fix(ai): keep chat reasoning in one lifecycle

fix(ai): finish chat streams at done sentinel (#45850 )
fix(ai): ignore late converse tool deltas (#45847 )
2026-08-28 12:36:15 +00:00 · 2026-08-28 01:46:25 -05:00 · 2026-08-28 00:53:53 -05:00 · 2026-08-28 00:38:01 -05:00 · 2026-08-28 00:21:17 -05:00 · 2026-08-28 00:19:15 -05:00
148 changed files with 4330 additions and 3180 deletions
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Preserve provider metadata on assistant text when replaying conversation history through AI SDK providers.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/theme": patch
---
-
-Use the unread accent color by default for question and permission status indicators, while preserving explicit theme overrides.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Align the built-in review and system prompts with available documentation and code-search tools and the current Plan mode reminder.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Preserve prompt cache prefixes when sessions move between locations with unchanged instructions.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Correct the compaction prompt to point existing summaries at the conversation history that follows them.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Correct the published Newtype documentation to recommend `Schema.decodeUnknownSync` for schema-based synchronous decoding.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Fix OpenCode Console device authorization URLs when the server returns an origin-rooted verification path.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Propagate fatal Git ignore-check errors during index refresh so best-effort snapshot capture returns unavailable instead of treating the check as having no matches.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Prompt and synthetic inbox ID reuse is now idempotent: reusing an ID within the same Session succeeds and returns the first admission, ignoring the retried payload, metadata, and delivery mode. Previously reuse with a differing payload failed with a conflict. Cross-Session and cross-type reuse still fail, and control items keep their operation-specific conflict behavior.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": major
---
-
-Treat MCP as a word in current Core namespace exports: rename `MCP` to `Mcp`, `MCPClient` to `McpClient`, `MCPStdio` to `McpStdio`, `MCPOAuth` to `McpOAuth`, `ConfigMCPPlugin` to `ConfigMcpPlugin`, and `MCPCodeModeExclusionPlugin` to `McpCodeModeExclusionPlugin`. Direct consumers must update their imports. Module paths, Schema contracts, runtime service keys, error tags, and behavior are unchanged.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Rename the write, patch, and question tool formatting helpers from `toModelOutput` to `toModelContent` to match the result field they populate. Direct imports of these helpers must use the new name; generated content and declared machine output are unchanged.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": minor
---
-
-Rename ModelResolver.supported to ModelResolver.hasPackage. Consumers of the old export must update the name; the predicate remains Boolean(model.package), checking only whether a catalog model declares a provider package, not whether it can be loaded. Default-model selection behavior is unchanged.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Nested AGENTS.md instructions are re-injected after compaction. Previously the in-memory dedup claim outlived the synthetic message that compaction dropped from model-visible history, so nested instructions were silently lost for the rest of the process lifetime. The claim now only guards in-flight loads; the synthetic message metadata in durable history is the sole lasting ledger, so any history truncation (compaction, revert) self-heals on the next read in that subtree.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Forward plugin Session interrupt options so continuation requests reach the Session service.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/plugin": patch
---
-
-Derive Promise plugin API request and response conversion from the canonical protocol schemas.
@@ -1,8 +0,0 @@
---
-"@opencode-ai/core": minor
-"@opencode-ai/schema": minor
-"@opencode-ai/protocol": minor
-"@opencode-ai/client": minor
---
-
-Remove the unused question request API and use session forms for question tool interactions.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Wake idle sessions when recovering background shell outcomes after a server restart. Admit shell outcomes before resuming background child sessions, while preserving restart retry budgets and completion-driven parent notifications.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Include both paths of renamed files in new snapshot change lists so undo restores the original file instead of only deleting the renamed file.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Preserve explicit function tool strictness in Copilot Responses requests.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Apply shared Session model-request preparation to transient generation.
@@ -1,9 +0,0 @@
---
-"@opencode-ai/core": minor
-"@opencode-ai/schema": minor
-"@opencode-ai/protocol": minor
-"@opencode-ai/client": minor
---
-
-Add an opt-in portable shell permission scanner. Opaque commands use normal shell authorization without inferring
-external directories, while the default tree-sitter path remains unchanged.
@@ -1,10 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Make the experimental portable shell scanner authoritative, with no Tree-sitter
-fallback. Scan common Bash and PowerShell control flow, heredocs, functions,
-expressions, quoting, and substitutions natively. Preserve existing redirect and
-declaration permission matching, and make PowerShell saved approvals cover the
-original command spelling. Parser failures remain visible without changing the
-permission engine. The default Tree-sitter path is unchanged.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Use parent directory names for SKILL.md IDs so individually downloaded skills do not overwrite each other.
@@ -1,8 +0,0 @@
---
-"@opencode-ai/core": patch
-"@opencode-ai/app": patch
---
-
-Keep project labels stable when opening multiple clones of the same repository, while still refreshing the canonical path when its directory is renamed or removed.
-
-Worktree setup scripts receive the selected source directory as `OPENCODE_WORKTREE_BASE` rather than another clone's shared project path.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Simplify interrupt continuation: the steer-scoped resume decision now lives in SessionExecution as a post-cleanup inbox check, and the run coordinator drops its continuation state machine. Wakes arriving during cancellation cleanup now restart a normal full drain, and interrupting an idle session with continue now resumes pending steering input. Recovery-applied moves now end with the same full wake as inbox-admitted moves, retrying any stranded inbox work at the new location. Interrupting with continue now also resumes a next-in-line control item: between-turn manual compaction and moves run under any drain scope, while queued prompts remain parked.
@@ -1,6 +0,0 @@
---
-"@opencode-ai/client": patch
-"@opencode-ai/plugin": patch
---
-
-Add form reply and cancellation operations that reconcile terminal forms in the local TUI projection.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Title generation and compaction summaries now build their model requests through the shared session request boundary, gaining unsupported-media filtering and image bounds while explicitly opting out of session context hooks: plugins that shape the agent conversation do not observe title or compaction requests. Title requests gain the fork-aware session prompt cache key, and compaction summaries in forked sessions reuse the fork root's prompt cache key instead of the fork's own.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Keep Google Vertex catalog settings serializable during model projection.
@@ -1,6 +0,0 @@
---
-"@opencode-ai/plugin": patch
-"@opencode-ai/core": patch
---
-
-Add transport-neutral Session model request hooks and provider-scoped hook registration so eligible OpenAI Responses requests can prefer WebSocket without bypassing HTTP-only middleware.
@@ -185,7 +185,7 @@
        "solid-js": "catalog:",
      },
      "peerDependencies": {
-        "effect": "4.0.0-rc.111",
+        "effect": "4.0.0-rc.112",
        "solid-js": ">=1.9.0",
      },
      "optionalPeers": [
@@ -506,7 +506,7 @@
      "name": "@opencode-ai/http-recorder",
      "version": "1.18.15",
      "dependencies": {
-        "@effect/platform-node-shared": "4.0.0-rc.111",
+        "@effect/platform-node-shared": "4.0.0-rc.112",
      },
      "devDependencies": {
        "@effect/platform-node": "catalog:",
@@ -1062,10 +1062,10 @@
  "catalog": {
    "@cloudflare/workers-types": "4.20251008.0",
    "@corvu/drawer": "0.2.4",
-    "@effect/opentelemetry": "4.0.0-rc.111",
-    "@effect/platform-node": "4.0.0-rc.111",
-    "@effect/platform-node-shared": "4.0.0-rc.111",
-    "@effect/sql-sqlite-bun": "4.0.0-rc.111",
+    "@effect/opentelemetry": "4.0.0-rc.112",
+    "@effect/platform-node": "4.0.0-rc.112",
+    "@effect/platform-node-shared": "4.0.0-rc.112",
+    "@effect/sql-sqlite-bun": "4.0.0-rc.112",
    "@hono/standard-validator": "0.2.0",
    "@hono/zod-validator": "0.4.2",
    "@kobalte/core": "0.13.13",
@@ -1105,7 +1105,7 @@
    "dompurify": "3.4.14",
    "drizzle-kit": "1.0.0-rc.5-ab785fc",
    "drizzle-orm": "1.0.0-rc.5-169397b",
-    "effect": "4.0.0-rc.111",
+    "effect": "4.0.0-rc.112",
    "fuzzysort": "3.1.0",
    "get-east-asian-width": "1.6.0",
    "hono": "4.10.7",
@@ -1664,13 +1664,13 @@

    "@drizzle-team/brocli": ["@drizzle-team/brocli@0.12.0", "", {}, "sha512-mlUE+rZ8CatQekLhnaiN91Iemdd+e2gFKooGlnRB3oPTL3VghLfX24dx7HrzMNeC1JrIB/0kpsfyty3f5HNfxQ=="],

-    "@effect/opentelemetry": ["@effect/opentelemetry@4.0.0-rc.111", "", { "peerDependencies": { "@opentelemetry/api": ">=1.9.0 <2.0.0", "@opentelemetry/api-logs": ">=0.203.0 <0.300.0", "@opentelemetry/resources": ">=2.0.0 <3.0.0", "@opentelemetry/sdk-logs": ">=0.203.0 <0.300.0", "@opentelemetry/sdk-metrics": ">=2.0.0 <3.0.0", "@opentelemetry/sdk-trace-base": ">=2.0.0 <3.0.0", "@opentelemetry/sdk-trace-node": ">=2.0.0 <3.0.0", "@opentelemetry/sdk-trace-web": ">=2.0.0 <3.0.0", "@opentelemetry/semantic-conventions": ">=1.33.0 <2.0.0", "effect": "^4.0.0-rc.111" }, "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-bztAYpWoipn/a4tFjECMNvtWLkf2TS+Qn23PBI+f4q5DP9cBKfV00uhX8cwEVcfAtZd+lflSbGURHa4xlSewOA=="],
+    "@effect/opentelemetry": ["@effect/opentelemetry@4.0.0-rc.112", "", { "peerDependencies": { "@opentelemetry/api": ">=1.9.0 <2.0.0", "@opentelemetry/api-logs": ">=0.203.0 <0.300.0", "@opentelemetry/resources": ">=2.0.0 <3.0.0", "@opentelemetry/sdk-logs": ">=0.203.0 <0.300.0", "@opentelemetry/sdk-metrics": ">=2.0.0 <3.0.0", "@opentelemetry/sdk-trace-base": ">=2.0.0 <3.0.0", "@opentelemetry/sdk-trace-node": ">=2.0.0 <3.0.0", "@opentelemetry/sdk-trace-web": ">=2.0.0 <3.0.0", "@opentelemetry/semantic-conventions": ">=1.33.0 <2.0.0", "effect": "^4.0.0-rc.112" }, "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-OTRv1DxTHUmnakgJ6XVM8wVgF1KgZH4UXnOemwSLUwUjXO+RCikzF8oR/rlVmOGq81KtQzj1URM4M4nchlQOuQ=="],

-    "@effect/platform-node": ["@effect/platform-node@4.0.0-rc.111", "", { "dependencies": { "@effect/platform-node-shared": "^4.0.0-rc.111", "mime": "^4.1.0", "undici": "^8.10.0" }, "peerDependencies": { "effect": "^4.0.0-rc.111", "redis": ">=5.0.0 <7.0.0" } }, "sha512-oy1i7HsOGg/5r+DuBe5+ddmnUhnXmyZFPFPXZCBdO/RQpHK3PIFe1/2UMGxZE+ngDymrSksuQTSgQLF6P+MLqw=="],
+    "@effect/platform-node": ["@effect/platform-node@4.0.0-rc.112", "", { "dependencies": { "@effect/platform-node-shared": "^4.0.0-rc.112", "mime": "^4.1.0", "undici": "^8.10.0" }, "peerDependencies": { "effect": "^4.0.0-rc.112", "redis": ">=5.0.0 <7.0.0" } }, "sha512-/BMAcdNGQQskLmI0Zoa95KfTZkr9HV9N4NSxaSrusG6GeW6Ulp9KvZ+Rlaiw8lnOt43CXjFLdfll5/k5rxL4hQ=="],

-    "@effect/platform-node-shared": ["@effect/platform-node-shared@4.0.0-rc.111", "", { "dependencies": { "@types/ws": "^8.18.1", "ws": "^8.21.3" }, "peerDependencies": { "effect": "^4.0.0-rc.111" } }, "sha512-iES0Q9vmjhaUKqeW9ceonuD45MUg/Ouk08LzRSptZ+B5qB0w9WlRjDmUz5TJmY2betNop5FRI5k4AD4mtQt3Bw=="],
+    "@effect/platform-node-shared": ["@effect/platform-node-shared@4.0.0-rc.112", "", { "dependencies": { "@types/ws": "^8.18.1", "ws": "^8.21.3" }, "peerDependencies": { "effect": "^4.0.0-rc.112" } }, "sha512-ttjz0xKamFN7vL8pNDYVwddJLjZvqKePc05djlz2VcdaKbLsnYbtMnL1rbOfHgEnIUSHGh7FkjaN4DM1Ov81sQ=="],

-    "@effect/sql-sqlite-bun": ["@effect/sql-sqlite-bun@4.0.0-rc.111", "", { "peerDependencies": { "effect": "^4.0.0-rc.111" } }, "sha512-u5HqWLYISTH5ydsCr45nOGmkspmAeNzK4q+plMrJntDoG8sQttwizC4akGfbQDgoSxyYfyBzi3YyVW/NvhvSQQ=="],
+    "@effect/sql-sqlite-bun": ["@effect/sql-sqlite-bun@4.0.0-rc.112", "", { "peerDependencies": { "effect": "^4.0.0-rc.112" } }, "sha512-EqR8pWZo3VzedRvP6qo5HcfqNmFvSa+sQLWQl3oBMx2KY1FCc8NYjep79wYjNkW0qABnffrPUXCMTOncd1A+5g=="],

    "@electron-internal/extract-zip": ["@electron-internal/extract-zip@1.0.5", "", {}, "sha512-+bqFCP98pLI0Tt0XQo1TmlXtwjWchISndDOxCkEcIuUgXWpBnLyRI+2DU+mesvnMMX6L1XDqYNA0lXNDHd/yiA=="],

@@ -3834,7 +3834,7 @@

    "ee-first": ["ee-first@1.1.1", "", {}, "sha512-WMwm9LhRUo+WUaRN+vRuETqG89IgZphVSNkdFgeb6sS/E4OrDIN7t48CAewSHXc6C8lefD8KKfr5vY61brQlow=="],

-    "effect": ["effect@4.0.0-rc.111", "", { "dependencies": { "@standard-schema/spec": "^1.1.0", "fast-check": "^4.9.0", "msgpackr": "^2.0.5" } }, "sha512-ASd5L58EIR0CUNueZNKKjSsyOCd+2alxOAIaTcHaqkJkPsaYSsw5Cg/cfANk5K4Jr2YsX756xvX11shzqsreWA=="],
+    "effect": ["effect@4.0.0-rc.112", "", { "dependencies": { "fast-check": "^4.9.0", "msgpackr": "^2.0.5" } }, "sha512-wXxwuh1Ywnv4cPRM3Wfa0vDwuOHnZ1TsTgHJkG9XgzND6inhBH9n1vBxhg3iIXOia/OrpmvVmd3lrD4vq6bF3A=="],

    "ejs": ["ejs@3.1.10", "", { "dependencies": { "jake": "^10.8.5" }, "bin": { "ejs": "bin/cli.js" } }, "sha512-UeJmFfOrAQS8OJWPZ4qtgHyWExa088/MtK5UEyoJGFH67cDEXkZSviOiKRCZ4Xij0zxI3JECgYs3oKx+AizQBA=="],

@@ -6316,6 +6316,10 @@

    "@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-rc.111", "", { "dependencies": { "@standard-schema/spec": "^1.1.0", "fast-check": "^4.9.0", "msgpackr": "^2.0.5" } }, "sha512-ASd5L58EIR0CUNueZNKKjSsyOCd+2alxOAIaTcHaqkJkPsaYSsw5Cg/cfANk5K4Jr2YsX756xvX11shzqsreWA=="],
+
+    "@standard-community/standard-openapi/effect": ["effect@4.0.0-rc.111", "", { "dependencies": { "@standard-schema/spec": "^1.1.0", "fast-check": "^4.9.0", "msgpackr": "^2.0.5" } }, "sha512-ASd5L58EIR0CUNueZNKKjSsyOCd+2alxOAIaTcHaqkJkPsaYSsw5Cg/cfANk5K4Jr2YsX756xvX11shzqsreWA=="],
+
    "@tailwindcss/node/lightningcss": ["lightningcss@1.32.0", "", { "dependencies": { "detect-libc": "^2.0.3" }, "optionalDependencies": { "lightningcss-android-arm64": "1.32.0", "lightningcss-darwin-arm64": "1.32.0", "lightningcss-darwin-x64": "1.32.0", "lightningcss-freebsd-x64": "1.32.0", "lightningcss-linux-arm-gnueabihf": "1.32.0", "lightningcss-linux-arm64-gnu": "1.32.0", "lightningcss-linux-arm64-musl": "1.32.0", "lightningcss-linux-x64-gnu": "1.32.0", "lightningcss-linux-x64-musl": "1.32.0", "lightningcss-win32-arm64-msvc": "1.32.0", "lightningcss-win32-x64-msvc": "1.32.0" } }, "sha512-NXYBzinNrblfraPGyrbPoD19C1h9lfI/1mzgWYvXUTe414Gz/X1FD2XBZSZM7rRTrMA8JL3OtAaGifrIKhQ5yQ=="],

    "@tailwindcss/oxide-wasm32-wasi/@emnapi/core": ["@emnapi/core@1.11.3", "", { "dependencies": { "@emnapi/wasi-threads": "1.2.3", "tslib": "^2.4.0" }, "bundled": true }, "sha512-zLpS5asjEb7lq8jYLq37N6XKaE41DIexlY1rF/z4/tIl3wo13Sqm28fRyfIsKZD+NZ8mM5RoKkpW/rBcuoSZSg=="],
@@ -6896,6 +6900,8 @@

    "@brendonovich/vite-plugin-opencode/@opencode-ai/client/@opencode-ai/schema": ["@opencode-ai/schema@0.0.0-beta-18050", "", { "dependencies": { "@standard-schema/spec": "1.1.0", "effect": "4.0.0-rc.111" } }, "sha512-/D6VXaWlytTXR3IOiMLIKuPcfp7FQNUzRPm9z3K7UBFd1Bw4q/WZksaf5RVcBGz+0YRxYMc1V4D7MFlceSgtyg=="],

