.promotion, step)
           }),
         ),
       )
     })
 
-    const runTurn: RunTurn = Effect.fnUntraced(function* (sessionID, promotion) {
-      return yield* runTurnAttempt(sessionID, promotion, compaction.compactAfterOverflow).pipe(
+    const runTurn: RunTurn = Effect.fnUntraced(function* (sessionID, promotion, step) {
+      return yield* runTurnAttempt(sessionID, promotion, step, compaction.compactAfterOverflow).pipe(
         Effect.catchDefect(
           Effect.fnUntraced(function* (defect) {
             if (!(defect instanceof TurnTransitionError)) return yield* Effect.die(defect)
             yield* Effect.yieldNow
             if (defect.transition._tag === "ContinueAfterOverflowCompaction")
-              return yield* runAfterOverflowCompaction(sessionID, undefined)
-            return yield* runTurn(sessionID, defect.transition.promotion)
+              return yield* runAfterOverflowCompaction(sessionID, undefined, step)
+            return yield* runTurn(sessionID, defect.transition.promotion, step)
           }),
         ),
       )
@@ -382,14 +389,11 @@ export const layer = Layer.effect(
       let openActivity = input.force === true || hasSteer || hasQueue
       while (openActivity) {
         let needsContinuation = true
-        for (let step = 0; step < MAX_STEPS; step++) {
-          needsContinuation = yield* runTurn(input.sessionID, promotion)
+        for (let step = 1; needsContinuation; step++) {
+          needsContinuation = yield* runTurn(input.sessionID, promotion, step)
           promotion = "steer"
           if (!needsContinuation) needsContinuation = yield* SessionInput.hasPending(db, input.sessionID, "steer")
-          if (!needsContinuation) break
         }
-        if (needsContinuation)
-          return yield* new StepLimitExceededError({ sessionID: input.sessionID, limit: MAX_STEPS })
         openActivity = yield* SessionInput.hasPending(db, input.sessionID, "queue")
         promotion = openActivity ? "queue" : undefined
       }

packages/core/src/session/runner/max-steps.ts

@@ -1,4 +1,4 @@
-CRITICAL - MAXIMUM STEPS REACHED
+export const MAX_STEPS_PROMPT = `CRITICAL - MAXIMUM STEPS REACHED
 
 The maximum number of steps allowed for this task has been reached. Tools are disabled until next user input. Respond with text only.
 
@@ -13,4 +13,4 @@ Response must include:
 - List of any remaining tasks that were not completed
 - Recommendations for what should be done next
 
-Any attempt to use tools is a critical violation. Respond with text ONLY.
+Any attempt to use tools is a critical violation. Respond with text ONLY.`

packages/core/src/tool-output-store.ts

@@ -28,7 +28,7 @@ export interface BoundResult {
 
 export class StorageError extends Schema.TaggedErrorClass<StorageError>()("ToolOutputStore.StorageError", {
   operation: Schema.Literals(["encode", "write"]),
-  cause: Schema.Defect,
+  cause: Schema.Defect(),
 }) {}
 
 export type Error = StorageError

packages/core/src/tool/bash.ts

@@ -28,6 +28,9 @@ export const Input = Schema.Struct({
     .annotate({
       description: `Timeout in milliseconds. Defaults to ${DEFAULT_TIMEOUT_MS} and may not exceed ${MAX_TIMEOUT_MS}.`,
     }),
+  description: Schema.String.pipe(Schema.optional).annotate({
+    description: "Concise description of the command's purpose",
+  }),
 })
 
 const Output = Schema.Struct({

packages/core/src/util/effect-flock.ts

@@ -24,7 +24,7 @@ export namespace EffectFlock {
 
   class ReleaseError extends Schema.TaggedErrorClass<ReleaseError>()("ReleaseError", {
     detail: Schema.String,
-    cause: Schema.optional(Schema.Defect),
+    cause: Schema.optional(Schema.Defect()),
   }) {
     override get message() {
       return this.detail

packages/core/test/config/command.test.ts

@@ -1,10 +1,11 @@
 import fs from "fs/promises"
 import path from "path"
 import { describe, expect } from "bun:test"
-import { Effect, Layer, Schema } from "effect"
+import { Effect, Schema } from "effect"
 import { CommandV2 } from "@opencode-ai/core/command"
 import { Config } from "@opencode-ai/core/config"
 import { ConfigCommandPlugin } from "@opencode-ai/core/config/plugin/command"
+import { LayerNode } from "@opencode-ai/core/effect/layer-node"
 import { FSUtil } from "@opencode-ai/core/fs-util"
 import { ModelV2 } from "@opencode-ai/core/model"
 import { ProviderV2 } from "@opencode-ai/core/provider"
@@ -12,7 +13,7 @@ import { AbsolutePath } from "@opencode-ai/core/schema"
 import { tmpdir } from "../fixture/tmpdir"
 import { testEffect } from "../lib/effect"
 
-const it = testEffect(Layer.mergeAll(CommandV2.locationLayer, FSUtil.defaultLayer))
+const it = testEffect(LayerNode.buildLayer(LayerNode.group([CommandV2.node, FSUtil.node])))
 const decode = Schema.decodeUnknownSync(Config.Info)
 
 describe("ConfigCommandPlugin.Plugin", () => {

packages/core/test/session-runner.test.ts

@@ -704,7 +704,7 @@ describe("SessionRunnerLLM", () => {
       yield* events.publish(SessionEvent.Moved, {
         sessionID,
         timestamp: DateTime.makeUnsafe(1),
-        location: { directory: AbsolutePath.make("/moved") },
+        location: Location.Ref.make({ directory: AbsolutePath.make("/moved") }),
       })
       expect(
         yield* db
@@ -762,7 +762,7 @@ describe("SessionRunnerLLM", () => {
           .publish(SessionEvent.Moved, {
             sessionID,
             timestamp: DateTime.makeUnsafe(1),
-            location: { directory: AbsolutePath.make("/moved") },
+            location: Location.Ref.make({ directory: AbsolutePath.make("/moved") }),
           })
           .pipe(Effect.asVoid)
       })
@@ -1461,6 +1461,7 @@ describe("SessionRunnerLLM", () => {
       })
 
       requests.length = 0
+      executions.length = 0
       responses = [
         fragmentFixture("text", "text-summary-2", ["## Goal\n- Preserve the updated task"]).completeEvents,
         fragmentFixture("text", "text-final-2", ["Continued again"]).completeEvents,
@@ -3177,7 +3178,7 @@ describe("SessionRunnerLLM", () => {
     }),
   )
 