+    "@brendonovich/vite-plugin-opencode/@opencode-ai/client/effect": ["effect@4.0.0-rc.111", "", { "dependencies": { "@standard-schema/spec": "^1.1.0", "fast-check": "^4.9.0", "msgpackr": "^2.0.5" } }, "sha512-ASd5L58EIR0CUNueZNKKjSsyOCd+2alxOAIaTcHaqkJkPsaYSsw5Cg/cfANk5K4Jr2YsX756xvX11shzqsreWA=="],
+
    "@bruits/satteri-wasm32-wasi/@emnapi/core/@emnapi/wasi-threads": ["@emnapi/wasi-threads@1.2.2", "", { "dependencies": { "tslib": "^2.4.0" } }, "sha512-c95qOXkHdydNKhscBTebqEC1CVAZpyqOfVfBzQ1qgzyl3gfeldUjIggDbIZgDKsHLgnsM+igH7TJ/eAasaVuMA=="],

    "@electron/asar/minimatch/brace-expansion": ["brace-expansion@1.1.18", "", { "dependencies": { "balanced-match": "^1.0.0", "concat-map": "0.0.1" } }, "sha512-Edep/X9fGqVNmzKBVsDYIOtD+z1tuezV70LBjdCst9Tqu76lsnvRiZ6oTic1n+/BIwX6QDGAO94PN4N2SADvtw=="],
@@ -1,8 +1,8 @@
 {
  "nodeModules": {
-    "x86_64-linux": "sha256-vn4haT0uuD5tCbMD2F5IuDj+/XS/U/sVQ0bk5xJCbIM=",
-    "aarch64-linux": "sha256-XUGJ6hE7xvIyT53k5uCqaF/eGU4d4tIbuVuGrHU12Fg=",
-    "aarch64-darwin": "sha256-o3Os6rO8nGVVYs1aJBJAdYQaLbDsYNtGub4Gg1gHRQU=",
-    "x86_64-darwin": "sha256-YB00nH7WmgqRXvzA+zYEbaaik/vKheu3n/vJ6Ombx9k="
+    "x86_64-linux": "sha256-EtUp4pHl9TyPtRrLGvk/X7kd2LuIxNxCpUwF5aLtzN4=",
+    "aarch64-linux": "sha256-m0j/pMZCguclR3/T9JmzCfi11YzmIvBFyR2bVhIO37Y=",
+    "aarch64-darwin": "sha256-nqefk68ZTUfNU15q1WkXaGsFzPNwOjCtMHpp6WrpNqM=",
+    "x86_64-darwin": "sha256-syD7hX62E4yCDV/wux1QKw4q/zZr24f99Y2mmzMJo6o="
  }
 }
@@ -39,10 +39,10 @@
      "packages/stats/*"
    ],
    "catalog": {
-      "@effect/opentelemetry": "4.0.0-rc.111",
-      "@effect/platform-node": "4.0.0-rc.111",
-      "@effect/platform-node-shared": "4.0.0-rc.111",
-      "@effect/sql-sqlite-bun": "4.0.0-rc.111",
+      "@effect/opentelemetry": "4.0.0-rc.112",
+      "@effect/platform-node": "4.0.0-rc.112",
+      "@effect/platform-node-shared": "4.0.0-rc.112",
+      "@effect/sql-sqlite-bun": "4.0.0-rc.112",
      "@npmcli/arborist": "9.4.0",
      "@types/bun": "1.3.13",
      "@types/cross-spawn": "6.0.6",
@@ -76,7 +76,7 @@
      "dompurify": "3.4.14",
      "drizzle-kit": "1.0.0-rc.5-ab785fc",
      "drizzle-orm": "1.0.0-rc.5-169397b",
-      "effect": "4.0.0-rc.111",
+      "effect": "4.0.0-rc.112",
      "ai": "6.0.168",
      "cross-spawn": "7.0.6",
      "hono": "4.10.7",
@@ -496,6 +496,7 @@ const mapUsage = (usage: BedrockUsageSchema | undefined, providerMetadataKey: st
 interface ParserState {
  readonly providerMetadataKey: string
  readonly tools: ToolStream.State<number>
+  readonly finishedTools: ReadonlySet<number>
  // Bedrock splits the finish into `messageStop` (carries `stopReason`) and
  // `metadata` (carries usage). Hold the terminal event in state so `onHalt`
  // can emit exactly one finish after both chunks have had a chance to arrive.
@@ -574,6 +575,7 @@ const step = (state: ParserState, event: BedrockEvent) =>

    if (event.contentBlockDelta?.delta?.toolUse) {
      const index = event.contentBlockDelta.contentBlockIndex
+      if (state.finishedTools.has(index)) return [state, []] as const
      const result = ToolStream.appendExisting(
        ADAPTER,
        state.tools,
@@ -612,6 +614,7 @@ const step = (state: ParserState, event: BedrockEvent) =>
            state.hasToolCalls,
          lifecycle,
          tools: result.tools,
+          finishedTools: resultEvents.length > 0 ? new Set([...state.finishedTools, index]) : state.finishedTools,
          reasoningSignatures: Object.fromEntries(
            Object.entries(state.reasoningSignatures).filter(([key]) => key !== String(index)),
          ),
@@ -703,6 +706,7 @@ export const protocol = Protocol.make({
    initial: (request) => ({
      providerMetadataKey: request.model.route.providerMetadataKey ?? String(request.model.provider),
      tools: ToolStream.empty<number>(),
+      finishedTools: new Set<number>(),
      pendingFinish: undefined,
      hasToolCalls: false,
      lifecycle: Lifecycle.initial(),
@@ -391,17 +391,19 @@ export interface ParserState {
  readonly name: string
  readonly providerMetadataKey: string
  readonly tools: ToolStream.State<string>
+  // Call ids stay independent of item ids, which may be omitted or reused.
+  readonly completedTools: ReadonlySet<string>
  readonly hasFunctionCall: boolean
  readonly lifecycle: Lifecycle.State
  readonly outputItems: Readonly<Record<number, string>>
-  readonly messageItems: ReadonlySet<string>
-  readonly messagePhases: Readonly<Record<string, MessagePhase | null>>
+  readonly message: { readonly id: string; readonly phase: MessagePhase | null | undefined } | undefined
  readonly reasoningItems: Readonly<Record<string, ReasoningStreamItem>>
 }

 type ReasoningSummaryStatus = "active" | "can-conclude" | "concluded"

 interface ReasoningStreamItem {
+  readonly open: boolean
  readonly encryptedContent: string | null | undefined
  // Keyed by the wire protocol's numeric `summary_index`. JS object keys coerce to
  // strings, but typing the map as `Record<number, ...>` documents intent
@@ -826,16 +828,16 @@ const TERMINAL_TYPES = new Set(["error", "response.completed", "response.incompl
 export const terminal = (event: Event) => TERMINAL_TYPES.has(event.type)

 const onOutputTextDelta = (state: ParserState, event: Event, id: string): StepResult => {
-  if (!event.delta || !state.messageItems.has(id)) return [state, NO_EVENTS]
+  if (!event.delta || state.message?.id !== id) return [state, NO_EVENTS]
  const events: LLMEvent[] = []
-  const phase = state.messagePhases[id]
+  const phase = state.message.phase
  const metadata = providerMetadata(state, { itemId: id, ...(phase === undefined ? {} : { phase }) })
  const lifecycle = Lifecycle.textStart(state.lifecycle, events, id, metadata)
  return [{ ...state, lifecycle: Lifecycle.textDelta(lifecycle, events, id, event.delta) }, events]
 }

 const onOutputTextDone = (state: ParserState, event: Event, id: string): StepResult => {
-  if (state.messageItems.has(id)) {
+  if (state.message?.id === id) {
    if (state.lifecycle.text.has(id) || event.text === undefined) return [state, NO_EVENTS]
    return onOutputTextDelta(state, { ...event, delta: event.text }, id)
  }
@@ -846,18 +848,62 @@ const onOutputTextDone = (state: ParserState, event: Event, id: string): StepRes
 export const outputItemID = (state: ParserState, event: Event) =>
  event.output_index === undefined ? event.item_id : (state.outputItems[event.output_index] ?? event.item_id)

-export const onReasoningDelta = (state: ParserState, event: Event, itemID: string): StepResult => {
+const startReasoningSummaryPart = (state: ParserState, itemID: string, index: number): StepResult => {
  const item = state.reasoningItems[itemID]
-  if (!event.delta || !item) return [state, NO_EVENTS]
-  const index = event.summary_index ?? 0
+  if (!item?.open || index === 0 || item.summaryParts[index] !== undefined) return [state, NO_EVENTS]
+
  const events: LLMEvent[] = []
+  const lifecycle = Object.entries(item.summaryParts)
+    .filter((entry) => entry[1] !== "concluded")
+    .reduce(
+      (lifecycle, entry) =>
+        Lifecycle.reasoningEnd(lifecycle, events, `${itemID}:${entry[0]}`, providerMetadata(state, { itemId: itemID })),
+      state.lifecycle,
+    )
  return [
    {
      ...state,
-      lifecycle: Lifecycle.reasoningDelta(state.lifecycle, events, `${itemID}:${index}`, event.delta),
+      lifecycle: Lifecycle.reasoningStart(
+        lifecycle,
+        events,
+        `${itemID}:${index}`,
+        providerMetadata(state, { itemId: itemID, reasoningEncryptedContent: item.encryptedContent ?? null }),
+      ),
      reasoningItems: {
        ...state.reasoningItems,
-        [itemID]: { ...item, deltaIndexes: new Set([...item.deltaIndexes, index]) },
+        [itemID]: {
+          ...item,
+          summaryParts: {
+            ...Object.fromEntries(
+              Object.entries(item.summaryParts).map((entry) =>
+                entry[1] === "concluded" ? entry : [entry[0], "concluded" as const],
+              ),
+            ),
+            [index]: "active",
+          },
+        },
+      },
+    },
+    events,
+  ]
+}
+
+export const onReasoningDelta = (state: ParserState, event: Event, itemID: string): StepResult => {
+  const item = state.reasoningItems[itemID]
+  if (!event.delta || !item?.open) return [state, NO_EVENTS]
+  const index = event.summary_index ?? 0
+  if (item.summaryParts[index] === "concluded") return [state, NO_EVENTS]
+  const [started, emitted] = startReasoningSummaryPart(state, itemID, index)
+  const current = started.reasoningItems[itemID]
+  if (!current) return [started, emitted]
+  const events: LLMEvent[] = [...emitted]
+  return [
+    {
+      ...started,
+      lifecycle: Lifecycle.reasoningDelta(started.lifecycle, events, `${itemID}:${index}`, event.delta),
+      reasoningItems: {
+        ...started.reasoningItems,
+        [itemID]: { ...current, deltaIndexes: new Set([...current.deltaIndexes, index]) },
      },
    },
    events,
@@ -869,7 +915,7 @@ export const onReasoningDelta = (state: ParserState, event: Event, itemID: strin
 // as a single delta unless that summary index already streamed one.
 export const onReasoningDone = (state: ParserState, event: Event, itemID: string): StepResult => {
  const item = state.reasoningItems[itemID]
-  if (!item || typeof event.text !== "string") return [state, NO_EVENTS]
+  if (!item?.open || typeof event.text !== "string") return [state, NO_EVENTS]
  const index = event.summary_index ?? 0
  if (item.deltaIndexes.has(index)) return [state, NO_EVENTS]
  return onReasoningDelta(state, { ...event, delta: event.text }, itemID)
@@ -878,32 +924,48 @@ export const onReasoningDone = (state: ParserState, event: Event, itemID: string
 const reasoningMetadata = (state: ParserState, item: StreamItem & { id: string }) =>
  providerMetadata(state, { itemId: item.id, reasoningEncryptedContent: item.encrypted_content ?? null })

-// Responses APIs stream reasoning items in a stable order:
+// Responses APIs normally stream reasoning items in this order:
 //   `output_item.added` (reasoning) →
 //     `reasoning_summary_part.added` (index=0) →
 //     `reasoning_summary_text.delta` →
 //     `reasoning_summary_part.done` (index=0) →
 //     (repeat for index>0) →
 //   `output_item.done` (reasoning).
-// The handlers below rely on this ordering: `onOutputItemAdded` seeds the
-// per-item entry, `onReasoningSummaryPartAdded` for `summary_index === 0`
-// short-circuits when the entry already exists, and higher-index handlers
-// fold against the same entry. Behaviour for out-of-order events is
-// best-effort, not guaranteed.
+// `onOutputItemAdded` seeds the per-item entry, while each later part start is
+// also an implicit boundary for the previous part. This keeps the common event
+// lifecycle ordered when a compatible provider omits or delays a part-done event.
 const onOutputItemAdded = (state: ParserState, event: Event): StepResult => {
  const item = event.item
  if (item?.type === "message" && item.id !== undefined) {
+    const itemID = item.id
    const phase = messagePhase(item.phase)
+    // A new message closes earlier messages, including ones that never streamed.
+    const events: LLMEvent[] = []
+    const lifecycle = [...state.lifecycle.text]
+      .filter((id) => id !== itemID)
+      .reduce((lifecycle, id) => {
+        const openPhase = state.message?.id === id ? state.message.phase : undefined
+        return Lifecycle.textEnd(
+          lifecycle,
+          events,
+          id,
+          providerMetadata(state, { itemId: id, ...(openPhase === undefined ? {} : { phase: openPhase }) }),
+        )
+      }, state.lifecycle)
    return [
      {
        ...state,
-        messageItems: new Set([...state.messageItems, item.id]),
-        messagePhases: phase === undefined ? state.messagePhases : { ...state.messagePhases, [item.id]: phase },
+        lifecycle,
+        message: {
+          id: itemID,
+          phase: phase === undefined && state.message?.id === itemID ? state.message.phase : phase,
+        },
      },
-      NO_EVENTS,
+      events,
    ]
  }
  if (item && isReasoningItem(item)) {
+    if (state.reasoningItems[item.id] !== undefined) return [state, NO_EVENTS]
    const events: LLMEvent[] = []
    return [
      {
@@ -912,6 +974,7 @@ const onOutputItemAdded = (state: ParserState, event: Event): StepResult => {
        reasoningItems: {
          ...state.reasoningItems,
          [item.id]: {
+            open: true,
            encryptedContent: item.encrypted_content,
            summaryParts: { 0: "active" },
            deltaIndexes: new Set(),
@@ -923,6 +986,8 @@ const onOutputItemAdded = (state: ParserState, event: Event): StepResult => {
  }
  if (item?.type !== "function_call" || !item.call_id) return [state, NO_EVENTS]
  const id = item.id ?? item.call_id
+  if (Object.values(state.tools).some((tool) => tool?.id === item.call_id) || state.completedTools.has(item.call_id))
+    return [state, NO_EVENTS]
  const metadata = item.id !== undefined ? providerMetadata(state, { itemId: item.id }) : undefined
  const events: LLMEvent[] = []
  const lifecycle = Lifecycle.stepStart(state.lifecycle, events)
@@ -943,55 +1008,14 @@ const onOutputItemAdded = (state: ParserState, event: Event): StepResult => {

 const onReasoningSummaryPartAdded = (state: ParserState, event: Event): StepResult => {
  if (event.item_id === undefined || event.summary_index === undefined) return [state, NO_EVENTS]
-  const item = state.reasoningItems[event.item_id]
-  if (!item) return [state, NO_EVENTS]
-  if (event.summary_index === 0) return [state, NO_EVENTS]
-
-  const events: LLMEvent[] = []
-  const closed = Object.entries(item.summaryParts)
-    .filter((entry) => entry[1] === "can-conclude")
-    .reduce(
-      (lifecycle, entry) =>
-        Lifecycle.reasoningEnd(
-          lifecycle,
-          events,
-          `${event.item_id}:${entry[0]}`,
-          providerMetadata(state, { itemId: event.item_id }),
-        ),
-      state.lifecycle,
-    )
-  return [
-    {
-      ...state,
-      lifecycle: Lifecycle.reasoningStart(
-        closed,
-        events,
-        `${event.item_id}:${event.summary_index}`,
-        providerMetadata(state, { itemId: event.item_id, reasoningEncryptedContent: item.encryptedContent ?? null }),
-      ),
-      reasoningItems: {
-        ...state.reasoningItems,
-        [event.item_id]: {
-          ...item,
-          summaryParts: {
-            ...Object.fromEntries(
-              Object.entries(item.summaryParts).map((entry) =>
-                entry[1] === "can-conclude" ? [entry[0], "concluded" as const] : entry,
-              ),
-            ),
-            [event.summary_index]: "active",
-          },
-        },
-      },
-    },
-    events,
-  ]
+  return startReasoningSummaryPart(state, event.item_id, event.summary_index)
 }

 const onReasoningSummaryPartDone = (state: ParserState, event: Event): StepResult => {
  if (event.item_id === undefined || event.summary_index === undefined) return [state, NO_EVENTS]
  const item = state.reasoningItems[event.item_id]
-  if (!item) return [state, NO_EVENTS]
+  if (!item?.open) return [state, NO_EVENTS]
+  if (item.summaryParts[event.summary_index] !== "active") return [state, NO_EVENTS]
  return [
    {
      ...state,
@@ -1047,11 +1071,8 @@ const onOutputItemDone = Effect.fn("OpenResponses.onOutputItemDone")(function* (

  if (item.type === "message" && item.id !== undefined) {
    const itemPhase = messagePhase(item.phase)
-    const phase = itemPhase === undefined ? state.messagePhases[item.id] : itemPhase
+    const phase = itemPhase === undefined && state.message?.id === item.id ? state.message.phase : itemPhase
    const events: LLMEvent[] = []
-    const messageItems = new Set(state.messageItems)
-    messageItems.delete(item.id)
-    const { [item.id]: _phase, ...messagePhases } = state.messagePhases
    return [
      {
        ...state,
@@ -1061,8 +1082,7 @@ const onOutputItemDone = Effect.fn("OpenResponses.onOutputItemDone")(function* (
          item.id,
          providerMetadata(state, { itemId: item.id, ...(phase === undefined ? {} : { phase }) }),
        ),
-        messageItems,
-        messagePhases,
+        message: state.message?.id === item.id ? undefined : state.message,
      },
      events,
    ] satisfies StepResult
@@ -1070,20 +1090,36 @@ const onOutputItemDone = Effect.fn("OpenResponses.onOutputItemDone")(function* (

  if (item.type === "function_call") {
    if (!item.call_id || !item.name) return [state, NO_EVENTS] satisfies StepResult
-    const id = item.id ?? item.call_id
-    const tools = state.tools[id]
-      ? state.tools
-      : ToolStream.start(state.tools, id, {
-          id: item.call_id,
-          name: item.name,
-          providerMetadata: item.id !== undefined ? providerMetadata(state, { itemId: item.id }) : undefined,
-        })
+    const callID = item.call_id
+    if (state.completedTools.has(callID)) return [state, NO_EVENTS] satisfies StepResult
+    const metadata = item.id !== undefined ? providerMetadata(state, { itemId: item.id }) : undefined
+    const fallback = item.id ?? callID
+    // Match the pending tool by call id so item events that disagree on
+    // whether `item.id` is present still resolve the same call.
+    const registered =
+      state.tools[fallback] !== undefined
+        ? fallback
+        : Object.keys(state.tools).find((key) => state.tools[key]?.id === callID)
+    const id = registered ?? fallback
+    const tools =
+      registered !== undefined
+        ? state.tools
+        : ToolStream.start(state.tools, id, {
+            id: callID,
+            name: item.name,
+            providerMetadata: metadata,
+          })
    const result =
      item.arguments === undefined
        ? yield* ToolStream.finish(state.id, tools, id)
        : yield* ToolStream.finishWithInput(state.id, tools, id, item.arguments)
    const events: LLMEvent[] = []
-    const resultEvents = result.events ?? []
+    const finished = result.events ?? []
+    // A done-only call never streamed a start event, so open its lifecycle here.
+    const resultEvents =
+      registered !== undefined || finished.length === 0
+        ? finished
+        : [LLMEvent.toolInputStart({ id: callID, name: item.name, providerMetadata: metadata }), ...finished]
    const lifecycle = resultEvents.length ? Lifecycle.stepStart(state.lifecycle, events) : state.lifecycle
    events.push(...resultEvents)
    return [
@@ -1094,6 +1130,7 @@ const onOutputItemDone = Effect.fn("OpenResponses.onOutputItemDone")(function* (
          resultEvents.some((event) => LLMEvent.is.toolCall(event) || LLMEvent.is.toolInputError(event)) ||
          state.hasFunctionCall,
        tools: result.tools,
+        completedTools: new Set([...state.completedTools, callID]),
      },
      events,
    ] satisfies StepResult
@@ -1104,20 +1141,49 @@ const onOutputItemDone = Effect.fn("OpenResponses.onOutputItemDone")(function* (
    const metadata = reasoningMetadata(state, item)
    const reasoningItem = state.reasoningItems[item.id]
    if (reasoningItem) {
+      if (!reasoningItem.open) return [state, NO_EVENTS] satisfies StepResult
      const lifecycle = Object.entries(reasoningItem.summaryParts)
        .filter((entry) => entry[1] === "active" || entry[1] === "can-conclude")
        .reduce(
          (lifecycle, entry) => Lifecycle.reasoningEnd(lifecycle, events, `${item.id}:${entry[0]}`, metadata),
          state.lifecycle,
        )
-      const { [item.id]: _removed, ...reasoningItems } = state.reasoningItems
-      return [{ ...state, lifecycle, reasoningItems }, events] satisfies StepResult
+      return [
+        {
+          ...state,
+          lifecycle,
+          reasoningItems: {
+            ...state.reasoningItems,
+            [item.id]: {
+              ...reasoningItem,
+              open: false,
+              encryptedContent: item.encrypted_content ?? reasoningItem.encryptedContent,
+            },
+          },
+        },
+        events,
+      ] satisfies StepResult
    }
    if (!state.lifecycle.reasoning.has(item.id)) {
      const lifecycle = Lifecycle.stepStart(state.lifecycle, events)
      events.push(LLMEvent.reasoningStart({ id: item.id, providerMetadata: metadata }))
      events.push(LLMEvent.reasoningEnd({ id: item.id, providerMetadata: metadata }))
-      return [{ ...state, lifecycle }, events] satisfies StepResult
+      return [
+        {
+          ...state,
+          lifecycle,
+          reasoningItems: {
+            ...state.reasoningItems,
+            [item.id]: {
+              open: false,
+              encryptedContent: item.encrypted_content,
+              summaryParts: { 0: "concluded" },
+              deltaIndexes: new Set(),
+            },
+          },
+        },
+        events,
+      ] satisfies StepResult
    }
    return [
      { ...state, lifecycle: Lifecycle.reasoningEnd(state.lifecycle, events, item.id, metadata) },
@@ -1139,7 +1205,7 @@ const onResponseFinish = Effect.fn("OpenResponses.onResponseFinish")(function* (
            if (
              id === undefined ||
              ((item.type !== "function_call" || !current.tools[id]) &&
-                (item.type !== "reasoning" || !current.reasoningItems[id]))
+                (item.type !== "reasoning" || !current.reasoningItems[id]?.open))
            )
              return Effect.succeed([current, events] satisfies StepResult)
            return onOutputItemDone(current, { type: "response.output_item.done", item }).pipe(
@@ -1256,6 +1322,13 @@ export const step = (state: ParserState, input: Event) => {
  if (event.type === "response.output_item.added") {
    if (event.item?.type === "message" && event.item.id === undefined)
      return ProviderShared.eventError(state.id, `${event.type} message is missing id`)
+    if (
+      event.item &&
+      isReasoningItem(event.item) &&
+      state.reasoningItems[event.item.id] === undefined &&
+      state.lifecycle.reasoning.size > 0
+    )
+      return ProviderShared.eventError(state.id, `${event.type} started reasoning before the previous item ended`)
    const id = event.item?.id ?? (event.item?.type === "function_call" ? event.item.call_id : undefined)
    return Effect.succeed(
      onOutputItemAdded(
@@ -1305,10 +1378,10 @@ export const initial = (request: LLMRequest, extension: Extension = BASE): Parse
  providerMetadataKey: request.model.route.providerMetadataKey ?? "openresponses",
  hasFunctionCall: false,
  tools: ToolStream.empty<string>(),
+  completedTools: new Set<string>(),
  lifecycle: Lifecycle.initial(),
  outputItems: {},
-  messageItems: new Set<string>(),
-  messagePhases: {},
+  message: undefined,
  reasoningItems: {},
 })

@@ -3,6 +3,7 @@ import { Tool } from "@opencode-ai/schema/tool"
 import { Route } from "../route/client.js"
 import { Auth } from "../route/auth.js"
 import { Endpoint } from "../route/endpoint.js"
+import { Framing } from "../route/framing.js"
 import { HttpTransport } from "../route/transport/index.js"
 import { Protocol } from "../route/protocol.js"
 import {
@@ -245,6 +246,8 @@ export const OpenAIChatEvent = Schema.StructWithRest(
  [Schema.Record(Schema.String, Schema.Unknown)],
 )
 export type OpenAIChatEvent = Schema.Schema.Type<typeof OpenAIChatEvent>
+const DONE = "[DONE]" as const
+const OpenAIChatStreamEvent = Schema.Union([Schema.Literal(DONE), Protocol.jsonEvent(OpenAIChatEvent)])
 type OpenAIChatRequestMessage = LLMRequest["messages"][number]

 interface PendingToolDelta {
@@ -997,33 +1000,12 @@ const step = (state: ParserState, event: OpenAIChatEvent) =>
      lifecycle = Lifecycle.reasoningStart(lifecycle, events, "reasoning-0", deltaMetadata)
    const reasoningEmitted = state.reasoningEmitted || lifecycle.reasoning.has("reasoning-0")

-    if (delta?.content) {
-      lifecycle = Lifecycle.reasoningEnd(
-        lifecycle,
-        events,
-        "reasoning-0",
-        reasoningMetadata(
-          state.providerMetadataKey,
-          reasoningField,
-          reasoningDetailsObserved ? state.reasoningDetails : undefined,
-        ),
-      )
-      lifecycle = Lifecycle.textDelta(lifecycle, events, "text-0", delta.content)
-    }
+    // Reasoning is one response-wide channel: it stays open alongside text and
+    // refusal output so late reasoning deltas and details join the same block,
+    // and `finishEvents` closes it once with the complete metadata.
+    if (delta?.content) lifecycle = Lifecycle.textDelta(lifecycle, events, "text-0", delta.content)

-    if (delta?.refusal) {
-      lifecycle = Lifecycle.reasoningEnd(
-        lifecycle,
-        events,
-        "reasoning-0",
-        reasoningMetadata(
-          state.providerMetadataKey,
-          reasoningField,
-          reasoningDetailsObserved ? state.reasoningDetails : undefined,
-        ),
-      )
-      lifecycle = Lifecycle.textDelta(lifecycle, events, "text-0", delta.refusal)
-    }
+    if (delta?.refusal) lifecycle = Lifecycle.textDelta(lifecycle, events, "text-0", delta.refusal)

    // Compatible providers may omit indexes. Prefer durable identity, then use
    // batch position for parallel deltas or the latest call for sparse chunks.
@@ -1129,10 +1111,12 @@ const finishEvents = Effect.fn("OpenAIChat.finishEvents")(function* (state: Pars
          state.finishReason.normalized === "stop" && hasToolCalls ? "tool-calls" : state.finishReason.normalized,
      }
    : { normalized: hasToolCalls ? ("tool-calls" as const) : ("stop" as const) }
+  // Snapshot details at publish time so the emitted event never observes later
+  // mutation of the accumulated `reasoningDetails` array.
  const metadata = reasoningMetadata(
    state.providerMetadataKey,
    state.reasoningField,
-    state.reasoningDetailsObserved ? state.reasoningDetails : undefined,
+    state.reasoningDetailsObserved ? [...state.reasoningDetails] : undefined,
  )
  const started =
    state.reasoningDetailsObserved && !state.reasoningEmitted
@@ -1166,7 +1150,7 @@ export const protocol = Protocol.make({
    from: fromRequest,
  },
  stream: {
-    event: Protocol.jsonEvent(OpenAIChatEvent),
+    event: OpenAIChatStreamEvent,
    initial: (request) => ({
      providerMetadataKey: request.model.route.providerMetadataKey ?? String(request.model.provider),
      tools: ToolStream.empty<number>(),
@@ -1180,12 +1164,14 @@ export const protocol = Protocol.make({
      nextToolIndex: 0,
      requireFinishReason: request.model.compatibility?.requireFinishReason ?? true,
    }),
-    step,
+    step: (state: ParserState, event) => (event === DONE ? Effect.succeed([state, []] as const) : step(state, event)),
+    terminal: (event) => event === DONE,
    onHalt: finishEvents,
  },
 })

-export const httpTransport = HttpTransport.sseJson.with<OpenAIChatBody>()
+export const framing = Framing.sseWithDone
+export const httpTransport = HttpTransport.sseJson.with<OpenAIChatBody>().with({ framing })

 export const route = Route.make({
  id: ADAPTER,
@@ -1,6 +1,5 @@
 import { Route, type RouteRoutedLanguageModelInput } from "../route/client.js"
 import { Endpoint } from "../route/endpoint.js"
-import { Framing } from "../route/framing.js"
 import * as OpenAIChat from "./openai-chat.js"

 const ADAPTER = "openai-compatible-chat"
@@ -19,7 +18,7 @@ export const route = Route.make({
  providerMetadataKey: "openai",
  protocol: OpenAIChat.protocol,
  endpoint: Endpoint.path("/chat/completions"),
-  framing: Framing.sse,
+  framing: OpenAIChat.framing,
 })

 export * as OpenAICompatibleChat from "./openai-compatible-chat.js"
@@ -207,15 +207,16 @@ export const errorText = (error: unknown) => {

 /**
 * `framing` step for Server-Sent Events. Decodes UTF-8, runs the SSE channel
- * decoder, optionally filters named events, and drops empty / `[DONE]`
- * keep-alive events so the protocol event schema sees one JSON string per
- * element. Retry control events are ignored without interrupting the stream.
+ * decoder, optionally filters named events, and drops empty events. `[DONE]`
+ * is dropped by default or retained for protocols that use it as their stream
+ * boundary. Retry control events are ignored without interrupting the stream.
 * Decoder failures become provider output errors so the public error channel
 * stays `AIError`.
 */
 export const sseFraming = (
  bytes: Stream.Stream<Uint8Array, AIError>,
  events?: ReadonlySet<string>,
+  includeDone = false,
 ): Stream.Stream<string, AIError> =>
  bytes.pipe(
    Stream.decodeText(),
@@ -240,7 +241,7 @@ export const sseFraming = (
      (event) =>
        (events === undefined || events.has(event.event)) &&
        event.data.length > 0 &&
-        (event.data !== "[DONE]" || (events !== undefined && event.event !== "message")),
+        (event.data !== "[DONE]" || includeDone || (events !== undefined && event.event !== "message")),
    ),
    Stream.map((event) => event.data),
  )
@@ -62,22 +62,31 @@ export const reasoningEnd = (
  events: LLMEvent[],
  id: string,
  providerMetadata?: ProviderMetadata,
+  /** Authoritative complete value; replaces accumulated deltas when present. */
+  text?: string,
 ): State => {
  if (!state.reasoning.has(id)) return state
  const stepped = stepStart(state, events)
-  events.push(LLMEvent.reasoningEnd({ id, providerMetadata }))
+  events.push(LLMEvent.reasoningEnd({ id, text, providerMetadata }))
  const reasoning = new Set(stepped.reasoning)
  reasoning.delete(id)
  return { ...stepped, reasoning }
 }

-export const textEnd = (state: State, events: LLMEvent[], id: string, providerMetadata?: ProviderMetadata): State => {
+export const textEnd = (
+  state: State,
+  events: LLMEvent[],
+  id: string,
+  providerMetadata?: ProviderMetadata,
+  /** Authoritative complete value; replaces accumulated deltas when present. */
+  text?: string,
+): State => {
  if (!state.text.has(id)) return state
  const stepped = stepStart(state, events)
-  events.push(LLMEvent.textEnd({ id, providerMetadata }))
-  const text = new Set(stepped.text)
-  text.delete(id)
-  return { ...stepped, text }
+  events.push(LLMEvent.textEnd({ id, text, providerMetadata }))
+  const open = new Set(stepped.text)
+  open.delete(id)
+  return { ...stepped, text: open }
 }

 const closeOpenBlocks = (state: State, events: LLMEvent[]): State => {
@@ -37,6 +37,7 @@ const patterns = [
  /too large for model with \d+ maximum context length/i,
  /prompt has [\d,]+ tokens?, but the configured context size is [\d,]+ tokens?/i,
  /model_context_window_exceeded/i,
+  /range of input length should be/i,
  /too many tokens/i,
  /token limit exceeded/i,
  /request_too_large/i,
@@ -59,6 +60,7 @@ export const isContextOverflowFailure = (failure: unknown) =>

 const decodeJson = Schema.decodeUnknownOption(Schema.fromJsonString(Schema.Unknown))
 const QUOTA_CODES = new Set(["insufficient_quota", "usage_not_included", "billing_error"])
+const AUTH_CODES = new Set(["authentication_error", "permission_error"])
 const SERVER_CODES = new Set([
  "api_error",
  "internal_error",
@@ -74,7 +76,6 @@ const INVALID_REQUEST_CODES = new Set(["invalid_prompt", "invalid_request_error"
 const RATE_LIMIT_TEXT = /rate increased too quickly|rate[-_\s]?limit|too[_\s]?many[_\s]?requests/i
 const QUOTA_TEXT = /insufficient[-_\s]?quota|quota[-_\s]?exceeded/i
 const CONTENT_POLICY_TEXT = /content[-_\s]?policy|content_filter|safety/i
-const NETWORK_ERROR_TEXT = /network[-_\s]error/i

 export interface ProviderFailure {
  readonly message: string
@@ -90,8 +91,12 @@ export interface ProviderFailure {
  readonly rateLimit?: HttpRateLimitDetails | undefined
 }

-// Keep HTTP failures and provider-reported stream failures on one typed path so
-// session retry policy never needs provider-specific string matching.
+// Classification records affirmative evidence about a failure. Deterministic
+// failures need positive identification (a 4xx status, quota/auth/policy
+// signals); anything unrecognized stays UnknownProvider, which the session
+// retry policy treats as retry-eligible because transient failures arrive in
+// unpredictable shapes while deterministic rejections almost always carry a
+// status or known code.
 export function classifyProviderFailure(input: ProviderFailure): AIError["reason"] {
  const details = { message: input.message, body: input.rawBody, http: input.http, cause: input.cause }
  const body = input.rawBody ?? ""
@@ -116,46 +121,33 @@ export function classifyProviderFailure(input: ProviderFailure): AIError["reason
  if (CONTENT_POLICY_TEXT.test(text)) return new ContentPolicyError(details)
  if (codes.some((code) => QUOTA_CODES.has(code)) || (input.status === 429 && QUOTA_TEXT.test(text)))
    return new QuotaExceededError(details)
-  if (input.status === 401) return new AuthenticationError({ ...details, kind: "invalid" })
-  if (input.status === 403) return new AuthenticationError({ ...details, kind: "insufficient-permissions" })
-  if (codes.includes("authentication_error")) return new AuthenticationError({ ...details, kind: "invalid" })
-  if (codes.includes("permission_error"))
-    return new AuthenticationError({ ...details, kind: "insufficient-permissions" })
+  if (input.status === 401 || input.status === 403 || codes.some((code) => AUTH_CODES.has(code)))
+    return new AuthenticationError(details)
  if (
-    codes.some((code) => code.includes("rate_limit") || code === "too_many_requests" || code === "throttlingexception")
+    input.status === 429 ||
+    codes.some(
+      (code) => code.includes("rate_limit") || code === "too_many_requests" || code === "throttlingexception",
+    ) ||
+    RATE_LIMIT_TEXT.test(text)
  )
    return new RateLimitError({
      ...details,
      retryAfterMs: input.retryAfterMs,
      rateLimit: input.rateLimit,
    })
-  if (RATE_LIMIT_TEXT.test(text))
-    return new RateLimitError({
-      ...details,
-      retryAfterMs: input.retryAfterMs,
-      rateLimit: input.rateLimit,
-    })
-  if (NETWORK_ERROR_TEXT.test(text)) return new ProviderInternalError(details)
-  if (codes.some((code) => SERVER_CODES.has(code) || code.includes("exhausted") || code.includes("unavailable")))
-    return new ProviderInternalError({
-      ...details,
-      retryAfterMs: input.retryAfterMs,
-    })
-  if (input.status === 429) {
-    return new RateLimitError({
-      ...details,
-      retryAfterMs: input.retryAfterMs,
-      rateLimit: input.rateLimit,
-    })
-  }
-  if (input.status === 408 || input.status === 409 || (input.status !== undefined && input.status >= 500))
+  if (
+    input.status === 408 ||
+    input.status === 409 ||
+    (input.status !== undefined && input.status >= 500) ||
+    codes.some((code) => SERVER_CODES.has(code) || code.includes("exhausted") || code.includes("unavailable"))
+  )
    return new ProviderInternalError({
      ...details,
      retryAfterMs: input.retryAfterMs,
    })
  if (codes.some((code) => INVALID_REQUEST_CODES.has(code))) return new InvalidRequestError(details)
-  if (input.status === 400 || input.status === 404 || input.status === 413 || input.status === 422)
-    return new InvalidRequestError(details)
+  // Any remaining 4xx is a deterministic rejection of this request.
+  if (input.status !== undefined && input.status >= 400 && input.status < 500) return new InvalidRequestError(details)
  return new UnknownProviderError(details)
 }