-  it.effect("fails after the bounded number of local tool continuation steps", () =>
+  it.effect("continues past 25 local tool steps when the agent has no step limit", () =>
     Effect.gen(function* () {
       yield* setup
       const session = yield* SessionV2.Service
@@ -3188,62 +3189,10 @@ describe("SessionRunnerLLM", () => {
       executions.length = 0
       streamGate = undefined
       streamStarted = undefined
-      responses = Array.from({ length: 25 }, (_, index) => [
-        LLMEvent.stepStart({ index: 0 }),
-        LLMEvent.toolCall({ id: `call-echo-${index}`, name: "echo", input: { text: `${index}` } }),
-        LLMEvent.stepFinish({ index: 0, reason: "tool-calls" }),
-        LLMEvent.finish({ reason: "tool-calls" }),
-      ])
-
-      const failure = yield* session.resume(sessionID).pipe(Effect.flip)
-
-      expect(failure).toMatchObject({ _tag: "SessionRunner.StepLimitExceededError", sessionID, limit: 25 })
-      expect(requests).toHaveLength(25)
-      expect(executions).toHaveLength(25)
-    }),
-  )
-
-  it.effect("does not restart a capped tool loop for a coalesced stale wake", () =>
-    Effect.gen(function* () {
-      yield* setup
-      const session = yield* SessionV2.Service
-      const coordinator = yield* SessionRunCoordinator.Service
-      yield* session.prompt({ sessionID, prompt: new Prompt({ text: "Loop forever" }), resume: false })
-
-      requests.length = 0
-      responses = Array.from({ length: 25 }, (_, index) => [
-        LLMEvent.stepStart({ index: 0 }),
-        LLMEvent.toolCall({ id: `call-capped-${index}`, name: "echo", input: { text: `${index}` } }),
-        LLMEvent.stepFinish({ index: 0, reason: "tool-calls" }),
-        LLMEvent.finish({ reason: "tool-calls" }),
-      ])
-      streamGate = yield* Deferred.make<void>()
-      streamStarted = yield* Deferred.make<void>()
-
-      const run = yield* session.resume(sessionID).pipe(Effect.forkChild)
-      yield* Deferred.await(streamStarted)
-      yield* coordinator.wake(sessionID)
-      yield* Deferred.succeed(streamGate, undefined)
-      expect(yield* Fiber.join(run).pipe(Effect.flip)).toMatchObject({ _tag: "SessionRunner.StepLimitExceededError" })
-      streamGate = undefined
-      streamStarted = undefined
-      yield* Effect.yieldNow
-
-      expect(requests).toHaveLength(25)
-    }),
-  )
-
-  it.effect("accepts a terminal response on the final bounded provider turn", () =>
-    Effect.gen(function* () {
-      yield* setup
-      const session = yield* SessionV2.Service
-      yield* session.prompt({ sessionID, prompt: new Prompt({ text: "Finish at the limit" }), resume: false })
-
-      requests.length = 0
       responses = [
-        ...Array.from({ length: 24 }, (_, index) => [
+        ...Array.from({ length: 25 }, (_, index) => [
           LLMEvent.stepStart({ index: 0 }),
-          LLMEvent.toolCall({ id: `call-terminal-${index}`, name: "echo", input: { text: `${index}` } }),
+          LLMEvent.toolCall({ id: `call-echo-${index}`, name: "echo", input: { text: `${index}` } }),
           LLMEvent.stepFinish({ index: 0, reason: "tool-calls" }),
           LLMEvent.finish({ reason: "tool-calls" }),
         ]),
@@ -3256,7 +3205,56 @@ describe("SessionRunnerLLM", () => {
 
       yield* session.resume(sessionID)
 
-      expect(requests).toHaveLength(25)
+      expect(requests).toHaveLength(26)
+      expect(executions).toHaveLength(25)
+    }),
+  )
+
+  it.effect("forces a text response on an agent's configured final step", () =>
+    Effect.gen(function* () {
+      yield* setup
+      const agents = yield* AgentV2.Service
+      yield* agents.update((editor) =>
+        editor.update(AgentV2.ID.make("build"), (agent) => {
+          agent.steps = 2
+        }),
+      )
+      const session = yield* SessionV2.Service
+      yield* session.prompt({ sessionID, prompt: new Prompt({ text: "Finish at the limit" }), resume: false })
+
+      requests.length = 0
+      executions.length = 0
+      responses = [
+        [
+          LLMEvent.stepStart({ index: 0 }),
+          LLMEvent.toolCall({ id: "call-terminal", name: "echo", input: { text: "done" } }),
+          LLMEvent.stepFinish({ index: 0, reason: "tool-calls" }),
+          LLMEvent.finish({ reason: "tool-calls" }),
+        ],
+        [
+          LLMEvent.stepStart({ index: 0 }),
+          LLMEvent.toolCall({ id: "call-forbidden", name: "echo", input: { text: "forbidden" } }),
+          LLMEvent.stepFinish({ index: 0, reason: "tool-calls" }),
+          LLMEvent.finish({ reason: "tool-calls" }),
+        ],
+      ]
+
+      yield* session.resume(sessionID)
+
+      expect(requests).toHaveLength(2)
+      expect(requests[0]?.toolChoice).toBeUndefined()
+      expect(requests[1]?.toolChoice).toMatchObject({ type: "none" })
+      expect(requests[1]?.tools).toEqual([])
+      expect(requests[1]?.messages.at(-1)).toMatchObject({
+        role: "assistant",
+        content: [{ type: "text", text: expect.stringContaining("MAXIMUM STEPS REACHED") }],
+      })
+      expect(executions).toEqual(["done"])
+      expect(yield* session.context(sessionID)).toMatchObject([
+        { type: "user", text: "Finish at the limit" },
+        { type: "assistant", content: [{ type: "tool", id: "call-terminal", state: { status: "completed" } }] },
+        { type: "assistant", content: [{ type: "tool", id: "call-forbidden", state: { status: "error" } }] },
+      ])
     }),
   )
 

packages/core/test/tool-bash.test.ts

@@ -134,9 +134,10 @@ describe("BashTool", () => {
             const definitions = yield* toolDefinitions(registry)
             expect(definitions.map((tool) => tool.name)).toEqual(["bash"])
             expect(definitions[0]?.inputSchema).not.toHaveProperty("properties.background")
-            expect(definitions[0]?.inputSchema).not.toHaveProperty("properties.description")
             expect(yield* toolDefinitions(registry, [{ action: "bash", resource: "*", effect: "deny" }])).toEqual([])
-            expect(yield* settleTool(registry, call({ command: "pwd" }))).toEqual({
+            expect(
+              yield* settleTool(registry, call({ command: "pwd", description: "Print working directory" })),
+            ).toEqual({
               result: { type: "text", value: "hello\n\n\nCommand exited with code 0." },
               output: {
                 structured: {

packages/desktop/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@opencode-ai/desktop",
   "private": true,
-  "version": "1.17.8",
+  "version": "1.17.9",
   "type": "module",
   "license": "MIT",
   "homepage": "https://opencode.ai",

packages/effect-drizzle-sqlite/examples/basic.ts

@@ -25,7 +25,7 @@ class Database extends Context.Service<Database, DatabaseShape>()("@opencode/exa
 
 class UserStoreError extends Schema.TaggedErrorClass<UserStoreError>()("UserStoreError", {
   message: Schema.String,
-  cause: Schema.optional(Schema.Defect),
+  cause: Schema.optional(Schema.Defect()),
 }) {}
 
 const mapStoreError = (message: string) => (cause: unknown) => new UserStoreError({ message, cause })

packages/effect-drizzle-sqlite/package.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "name": "@opencode-ai/effect-drizzle-sqlite",
   "type": "module",
   "license": "MIT",

packages/effect-sqlite-node/package.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "name": "@opencode-ai/effect-sqlite-node",
   "type": "module",
   "license": "MIT",

packages/enterprise/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@opencode-ai/enterprise",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "private": true,
   "type": "module",
   "license": "MIT",

packages/function/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@opencode-ai/function",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "$schema": "https://json.schemastore.org/package.json",
   "private": true,
   "type": "module",

packages/http-recorder/package.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "name": "@opencode-ai/http-recorder",
   "description": "Record and replay Effect HTTP client traffic with deterministic cassettes",
   "type": "module",
@@ -51,10 +51,10 @@
     "typescript": "catalog:"
   },
   "dependencies": {
-    "@effect/platform-node": "4.0.0-beta.74",
-    "@effect/platform-node-shared": "4.0.0-beta.74"
+    "@effect/platform-node": "4.0.0-beta.83",
+    "@effect/platform-node-shared": "4.0.0-beta.83"
   },
   "peerDependencies": {
-    "effect": "4.0.0-beta.74"
+    "effect": "4.0.0-beta.83"
   }
 }

packages/llm/package.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "name": "@opencode-ai/llm",
   "type": "module",
   "license": "MIT",

packages/llm/src/protocols/bedrock-converse.ts

@@ -412,6 +412,9 @@ const fromRequest = Effect.fn("BedrockConverse.fromRequest")(function* (request:
             stopSequences: generation?.stop,
           },
     toolConfig,
+    // Converse's base inferenceConfig has no topK; Anthropic/Nova accept it
+    // as a model-specific field, so it goes through additionalModelRequestFields.
+    additionalModelRequestFields: generation?.topK === undefined ? undefined : { top_k: generation.topK },
   }
 })
 

packages/llm/src/schema/errors.ts

@@ -202,6 +202,6 @@ export class LLMError extends Schema.TaggedErrorClass<LLMError>()("LLM.Error", {
  */
 export class ToolFailure extends Schema.TaggedErrorClass<ToolFailure>()("LLM.ToolFailure", {
   message: Schema.String,
-  error: Schema.optional(Schema.Defect),
+  error: Schema.optional(Schema.Defect()),
   metadata: Schema.optional(Schema.Record(Schema.String, Schema.Unknown)),
 }) {}

packages/llm/src/schema/events.ts

@@ -175,7 +175,7 @@ export const ToolError = Schema.Struct({
   id: ToolCallID,
   name: Schema.String,
   message: Schema.String,
-  error: Schema.optional(Schema.Defect),
+  error: Schema.optional(Schema.Defect()),
   providerMetadata: Schema.optional(ProviderMetadata),
 }).annotate({ identifier: "LLM.Event.ToolError" })
 export type ToolError = Schema.Schema.Type<typeof ToolError>

packages/llm/test/provider/bedrock-converse.test.ts

@@ -83,6 +83,26 @@ describe("Bedrock Converse route", () => {
     }),
   )
 