@@ -5,7 +5,6 @@ import { ProviderShared } from "../protocols/shared.js"
 import { AuthOptions, type ProviderAuthOption } from "../route/auth-options.js"
 import { Route, type RouteDefaultsInput } from "../route/client.js"
 import { Endpoint } from "../route/endpoint.js"
-import { Framing } from "../route/framing.js"
 import { Protocol } from "../route/protocol.js"
 import { ProviderID, type ModelID, type LLMRequest } from "../schema/index.js"
 import { profiles } from "./openai-compatible-profile.js"
@@ -75,7 +74,7 @@ export const route = Route.make({
  providerMetadataKey: "openai",
  protocol,
  endpoint: Endpoint.path("/chat/completions", { baseURL: profiles.groq.baseURL }),
-  framing: Framing.sse,
+  framing: OpenAIChat.framing,
 })

 export const configure = (input: LanguageModelOptions = {}) => {
@@ -1,7 +1,6 @@
 import { Effect, Schema } from "effect"
 import { Route, type RouteDefaultsInput } from "../route/client.js"
 import { Endpoint } from "../route/endpoint.js"
-import { Framing } from "../route/framing.js"
 import { Protocol } from "../route/protocol.js"
 import { AuthOptions, type ProviderAuthOption } from "../route/auth-options.js"
 import { ProviderID, type CacheHint, type ModelID } from "../schema/index.js"
@@ -167,7 +166,7 @@ export const route = Route.make({
  providerMetadataKey: "openrouter",
  protocol,
  endpoint: Endpoint.path("/chat/completions", { baseURL: profile.baseURL }),
-  framing: Framing.sse,
+  framing: OpenAIChat.framing,
 })

 export const routes = [route]
@@ -139,7 +139,7 @@ const toAIError = (error: AuthError): AIError => {
    return new AIError({
      reason:
        error instanceof MissingCredentialError
-          ? new AuthenticationError({ message: error.message, cause: error, kind: "missing" })
+          ? new AuthenticationError({ message: error.message, cause: error })
          : new InvalidRequestError({ message: `Failed to resolve auth config: ${error.message}`, cause: error }),
    })
  }
@@ -8,8 +8,8 @@ import type { AIError } from "../schema/index.js"
 * `Framing` is the byte-stream-shaped seam between transport and protocol:
 *
 * - SSE (`Framing.sse`) — UTF-8 decode the body, run the SSE channel decoder,
- *   drop empty / `[DONE]` keep-alives. Each emitted frame is the JSON `data:`
- *   payload of one event.
+ *   and emit the `data:` payload of each non-empty event. The default drops
+ *   `[DONE]`; protocols that use it as a terminal select `sseWithDone`.
 * - AWS event stream — length-prefixed binary frames with CRC checksums.
 *   Each emitted frame is one parsed binary event record.
 *
@@ -26,6 +26,12 @@ export interface Definition<Frame> {
 /** Server-Sent Events framing. Used by every JSON-streaming HTTP provider. */
 export const sse: Definition<string> = { id: "sse", frame: ProviderShared.sseFraming }

+/** Server-Sent Events framing that retains the conventional `[DONE]` sentinel. */
+export const sseWithDone: Definition<string> = {
+  id: "sse",
+  frame: (bytes) => ProviderShared.sseFraming(bytes, undefined, true),
+}
+
 /** SSE framing restricted to protocol-recognized event names. */
 export const sseEvents = (events: ReadonlySet<string>): Definition<string> => ({
  id: "sse",
@@ -44,10 +44,7 @@ export class NoRouteError extends Schema.TaggedError<NoRouteError>("AI.Error.NoR

 export class AuthenticationError extends Schema.TaggedError<AuthenticationError>("AI.Error.Authentication")(
  "Authentication",
-  {
-    ...ReasonFields,
-    kind: Schema.Literals(["missing", "invalid", "expired", "insufficient-permissions", "unknown"]),
-  },
+  ReasonFields,
 ) {}

 export class RateLimitError extends Schema.TaggedError<RateLimitError>("AI.Error.RateLimit")("RateLimit", {
@@ -112,6 +112,8 @@ export type TextDelta = Schema.Schema.Type<typeof TextDelta>
 export const TextEnd = Schema.Struct({
  type: Schema.tag("text-end"),
  id: ContentBlockID,
+  /** Authoritative complete value; replaces accumulated deltas when present. */
+  text: Schema.optional(Schema.String),
  providerMetadata: Schema.optional(ProviderMetadata),
 }).annotate({ identifier: "LLM.Event.TextEnd" })
 export type TextEnd = Schema.Schema.Type<typeof TextEnd>
@@ -134,6 +136,8 @@ export type ReasoningDelta = Schema.Schema.Type<typeof ReasoningDelta>
 export const ReasoningEnd = Schema.Struct({
  type: Schema.tag("reasoning-end"),
  id: ContentBlockID,
+  /** Authoritative complete value; replaces accumulated deltas when present. */
+  text: Schema.optional(Schema.String),
  providerMetadata: Schema.optional(ProviderMetadata),
 }).annotate({ identifier: "LLM.Event.ReasoningEnd" })
 export type ReasoningEnd = Schema.Schema.Type<typeof ReasoningEnd>
@@ -328,17 +332,32 @@ export const LLMEvent = Object.assign(llmEventTagged, {
 })
 export type LLMEvent = Schema.Schema.Type<typeof llmEventTagged>

+/** Joins deltas per fragment, letting an authoritative end value replace that fragment's accumulated deltas. */
+const joinFragments = <Delta extends { id: string; text: string }, End extends { id: string; text?: string }>(
+  events: ReadonlyArray<LLMEvent>,
+  isDelta: (event: LLMEvent) => event is Extract<LLMEvent, Delta>,
+  isEnd: (event: LLMEvent) => event is Extract<LLMEvent, End>,
+) => {
+  const order: string[] = []
+  const parts = new Map<string, string>()
+  for (const event of events) {
+    if (isDelta(event)) {
+      if (!parts.has(event.id)) order.push(event.id)
+      parts.set(event.id, (parts.get(event.id) ?? "") + event.text)
+    }
+    if (isEnd(event) && event.text !== undefined) {
+      if (!parts.has(event.id)) order.push(event.id)
+      parts.set(event.id, event.text)
+    }
+  }
+  return order.map((id) => parts.get(id)).join("")
+}
+
 const responseText = (events: ReadonlyArray<LLMEvent>) =>
-  events
-    .filter(LLMEvent.is.textDelta)
-    .map((event) => event.text)
-    .join("")
+  joinFragments(events, LLMEvent.is.textDelta, LLMEvent.is.textEnd)

 const responseReasoning = (events: ReadonlyArray<LLMEvent>) =>
-  events
-    .filter(LLMEvent.is.reasoningDelta)
-    .map((event) => event.text)
-    .join("")
+  joinFragments(events, LLMEvent.is.reasoningDelta, LLMEvent.is.reasoningEnd)

 const responseUsage = (events: ReadonlyArray<LLMEvent>) =>
  events.reduce<Usage | undefined>(
@@ -445,10 +464,11 @@ const reduceTextDelta = (state: ResponseState, event: TextDelta): ResponseState
 const reduceTextEnd = (state: ResponseState, event: TextEnd): ResponseState => {
  const current = state.textParts[event.id]
  if (!current) return state
+  const text = event.text ?? current.text
  const providerMetadata = event.providerMetadata ?? current.providerMetadata
  return {
-    ...replaceContent(state, current.contentIndex, textContent(current.text, providerMetadata)),
-    textParts: { ...state.textParts, [event.id]: { ...current, providerMetadata } },
+    ...replaceContent(state, current.contentIndex, textContent(text, providerMetadata)),
+    textParts: { ...state.textParts, [event.id]: { ...current, text, providerMetadata } },
  }
 }

@@ -478,10 +498,11 @@ const reduceReasoningDelta = (state: ResponseState, event: ReasoningDelta): Resp
 const reduceReasoningEnd = (state: ResponseState, event: ReasoningEnd): ResponseState => {
  const current = state.reasoningParts[event.id]
  if (!current) return state
+  const text = event.text ?? current.text
  const providerMetadata = event.providerMetadata ?? current.providerMetadata
  return {
-    ...replaceContent(state, current.contentIndex, reasoningContent(current.text, providerMetadata)),
-    reasoningParts: { ...state.reasoningParts, [event.id]: { ...current, providerMetadata } },
+    ...replaceContent(state, current.contentIndex, reasoningContent(text, providerMetadata)),
+    reasoningParts: { ...state.reasoningParts, [event.id]: { ...current, text, providerMetadata } },
  }
 }

@@ -579,12 +600,12 @@ export class LLMResponse extends Schema.Class<LLMResponse>("LLM.Response")({
  usage: Schema.optional(Usage),
  finishReason: FinishReasonDetails,
 }) {
-  /** Concatenated assistant text assembled from streamed `text-delta` events. */
+  /** Concatenated assistant text; each fragment's `text-end` value replaces its accumulated deltas when present. */
  get text() {
    return responseText(this.events)
  }

-  /** Concatenated reasoning text assembled from streamed `reasoning-delta` events. */
+  /** Concatenated reasoning text; each fragment's `reasoning-end` value replaces its accumulated deltas when present. */
  get reasoning() {
    return responseReasoning(this.events)
  }
@@ -11,6 +11,7 @@ describe("provider error classification", () => {
      "Input length 131393 exceeds the maximum allowed input length of 131040 tokens.",
      "The input (516368 tokens) is longer than the model's context length (262144 tokens).",
      "Prompt has 5,958,968 tokens, but the configured context size is 256,000 tokens",
+      "Range of input length should be [1, 129024]",
      "Too many tokens",
      "Token limit exceeded",
    ]
@@ -87,10 +88,12 @@ describe("provider error classification", () => {
    ])
  })

-  test("classifies network error text as provider internal", () => {
+  test("classifies any remaining 4xx status as an invalid request", () => {
    expect(
-      ["network error", "network-error", "network_error"].map((message) => classifyProviderFailure({ message })._tag),
-    ).toEqual(["ProviderInternal", "ProviderInternal", "ProviderInternal"])
+      [400, 402, 404, 418, 422, 451].map(
+        (status) => classifyProviderFailure({ message: `HTTP ${status}`, status })._tag,
+      ),
+    ).toEqual(Array(6).fill("InvalidRequest"))
  })

  test("classifies nested provider codes when a top-level code is also present", () => {
@@ -103,10 +106,12 @@ describe("provider error classification", () => {
    ).toEqual(["QuotaExceeded", "ProviderInternal", "InvalidRequest"])
  })

-  test("keeps unknown and malformed provider payloads non-retryable", () => {
+  test("leaves unrecognized failures unclassified for the retry default", () => {
    expect(classifyProviderFailure({ message: '{"error":{"message":"no_kv_space"}}' })._tag).toBe("UnknownProvider")
    expect(classifyProviderFailure({ message: '{"type":"error","error":{"code":123}}' })._tag).toBe("UnknownProvider")
    expect(classifyProviderFailure({ message: "not-json" })._tag).toBe("UnknownProvider")
+    expect(classifyProviderFailure({ message: "network error" })._tag).toBe("UnknownProvider")
+    expect(classifyProviderFailure({ message: "Provider returned error" })._tag).toBe("UnknownProvider")
  })
 })

@@ -491,6 +491,59 @@ describe("Bedrock Converse route", () => {
    }),
  )

+  it.effect("ignores late tool deltas after contentBlockStop", () =>
+    Effect.gen(function* () {
+      const body = eventStreamBody(
+        [
+          "contentBlockStart",
+          {
+            contentBlockIndex: 0,
+            start: { toolUse: { toolUseId: "tool_1", name: "lookup" } },
+          },
+        ],
+        ["contentBlockDelta", { contentBlockIndex: 0, delta: { toolUse: { input: '{"query":"weather"}' } } }],
+        ["contentBlockStop", { contentBlockIndex: 0 }],
+        ["contentBlockDelta", { contentBlockIndex: 0, delta: { toolUse: { input: '{"late":true}' } } }],
+        ["messageStop", { stopReason: "tool_use" }],
+      )
+      const response = yield* LLMClient.generate(baseRequest).pipe(Effect.provide(fixedBytes(body)))
+
+      expect(response.toolCalls).toEqual([
+        { type: "tool-call", id: "tool_1", name: "lookup", input: { query: "weather" } },
+      ])
+      expect(response.events.filter((event) => event.type === "tool-input-delta")).toEqual([
+        {
+          type: "tool-input-delta",
+          id: "tool_1",
+          name: "lookup",
+          text: '{"query":"weather"}',
+          input: { query: "weather" },
+        },
+      ])
+    }),
+  )
+
+  it.effect("rejects tool deltas without contentBlockStart", () =>
+    Effect.gen(function* () {
+      const error = yield* LLMClient.generate(baseRequest).pipe(
+        Effect.provide(
+          fixedBytes(
+            eventStreamBody(
+              ["contentBlockDelta", { contentBlockIndex: 0, delta: { toolUse: { input: "{}" } } }],
+              ["messageStop", { stopReason: "tool_use" }],
+            ),
+          ),
+        ),
+        Effect.flip,
+      )
+
+      expect(error).toMatchObject({
+        reason: { _tag: "InvalidProviderOutput" },
+        message: "Bedrock Converse tool delta is missing its tool call",
+      })
+    }),
+  )
+
  it.effect("recovers incomplete tool input at finalization", () =>
    Effect.gen(function* () {
      const body = eventStreamBody(
@@ -52,7 +52,7 @@ describe("provider error retention", () => {
          Effect.flip,
        )
        expect(error.message).toContain("Slow down")
-        expect(error.reason._tag).toBe(entry.name === "Gemini" ? "ProviderInternal" : "RateLimit")
+        expect(error.reason._tag).toBe("RateLimit")
        expect(error.reason.body).toBe(body)
        expect(error.reason.http).toMatchObject({ status: 200, headers: { "x-provider-trace": "trace-1" } })
        expect(error.reason.http?.url).toStartWith("https://provider.test/")
@@ -0,0 +1,467 @@
+import { describe, expect } from "bun:test"
+import { Effect, Stream } from "effect"
+import { LLM, LLMEvent } from "../../src/index.js"
+import { OpenResponses } from "../../src/protocols/open-responses.js"
+import { configure } from "../../src/providers/openai-compatible-responses.js"
+import { LLMClient } from "../../src/route.js"
+import { it } from "../lib/effect.js"
+import { fixedResponse } from "../lib/http.js"
+import { sseEvents } from "../lib/sse.js"
+
+const request = LLM.request({
+  model: configure({ apiKey: "test-key", baseURL: "https://responses.example.test/v1" }).model("example-model"),
+  prompt: "Respond.",
+})
+const completed = { type: "response.completed", response: { id: "resp_1" } }
+
+const collect = (...input: OpenResponses.Event[]) =>
+  Effect.gen(function* () {
+    const events = yield* LLMClient.stream(request).pipe(
+      Stream.runCollect,
+      Effect.provide(fixedResponse(sseEvents(...input))),
+    )
+    expectLifecycle(
+      events,
+      input.some((event) => event.type === "response.completed"),
+    )
+    return events
+  })
+
+// Deliberately local to these basic-item fixtures, not a general stream validator.
+function expectLifecycle(events: ReadonlyArray<LLMEvent>, completed: boolean) {
+  const active = { text: new Set<string>(), reasoning: new Set<string>() }
+  const tools = new Map<string, "started" | "ended" | "called">()
+  events.forEach((event) => {
+    if (event.type === "text-start" || event.type === "reasoning-start") {
+      const blocks = event.type === "text-start" ? active.text : active.reasoning
+      expect(blocks.size).toBe(0)
+      blocks.add(event.id)
+    }
+    if (event.type === "text-delta" || event.type === "reasoning-delta") {
+      expect((event.type === "text-delta" ? active.text : active.reasoning).has(event.id)).toBe(true)
+    }
+    if (event.type === "text-end" || event.type === "reasoning-end") {
+      expect((event.type === "text-end" ? active.text : active.reasoning).delete(event.id)).toBe(true)
+    }
+    if (event.type === "tool-input-start") {
+      expect(tools.has(event.id)).toBe(false)
+      tools.set(event.id, "started")
+    }
+    if (event.type === "tool-input-delta") expect(tools.get(event.id)).toBe("started")
+    if (event.type === "tool-input-end") {
+      expect(tools.get(event.id)).toBe("started")
+      tools.set(event.id, "ended")
+    }
+    if (event.type === "tool-call") {
+      expect(tools.get(event.id)).toBe("ended")
+      tools.set(event.id, "called")
+    }
+    // Incomplete responses may leave pending tool inputs without a call.
+    if (event.type === "finish" && completed) {
+      expect(active.text.size).toBe(0)
+      expect(active.reasoning.size).toBe(0)
+      expect([...tools.values()].every((status) => status === "called")).toBe(true)
+    }
+  })
+  expect(events.filter(LLMEvent.is.stepStart)).toHaveLength(1)
+  expect(events[0]?.type).toBe("step-start")
+  expect(events.filter(LLMEvent.is.stepFinish)).toHaveLength(1)
+  expect(events.filter(LLMEvent.is.finish)).toHaveLength(1)
+  expect(events.slice(-2).map((event) => event.type)).toEqual(["step-finish", "finish"])
+}
+
+describe("Open Responses basic-item lifecycles", () => {
+  it.effect("closes implicit summary boundaries and ignores late events for completed reasoning", () =>
+    Effect.gen(function* () {
+      const item = { type: "reasoning", id: "rs_1", encrypted_content: "encrypted-state" }
+      const events = yield* collect(
+        { type: "response.output_item.added", output_index: 0, item: { ...item, encrypted_content: null } },
+        { type: "response.output_item.added", item: { ...item, encrypted_content: null } },
+        { type: "response.reasoning_summary_text.delta", item_id: "rs_1", summary_index: 0, delta: "First" },
+        { type: "response.reasoning_summary_part.added", item_id: "rs_1", summary_index: 1 },
+        { type: "response.reasoning_summary_part.done", item_id: "rs_1", summary_index: 0 },
+        { type: "response.reasoning_summary_text.done", item_id: "rs_1", summary_index: 1, text: "Second" },
+        // The third part omits both explicit summary boundaries.
+        {
+          type: "response.reasoning_summary_text.delta",
+          output_index: 0,
+          item_id: "wrong",
+          summary_index: 2,
+          delta: "Third",
+        },
+        { type: "response.output_item.done", item },
+        { type: "response.output_item.done", item },
+        { type: "response.output_item.added", item },
+        { type: "response.reasoning_summary_part.added", item_id: "rs_1", summary_index: 3 },
+        { type: "response.reasoning_summary_text.delta", item_id: "rs_1", summary_index: 3, delta: "late" },
+        { type: "response.reasoning_summary_text.done", item_id: "rs_1", summary_index: 2, text: "late final" },
+        { type: "response.reasoning_summary_part.done", item_id: "rs_1", summary_index: 3 },
+        completed,
+      )
+
+      expect(events.filter((event) => event.type.startsWith("reasoning-"))).toEqual([
+        {
+          type: "reasoning-start",
+          id: "rs_1:0",
+          providerMetadata: { "openai-compatible": { itemId: "rs_1", reasoningEncryptedContent: null } },
+        },
+        { type: "reasoning-delta", id: "rs_1:0", text: "First" },
+        { type: "reasoning-end", id: "rs_1:0", providerMetadata: { "openai-compatible": { itemId: "rs_1" } } },
+        {
+          type: "reasoning-start",
+          id: "rs_1:1",
+          providerMetadata: { "openai-compatible": { itemId: "rs_1", reasoningEncryptedContent: null } },
+        },
+        { type: "reasoning-delta", id: "rs_1:1", text: "Second" },
+        { type: "reasoning-end", id: "rs_1:1", providerMetadata: { "openai-compatible": { itemId: "rs_1" } } },
+        {
+          type: "reasoning-start",
+          id: "rs_1:2",
+          providerMetadata: { "openai-compatible": { itemId: "rs_1", reasoningEncryptedContent: null } },
+        },
+        { type: "reasoning-delta", id: "rs_1:2", text: "Third" },
+        {
+          type: "reasoning-end",
+          id: "rs_1:2",
+          providerMetadata: { "openai-compatible": { itemId: "rs_1", reasoningEncryptedContent: "encrypted-state" } },
+        },
+      ])
+    }),
+  )
+
+  it.effect("preserves done-only encrypted reasoning without replaying its summary or late events", () =>
+    Effect.gen(function* () {
+      const item = {
+        type: "reasoning",
+        id: "rs_1",
+        encrypted_content: "encrypted-state",
+        summary: [{ type: "summary_text", text: "Not streamed" }],
+      }
+      const events = yield* collect(
+        { type: "response.output_item.done", item },
+        { type: "response.output_item.done", item },
+        { type: "response.output_item.added", item },
+        { type: "response.reasoning_summary_text.delta", item_id: "rs_1", delta: "late" },
+        { type: "response.reasoning_summary_part.added", item_id: "rs_1", summary_index: 1 },
+        { type: "response.reasoning_summary_text.done", item_id: "rs_1", summary_index: 1, text: "late final" },
+        completed,
+        // Route termination must also prevent events after response completion.
+        { type: "response.output_item.added", item: { type: "reasoning", id: "rs_after" } },
+      )
+      expect(events.filter((event) => event.type.startsWith("reasoning-"))).toEqual([
+        {
+          type: "reasoning-start",
+          id: "rs_1",
+          providerMetadata: { "openai-compatible": { itemId: "rs_1", reasoningEncryptedContent: "encrypted-state" } },
+        },
+        {
+          type: "reasoning-end",
+          id: "rs_1",
+          providerMetadata: { "openai-compatible": { itemId: "rs_1", reasoningEncryptedContent: "encrypted-state" } },
+        },
+      ])
+    }),
+  )
+
+  it.effect("forgets never-streamed messages at implicit boundaries and preserves refusal phases", () =>
+    Effect.gen(function* () {
+      const events = yield* collect(
+        { type: "response.output_item.added", item: { type: "message", id: "msg_empty" } },
+        { type: "response.output_item.added", item: { type: "message", id: "msg_1", phase: "commentary" } },
+        { type: "response.output_text.done", item_id: "msg_1", text: "Checking" },
+        { type: "response.output_text.done", item_id: "msg_1", text: "Duplicate" },
+        { type: "response.output_item.added", item: { type: "message", id: "msg_2", phase: null } },
+        { type: "response.output_text.delta", item_id: "msg_empty", delta: "stale" },
+        { type: "response.output_text.done", item_id: "msg_empty", text: "stale final" },
+        { type: "response.output_text.delta", item_id: "msg_1", delta: "late" },
+        { type: "response.refusal.delta", item_id: "msg_2", delta: "Cannot help." },
+        { type: "response.refusal.done", item_id: "msg_2", refusal: "Cannot help." },
+        { type: "response.output_item.done", item: { type: "message", id: "msg_2", phase: "final_answer" } },
+        { type: "response.output_item.added", item: { type: "message", id: "msg_3", phase: null } },
+        { type: "response.refusal.done", item_id: "msg_3", refusal: "Done-only refusal." },
+        { type: "response.output_item.done", item: { type: "message", id: "msg_3" } },
+        completed,
+      )
+      expect(events.filter((event) => event.type.startsWith("text-"))).toEqual([
+        {
+          type: "text-start",
+          id: "msg_1",
+          providerMetadata: { "openai-compatible": { itemId: "msg_1", phase: "commentary" } },
+        },
+        { type: "text-delta", id: "msg_1", text: "Checking" },
+        {
+          type: "text-end",
+          id: "msg_1",
+          providerMetadata: { "openai-compatible": { itemId: "msg_1", phase: "commentary" } },
+        },
+        {
+          type: "text-start",
+          id: "msg_2",
+          providerMetadata: { "openai-compatible": { itemId: "msg_2", phase: null } },
+        },
+        { type: "text-delta", id: "msg_2", text: "Cannot help." },
+        {
+          type: "text-end",
+          id: "msg_2",
+          providerMetadata: { "openai-compatible": { itemId: "msg_2", phase: "final_answer" } },
+        },
+        {
+          type: "text-start",
+          id: "msg_3",
+          providerMetadata: { "openai-compatible": { itemId: "msg_3", phase: null } },
+        },
+        { type: "text-delta", id: "msg_3", text: "Done-only refusal." },
+        { type: "text-end", id: "msg_3", providerMetadata: { "openai-compatible": { itemId: "msg_3", phase: null } } },
+      ])
+    }),
+  )
+  it.effect("allows a message to be registered again without inheriting its previous phase", () =>
+    Effect.gen(function* () {
+      const events = yield* collect(
+        { type: "response.output_item.added", item: { type: "message", id: "msg_1", phase: "commentary" } },
+        { type: "response.output_text.delta", item_id: "msg_1", delta: "First" },
+        { type: "response.output_item.done", item: { type: "message", id: "msg_1" } },
+        { type: "response.output_item.added", item: { type: "message", id: "msg_1" } },
+        { type: "response.output_text.delta", item_id: "msg_1", delta: "Second" },
+        { type: "response.output_item.done", item: { type: "message", id: "msg_1" } },
+        completed,
+      )
+      expect(events.filter(LLMEvent.is.textEnd)).toEqual([
+        {
+          type: "text-end",
+          id: "msg_1",
+          providerMetadata: { "openai-compatible": { itemId: "msg_1", phase: "commentary" } },
+        },
+        { type: "text-end", id: "msg_1", providerMetadata: { "openai-compatible": { itemId: "msg_1" } } },
+      ])
+      expect(events.filter(LLMEvent.is.textDelta).map((event) => event.text)).toEqual(["First", "Second"])
+    }),
+  )
+  ;[undefined, "fc_1"].forEach((id) => {
+    it.effect(`opens and closes a done-only tool ${id === undefined ? "without" : "with"} an item id`, () =>
+      Effect.gen(function* () {
+        const item = {
+          type: "function_call",
+          ...(id === undefined ? {} : { id }),
+          call_id: "call_1",
+          name: "lookup",
+          arguments: '{"query":"weather"}',
+        }
+        const events = yield* collect(
+          { type: "response.output_item.done", item },
+          { type: "response.output_item.done", item: { ...item, id: "fc_1" } },
+          { type: "response.output_item.added", item },
+          completed,
+        )
+        const providerMetadata = id === undefined ? undefined : { "openai-compatible": { itemId: id } }
+        expect(events.filter((event) => event.type.startsWith("tool-"))).toEqual([
+          { type: "tool-input-start", id: "call_1", name: "lookup", providerMetadata },
+          { type: "tool-input-end", id: "call_1", name: "lookup", providerMetadata },
+          { type: "tool-call", id: "call_1", name: "lookup", input: { query: "weather" }, providerMetadata },
+        ])
+        expect(events.filter(LLMEvent.is.finish)).toEqual([
+          {
+            type: "finish",
+            reason: { normalized: "tool-calls", raw: undefined },
+            providerMetadata: { "openai-compatible": { responseId: "resp_1", serviceTier: undefined } },
+          },
+        ])
+      }),
+    )
+
+    it.effect(`deduplicates a pending call whose item id is ${id === undefined ? "introduced" : "omitted"} later`, () =>
+      Effect.gen(function* () {
+        const item = { type: "function_call", call_id: "call_1", name: "lookup" }
+        const first = { ...item, ...(id === undefined ? {} : { id }) }
+        const duplicate = { ...item, ...(id === undefined ? { id: "fc_1" } : {}) }
+        const events = yield* collect(
+          { type: "response.output_item.added", item: first },
+          { type: "response.function_call_arguments.delta", item_id: id ?? "call_1", delta: '{"query":"weather"}' },
+          { type: "response.output_item.added", item: duplicate },
+          { type: "response.output_item.done", item: duplicate },
+          { type: "response.output_item.done", item: first },
+          { type: "response.output_item.added", item: duplicate },
+          completed,
+        )
+        // Identity metadata comes from the first admission, not the duplicate.
+        const providerMetadata = id === undefined ? undefined : { "openai-compatible": { itemId: id } }
+        expect(events.filter((event) => event.type.startsWith("tool-"))).toEqual([
+          { type: "tool-input-start", id: "call_1", name: "lookup", providerMetadata },
+          {
+            type: "tool-input-delta",
+            id: "call_1",
+            name: "lookup",
+            text: '{"query":"weather"}',
+            input: { query: "weather" },
+          },
+          { type: "tool-input-end", id: "call_1", name: "lookup", providerMetadata },
+          { type: "tool-call", id: "call_1", name: "lookup", input: { query: "weather" }, providerMetadata },
+        ])
+      }),
+    )
+  })
+
+  it.effect("recovers pending items in completed output order with terminal encrypted metadata", () =>
+    Effect.gen(function* () {
+      const events = yield* collect(
+        {
+          type: "response.output_item.added",
+          item: { type: "function_call", id: "fc_1", call_id: "call_1", name: "lookup" },
+        },
+        { type: "response.function_call_arguments.delta", item_id: "fc_1", delta: '{"query":"draft"}' },
+        { type: "response.output_item.added", item: { type: "reasoning", id: "rs_1", encrypted_content: null } },
+        { type: "response.reasoning_summary_text.delta", item_id: "rs_1", delta: "Thinking" },
+        { type: "response.reasoning_summary_part.done", item_id: "rs_1", summary_index: 0 },
+        {
+          type: "response.completed",
+          response: {
+            id: "resp_1",
+            output: [
+              { type: "reasoning", id: "rs_1", encrypted_content: "terminal-state" },
+              { type: "function_call", id: "fc_1", call_id: "call_1", name: "lookup", arguments: '{"query":"final"}' },
+              { type: "function_call", id: "fc_unseen", call_id: "call_unseen", name: "lookup", arguments: "{}" },
+            ],
+          },
+        },
+      )
+      expect(events.slice(5, -2)).toEqual([
+        {
+          type: "reasoning-end",
+          id: "rs_1:0",
+          providerMetadata: { "openai-compatible": { itemId: "rs_1", reasoningEncryptedContent: "terminal-state" } },
+        },
+        {
+          type: "tool-input-end",
+          id: "call_1",
+          name: "lookup",
+          providerMetadata: { "openai-compatible": { itemId: "fc_1" } },
+        },
+        {
+          type: "tool-call",
+          id: "call_1",
+          name: "lookup",
+          input: { query: "final" },
+          providerMetadata: { "openai-compatible": { itemId: "fc_1" } },
+        },
+      ])
+    }),
+  )
+
+  it.effect("preserves call identity and pending order when an item id is reused", () =>
+    Effect.gen(function* () {
+      const first = { type: "function_call", id: "fc_1", call_id: "call_1", name: "lookup", arguments: "{}" }
+      const events = yield* collect(
+        { type: "response.output_item.added", item: first },
+        { type: "response.output_item.added", item: { ...first, id: "fc_2", call_id: "call_2" } },
+        { type: "response.output_item.done", item: first },
+        { type: "response.output_item.added", item: { ...first, call_id: "call_3" } },
+        { type: "response.output_item.done", item: first },
+        completed,
+      )
+      expect(events.filter(LLMEvent.is.toolCall).map((event) => event.id)).toEqual(["call_1", "call_2", "call_3"])
+    }),
+  )
+
+  it.effect("keeps text and reasoning identities separate even with empty item ids", () =>
+    Effect.gen(function* () {
+      const events = yield* collect(
+        { type: "response.output_item.added", item: { type: "reasoning", id: "" } },
+        { type: "response.output_item.added", item: { type: "message", id: "" } },
+        { type: "response.output_item.added", item: { type: "reasoning", id: "" } },
+        { type: "response.reasoning_summary_text.delta", item_id: "", delta: "Thinking" },
+        { type: "response.output_text.delta", item_id: "", delta: "Answer" },
+        { type: "response.output_item.done", item: { type: "reasoning", id: "", encrypted_content: "state" } },
+        { type: "response.output_item.done", item: { type: "message", id: "" } },
+        completed,
+      )
+      expect(events.filter(LLMEvent.is.reasoningDelta).map((event) => event.text)).toEqual(["Thinking"])
+      expect(events.filter(LLMEvent.is.textDelta).map((event) => event.text)).toEqual(["Answer"])
+      expect(events.filter(LLMEvent.is.reasoningEnd)).toEqual([
+        {
+          type: "reasoning-end",
+          id: ":0",
+          providerMetadata: { "openai-compatible": { itemId: "", reasoningEncryptedContent: "state" } },
+        },
+      ])
+    }),
+  )
+
+  it.effect("does not recover a completed tool from a tracked message with the same id", () =>
+    Effect.gen(function* () {
+      const events = yield* collect(
+        { type: "response.output_item.added", item: { type: "message", id: "item_1" } },
+        { type: "response.output_text.delta", item_id: "item_1", delta: "Answer" },
+        {
+          type: "response.completed",
+          response: {
+            id: "resp_1",
+            output: [{ type: "function_call", id: "item_1", call_id: "call_1", name: "lookup", arguments: "{}" }],
+          },
+        },
+      )
+      expect(events.filter(LLMEvent.is.toolCall)).toEqual([])
+      expect(events.filter(LLMEvent.is.finish).map((event) => event.reason.normalized)).toEqual(["stop"])
+    }),
+  )
+
+  it.effect("flushes pending calls and open text when completed output is absent", () =>
+    Effect.gen(function* () {
+      const events = yield* collect(
+        { type: "response.output_item.added", item: { type: "message", id: "msg_1", phase: "final_answer" } },
+        { type: "response.output_text.delta", item_id: "msg_1", delta: "Answer" },
+        {
+          type: "response.output_item.added",
+          item: { type: "function_call", call_id: "call_1", name: "lookup", arguments: "{}" },
+        },
+        completed,
+      )
+      // Generic terminal closure does not repeat the message's phase metadata.
+      expect(events.slice(4, -2)).toEqual([
+        { type: "tool-input-end", id: "call_1", name: "lookup" },
+        { type: "tool-call", id: "call_1", name: "lookup", input: {} },
+        { type: "text-end", id: "msg_1" },
+      ])
+    }),
+  )
+
+  it.effect("does not reconcile pending calls or terminal reasoning metadata on incomplete responses", () =>
+    Effect.gen(function* () {
+      const events = yield* collect(
+        { type: "response.output_item.added", item: { type: "reasoning", id: "rs_1", encrypted_content: null } },
+        { type: "response.reasoning_summary_text.delta", item_id: "rs_1", delta: "Partial" },
+        {
+          type: "response.output_item.added",
+          item: { type: "function_call", id: "fc_1", call_id: "call_1", name: "lookup" },
+        },
+        { type: "response.function_call_arguments.delta", item_id: "fc_1", delta: '{"query":' },
+        {
+          type: "response.incomplete",
+          response: {
+            id: "resp_1",
+            incomplete_details: { reason: "max_output_tokens" },
+            output: [
+              { type: "reasoning", id: "rs_1", encrypted_content: "not-reconciled" },
+              {
+                type: "function_call",
+                id: "fc_1",
+                call_id: "call_1",
+                name: "lookup",
+                arguments: '{"query":"not-reconciled"}',
+              },
+            ],
+          },
+        },
+      )
+      expect(events.filter(LLMEvent.is.toolInputEnd)).toEqual([])
+      expect(events.filter(LLMEvent.is.toolCall)).toEqual([])
+      expect(events.filter(LLMEvent.is.reasoningEnd)).toEqual([{ type: "reasoning-end", id: "rs_1:0" }])
+      expect(events.filter(LLMEvent.is.finish)).toEqual([
+        {
+          type: "finish",
+          reason: { normalized: "length", raw: "max_output_tokens" },
+          providerMetadata: { "openai-compatible": { responseId: "resp_1", serviceTier: undefined } },
+        },
+      ])
+    }),
+  )
+})
@@ -7,6 +7,7 @@ import {
  AIError,
  LLMEvent,
  LLMRequest,
+  LLMResponse,
  Message,
  LanguageModel,
  ToolCallPart,
@@ -807,6 +808,28 @@ describe("OpenAI Chat route", () => {
    }),
  )