+  it.effect("passes topK through additionalModelRequestFields as top_k", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare<BedrockConverse.BedrockConverseBody>(
+        LLM.updateRequest(baseRequest, { generation: { maxTokens: 64, temperature: 0, topK: 40 } }),
+      )
+
+      // Converse's inferenceConfig has no topK; Anthropic/Nova read it from
+      // additionalModelRequestFields as top_k.
+      expect(prepared.body.inferenceConfig).toEqual({ maxTokens: 64, temperature: 0 })
+      expect(prepared.body.additionalModelRequestFields).toEqual({ top_k: 40 })
+    }),
+  )
+
+  it.effect("omits additionalModelRequestFields when topK is unset", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare<BedrockConverse.BedrockConverseBody>(baseRequest)
+      expect(prepared.body.additionalModelRequestFields).toBeUndefined()
+    }),
+  )
+
   it.effect("lowers chronological system updates to wrapped user text in order", () =>
     Effect.gen(function* () {
       const prepared = yield* LLMClient.prepare<BedrockConverse.BedrockConverseBody>(

packages/opencode/package.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "name": "opencode",
   "type": "module",
   "license": "MIT",

packages/opencode/src/account/schema.ts

@@ -33,19 +33,19 @@ export class Org extends Schema.Class<Org>("Org")({
 
 export class AccountRepoError extends Schema.TaggedErrorClass<AccountRepoError>()("AccountRepoError", {
   message: Schema.String,
-  cause: Schema.optional(Schema.Defect),
+  cause: Schema.optional(Schema.Defect()),
 }) {}
 
 export class AccountServiceError extends Schema.TaggedErrorClass<AccountServiceError>()("AccountServiceError", {
   message: Schema.String,
-  cause: Schema.optional(Schema.Defect),
+  cause: Schema.optional(Schema.Defect()),
 }) {}
 
 export class AccountTransportError extends Schema.TaggedErrorClass<AccountTransportError>()("AccountTransportError", {
   method: Schema.String,
   url: Schema.String,
   description: Schema.optional(Schema.String),
-  cause: Schema.optional(Schema.Defect),
+  cause: Schema.optional(Schema.Defect()),
 }) {
   static fromHttpClientError(error: HttpClientError.TransportError): AccountTransportError {
     return new AccountTransportError({
@@ -92,7 +92,7 @@ export class PollExpired extends Schema.TaggedClass<PollExpired>()("PollExpired"
 export class PollDenied extends Schema.TaggedClass<PollDenied>()("PollDenied", {}) {}
 
 export class PollError extends Schema.TaggedClass<PollError>()("PollError", {
-  cause: Schema.Defect,
+  cause: Schema.Defect(),
 }) {}
 
 export const PollResult = Schema.Union([PollSuccess, PollPending, PollSlow, PollExpired, PollDenied, PollError])

packages/opencode/src/acp/tool.ts

@@ -266,7 +266,7 @@ export function shellOutputSnapshot(state: { readonly metadata?: unknown }) {
 // For shell tools, surface the actual command as the title so it stays visible
 // before output lands; non-shell tools keep their model-provided title.
 function toolTitle(toolName: string, input: ToolInput, fallback: string | undefined) {
-  if (isShell(toolName)) return shellCommand(input) ?? fallback ?? toolName
+  if (isShell(toolName)) return shellCommand(input) ?? stringValue(input.description) ?? fallback ?? toolName
   return fallback || toolName
 }
 

packages/opencode/src/auth/index.ts

@@ -37,7 +37,7 @@ export type Info = Schema.Schema.Type<typeof Info>
 
 export class AuthError extends Schema.TaggedErrorClass<AuthError>()("AuthError", {
   message: Schema.String,
-  cause: Schema.optional(Schema.Defect),
+  cause: Schema.optional(Schema.Defect()),
 }) {}
 
 export interface Interface {

packages/opencode/src/cli/cmd/run/tool.ts

@@ -623,18 +623,20 @@ function snapQuestion(p: ToolProps<typeof QuestionTool>): ToolSnapshot {
 
 function scrollBashStart(p: ToolProps<typeof BashTool>): string {
   const cmd = p.input.command ?? ""
+  const desc = p.input.description || "Shell"
   const wd = p.input.workdir ?? ""
-  const formatted = wd && wd !== "." ? toolPath(wd) : ""
-  const dir = formatted === "." ? "" : formatted
-  if (cmd && !dir) {
+  const dir = wd && wd !== "." ? toolPath(wd) : ""
+  if (cmd && desc === "Shell" && !dir) {
     return `$ ${cmd}`
   }
 
+  const title = dir && !desc.includes(dir) ? `${desc} in ${dir}` : desc
+
   if (!cmd) {
-    return dir ? `# Running in ${dir}` : ""
+    return `# ${title}`
   }
 
-  return `# Running in ${dir}\n$ ${cmd}`
+  return `# ${title}\n$ ${cmd}`
 }
 
 function scrollBashProgress(p: ToolProps<typeof BashTool>): string {
@@ -966,10 +968,11 @@ function permList(p: ToolPermissionProps): ToolPermissionInfo {
 }
 
 function permBash(p: ToolPermissionProps<typeof BashTool>): ToolPermissionInfo {
+  const title = p.input.description || "Shell command"
   const cmd = p.input.command || ""
   return {
     icon: "#",
-    title: "Shell command",
+    title,
     lines: cmd ? [`$ ${cmd}`] : p.patterns.map((item) => `- ${item}`),
   }
 }

packages/opencode/src/control-plane/workspace.ts

@@ -131,7 +131,7 @@ export class SyncTimeoutError extends Schema.TaggedErrorClass<SyncTimeoutError>(
 
 export class SyncAbortedError extends Schema.TaggedErrorClass<SyncAbortedError>()("WorkspaceSyncAbortedError", {
   message: Schema.String,
-  cause: Schema.optional(Schema.Defect),
+  cause: Schema.optional(Schema.Defect()),
 }) {}
 
 type CreateError = Auth.AuthError

packages/opencode/src/lsp/client.ts

@@ -28,7 +28,7 @@ export type Diagnostic = VSCodeDiagnostic
 
 export class InitializeError extends Schema.TaggedErrorClass<InitializeError>()("LSPInitializeError", {
   serverID: Schema.String,
-  cause: Schema.optional(Schema.Defect),
+  cause: Schema.optional(Schema.Defect()),
 }) {}
 
 type DocumentDiagnosticReport = {

packages/opencode/src/provider/provider.ts

@@ -1076,7 +1076,7 @@ export class ModelNotFoundError extends Schema.TaggedErrorClass<ModelNotFoundErr
   providerID: ProviderV2.ID,
   modelID: ModelV2.ID,
   suggestions: Schema.optional(Schema.Array(Schema.String)),
-  cause: Schema.optional(Schema.Defect),
+  cause: Schema.optional(Schema.Defect()),
 }) {
   static isInstance(input: unknown): input is ModelNotFoundError {
     return input instanceof ModelNotFoundError
@@ -1085,7 +1085,7 @@ export class ModelNotFoundError extends Schema.TaggedErrorClass<ModelNotFoundErr
 
 export class InitError extends Schema.TaggedErrorClass<InitError>()("ProviderInitError", {
   providerID: ProviderV2.ID,
-  cause: Schema.optional(Schema.Defect),
+  cause: Schema.optional(Schema.Defect()),
 }) {
   static isInstance(input: unknown): input is InitError {
     return input instanceof InitError