+  it.effect("finishes at the done sentinel without waiting for response EOF", () =>
+    Effect.gen(function* () {
+      const stream = new ReadableStream<Uint8Array>({
+        start(controller) {
+          controller.enqueue(
+            new TextEncoder().encode(sseEvents(deltaChunk({ content: "Hello" }), deltaChunk({}, "stop"))),
+          )
+        },
+      })
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(stream, {
+            headers: { "content-type": "text/event-stream" },
+          }),
+        ),
+      )
+
+      expect(response.text).toBe("Hello")
+      expect(response.events.at(-1)?.type).toBe("finish")
+    }),
+  )
+
  it.effect("preserves streamed refusals as ordinary assistant text", () =>
    Effect.gen(function* () {
      const response = yield* LLMClient.generate(request).pipe(
@@ -1127,7 +1150,7 @@ describe("OpenAI Chat route", () => {
    }),
  )

-  it.effect("preserves scalar reasoning after content starts", () =>
+  it.effect("preserves scalar reasoning after content starts in one lifecycle", () =>
    Effect.gen(function* () {
      const details = [{ type: "reasoning.text", text: "detail", format: "unknown", index: 0 }]
      const response = yield* LLMClient.generate(request).pipe(
@@ -1144,8 +1167,35 @@ describe("OpenAI Chat route", () => {
      )

      expect(response.reasoning).toBe("detailscalar")
-      expect(response.events.filter(LLMEvent.is.reasoningStart)).toHaveLength(2)
-      expect(response.events.filter(LLMEvent.is.reasoningEnd)).toHaveLength(2)
+      expect(response.events.filter(LLMEvent.is.reasoningStart)).toHaveLength(1)
+      expect(response.events.filter(LLMEvent.is.reasoningEnd)).toHaveLength(1)
+      expect(response.message.content.filter((part) => part.type === "reasoning")).toHaveLength(1)
+      expect(response.message.content.find((part) => part.type === "reasoning")?.providerMetadata).toEqual({
+        openai: { reasoningField: "reasoning", reasoningDetails: details },
+      })
+    }),
+  )
+
+  it.effect("keeps one reasoning lifecycle across many content chunks", () =>
+    Effect.gen(function* () {
+      const details = [{ type: "reasoning.text", text: "thinking", format: "anthropic-claude-v1", index: 0 }]
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              { choices: [{ delta: { reasoning: "thinking", reasoning_details: details } }] },
+              ...Array.from({ length: 25 }, (_, index) => deltaChunk({ content: `chunk-${index} ` })),
+              deltaChunk({}, "stop"),
+            ),
+          ),
+        ),
+      )
+
+      expect(response.reasoning).toBe("thinking")
+      expect(response.text).toBe(Array.from({ length: 25 }, (_, index) => `chunk-${index} `).join(""))
+      expect(response.events.filter(LLMEvent.is.reasoningStart)).toHaveLength(1)
+      expect(response.events.filter(LLMEvent.is.reasoningEnd)).toHaveLength(1)
+      expect(response.message.content.filter((part) => part.type === "reasoning")).toHaveLength(1)
      expect(response.message.content.find((part) => part.type === "reasoning")?.providerMetadata).toEqual({
        openai: { reasoningField: "reasoning", reasoningDetails: details },
      })
@@ -1191,7 +1241,18 @@ describe("OpenAI Chat route", () => {
          index: 0,
        },
      ]
-      const response = yield* LLMClient.generate(request).pipe(
+      // Snapshot reasoning-end metadata as each event is published so the
+      // assertion cannot pass through later mutation of a shared array.
+      const publishedEndMetadata: unknown[] = []
+      const response = yield* LLMClient.stream(request).pipe(
+        Stream.tap((event) =>
+          Effect.sync(() => {
+            if (LLMEvent.is.reasoningEnd(event))
+              publishedEndMetadata.push(decodeJson(encodeJson(event.providerMetadata)))
+          }),
+        ),
+        Stream.runFold(LLMResponse.empty, LLMResponse.reduce),
+        Effect.map((state) => LLMResponse.complete(state)!),
        Effect.provide(
          fixedResponse(
            sseEvents(
@@ -1212,10 +1273,12 @@ describe("OpenAI Chat route", () => {
      expect(response.events.filter(LLMEvent.is.reasoningStart)).toHaveLength(1)
      expect(response.events.filter(LLMEvent.is.reasoningDelta)).toHaveLength(1)
      expect(response.events.filter(LLMEvent.is.reasoningEnd)).toHaveLength(1)
-      expect(response.events.filter(LLMEvent.is.reasoningEnd).at(-1)?.providerMetadata).toEqual({
-        openai: { reasoningField: "reasoning", reasoningDetails: merged },
-      })
-      expect(response.events.findIndex(LLMEvent.is.reasoningEnd)).toBeLessThan(
+      expect(publishedEndMetadata).toEqual([{ openai: { reasoningField: "reasoning", reasoningDetails: merged } }])
+      expect(response.events.findIndex(LLMEvent.is.reasoningStart)).toBeLessThan(
+        response.events.findIndex(LLMEvent.is.textStart),
+      )
+      // Reasoning stays open alongside text and closes once during finalization.
+      expect(response.events.findIndex(LLMEvent.is.reasoningEnd)).toBeGreaterThan(
        response.events.findIndex(LLMEvent.is.textStart),
      )

@@ -405,6 +405,19 @@ describe("OpenAI-compatible Chat route", () => {
    }),
  )

+  it.effect("ignores events after the done sentinel", () =>
+    Effect.gen(function* () {
+      const body = `${sseEvents(
+        deltaChunk({ content: "Hello" }),
+        deltaChunk({}, "stop"),
+      )}data: ${JSON.stringify(deltaChunk({ content: " late" }))}\n\n`
+      const response = yield* LLMClient.generate(request).pipe(Effect.provide(fixedResponse(body)))
+
+      expect(response.text).toBe("Hello")
+      expect(response.finishReason).toEqual({ normalized: "stop", raw: "stop" })
+    }),
+  )
+
  it.effect("accepts nullable usage and preserves provider fields", () =>
    Effect.gen(function* () {
      const response = yield* LLMClient.generate(request).pipe(
@@ -2750,6 +2750,227 @@ describe("OpenAI Responses route", () => {
    }),
  )

+  it.effect("concludes reasoning at implicit summary boundaries", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(
+        LLMRequest.update(request, { providerOptions: { store: false } }),
+      ).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              {
+                type: "response.output_item.added",
+                item: { type: "reasoning", id: "rs_1", encrypted_content: null },
+              },
+              { type: "response.reasoning_summary_part.added", item_id: "rs_1", summary_index: 0 },
+              { type: "response.reasoning_summary_text.delta", item_id: "rs_1", summary_index: 0, delta: "First" },
+              // The next part is enough to conclude the previous one even when
+              // its done event is delayed.
+              { type: "response.reasoning_summary_part.added", item_id: "rs_1", summary_index: 1 },
+              { type: "response.reasoning_summary_part.done", item_id: "rs_1", summary_index: 0 },
+              { type: "response.reasoning_summary_text.delta", item_id: "rs_1", summary_index: 1, delta: "Second" },
+              { type: "response.reasoning_summary_part.done", item_id: "rs_1", summary_index: 1 },
+              // Some compatible providers begin the next part with its first delta.
+              { type: "response.reasoning_summary_text.delta", item_id: "rs_1", summary_index: 2, delta: "Third" },
+              {
+                type: "response.output_item.done",
+                item: { type: "reasoning", id: "rs_1", encrypted_content: "encrypted-state" },
+              },
+              { type: "response.completed", response: { id: "resp_1" } },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.reasoning).toBe("FirstSecondThird")
+      expect(response.events.filter((event) => event.type.startsWith("reasoning-"))).toEqual([
+        {
+          type: "reasoning-start",
+          id: "rs_1:0",
+          providerMetadata: { openai: { itemId: "rs_1", reasoningEncryptedContent: null } },
+        },
+        { type: "reasoning-delta", id: "rs_1:0", text: "First", providerMetadata: undefined },
+        { type: "reasoning-end", id: "rs_1:0", providerMetadata: { openai: { itemId: "rs_1" } } },
+        {
+          type: "reasoning-start",
+          id: "rs_1:1",
+          providerMetadata: { openai: { itemId: "rs_1", reasoningEncryptedContent: null } },
+        },
+        { type: "reasoning-delta", id: "rs_1:1", text: "Second", providerMetadata: undefined },
+        {
+          type: "reasoning-end",
+          id: "rs_1:1",
+          providerMetadata: { openai: { itemId: "rs_1" } },
+        },
+        {
+          type: "reasoning-start",
+          id: "rs_1:2",
+          providerMetadata: { openai: { itemId: "rs_1", reasoningEncryptedContent: null } },
+        },
+        { type: "reasoning-delta", id: "rs_1:2", text: "Third", providerMetadata: undefined },
+        {
+          type: "reasoning-end",
+          id: "rs_1:2",
+          providerMetadata: { openai: { itemId: "rs_1", reasoningEncryptedContent: "encrypted-state" } },
+        },
+      ])
+    }),
+  )
+
+  it.effect("rejects a reasoning item that starts before the previous item ends", () =>
+    Effect.gen(function* () {
+      const error = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              { type: "response.output_item.added", item: { type: "reasoning", id: "rs_1" } },
+              { type: "response.reasoning_summary_text.delta", item_id: "rs_1", summary_index: 0, delta: "First" },
+              { type: "response.output_item.added", item: { type: "reasoning", id: "rs_2" } },
+            ),
+          ),
+        ),
+        Effect.flip,
+      )
+
+      expect(error.reason._tag).toBe("InvalidProviderOutput")
+      expect(error.message).toContain("started reasoning before the previous item ended")
+    }),
+  )
+
+  it.effect("concludes text at implicit message boundaries", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              // An item that never streams text is untracked at the boundary too.
+              { type: "response.output_item.added", item: { type: "message", id: "msg_0" } },
+              { type: "response.output_item.added", item: { type: "message", id: "msg_1" } },
+              { type: "response.output_text.delta", item_id: "msg_1", delta: "First" },
+              // The previous message's done event is missing; the next message
+              // item is the boundary for its open text.
+              { type: "response.output_item.added", item: { type: "message", id: "msg_2" } },
+              // Late deltas for concluded or untracked messages must stay no-ops.
+              { type: "response.output_text.delta", item_id: "msg_1", delta: " late" },
+              { type: "response.output_text.delta", item_id: "msg_0", delta: " stale" },
+              { type: "response.output_text.delta", item_id: "msg_2", delta: "Second" },
+              { type: "response.output_item.done", item: { type: "message", id: "msg_2" } },
+              { type: "response.completed", response: { id: "resp_1" } },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.text).toBe("FirstSecond")
+      expect(response.events.filter((event) => event.type.startsWith("text-"))).toMatchObject([
+        { type: "text-start", id: "msg_1" },
+        { type: "text-delta", id: "msg_1", text: "First" },
+        { type: "text-end", id: "msg_1" },
+        { type: "text-start", id: "msg_2" },
+        { type: "text-delta", id: "msg_2", text: "Second" },
+        { type: "text-end", id: "msg_2" },
+      ])
+    }),
+  )
+
+  it.effect("opens the tool lifecycle for a done-only function call", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              // No output_item.added: the call arrives only as a completed item.
+              {
+                type: "response.output_item.done",
+                item: {
+                  type: "function_call",
+                  id: "fc_1",
+                  call_id: "call_1",
+                  name: "lookup",
+                  arguments: '{"query":"weather"}',
+                },
+              },
+              { type: "response.completed", response: { id: "resp_1" } },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.events.filter((event) => event.type.startsWith("tool-"))).toMatchObject([
+        { type: "tool-input-start", id: "call_1", name: "lookup" },
+        { type: "tool-input-end", id: "call_1", name: "lookup" },
+        { type: "tool-call", id: "call_1", name: "lookup", input: { query: "weather" } },
+      ])
+      expect(response.finishReason.normalized).toBe("tool-calls")
+    }),
+  )
+
+  it.effect("ignores duplicate item boundary events", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              { type: "response.output_item.added", item: { type: "reasoning", id: "rs_1" } },
+              // Duplicate added for a known item is not overlap and must no-op.
+              { type: "response.output_item.added", item: { type: "reasoning", id: "rs_1" } },
+              { type: "response.reasoning_summary_text.delta", item_id: "rs_1", summary_index: 0, delta: "Think" },
+              { type: "response.output_item.done", item: { type: "reasoning", id: "rs_1" } },
+              { type: "response.output_item.done", item: { type: "reasoning", id: "rs_1" } },
+              {
+                type: "response.output_item.added",
+                item: { type: "function_call", id: "fc_1", call_id: "call_1", name: "lookup", arguments: "" },
+              },
+              {
+                type: "response.output_item.added",
+                item: { type: "function_call", id: "fc_1", call_id: "call_1", name: "lookup", arguments: "" },
+              },
+              { type: "response.function_call_arguments.delta", item_id: "fc_1", delta: '{"query":"weather"}' },
+              {
+                type: "response.output_item.done",
+                item: {
+                  type: "function_call",
+                  id: "fc_1",
+                  call_id: "call_1",
+                  name: "lookup",
+                  arguments: '{"query":"weather"}',
+                },
+              },
+              {
+                type: "response.output_item.done",
+                item: {
+                  type: "function_call",
+                  id: "fc_1",
+                  call_id: "call_1",
+                  name: "lookup",
+                  arguments: '{"query":"weather"}',
+                },
+              },
+              // Duplicates that drop the item id still resolve the same call.
+              {
+                type: "response.output_item.done",
+                item: { type: "function_call", call_id: "call_1", name: "lookup", arguments: '{"query":"weather"}' },
+              },
+              {
+                type: "response.output_item.added",
+                item: { type: "function_call", call_id: "call_1", name: "lookup", arguments: "" },
+              },
+              { type: "response.completed", response: { id: "resp_1" } },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.reasoning).toBe("Think")
+      expect(response.events.filter((event) => event.type === "reasoning-start")).toHaveLength(1)
+      expect(response.events.filter((event) => event.type === "reasoning-end")).toHaveLength(1)
+      expect(response.events.filter((event) => event.type === "tool-input-start")).toHaveLength(1)
+      expect(response.events.filter(LLMEvent.is.toolCall)).toEqual([
+        expect.objectContaining({ id: "call_1", input: { query: "weather" } }),
+      ])
+    }),
+  )
+
  it.effect("reconciles reasoning summaries that arrive only as finals", () =>
    Effect.gen(function* () {
      const response = yield* LLMClient.generate(
@@ -104,6 +104,60 @@ describe("LLMResponse reducer", () => {
    ])
  })

+  test("authoritative text-end value replaces accumulated deltas", () => {
+    const response = LLMResponse.fromEvents([
+      LLMEvent.textStart({ id: "t1" }),
+      LLMEvent.textDelta({ id: "t1", text: "Hel" }),
+      LLMEvent.textEnd({ id: "t1", text: "Hello!" }),
+      LLMEvent.finish({ reason: { normalized: "stop" } }),
+    ])
+
+    expect(response?.message.content).toEqual([{ type: "text", text: "Hello!" }])
+    expect(response?.text).toBe("Hello!")
+  })
+
+  test("text-end without value keeps joined deltas", () => {
+    const response = LLMResponse.fromEvents([
+      LLMEvent.textStart({ id: "t1" }),
+      LLMEvent.textDelta({ id: "t1", text: "Hel" }),
+      LLMEvent.textDelta({ id: "t1", text: "lo" }),
+      LLMEvent.textEnd({ id: "t1" }),
+      LLMEvent.finish({ reason: { normalized: "stop" } }),
+    ])
+
+    expect(response?.message.content).toEqual([{ type: "text", text: "Hello" }])
+    expect(response?.text).toBe("Hello")
+  })
+
+  test("authoritative reasoning-end value replaces only its own fragment", () => {
+    const response = LLMResponse.fromEvents([
+      LLMEvent.reasoningStart({ id: "r1:0" }),
+      LLMEvent.reasoningDelta({ id: "r1:0", text: "First summ" }),
+      LLMEvent.reasoningEnd({ id: "r1:0", text: "First summary." }),
+      LLMEvent.reasoningStart({ id: "r1:1" }),
+      LLMEvent.reasoningDelta({ id: "r1:1", text: "Second summary." }),
+      LLMEvent.reasoningEnd({ id: "r1:1" }),
+      LLMEvent.finish({ reason: { normalized: "stop" } }),
+    ])
+
+    expect(response?.message.content).toEqual([
+      { type: "reasoning", text: "First summary." },
+      { type: "reasoning", text: "Second summary." },
+    ])
+    expect(response?.reasoning).toBe("First summary.Second summary.")
+  })
+
+  test("end value recovers a fragment that streamed no deltas", () => {
+    const response = LLMResponse.fromEvents([
+      LLMEvent.textStart({ id: "t1" }),
+      LLMEvent.textEnd({ id: "t1", text: "Hello!" }),
+      LLMEvent.finish({ reason: { normalized: "stop" } }),
+    ])
+
+    expect(response?.message.content).toEqual([{ type: "text", text: "Hello!" }])
+    expect(response?.text).toBe("Hello!")
+  })
+
  test("clears malformed tool input without appending an executable call", () => {
    const state = reduce([
      LLMEvent.toolInputStart({ id: "call_1", name: "lookup" }),
@@ -250,7 +250,7 @@ test("AI error reasons are tagged Errors with required messages", () => {
      provider: model.provider,
      model: model.id,
    }),
-    new AuthenticationError({ message: "Missing credentials", kind: "missing" }),
+    new AuthenticationError({ message: "Missing credentials" }),
    new RateLimitError({ message: "Rate limited" }),
    new QuotaExceededError({ message: "Quota exceeded" }),
    new ContentPolicyError({ message: "Content blocked" }),
@@ -37,7 +37,7 @@
    "@opencode-ai/protocol": "workspace:*"
  },
  "peerDependencies": {
-    "effect": "4.0.0-rc.111",
+    "effect": "4.0.0-rc.112",
    "solid-js": ">=1.9.0"
  },
  "peerDependenciesMeta": {
@@ -19,7 +19,7 @@

 - If a captured user-visible output channel returns (an earlier `output.text`/`output.file`/`output.image` API was removed from v1), keep `output` as its name, distinct from the program return value: `return` stays the structured result for the model, while `output.*` describes artifacts the host may render into a conversation or UI after execution. Keep this host-neutral and let applications decide how captured output is delivered. In v1, hosts collect media host-side (outside CodeMode) instead.
 - Improve the failure taxonomy. Distinguish parse/compile mistakes, unsupported syntax, user-thrown errors, invalid returned data, tool refusal, tool internal failure, timeout, and genuine runtime defects so agents can recover accurately instead of treating everything as a generic execution failure.
- Preserve the public/private error split. Tool authors should be able to return a safe model-visible message while retaining a private cause for host diagnostics. Unknown host failures must remain sanitized by default.
+- Report host failure messages and underlying causes rather than replacing them with generic diagnostics. Preserve interruption behavior.
 - Think deliberately about richer binary boundaries before allowing `Blob`, `File`, `ArrayBuffer`, streams, or typed arrays beyond today's JSON-like values. If CodeMode supports binary tool args/results, use explicit tagged data shapes and clear size limits rather than relying on ambient runtime serialization.
 - Keep host capabilities explicit. Globals such as `fetch`, `crypto`, filesystem handles, extra modules, or network clients should be opt-in runtime capabilities with obvious policy defaults, not ambient authority. Default to unavailable unless a host deliberately provides the capability.
 - If `fetch` is added, model it as a host-provided outbound capability with policy controls: allowed origins, methods, headers, response size, timeout, and whether response bodies may be returned, emitted, or only summarized through a tool.
@@ -139,8 +139,8 @@ Diagnostic kinds:
 | `ExecutionFailure`      | The program threw or another execution error occurred.                                         |
 | `Truncated`             | Warning only: additional warnings were omitted by `maxOutputBytes`.                            |

-Unknown host failures, defects, and invalid outputs are sanitized. `toolError("safe message")` explicitly exposes a
-safe refusal to the model; its optional cause remains private.
+Host failures and defects report their messages and underlying causes. Invalid outputs include the validation or
+copying error. Interruption propagates without becoming an error diagnostic.