packages/opencode/src/provider/transform.ts

@@ -218,7 +218,7 @@ function normalizeMessages(
   if (
     model.providerID === "mistral" ||
     model.api.id.toLowerCase().includes("mistral") ||
-    model.api.id.toLocaleLowerCase().includes("devstral")
+    model.api.id.toLowerCase().includes("devstral")
   ) {
     const scrub = (id: string) => {
       return id
@@ -666,6 +666,9 @@ export function variants(model: Provider.Model): Record<string, Record<string, a
   if (!model.capabilities.reasoning) return {}
 
   const id = model.id.toLowerCase()
+  const glm52 = ["glm-5.2", "glm-5-2", "glm-5p2"].some(
+    (name) => id.includes(name) || model.api.id.toLowerCase().includes(name),
+  )
   if (
     model.api.id.toLowerCase().includes("minimax-m3") &&
     ["@ai-sdk/anthropic", "@ai-sdk/openai-compatible"].includes(model.api.npm)
@@ -677,13 +680,32 @@ export function variants(model: Provider.Model): Record<string, Record<string, a
   }
   const adaptiveThinkingOmitted = anthropicOmitsThinking(model.api.id)
   const adaptiveEfforts = anthropicAdaptiveEfforts(model.api.id)
+  if (glm52 && model.api.npm === "@openrouter/ai-sdk-provider") {
+    // OpenRouter maps xhigh to GLM-5.2's native max effort.
+    return {
+      high: { reasoning: { effort: "high" } },
+      xhigh: { reasoning: { effort: "xhigh" } },
+    }
+  }
+  if (glm52 && model.api.npm === "@ai-sdk/openai-compatible") {
+    return {
+      high: { reasoningEffort: "high" },
+      max: { reasoningEffort: "max" },
+    }
+  }
+  if (glm52 && model.api.npm === "@ai-sdk/anthropic") {
+    return {
+      high: { effort: "high" },
+      max: { effort: "max" },
+    }
+  }
   if (
     id.includes("deepseek-chat") ||
     id.includes("deepseek-reasoner") ||
     id.includes("deepseek-r1") ||
     id.includes("deepseek-v3") ||
     id.includes("minimax") ||
-    id.includes("glm") ||
+    (id.includes("glm") && !glm52) ||
     id.includes("kimi") ||
     id.includes("k2p") ||
     id.includes("qwen") ||

packages/opencode/src/session/message-v2.ts

@@ -22,6 +22,7 @@ import {
 import { NamedError } from "@opencode-ai/core/util/error"
 import { APICallError, convertToModelMessages, LoadAPIKeyError, type ModelMessage, type UIMessage } from "ai"
 import { Database } from "@opencode-ai/core/database/database"
+import { LayerNode } from "@opencode-ai/core/effect/layer-node"
 import { NotFoundError } from "@/storage/storage"
 import { and } from "drizzle-orm"
 import { desc } from "drizzle-orm"
@@ -38,6 +39,8 @@ import type { SystemError } from "bun"
 import type { Provider } from "@/provider/provider"
 import { Effect, Schema } from "effect"
 
+export const node = LayerNode.group([Database.node])
+
 /** Error shape thrown by Bun's fetch() when gzip/br decompression fails mid-stream */
 interface FetchDecompressionError extends Error {
   code: "ZlibError"

packages/opencode/src/session/prompt.ts

@@ -16,7 +16,7 @@ import { SessionCompaction } from "./compaction"
 import { SystemPrompt } from "./system"
 import { Instruction } from "./instruction"
 import { Plugin } from "../plugin"
-import MAX_STEPS from "../session/prompt/max-steps.txt"
+import { MAX_STEPS_PROMPT } from "@opencode-ai/core/session/runner/max-steps"
 import { ToolRegistry } from "@/tool/registry"
 import { MCP } from "../mcp"
 import { LSP } from "@/lsp/lsp"
@@ -542,7 +542,7 @@ export const layer = Layer.effect(
                   time: { ...part.state.time, end: completed },
                   input: part.state.input,
                   title: "",
-                  metadata: { output },
+                  metadata: { output, description: "" },
                   output,
                 }
                 yield* sessions.updatePart(part)
@@ -569,7 +569,7 @@ export const layer = Layer.effect(
                 Effect.gen(function* () {
                   output += chunk
                   if (part.state.status === "running") {
-                    part.state.metadata = { output }
+                    part.state.metadata = { output, description: "" }
                     yield* sessions.updatePart(part)
                   }
                 }),
@@ -1304,24 +1304,6 @@ export const layer = Layer.effect(
             if (step === 1)
               yield* summary.summarize({ sessionID, messageID: lastUser.id }).pipe(Effect.ignore, Effect.forkIn(scope))
 
-            if (step > 1 && lastFinished) {
-              for (const m of msgs) {
-                if (m.info.role !== "user" || m.info.id <= lastFinished.id) continue
-                for (const p of m.parts) {
-                  if (p.type !== "text" || p.ignored || p.synthetic) continue
-                  if (!p.text.trim()) continue
-                  p.text = [
-                    "<system-reminder>",
-                    "The user sent the following message:",
-                    p.text,
-                    "",
-                    "Please address this message and continue with your tasks.",
-                    "</system-reminder>",
-                  ].join("\n")
-                }
-              }
-            }
-
             yield* plugin.trigger("experimental.chat.messages.transform", {}, { messages: msgs })
 
             const [skills, env, instructions, modelMsgs] = yield* Effect.all([
@@ -1340,7 +1322,10 @@ export const layer = Layer.effect(
               sessionID,
               parentSessionID: session.parentID,
               system,
-              messages: [...modelMsgs, ...(isLastStep ? [{ role: "assistant" as const, content: MAX_STEPS }] : [])],
+              messages: [
+                ...modelMsgs,
+                ...(isLastStep ? [{ role: "assistant" as const, content: MAX_STEPS_PROMPT }] : []),
+              ],
               tools,
               model,
               toolChoice: format.type === "json_schema" ? "required" : undefined,

packages/opencode/src/tool/shell.ts

@@ -263,7 +263,7 @@ const parse = Effect.fn("ShellTool.parse")(function* (command: string, ps: boole
 const ask = Effect.fn("ShellTool.ask")(function* (
   ctx: Tool.Context,
   scan: Scan,
-  input: { command: string },
+  input: { command: string; description: string },
 ) {
   if (scan.dirs.size > 0) {
     const directories = Array.from(scan.dirs)
@@ -277,6 +277,7 @@ const ask = Effect.fn("ShellTool.ask")(function* (
       always: globs,
       metadata: {
         command: input.command,
+        description: input.description,
         directories,
         patterns: globs,
       },
@@ -290,6 +291,7 @@ const ask = Effect.fn("ShellTool.ask")(function* (
     always: Array.from(scan.always),
     metadata: {
       command: input.command,
+      description: input.description,
     },
   })
 })
@@ -436,6 +438,7 @@ export const ShellTool = Tool.define(
         cwd: string
         env: NodeJS.ProcessEnv
         timeout: number
+        description: string
       },
       ctx: Tool.Context,
     ) {
@@ -479,6 +482,7 @@ export const ShellTool = Tool.define(
       yield* ctx.metadata({
         metadata: {
           output: "",
+          description: input.description,
         },
       })
 
@@ -519,6 +523,7 @@ export const ShellTool = Tool.define(
                       ctx.metadata({
                         metadata: {
                           output: last,
+                          description: input.description,
                         },
                       }),
                     ),
@@ -529,6 +534,7 @@ export const ShellTool = Tool.define(
               return ctx.metadata({
                 metadata: {
                   output: last,
+                  description: input.description,
                 },
               })
             }),
@@ -587,10 +593,11 @@ export const ShellTool = Tool.define(
         output += "\n\n<shell_metadata>\n" + meta.join("\n") + "\n</shell_metadata>"
       }
       return {
-        title: input.command,
+        title: input.description,
         metadata: {
           output: last || preview(output),
           exit: code,
+          description: input.description,
           truncated: cut,
           ...(cut && file ? { outputPath: file } : {}),
         },
@@ -639,6 +646,7 @@ export const ShellTool = Tool.define(
                   cwd,
                   env: yield* shellEnv(ctx, cwd),
                   timeout,
+                  description: params.description,
                 },
                 ctx,
               )

packages/opencode/src/tool/shell/prompt.ts

@@ -7,22 +7,30 @@ import { ShellID } from "./id"
 const PS = new Set(["powershell", "pwsh"])
 const CMD = new Set(["cmd"])
 
+const descriptions = {
+  bash: "Clear, concise description of what this command does in 5-10 words. Examples:\nInput: ls\nOutput: Lists files in current directory\n\nInput: git status\nOutput: Shows working tree status\n\nInput: npm install\nOutput: Installs package dependencies\n\nInput: mkdir foo\nOutput: Creates directory 'foo'",
+  powershell:
+    'Clear, concise description of what this command does in 5-10 words. Examples:\nInput: Get-ChildItem -LiteralPath "."\nOutput: Lists current directory\n\nInput: git status\nOutput: Shows working tree status\n\nInput: npm install\nOutput: Installs package dependencies\n\nInput: New-Item -ItemType Directory -Path "tmp"\nOutput: Creates directory tmp',
+  cmd: 'Clear, concise description of what this command does in 5-10 words. Examples:\nInput: dir\nOutput: Lists current directory\n\nInput: if exist "package.json" type "package.json"\nOutput: Prints package.json when it exists\n\nInput: mkdir tmp\nOutput: Creates directory tmp',
+}
+
 export type Limits = {
   maxLines: number
   maxBytes: number
 }
 
-export function parameterSchema() {
+export function parameterSchema(description: string) {
   return Schema.Struct({
     command: Schema.String.annotate({ description: "The command to execute" }),
     timeout: Schema.optional(PositiveInt).annotate({ description: "Optional timeout in milliseconds" }),
     workdir: Schema.optional(Schema.String).annotate({
       description: `The working directory to run the command in. Defaults to the current directory. Use this instead of 'cd' commands.`,
     }),
+    description: Schema.String.annotate({ description }),
   })
 }
 
-export const Parameters = parameterSchema()
+export const Parameters = parameterSchema(descriptions.bash)
 export type Parameters = Schema.Schema.Type<typeof Parameters>
 
 function renderPrompt(template: string, values: Record<string, string>) {
@@ -95,6 +103,7 @@ function bashCommandSection(chain: string, limits: Limits, defaultTimeoutMs: num
 Usage notes:
   - The command argument is required.
   - You can specify an optional timeout in milliseconds. If not specified, commands will time out after ${defaultTimeoutMs}ms.
+  - It is very helpful if you write a clear, concise description of what this command does in 5-10 words.
   - If the output exceeds ${limits.maxLines} lines or ${limits.maxBytes} bytes, it will be truncated and the full output will be written to a file. You can use Read with offset/limit to read specific sections or Grep to search the full content. Do NOT use \`head\`, \`tail\`, or other truncation commands to limit output; the full output will already be captured to a file for more precise searching.
 
   - Avoid using Bash with the \`find\`, \`grep\`, \`cat\`, \`head\`, \`tail\`, \`sed\`, \`awk\`, or \`echo\` commands, unless explicitly instructed or when these commands are truly necessary for the task. Instead, always prefer using the dedicated tools for these commands:
@@ -146,6 +155,7 @@ Before executing the command, please follow these steps:
 Usage notes:
   - The command argument is required.
   - You can specify an optional timeout in milliseconds. If not specified, commands will time out after ${defaultTimeoutMs}ms.
+  - It is very helpful if you write a clear, concise description of what this command does in 5-10 words.
   - If the output exceeds ${limits.maxLines} lines or ${limits.maxBytes} bytes, it will be truncated and the full output will be written to a file. You can use Read with offset/limit to read specific sections or Grep to search the full content. Do NOT use \`Select-Object -First\`, \`Select-Object -Last\`, or other truncation commands to limit output; the full output will already be captured to a file for more precise searching.
 
   - Avoid using Shell with PowerShell file/content cmdlets unless explicitly instructed or when these cmdlets are truly necessary for the task. Instead, always prefer using the dedicated tools for these commands:
@@ -195,6 +205,7 @@ Before executing the command, please follow these steps:
 Usage notes:
   - The command argument is required.
   - You can specify an optional timeout in milliseconds. If not specified, commands will time out after ${defaultTimeoutMs}ms.
+  - It is very helpful if you write a clear, concise description of what this command does in 5-10 words.
   - If the output exceeds ${limits.maxLines} lines or ${limits.maxBytes} bytes, it will be truncated and the full output will be written to a file. You can use Read with offset/limit to read specific sections or Grep to search the full content. Do NOT use \`more\` or other pagination commands to limit output; the full output will already be captured to a file for more precise searching.
 
   - Avoid using Shell with cmd.exe file/content commands unless explicitly instructed or when these commands are truly necessary for the task. Instead, always prefer using the dedicated tools for these commands:
@@ -231,6 +242,7 @@ function profile(name: string, platform: NodeJS.Platform, limits: Limits, defaul
       gitCommandRestriction: "git commands",
       createPrInstruction: "Create PR using a temporary body file so cmd.exe quoting stays simple.",
       createPrExample: `(\n  echo ## Summary\n  echo - ^<1-3 bullet points^>\n) > pr-body.txt\ngh pr create --title "the pr title" --body-file pr-body.txt`,
+      parameterDescription: descriptions.cmd,
     }
   }
   if (isPowerShell) {
@@ -252,6 +264,7 @@ function profile(name: string, platform: NodeJS.Platform, limits: Limits, defaul
 ## Summary
 - <1-3 bullet points>
 '@`,
+      parameterDescription: descriptions.powershell,
     }
   }
   return {
@@ -267,6 +280,7 @@ function profile(name: string, platform: NodeJS.Platform, limits: Limits, defaul
     createPrExample: `gh pr create --title "the pr title" --body "$(cat <<'EOF'
 ## Summary
 <1-3 bullet points>`,
+    parameterDescription: descriptions.bash,
   }
 }
 
@@ -286,7 +300,7 @@ export function render(name: string, platform: NodeJS.Platform, limits: Limits,
       createPrInstruction: selected.createPrInstruction,
       createPrExample: selected.createPrExample,
     }),
-    parameters: parameterSchema(),
+    parameters: parameterSchema(selected.parameterDescription),
   }
 }
 

packages/opencode/test/cli/run/scrollback.surface.test.ts

@@ -589,38 +589,6 @@ test("coalesces same-line tool progress into one snapshot", async () => {
   }
 })
 
-test("omits the current directory from bash titles", async () => {
-  const out = await setup()
-
-  try {
-    await out.scrollback.append(
-      toolCommit({
-        tool: "bash",
-        phase: "start",
-        toolState: "running",
-        state: {
-          status: "running",
-          input: {
-            command: "pwd",
-            workdir: process.cwd(),
-          },
-          time: { start: 1 },
-        },
-      }),
-    )
-
-    const commits = claim(out.renderer)
-    try {
-      expect(render(commits)).toContain("$ pwd")
-      expect(render(commits)).not.toContain("Running in .")
-    } finally {
-      destroy(commits)
-    }
-  } finally {
-    out.scrollback.destroy()
-  }
-})
-
 test("renders completed bash output with one blank line after the command and before the next group", async () => {
   const out = await setup()
 