 ## Discovery

@@ -365,7 +365,7 @@ ultimate source of truth.
      `catch`.
 - [x] Source locations on unsupported-syntax diagnostics for JavaScript-shaped input; TypeScript transpilation may
      shift them.
- [x] Sanitized model-visible diagnostics and explicit safe `ToolError` messages.
- [ ] Distinguish user-thrown failures from interpreter defects and explicit tool refusals from sanitized internal tool
+- [x] Model-visible host failure messages and underlying causes, including output-validation errors.
+- [ ] Distinguish user-thrown failures from interpreter defects and explicit tool refusals from internal tool
      failures; preserve those categories in caught errors, promise rejection handlers, and `Promise.allSettled`
      reasons.
@@ -1,11 +1,11 @@
 import { Schema } from "effect"

-/** Safe operational refusal from a standard tool pack, reported as `ToolFailure`. */
+/** Tool failure reported as `ToolFailure`. */
 export class ToolError extends Schema.TaggedError<ToolError>()("ToolError", {
  message: Schema.String,
  cause: Schema.optionalKey(Schema.Defect()),
 }) {}

-/** Creates a tool refusal whose message is safe to include in an execution diagnostic. */
+/** Creates a tool failure with an optional underlying cause. */
 export const toolError = (message: string, cause?: unknown): ToolError =>
  new ToolError({ message, ...(cause === undefined ? {} : { cause }) })
@@ -1,5 +1,5 @@
-import { Cause, Effect, Exit, Schema } from "effect"
-import { ToolError, toolError } from "./tool-error.js"
+import { Cause, Effect, Exit, Formatter, Schema } from "effect"
+import { toolError } from "./tool-error.js"
 import {
  decodeInput as decodeToolInput,
  decodeOutput as decodeToolOutput,
@@ -117,15 +117,6 @@ export class ToolRuntimeError extends Error {
  }
 }

-const runHost = <A, E, R>(effect: Effect.Effect<A, E, R>): Effect.Effect<A, ToolError, R> =>
-  effect.pipe(
-    Effect.catchCause((cause) => {
-      if (Cause.hasInterruptsOnly(cause)) return Effect.interrupt
-      const error = Cause.squash(cause)
-      return Effect.fail(error instanceof ToolError ? error : toolError("Tool execution failed", error))
-    }),
-  )
-
 const blockedMemberNames = new Set(["__proto__", "constructor", "prototype"])

 export const isBlockedMember = (name: string): boolean => blockedMemberNames.has(name)
@@ -507,19 +498,12 @@ export const make = <R>(
        if (Exit.isSuccess(exit)) return onEnd({ ...call, durationMs, outcome: "success" })
        if (Cause.hasInterruptsOnly(exit.cause)) return onEnd({ ...call, durationMs, outcome: "interrupted" })
        const error = Cause.squash(exit.cause)
-        const message =
-          error instanceof ToolError || error instanceof ToolRuntimeError ? error.message : "Tool execution failed"
+        const message = error instanceof Error ? error.message : Cause.pretty(exit.cause)
        return onEnd({ ...call, durationMs, outcome: "failure", message })
      }),
    )
  }

-  const decodeOutput = (value: unknown, name: string) =>
-    Effect.try({
-      try: () => copyIn(value, `Result from tool '${name}'`),
-      catch: () => new ToolRuntimeError("InvalidToolOutput", `Invalid output from tool '${name}'.`),
-    })
-
  const recordCall = (call: ToolCall): void => {
    if (maxToolCalls !== undefined && calls.length >= maxToolCalls) {
      throw new ToolRuntimeError("ToolCallLimitExceeded", `Execution exceeded its tool-call limit of ${maxToolCalls}.`)
@@ -548,12 +532,22 @@ export const make = <R>(
      return yield* observeEnd(
        Effect.gen(function* () {
          if (hooks?.onToolCallStart !== undefined) yield* hooks.onToolCallStart(call)
-          const raw = yield* runHost(Effect.suspend(() => tool.execute(input)))
-          const result = yield* Effect.try({
-            try: () => decodeToolOutput(tool, raw),
-            catch: () => new ToolRuntimeError("InvalidToolOutput", `Invalid output from tool '${name}'.`),
+          const raw = yield* Effect.suspend(() => tool.execute(input)).pipe(
+            Effect.catchCause((cause) => {
+              if (Cause.hasInterruptsOnly(cause)) return Effect.interrupt
+              return Effect.fail(
+                toolError(
+                  Cause.prettyErrors(cause)
+                    .map((error) => (error.cause ? Formatter.format(error) : error.message || error.name))
+                    .join("\n"),
+                ),
+              )
+            }),
+          )
+          return yield* Effect.try({
+            try: () => copyIn(decodeToolOutput(tool, raw), `Result from tool '${name}'`),
+            catch: (cause) => new ToolRuntimeError("InvalidToolOutput", `Invalid output from tool '${name}': ${cause}`),
          })
-          return yield* decodeOutput(result, name)
        }),
        call,
      )
@@ -5,15 +5,15 @@ import { CodeMode, Tool, toolError } from "../src/index.js"
 const run = (tool: Tool.Tool<never>) =>
  Effect.runPromise(CodeMode.make({ tools: { host: { call: tool } } }).execute("return await tools.host.call({})"))

-class UnsafeHostError extends Schema.TaggedError<UnsafeHostError>()("UnsafeHostError", {
-  reason: Schema.String,
+class HostError extends Schema.TaggedError<HostError>()("HostError", {
+  message: Schema.String,
 }) {}

 describe("CodeMode host failure boundary", () => {
-  test("preserves explicit safe tool failures", async () => {
+  test("preserves explicit tool failures", async () => {
    const result = await run(
      Tool.make({
-        description: "Fail safely",
+        description: "Fail",
        input: Schema.Struct({}),
        output: Schema.String,
        execute: () => Effect.fail(toolError("Authorized request was refused")),
@@ -26,10 +26,10 @@ describe("CodeMode host failure boundary", () => {
    })
  })

-  test("does not rewrite explicit safe tool failures", async () => {
+  test("does not rewrite explicit tool failures", async () => {
    const result = await run(
      Tool.make({
-        description: "Fail safely",
+        description: "Fail",
        input: Schema.Struct({}),
        output: Schema.String,
        execute: () => Effect.fail(toolError("File not found: /tmp/report.json")),
@@ -42,10 +42,15 @@ describe("CodeMode host failure boundary", () => {
    })
  })

-  test("sanitizes unknown host failures and defects", async () => {
+  test("reports failures, defects, rejected Promises, and nested causes", async () => {
    for (const failure of [
-      Effect.fail(new UnsafeHostError({ reason: "Authorization: Bearer typed-secret" })),
-      Effect.die(new Error("postgres://user:defect-secret@example.invalid")),
+      Effect.fail(new HostError({ message: "Connection refused" })),
+      Effect.die(new Error("Connection refused")),
+      Effect.promise(async () => {
+        throw new Error("Connection refused")
+      }),
+      Effect.fail(toolError("Request failed", new Error("Connection refused"))),
+      Effect.failCause(Cause.combine(Cause.fail("Request failed"), Cause.die("Connection refused"))),
    ]) {
      const result = await run(
        Tool.make({
@@ -58,31 +63,28 @@ describe("CodeMode host failure boundary", () => {

      expect(result.ok ? undefined : result.error).toStrictEqual({
        kind: "ToolFailure",
-        message: "Tool execution failed",
+        message: expect.stringContaining("Connection refused"),
      })
-      expect(JSON.stringify(result)).not.toMatch(/typed-secret|defect-secret|Authorization: Bearer/)
    }
  })

-  test("sanitizes invalid host output", async () => {
-    const secret = "invalid-output-secret"
+  test("reports invalid host output", async () => {
    const result = await run(
      Tool.make({
        description: "Return invalid output",
        input: Schema.Struct({}),
-        output: Schema.Struct({ safe: Schema.String }),
-        execute: () => Effect.succeed({ safe: 1, secret } as unknown as { readonly safe: string }),
+        output: Schema.Struct({ value: Schema.String }),
+        execute: () => Effect.succeed({ value: 1 } as unknown as { readonly value: string }),
      }),
    )

    expect(result.ok ? undefined : result.error).toStrictEqual({
      kind: "InvalidToolOutput",
-      message: "Invalid output from tool 'host.call'.",
+      message: "Invalid output from tool 'host.call': SchemaError(Expected string\n  at [\"value\"])",
    })
-    expect(JSON.stringify(result)).not.toMatch(/invalid-output-secret/)
  })

-  test("sanitizes host output that throws while being copied", async () => {
+  test("reports host output copying errors", async () => {
    const result = await run(
      Tool.make({
        description: "Return hostile output",
@@ -94,7 +96,7 @@ describe("CodeMode host failure boundary", () => {
              {},
              {
                ownKeys: () => {
-                  throw new Error("host-output-secret")
+                  throw new Error("Cannot enumerate output")
                },
              },
            ),
@@ -104,9 +106,8 @@ describe("CodeMode host failure boundary", () => {

    expect(result.ok ? undefined : result.error).toStrictEqual({
      kind: "InvalidToolOutput",
-      message: "Invalid output from tool 'host.call'.",
+      message: "Invalid output from tool 'host.call': Error: Cannot enumerate output",
    })
-    expect(JSON.stringify(result)).not.toMatch(/host-output-secret/)
  })

  test("caught tool failures are Error values in-program", async () => {
@@ -229,7 +230,7 @@ describe("CodeMode tool-call observation", () => {
      { phase: "start", index: 0, name: "context.lookup" },
      { phase: "end", index: 0, name: "context.lookup", outcome: "failure", message: "Lookup refused" },
      { phase: "start", index: 0, name: "context.lookup" },
-      { phase: "end", index: 0, name: "context.lookup", outcome: "failure", message: "Tool execution failed" },
+      { phase: "end", index: 0, name: "context.lookup", outcome: "failure", message: "broken" },
    ])
  })

@@ -87,7 +87,7 @@ const layer = Layer.effect(
          draft.agents.delete(id)
        },
      }),
-      notify: () => bus.publish(Agent.Event.Updated, {}).pipe(Effect.asVoid),
+      finalize: () => bus.publish(Agent.Event.Updated, {}).pipe(Effect.asVoid),
    })
    const selectable = (agent: Info | undefined) =>
      agent && agent.mode !== "subagent" && !agent.hidden ? agent : undefined
@@ -612,12 +612,12 @@ function streamLanguage(language: LanguageModelV3, options: LanguageModelV3CallO
    Stream.unwrap(
      Effect.tryPromise({
        try: () => language.doStream(options),
-        catch: llmError,
+        catch: (error) => llmError(error, "request"),
      }).pipe(
        Effect.map((result) =>
          Stream.fromReadableStream({
            evaluate: () => result.stream,
-            onError: llmError,
+            onError: (error) => llmError(error, "read"),
          }).pipe(
            Stream.mapEffect((event) => streamPartEvents(state, event)),
            Stream.flatMap((events) => Stream.fromIterable(events)),
@@ -744,7 +744,7 @@ function streamPartEvents(
        }),
      ])
    case "error":
-      return Effect.fail(llmError(event.error))
+      return Effect.fail(llmError(event.error, "read"))
  }
 }

@@ -794,9 +794,20 @@ function messageValue(input: unknown) {
  }
 }

-function llmError(error: unknown) {
+function llmError(error: unknown, operation: "request" | "read") {
  if (error instanceof AIError) return error
  if (APICallError.isInstance(error)) return apiCallError(error)
+  const network = networkFailure(error)
+  if (network)
+    return new AIError({
+      reason: new TransportError({
+        message: network.message.trim() === "" ? unknownErrorMessage(error) : network.message,
+        cause: error,
+        transport: "http",
+        operation,
+        code: network.code,
+      }),
+    })
  return new AIError({
    reason: new UnknownProviderError({
      message: unknownErrorMessage(error),
@@ -806,6 +817,50 @@ function llmError(error: unknown) {
  })
 }

+// Runtime-generated network failure shapes. The codes mirror the AI SDK's own
+// Bun network error list in handleFetchError; the messages are undici's fetch
+// TypeError and stream termination strings plus our SSE chunk timeout error.
+// Unrecognized shapes still retry via the UnknownProvider default; this match
+// only adds transport semantics (continuation eligibility, display).
+const NETWORK_ERROR_CODES = new Set([
+  "ECONNRESET",
+  "ECONNREFUSED",
+  "ETIMEDOUT",
+  "EPIPE",
+  "ConnectionRefused",
+  "ConnectionClosed",
+  "FailedToOpenSocket",
+])
+const NETWORK_ERROR_MESSAGES = new Set([
+  "fetch failed",
+  "failed to fetch",
+  "terminated",
+  "other side closed",
+  "sse read timed out",
+])
+
+const NativeErrorShape = Schema.Struct({
+  message: Schema.String,
+  code: Schema.optionalKey(Schema.String),
+  cause: Schema.optionalKey(Schema.Unknown),
+})
+const decodeNativeErrorShape = Schema.decodeUnknownOption(NativeErrorShape)
+
+function networkFailure(error: unknown, depth = 0): { message: string; code?: string } | undefined {
+  if (depth > 4) return undefined
+  const shape = Option.getOrUndefined(decodeNativeErrorShape(error))
+  if (!shape) return undefined
+  // Prefer the deepest match: wrappers like undici's "fetch failed" TypeError
+  // carry the specific network code on their cause.
+  const cause = networkFailure(shape.cause, depth + 1)
+  if (cause) return cause
+  if (shape.code !== undefined && (NETWORK_ERROR_CODES.has(shape.code) || shape.code.startsWith("UND_ERR")))
+    return { message: shape.message, code: shape.code }
+  if (NETWORK_ERROR_MESSAGES.has(shape.message.trim().toLowerCase()))
+    return { message: shape.message, code: shape.code }
+  return undefined
+}
+
 function apiCallError(error: APICallError) {
  const failure = RequestExecutor.httpFailure({
    message: providerErrorMessage(error),
@@ -134,7 +134,7 @@ const layer = Layer.effect(
        }
        return result
      },
-      notify: Effect.fn("Catalog.notify")(function* () {
+      finalize: Effect.fn("Catalog.finalize")(function* () {
        yield* bus.publish(Catalog.Event.Updated, {})
      }),
    })
@@ -65,9 +65,7 @@ export const create = (
          (name, tool, input) =>
            Effect.gen(function* () {
              const index = yield* Ref.getAndUpdate(callIndex, (index) => index + 1)
-              const executed = yield* executeTool(name, tool, input, context).pipe(
-                Effect.mapError((failure) => toolError(failure.message, failure)),
-              )
+              const executed = yield* executeTool(name, tool, input, context)
              const content =
                typeof executed.content === "string"
                  ? [{ type: "text" as const, text: executed.content }]
@@ -60,7 +60,7 @@ export const layer = Layer.effect(
      draft: (draft) => ({
        add: (definition) => draft.set(definition.name, definition),
      }),
-      notify: () => bus.publish(Command.Event.Updated, {}).pipe(Effect.asVoid),
+      finalize: () => bus.publish(Command.Event.Updated, {}).pipe(Effect.asVoid),
    })
    const info = (definition: Definition) =>
      Info.make({
@@ -25,15 +25,19 @@ export class Service extends Context.Service<Service, Interface>()("@opencode/Lo
 const layer = Layer.effect(
  Service,
  Effect.gen(function* () {
+    let current: readonly string[] = []
    const listeners = new Set<(ignore: readonly string[]) => Effect.Effect<void>>()
-    const state: State.Interface<Data, Draft> = State.create<Data, Draft>({
+    const state = State.create<Data, Draft>({
      name: "location-watcher-policy",
      initial: () => ({ ignore: [] }),
      draft: (draft) => ({
        add: (ignore) => draft.ignore.push(...ignore),
        list: () => draft.ignore,
      }),
-      notify: () => Effect.forEach(listeners, (listener) => listener(state.get().ignore), { discard: true }),
+      finalize: (draft) =>
+        Effect.sync(() => {
+          current = [...draft.list()]
+        }).pipe(Effect.andThen(Effect.forEach(listeners, (listener) => listener(current), { discard: true }))),
    })
    const observe = Effect.fn("LocationWatcherPolicy.observe")(function* (
      listener: (ignore: readonly string[]) => Effect.Effect<void>,
@@ -52,7 +56,7 @@ const layer = Layer.effect(
    return Service.of({
      transform: state.transform,
      reload: state.reload,
-      current: () => state.get().ignore,
+      current: () => current,
      observe,
    })
  }),
@@ -74,7 +74,7 @@ export const layer = (options?: Options) =>
            draft.available = false
          },
        }),
-        notify: () => bus.publish(Event.Updated, {}).pipe(Effect.asVoid),
+        finalize: () => bus.publish(Event.Updated, {}).pipe(Effect.asVoid),
      })