@@ -647,6 +615,7 @@ test("renders completed bash output with one blank line after the command and be
           input: {
             command: "git status",
             workdir: "/tmp/demo",
+            description: "Show git status",
           },
           time: { start: 1 },
         },
@@ -664,6 +633,7 @@ test("renders completed bash output with one blank line after the command and be
           input: {
             command: "git status",
             workdir: "/tmp/demo",
+            description: "Show git status",
           },
           time: { start: 1, end: 2 },
         },
@@ -675,7 +645,6 @@ test("renders completed bash output with one blank line after the command and be
     take()
 
     const output = lines.join("\n")
-    expect(output).toContain("# Running in /tmp/demo\n$ git status")
     expect(output).toContain("$ git status\n\nOn branch demo")
     expect(output).toContain("nothing to commit, working tree clean\n\noc-run-dev ahead 1")
     expect(output).not.toContain("nothing to commit, working tree clean\n\n\noc-run-dev ahead 1")
@@ -708,6 +677,7 @@ test("inserts a spacer before the next tool after completed multiline bash outpu
           input: {
             command: "pwd; ls -la",
             workdir: "/tmp/demo",
+            description: "Lists current directory files",
           },
           time: { start: 1 },
         },
@@ -725,6 +695,7 @@ test("inserts a spacer before the next tool after completed multiline bash outpu
           input: {
             command: "pwd; ls -la",
             workdir: "/tmp/demo",
+            description: "Lists current directory files",
           },
           output: ["/tmp/demo", "pwd; ls -la", "/tmp/demo", "total 4", "", ""].join("\n"),
           title: "pwd; ls -la",
@@ -784,6 +755,7 @@ test("does not double-space before completed bash output when inline tool header
           input: {
             command: "ls",
             workdir: "src/cli/cmd/run",
+            description: "Lists files in run directory",
           },
           time: { start: 1 },
         },
@@ -833,6 +805,7 @@ test("does not double-space before completed bash output when inline tool header
           input: {
             command: "ls",
             workdir: "src/cli/cmd/run",
+            description: "Lists files in run directory",
           },
           output: ["src/cli/cmd/run", "ls", "demo.ts", "entry.body.ts", "", ""].join("\n"),
           title: "ls",

packages/opencode/test/cli/run/session-data.test.ts

@@ -435,6 +435,7 @@ describe("run session data", () => {
             title: "",
             metadata: {
               output: "/tmp/demo\n",
+              description: "",
             },
             time: { start: 1, end: 2 },
           },
@@ -489,6 +490,7 @@ describe("run session data", () => {
           title: "",
           metadata: {
             output: "/tmp/demo\n",
+            description: "",
           },
           time: { start: 1, end: 2 },
         },

packages/opencode/test/cli/run/session-replay.test.ts

@@ -238,6 +238,7 @@ function shellAssistantMessage(id: string, parentID: string): SessionMessages[nu
           title: "",
           metadata: {
             output: "account.ts\n",
+            description: "",
           },
           time: {
             start: 200,

packages/opencode/test/git/git.test.ts

@@ -3,12 +3,13 @@ import { describe, expect } from "bun:test"
 import fs from "fs/promises"
 import path from "path"
 import { Effect } from "effect"
+import { LayerNode } from "@opencode-ai/core/effect/layer-node"
 import { Git } from "../../src/git"
 import { tmpdir } from "../fixture/fixture"
 import { testEffect } from "../lib/effect"
 
 const weird = process.platform === "win32" ? "space file.txt" : "tab\tfile.txt"
-const it = testEffect(Git.defaultLayer)
+const it = testEffect(LayerNode.buildLayer(Git.node))
 
 const scopedTmpdir = (options?: Parameters<typeof tmpdir>[0]) =>
   Effect.acquireRelease(

packages/opencode/test/provider/transform.test.ts

@@ -2895,6 +2895,102 @@ describe("ProviderTransform.variants", () => {
     expect(result).toEqual({})
   })
 
+  test("glm-5.2 returns native effort variants for openai-compatible providers", () => {
+    const model = createMockModel({
+      id: "zhipuai/glm-5.2",
+      providerID: "zhipuai",
+      api: {
+        id: "glm-5.2",
+        url: "https://open.bigmodel.cn/api/paas/v4",
+        npm: "@ai-sdk/openai-compatible",
+      },
+    })
+    expect(ProviderTransform.variants(model)).toEqual({
+      high: { reasoningEffort: "high" },
+      max: { reasoningEffort: "max" },
+    })
+  })
+
+  test("recognizes GLM-5.2 provider model IDs", () => {
+    for (const id of ["accounts/fireworks/models/glm-5p2", "zai-org-glm-5-2", "umans-glm-5.2"]) {
+      const model = createMockModel({
+        id: `test/${id}`,
+        api: {
+          id,
+          url: "https://api.test.com",
+          npm: "@ai-sdk/openai-compatible",
+        },
+      })
+      expect(ProviderTransform.variants(model)).toEqual({
+        high: { reasoningEffort: "high" },
+        max: { reasoningEffort: "max" },
+      })
+    }
+  })
+
+  test("recognizes GLM-5.2 from the API ID when the configured model ID is an alias", () => {
+    const model = createMockModel({
+      id: "custom/my-glm",
+      api: {
+        id: "accounts/fireworks/models/glm-5p2",
+        url: "https://api.fireworks.ai/inference/v1",
+        npm: "@ai-sdk/openai-compatible",
+      },
+    })
+    expect(ProviderTransform.variants(model)).toEqual({
+      high: { reasoningEffort: "high" },
+      max: { reasoningEffort: "max" },
+    })
+  })
+
+  test("glm-5.2 returns openrouter effort variants for openrouter", () => {
+    const model = createMockModel({
+      id: "openrouter/z-ai/glm-5.2",
+      providerID: "openrouter",
+      api: {
+        id: "z-ai/glm-5.2",
+        url: "https://openrouter.ai/api/v1",
+        npm: "@openrouter/ai-sdk-provider",
+      },
+    })
+    expect(ProviderTransform.variants(model)).toEqual({
+      high: { reasoning: { effort: "high" } },
+      xhigh: { reasoning: { effort: "xhigh" } },
+    })
+  })
+
+  test("glm-5.2 returns effort variants for anthropic-compatible providers", () => {
+    const model = createMockModel({
+      id: "zai-coding-plan/glm-5.2",
+      providerID: "zai-coding-plan",
+      api: {
+        id: "glm-5.2",
+        url: "https://api.z.ai/api/anthropic",
+        npm: "@ai-sdk/anthropic",
+      },
+    })
+    expect(ProviderTransform.variants(model)).toEqual({
+      high: { effort: "high" },
+      max: { effort: "max" },
+    })
+  })
+
+  test("glm-5.2 falls back to provider defaults for other packages", () => {
+    const model = createMockModel({
+      id: "test/glm-5.2",
+      api: {
+        id: "glm-5.2",
+        url: "https://api.test.com",
+        npm: "@ai-sdk/amazon-bedrock",
+      },
+    })
+    expect(ProviderTransform.variants(model)).toEqual({
+      low: { reasoningConfig: { type: "enabled", maxReasoningEffort: "low" } },
+      medium: { reasoningConfig: { type: "enabled", maxReasoningEffort: "medium" } },
+      high: { reasoningConfig: { type: "enabled", maxReasoningEffort: "high" } },
+    })
+  })
+
   test("mistral models with reasoning support return variants", () => {
     const model = createMockModel({
       id: "mistral/mistral-small-latest",

packages/opencode/test/session/messages-pagination.test.ts

@@ -1,7 +1,8 @@
 import { describe, expect, test } from "bun:test"
 import { SessionV1 } from "@opencode-ai/core/v1/session"
-import { Database } from "@opencode-ai/core/database/database"
-import { Effect, Layer, Option } from "effect"
+import { LayerNode } from "@opencode-ai/core/effect/layer-node"
+import { SessionProjector } from "@opencode-ai/core/session/projector"
+import { Effect, Option } from "effect"
 import { Session as SessionNs } from "@/session/session"
 import { MessageV2 } from "../../src/session/message-v2"
 import { MessageID, PartID, type SessionID } from "../../src/session/schema"
@@ -11,7 +12,7 @@ import { testEffect } from "../lib/effect"
 import { ProviderV2 } from "@opencode-ai/core/provider"
 import { ModelV2 } from "@opencode-ai/core/model"
 
-const it = testEffect(Layer.mergeAll(SessionNs.defaultLayer, Database.defaultLayer))
+const it = testEffect(LayerNode.buildLayer(LayerNode.group([SessionNs.node, MessageV2.node, SessionProjector.node])))
 
 const withSession = <A, E, R>(
   fn: (input: { session: SessionNs.Interface; sessionID: SessionID }) => Effect.Effect<A, E, R>,

packages/opencode/test/session/prompt.test.ts

@@ -1346,7 +1346,9 @@ it.instance(
 
       const inputs = yield* llm.inputs
       expect(inputs).toHaveLength(2)
-      expect(JSON.stringify(inputs.at(-1)?.messages)).toContain("second")
+      const messages = inputs.at(-1)?.messages
+      if (!Array.isArray(messages)) throw new Error("expected LLM messages")
+      expect(messages.at(-1)).toEqual({ role: "user", content: "second" })
     }),
   3_000,
 )
@@ -1803,6 +1805,7 @@ unix(
       yield* llm.tool("bash", {
         command:
           'i=0; while [ "$i" -lt 4000 ]; do printf "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx %05d\\n" "$i"; i=$((i + 1)); done; printf truncation-ready; sleep 30',
+        description: "Print many lines",
         timeout: 30_000,
         workdir: path.resolve(dir),
       })

packages/opencode/test/session/retry.test.ts

@@ -3,7 +3,8 @@ import { SessionV1 } from "@opencode-ai/core/v1/session"
 import type { NamedError } from "@opencode-ai/core/util/error"
 import { APICallError } from "ai"
 import { setTimeout as sleep } from "node:timers/promises"
-import { Effect, Layer, Schedule, Schema } from "effect"
+import { Effect, Schedule, Schema } from "effect"
+import { LayerNode } from "@opencode-ai/core/effect/layer-node"
 import { CrossSpawnSpawner } from "@opencode-ai/core/cross-spawn-spawner"
 import { SessionRetry } from "../../src/session/retry"
 import { MessageV2 } from "../../src/session/message-v2"
@@ -15,7 +16,7 @@ import { ProviderV2 } from "@opencode-ai/core/provider"
 
 const providerID = ProviderV2.ID.make("test")
 const retryProvider = "test"
-const it = testEffect(Layer.mergeAll(SessionStatus.defaultLayer, CrossSpawnSpawner.defaultLayer))
+const it = testEffect(LayerNode.buildLayer(LayerNode.group([SessionStatus.node, CrossSpawnSpawner.node])))
 
 function apiError(headers?: Record<string, string>): SessionV1.APIError {
   return Schema.decodeUnknownSync(SessionV1.APIError.Schema)(

packages/opencode/test/session/snapshot-tool-race.test.ts

@@ -139,6 +139,7 @@ it.live("tool execution produces non-empty session diff (snapshot race)", () =>
       const command = `echo 'snapshot race test content' > ${path.join(dir, "race-test.txt")}`
       yield* llm.toolMatch((hit) => JSON.stringify(hit.body).includes("create the file"), "bash", {
         command,
+        description: "create test file",
       })
       yield* llm.textMatch((hit) => JSON.stringify(hit.body).includes("bash"), "done")
 

packages/opencode/test/tool/__snapshots__/parameters.test.ts.snap

@@ -24,6 +24,23 @@ exports[`tool parameters JSON Schema (wire shape) bash 1`] = `
       "description": "The command to execute",
       "type": "string",
     },
+    "description": {
+      "description": 
+"Clear, concise description of what this command does in 5-10 words. Examples:
+Input: ls
+Output: Lists files in current directory
+
+Input: git status
+Output: Shows working tree status
+
+Input: npm install
+Output: Installs package dependencies
+
+Input: mkdir foo
+Output: Creates directory 'foo'"
+,
+      "type": "string",
+    },
     "timeout": {
       "description": "Optional timeout in milliseconds",
       "exclusiveMinimum": 0,
@@ -38,6 +55,7 @@ exports[`tool parameters JSON Schema (wire shape) bash 1`] = `
   },
   "required": [
     "command",
+    "description",
   ],
   "type": "object",
 }

packages/opencode/test/tool/parameters.test.ts

@@ -106,16 +106,19 @@ describe("tool parameters", () => {
   })
 
   describe("shell", () => {
-    test("accepts command", () => {
-      expect(parse(Shell, { command: "ls" })).toEqual({ command: "ls" })
+    test("accepts minimum: command + description", () => {
+      expect(parse(Shell, { command: "ls", description: "list" })).toEqual({ command: "ls", description: "list" })
     })
     test("accepts optional timeout + workdir", () => {
-      const parsed = parse(Shell, { command: "ls", timeout: 5000, workdir: "/tmp" })
+      const parsed = parse(Shell, { command: "ls", description: "list", timeout: 5000, workdir: "/tmp" })
       expect(parsed.timeout).toBe(5000)
       expect(parsed.workdir).toBe("/tmp")
     })
+    test("rejects missing description", () => {
+      expect(accepts(Shell, { command: "ls" })).toBe(false)
+    })
     test("rejects missing command", () => {
-      expect(accepts(Shell, {})).toBe(false)
+      expect(accepts(Shell, { description: "list" })).toBe(false)
     })
   })
 

packages/opencode/test/tool/shell.test.ts

@@ -182,6 +182,7 @@ describe("tool.shell", () => {
       Effect.gen(function* () {
         const result = yield* run({
           command: "echo test",
+          description: "Echo test message",
         })
         expect(result.metadata.exit).toBe(0)
         expect(result.metadata.output).toContain("test")
@@ -203,6 +204,7 @@ describe("tool.shell", () => {
           const result = yield* bash.execute(
             {
               command: "echo fallback",
+              description: "Echo fallback text",
             },
             ctx,
           )
@@ -225,6 +227,7 @@ describe("tool.shell permissions", () => {
           yield* run(
             {
               command: "echo hello",
+              description: "Echo hello",
             },
             capture(requests),
           )
@@ -246,6 +249,7 @@ describe("tool.shell permissions", () => {
           yield* run(
             {
               command: "echo foo && echo bar",
+              description: "Echo twice",
             },
             capture(requests),
           )
@@ -269,6 +273,7 @@ describe("tool.shell permissions", () => {
             yield* run(
               {
                 command: "Write-Host foo; if ($?) { Write-Host bar }",
+                description: "Check PowerShell conditional",
               },
               capture(requests),
             )
@@ -298,6 +303,7 @@ describe("tool.shell permissions", () => {
                 yield* fail(
                   {
                     command: "Remove-Item -Recurse tmp",
+                    description: "Remove a temp directory",
                   },
                   capture(requests, err),
                 ),
@@ -325,6 +331,7 @@ describe("tool.shell permissions", () => {
           yield* fail(
             {
               command: `cat ${file}`,
+              description: "Read wildcard path",
             },
             capture(requests, err),
           ),
@@ -352,6 +359,7 @@ describe("tool.shell permissions", () => {
                 yield* run(
                   {
                     command: `echo $(cat "${file}")`,
+                    description: "Read nested bash file",
                   },
                   capture(requests),
                 )
@@ -381,6 +389,7 @@ describe("tool.shell permissions", () => {
                 yield* fail(
                   {
                     command: `Copy-Item -PassThru "${process.env.WINDIR!.replaceAll("\\", "/")}/win.ini" ./out`,
+                    description: "Copy Windows ini",
                   },
                   capture(requests, err),
                 ),
@@ -406,6 +415,7 @@ describe("tool.shell permissions", () => {
               yield* run(
                 {
                   command: `Write-Output $(Get-Content ${file})`,
+                  description: "Read nested PowerShell file",
                 },
                 capture(requests),
               )
@@ -436,6 +446,7 @@ describe("tool.shell permissions", () => {
                   yield* fail(
                     {
                       command: 'Get-Content "C:../outside.txt"',
+                      description: "Read drive-relative file",
                     },
                     capture(requests, err),
                   ),
@@ -463,6 +474,7 @@ describe("tool.shell permissions", () => {
                 yield* fail(
                   {
                     command: 'Get-Content "$HOME/.ssh/config"',
+                    description: "Read home config",
                   },
                   capture(requests, err),
                 ),
@@ -491,6 +503,7 @@ describe("tool.shell permissions", () => {
                   yield* fail(
                     {
                       command: 'Get-Content "$PWD/../outside.txt"',
+                      description: "Read pwd-relative file",
                     },
                     capture(requests, err),
                   ),
@@ -518,6 +531,7 @@ describe("tool.shell permissions", () => {
                 yield* fail(
                   {
                     command: 'Get-Content "$PSHOME/outside.txt"',
+                    description: "Read pshome file",
                   },
                   capture(requests, err),
                 ),
@@ -553,6 +567,7 @@ describe("tool.shell permissions", () => {
                     yield* fail(
                       {
                         command: `Get-Content -Path "${root}$env:${key}\\Windows\\win.ini"`,
+                        description: "Read Windows ini with missing env",
                       },
                       capture(requests, err),
                     ),
@@ -583,6 +598,7 @@ describe("tool.shell permissions", () => {
               yield* run(
                 {
                   command: "Get-Content $env:WINDIR/win.ini",
+                  description: "Read Windows ini from env",
                 },
                 capture(requests),
               )
@@ -610,6 +626,7 @@ describe("tool.shell permissions", () => {
                 yield* fail(
                   {
                     command: `Get-Content -Path FileSystem::${process.env.WINDIR!.replaceAll("\\", "/")}/win.ini`,
+                    description: "Read Windows ini from FileSystem provider",
                   },
                   capture(requests, err),
                 ),
@@ -638,6 +655,7 @@ describe("tool.shell permissions", () => {
                 yield* fail(
                   {
                     command: "Get-Content ${env:WINDIR}/win.ini",
+                    description: "Read Windows ini from braced env",
                   },
                   capture(requests, err),
                 ),
@@ -664,6 +682,7 @@ describe("tool.shell permissions", () => {
               yield* run(
                 {
                   command: "Set-Location C:/Windows",
+                  description: "Change location",
                 },
                 capture(requests),
               )
@@ -691,6 +710,7 @@ describe("tool.shell permissions", () => {
               yield* run(
                 {
                   command: "Write-Output ('a' * 3)",
+                  description: "Write repeated text",
                 },
                 capture(requests),
               )
@@ -716,6 +736,7 @@ describe("tool.shell permissions", () => {
             yield* run(
               {
                 command: `TYPE "${path.join(process.env.WINDIR!, "win.ini")}"`,
+                description: "Read Windows ini with cmd",
               },
               capture(requests),
             )
@@ -740,6 +761,7 @@ describe("tool.shell permissions", () => {
             yield* fail(
               {
                 command: "cd ../",
+                description: "Change to parent directory",
               },
               capture(requests, err),
             ),
@@ -764,6 +786,7 @@ describe("tool.shell permissions", () => {
               {
                 command: "echo ok",
                 workdir: os.tmpdir(),
+                description: "Echo from temp dir",
               },
               capture(requests, err),
             ),
@@ -794,6 +817,7 @@ describe("tool.shell permissions", () => {
                   {
                     command: "echo ok",
                     workdir: dir,
+                    description: "Echo from external dir",
                   },
                   capture(requests, err),
                 ),
@@ -826,6 +850,7 @@ describe("tool.shell permissions", () => {
                   {
                     command: "echo ok",
                     workdir: "/tmp",
+                    description: "Echo from Git Bash tmp",
                   },
                   capture(requests, err),
                 ),
@@ -853,6 +878,7 @@ describe("tool.shell permissions", () => {
                 yield* fail(
                   {
                     command: "cat /tmp/opencode-does-not-exist",
+                    description: "Read Git Bash tmp file",
                   },
                   capture(requests, err),
                 ),
@@ -884,6 +910,7 @@ describe("tool.shell permissions", () => {
             yield* fail(
               {
                 command: `cat ${filepath}`,
+                description: "Read external file",
               },
               capture(requests, err),
             ),
@@ -895,6 +922,7 @@ describe("tool.shell permissions", () => {
           expect(extDirReq!.always).toContain(expected)
           expect(extDirReq!.metadata).toMatchObject({
             command: `cat ${filepath}`,
+            description: "Read external file",
             directories: [outerTmp],
             patterns: [expected],
           })
@@ -914,6 +942,7 @@ describe("tool.shell permissions", () => {
           yield* run(
             {
               command: `rm -rf ${path.join(tmp, "nested")}`,
+              description: "Remove nested dir",
             },
             capture(requests),
           )
@@ -934,6 +963,7 @@ describe("tool.shell permissions", () => {
           yield* run(
             {
               command: "git log --oneline -5",
+              description: "Git log",
             },
             capture(requests),
           )
@@ -955,6 +985,7 @@ describe("tool.shell permissions", () => {
           yield* run(
             {
               command: "cd .",
+              description: "Stay in current directory",
             },
             capture(requests),
           )
@@ -975,7 +1006,7 @@ describe("tool.shell permissions", () => {
           const requests: Array<Omit<PermissionV1.Request, "id" | "sessionID" | "tool">> = []
           expect(
             yield* fail(
-              { command: "echo test > output.txt" },
+              { command: "echo test > output.txt", description: "Redirect test output" },
               capture(requests, err),
             ),
           ).toMatchObject({ message: err.message })
@@ -994,7 +1025,7 @@ describe("tool.shell permissions", () => {
         tmp,
         Effect.gen(function* () {
           const requests: Array<Omit<PermissionV1.Request, "id" | "sessionID" | "tool">> = []
-          yield* run({ command: "ls -la" }, capture(requests))
+          yield* run({ command: "ls -la", description: "List" }, capture(requests))
           const bashReq = requests.find((r) => r.permission === "bash")
           expect(bashReq).toBeDefined()
           expect(bashReq!.always[0]).toBe("ls *")
@@ -1016,6 +1047,7 @@ describe("tool.shell abort", () => {
           const res = yield* run(
             {
               command: `echo before && sleep 30`,
+              description: "Long running command",
             },
             {
               ...ctx,
@@ -1046,6 +1078,7 @@ describe("tool.shell abort", () => {
         Effect.gen(function* () {
           const result = yield* run({
             command: `sleep 60`,
+            description: "Timeout test",
             timeout: 500,
           })
           expect(result.output).toContain("shell tool terminated command after exceeding timeout")
@@ -1066,6 +1099,7 @@ describe("tool.shell abort", () => {
           const result = yield* tool.execute(
             {
               command: `sleep 60`,
+              description: "Default timeout test",
             },
             ctx,
           )
@@ -1082,6 +1116,7 @@ describe("tool.shell abort", () => {
         Effect.gen(function* () {
           const result = yield* run({
             command: `echo stdout_msg && echo stderr_msg >&2`,
+            description: "Stderr test",
           })
           expect(result.output).toContain("stdout_msg")
           expect(result.output).toContain("stderr_msg")
@@ -1097,6 +1132,7 @@ describe("tool.shell abort", () => {
       Effect.gen(function* () {
         const result = yield* run({
           command: `exit 42`,
+          description: "Non-zero exit",
         })
         expect(result.metadata.exit).toBe(42)
       }),
@@ -1111,6 +1147,7 @@ describe("tool.shell abort", () => {
         const result = yield* run(
           {
             command: `echo first && sleep 0.1 && echo second`,
+            description: "Streaming test",
           },
           {
             ...ctx,
@@ -1137,6 +1174,7 @@ describe("tool.shell truncation", () => {
         const lineCount = Truncate.MAX_LINES + 500
         const result = yield* run({
           command: fill("lines", lineCount),
+          description: "Generate lines exceeding limit",
         })
         mustTruncate(result)
         expect(result.output).toMatch(/\.\.\.output truncated\.\.\./)
@@ -1152,6 +1190,7 @@ describe("tool.shell truncation", () => {
         const byteCount = Truncate.MAX_BYTES + 10000
         const result = yield* run({
           command: fill("bytes", byteCount),
+          description: "Generate bytes exceeding limit",
         })
         mustTruncate(result)
         expect(result.output).toMatch(/\.\.\.output truncated\.\.\./)
@@ -1166,6 +1205,7 @@ describe("tool.shell truncation", () => {
       Effect.gen(function* () {
         const result = yield* run({
           command: fill("lines", 1),
+          description: "Generate one line",
         })
         expect((result.metadata as { truncated?: boolean }).truncated).toBe(false)
         expect(result.output).toContain("1")
@@ -1180,6 +1220,7 @@ describe("tool.shell truncation", () => {
         const lineCount = Truncate.MAX_LINES + 100
         const result = yield* run({
           command: fill("lines", lineCount),
+          description: "Generate lines for file check",
         })
         mustTruncate(result)
 

packages/plugin/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "@opencode-ai/plugin",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "type": "module",
   "license": "MIT",
   "scripts": {

packages/sdk/js/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "@opencode-ai/sdk",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "type": "module",
   "license": "MIT",
   "scripts": {

packages/server/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "@opencode-ai/server",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "private": true,
   "type": "module",
   "license": "MIT",

packages/slack/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@opencode-ai/slack",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "type": "module",
   "license": "MIT",
   "scripts": {

packages/stats/app/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "@opencode-ai/stats-app",
-  "version": "1.17.8",
+  "version": "1.17.9",
   "private": true,
   "type": "module",
   "license": "MIT",