      const source = (value: ReadonlyArray<File> | Instructions.Unavailable | Instructions.Removed) =>
@@ -328,7 +328,7 @@ const layer = Layer.effect(
          },
        },
      }),
-      notify: () => bus.publish(Integration.Event.Updated, {}).pipe(Effect.asVoid),
+      finalize: () => bus.publish(Integration.Event.Updated, {}).pipe(Effect.asVoid),
    })

    const createCredential = Effect.fnUntraced(function* (input: Parameters<Credential.Interface["create"]>[0]) {
@@ -402,13 +402,11 @@ const layer = Layer.effect(
          }

          yield* Effect.gen(function* () {
-            const persistence = yield* Effect.sync(() => {
-              const implementation = state
-                .get()
-                .integrations.get(attempt.integrationID)
-                ?.implementations.get(attempt.methodID)
-              return attempt.label ?? implementation?.label?.(exit.value)
-            }).pipe(
+            const implementation = state
+              .get()
+              .integrations.get(attempt.integrationID)
+              ?.implementations.get(attempt.methodID)
+            const persistence = yield* Effect.sync(() => attempt.label ?? implementation?.label?.(exit.value)).pipe(
              Effect.flatMap((label) =>
                createCredential({
                  integrationID: attempt.integrationID,
@@ -5,7 +5,7 @@ import { McpEvent } from "@opencode-ai/schema/mcp-event"
 import { ephemeral } from "@opencode-ai/schema/event"
 import { createHash } from "node:crypto"
 import { isDeepStrictEqual } from "node:util"
-import { Cause, Context, Effect, Exit, FiberSet, Latch, Layer, Schema, Scope, Semaphore, Stream, Types } from "effect"
+import { Cause, Context, Effect, Exit, FiberSet, Latch, Layer, Schema, Scope, Stream, Types } from "effect"
 import { makeLocationNode } from "@opencode-ai/util/effect/app-node"
 import { Credential } from "../credential.js"
 import { Bus } from "../bus.js"
@@ -613,10 +613,8 @@ export const layer = (options?: Options) =>

      let applied: Map<ServerName, Mcp.ServerConfig> | undefined
      const overrides = new Map<ServerName, Mcp.ServerConfig | false>()
-      const reconcileLock = Semaphore.makeUnsafe(1)
-      const reconcile = Effect.fnUntraced(function* () {
-        if (root.state._tag === "Closed") return
-        const servers = new Map(state.get().servers)
+      const reconcile = Effect.fnUntraced(function* (next: Draft) {
+        const servers = new Map(next.list())
        if (!applied && entries.size === 0) {
          for (const [name, server] of servers) {
            entries.set(name, {
@@ -678,7 +676,7 @@ export const layer = (options?: Options) =>
          Effect.ignore,
        ),
      )
-      const state: State.Interface<Data, Draft> = State.create<Data, Draft>({
+      const state = State.create<Data, Draft>({
        name: "mcp",
        initial: () => ({
          servers: new Map(
@@ -703,7 +701,7 @@ export const layer = (options?: Options) =>
          },
          remove: (server) => draft.servers.delete(ServerName.make(server)),
        }),
-        notify: () => reconcileLock.withPermit(reconcile()),
+        finalize: reconcile,
      })

      // Suspend so each await sees current entries; a bare Map iterator is exhausted after one run.
@@ -26,7 +26,6 @@ export type Info = Reference.Info

 type Data = {
  sources: Map<string, Types.DeepMutable<Source>>
-  materialized: Map<string, Info>
 }

 type Draft = {
@@ -48,71 +47,61 @@ const layer = Layer.effect(
    const bus = yield* Bus.Service
    const cache = yield* RepositoryCache.Service
    const scope = yield* Scope.Scope
-    const state: State.Interface<Data, Draft> = State.create<Data, Draft>({
+    const materialized = new Map<string, Info>()
+    const state = State.create<Data, Draft>({
      name: "reference",
-      initial: () => ({ sources: new Map(), materialized: new Map() }),
+      initial: () => ({ sources: new Map() }),
      draft: (draft) => ({
        add: (name, source) => draft.sources.set(name, source as Types.DeepMutable<Source>),
        remove: (name) => draft.sources.delete(name),
        list: () => Array.from(draft.sources.entries()) as [string, Source][],
      }),
-      prepare: (data) => {
-        for (const [name, source] of data.sources) {
-          if (source.type === "local") {
-            data.materialized.set(
+      finalize: (draft) =>
+        Effect.gen(function* () {
+          materialized.clear()
+          for (const [name, source] of draft.list()) {
+            if (source.type === "local") {
+              materialized.set(
+                name,
+                Info.make({
+                  name,
+                  path: source.path,
+                  ...(source.description === undefined ? {} : { description: source.description }),
+                  ...(source.hidden === undefined ? {} : { hidden: source.hidden }),
+                  source,
+                }),
+              )
+              continue
+            }
+            const repository = Repository.parse(source.repository)
+            if (!repository || !Repository.isRemote(repository)) continue
+            if (source.branch) {
+              try {
+                Repository.validateBranch(source.branch)
+              } catch {
+                continue
+              }
+            }
+            materialized.set(
              name,
              Info.make({
                name,
-                path: source.path,
+                path: AbsolutePath.make(Repository.cachePath(global.repos, repository, source.branch)),
                ...(source.description === undefined ? {} : { description: source.description }),
                ...(source.hidden === undefined ? {} : { hidden: source.hidden }),
                source,
              }),
            )
-            continue
-          }
-          const repository = Repository.parse(source.repository)
-          if (!repository || !Repository.isRemote(repository)) continue
-          if (source.branch) {
-            try {
-              Repository.validateBranch(source.branch)
-            } catch {
-              continue
-            }
-          }
-          data.materialized.set(
-            name,
-            Info.make({
-              name,
-              path: AbsolutePath.make(Repository.cachePath(global.repos, repository, source.branch)),
-              ...(source.description === undefined ? {} : { description: source.description }),
-              ...(source.hidden === undefined ? {} : { hidden: source.hidden }),
-              source,
-            }),
-          )
-        }
-      },
-      notify: () =>
-        Effect.gen(function* () {
-          for (const info of state.get().materialized.values()) {
-            const source = info.source
-            if (source.type !== "git") continue
-            yield* cache
-              .ensure({
-                reference: Repository.parseRemote(source.repository),
-                branch: source.branch,
-                refresh: true,
-              })
-              .pipe(
-                Effect.catchCause((cause) =>
-                  Effect.logWarning("failed to materialize reference", {
-                    name: info.name,
-                    repository: source.repository,
-                    cause,
-                  }),
-                ),
-                Effect.forkIn(scope),
-              )
+            yield* cache.ensure({ reference: repository, branch: source.branch, refresh: true }).pipe(
+              Effect.catchCause((cause) =>
+                Effect.logWarning("failed to materialize reference", {
+                  name,
+                  repository: source.repository,
+                  cause,
+                }),
+              ),
+              Effect.forkIn(scope),
+            )
          }
          yield* bus.publish(Reference.Event.Updated, {})
        }),
@@ -122,7 +111,7 @@ const layer = Layer.effect(
      transform: state.transform,
      reload: state.reload,
      list: Effect.fn("Reference.list")(function* () {
-        return Array.from(state.get().materialized.values())
+        return Array.from(materialized.values())
      }),
    })
  }),
@@ -396,7 +396,7 @@ export const createLLMEventPublisher = (bus: Pick<Bus.Interface, "publish">, inp
        yield* text.append(event.id, event.text, providerState(event.providerMetadata))
        return
      case "text-end":
-        yield* text.end(event.id, providerState(event.providerMetadata))
+        yield* text.end(event.id, providerState(event.providerMetadata), event.text)
        return
      case "reasoning-start":
        outputStarted = true
@@ -412,7 +412,7 @@ export const createLLMEventPublisher = (bus: Pick<Bus.Interface, "publish">, inp
        yield* reasoning.append(event.id, event.text, providerState(event.providerMetadata))
        return
      case "reasoning-end":
-        yield* reasoning.end(event.id, providerState(event.providerMetadata))
+        yield* reasoning.end(event.id, providerState(event.providerMetadata), event.text)
        return
      case "tool-input-start":
        outputStarted = true
@@ -26,12 +26,16 @@ export function isRetryable(error: AIError) {
      return error.reason.delivery === undefined || error.reason.delivery === "not-sent"
    case "InvalidProviderOutput":
      return error.reason.classification === "incomplete-stream"
+    // Unrecognized failures retry: classification records affirmative
+    // deterministic evidence, and transient failures are exactly the ones
+    // that arrive in shapes no classifier anticipates.
+    case "UnknownProvider":
+      return true
    case "Authentication":
    case "QuotaExceeded":
    case "ContentPolicy":
    case "InvalidRequest":
    case "NoRoute":
-    case "UnknownProvider":
      return false
    default: {
      const exhaustive: never = error.reason
@@ -109,7 +109,7 @@ const layer = Layer.effect(
          draft.skills.delete(ID.make(id))
        },
      }),
-      notify: () => bus.publish(Skill.Event.Updated, {}).pipe(Effect.asVoid),
+      finalize: () => bus.publish(Skill.Event.Updated, {}).pipe(Effect.asVoid),
    })

    return Service.of({
@@ -1,6 +1,6 @@
 export * as State from "./state.js"

-import { Clock, Context, Deferred, Effect, Exit, Scope } from "effect"
+import { Clock, Context, Deferred, Effect, Scope, Semaphore } from "effect"

 /**
 * A replayable transform applied to a draft during reload.
@@ -16,14 +16,13 @@ export interface Registration {
 }

 /**
- * Registers a scoped transform and invalidates the derived state. Closing the
- * owning Scope removes the transform. Reads synchronously replay pending changes.
+ * Registers and applies a scoped transform. Closing the owning Scope removes
+ * the transform and reloads the materialized state.
 */
 export type Transform<DraftApi> = (
  transform: TransformCallback<DraftApi>,
 ) => Effect.Effect<Registration, never, Scope.Scope>

-/** Invalidates captured inputs immediately and coalesces change notifications. */
 export type Reload = () => Effect.Effect<void>

 export interface Transformable<DraftApi> {
@@ -34,7 +33,7 @@ export interface Transformable<DraftApi> {
 type Batch = {
  active: boolean
  readonly flush: boolean
-  readonly notifications: Set<Reload>
+  readonly reloads: Set<Reload>
 }

 const CurrentBatch = Context.Reference<Batch | undefined>("@opencode/State/CurrentBatch", {
@@ -42,24 +41,17 @@ const CurrentBatch = Context.Reference<Batch | undefined>("@opencode/State/Curre
 })
 const reloadDebounce = 500

-/** Batches notifications, not read visibility. flush: false is terminal teardown. */
+/** flush: false is terminal teardown: states whose transforms are removed stop rebuilding, including pending reloads. */
 export function batch<A, E, R>(effect: Effect.Effect<A, E, R>, options: { readonly flush?: boolean } = {}) {
-  return Effect.uninterruptibleMask((restore) =>
-    Effect.gen(function* () {
-      const current = yield* CurrentBatch
-      if (current?.active && options.flush !== false) return yield* restore(effect)
-      const batch: Batch = { active: true, flush: options.flush !== false, notifications: new Set() }
-      const exit = yield* restore(effect.pipe(Effect.provideService(CurrentBatch, batch))).pipe(Effect.exit)
-      batch.active = false
-      const notifications = batch.flush
-        ? yield* Effect.forEach(batch.notifications, (notify) => restore(notify()).pipe(Effect.exit))
-        : []
-      // Accepted writes are not rolled back: one failed observer must not hide
-      // the other states' changes, or replace the batch body's failure.
-      yield* Exit.asVoidAll([exit, ...notifications])
-      return yield* exit
-    }),
-  )
+  return Effect.gen(function* () {
+    const current = yield* CurrentBatch
+    if (current?.active && options.flush !== false) return yield* effect
+    const batch: Batch = { active: true, flush: options.flush !== false, reloads: new Set() }
+    const exit = yield* effect.pipe(Effect.provideService(CurrentBatch, batch), Effect.exit)
+    batch.active = false
+    if (batch.flush) yield* Effect.forEach(batch.reloads, (reload) => reload(), { discard: true })
+    return yield* exit
+  })
 }

 export const inherit = Effect.fnUntraced(function* () {
@@ -73,117 +65,124 @@ export interface Options<State, DraftApi> {
  readonly initial: () => State
  /** Wraps mutable state in a domain-specific draft API. */
  readonly draft: MakeDraft<State, DraftApi>
-  /** Synchronously completes derived data after ordered transform replay. */
-  readonly prepare?: (state: State) => void
  /**
-   * Observes accepted changes outside the read path. Batched writes notify at
-   * batch completion; reloads debounce notifications. Reads never run this hook.
-   * Resource reconciliation owns any coordination it requires.
+   * Runs after the rebuilt state becomes visible. Update events published here
+   * act as read barriers: subscribers refetching on the event observe the
+   * committed state.
   */
-  readonly notify?: () => Effect.Effect<void>
+  readonly finalize?: (draft: DraftApi) => Effect.Effect<void>
 }

 export interface Interface<State, DraftApi> extends Transformable<DraftApi> {
-  /** Returns the latest accepted state, replaying stale inputs synchronously. */
  readonly get: () => State
 }

 export function create<State, DraftApi>(options: Options<State, DraftApi>): Interface<State, DraftApi> {
  let state = options.initial()
-  const transforms = new Set<{ run: TransformCallback<DraftApi> }>()
-  let dirty = false
+  let transforms: { run: TransformCallback<DraftApi> }[] = []
+  let generation = 0
  let requestedAt = 0
  let running = false
  let closed = false
-  let waiters: Deferred.Deferred<void>[] = []
+  let waiters: { generation: number; done: Deferred.Deferred<void> }[] = []
+  const semaphore = Semaphore.makeUnsafe(1)

-  const get = () => {
-    if (!dirty || closed) return state
-    const next = options.initial()
-    const api = options.draft(next)
-    transforms.forEach((transform) => transform.run(api))
-    options.prepare?.(next)
+  const commit = Effect.fn("State.commit")(function* (next: State) {
    state = next
-    dirty = false
-    return state
-  }
-
-  const notify = Effect.fn("State.notify")(function* () {
-    if (closed) return
-    get()
-    if (options.notify) yield* options.notify()
+    if (options.finalize) yield* options.finalize(options.draft(next))
  })

-  const publish = (): Effect.Effect<void> =>
+  const materialize = Effect.fnUntraced(function* () {
+    if (closed) return
+    const next = options.initial()
+    const api = options.draft(next)
+    for (const transform of transforms) {
+      yield* Effect.sync(() => {
+        transform.run(api)
+      })
+    }
+    yield* commit(next)
+  })
+
+  const materializeReload = () => semaphore.withPermit(materialize())
+
+  const rebuild = (): Effect.Effect<void> =>
    Effect.gen(function* () {
      const clock = yield* Clock.Clock
      const remaining = requestedAt + reloadDebounce - clock.currentTimeMillisUnsafe()
      if (remaining > 0) yield* Effect.sleep(remaining)
-      if (clock.currentTimeMillisUnsafe() < requestedAt + reloadDebounce) return yield* publish()
+      if (clock.currentTimeMillisUnsafe() < requestedAt + reloadDebounce) return yield* rebuild()

-      // Release scheduling ownership before observers run: an observer may
-      // request and await another reload without joining this notification.
-      const completed = waiters
-      waiters = []
-      running = false
-      const exit = yield* notify().pipe(Effect.exit)
-      yield* Effect.forEach(completed, (done) => Deferred.done(done, exit), {
+      const target = generation
+      const exit = yield* materializeReload().pipe(Effect.exit)
+      const completed = waiters.filter((waiter) => waiter.generation <= target)
+      waiters = waiters.filter((waiter) => waiter.generation > target)
+      yield* Effect.forEach(completed, (waiter) => Deferred.done(waiter.done, exit), {
        concurrency: "unbounded",
        discard: true,
      })
+      if (generation > target) return yield* rebuild()
+      running = false
    })

-  const changed = (debounce: boolean) =>
-    Effect.uninterruptibleMask((restore) =>
-      Effect.gen(function* () {
-        if (closed) return
-        if (debounce) dirty = true
-        const batch = yield* CurrentBatch
-        if (batch?.active) {
-          if (!batch.flush) {
-            closed = true
-            return
-          }
-          batch.notifications.add(notify)
-          return
-        }
-        if (!debounce) return yield* restore(notify())
-
-        const done = Deferred.makeUnsafe<void>()
-        const clock = yield* Clock.Clock
-        requestedAt = clock.currentTimeMillisUnsafe()
-        waiters.push(done)
-        if (!running) {
-          running = true
-          yield* publish().pipe(Effect.forkDetach)
-        }
-        yield* restore(Deferred.await(done))
-      }),
-    )
+  const reload = Effect.fnUntraced(function* () {
+    if (closed) return
+    const done = Deferred.makeUnsafe<void>()
+    const clock = yield* Clock.Clock
+    generation++
+    requestedAt = clock.currentTimeMillisUnsafe()
+    waiters.push({ generation, done })
+    if (!running) {
+      running = true
+      yield* rebuild().pipe(Effect.forkDetach)
+    }
+    yield* Deferred.await(done)
+  })

  return {
-    get,
+    get: () => state,
    transform: Effect.fn("State.transform")(function* (update) {
      yield* Effect.annotateCurrentSpan("state", options.name ?? "anonymous")
      const scope = yield* Scope.Scope
      return yield* Effect.uninterruptible(
        Effect.gen(function* () {
          const transform = { run: update }
+          let active = true
          const dispose = Effect.uninterruptible(
-            Effect.suspend(() => {
-              if (!transforms.delete(transform)) return Effect.void
-              dirty = true
-              return changed(false)
+            semaphore.withPermit(
+              Effect.suspend(() => {
+                if (!active) return Effect.void
+                active = false
+                transforms = transforms.filter((item) => item !== transform)
+                return Effect.gen(function* () {
+                  const batch = yield* CurrentBatch
+                  if (batch?.active) {
+                    // Detached debounced reloads must also stay quiet after teardown.
+                    if (!batch.flush) {
+                      closed = true
+                      return
+                    }
+                    batch.reloads.add(materializeReload)
+                    return
+                  }
+                  yield* materialize()
+                })
+              }),
+            ),
+          )
+          yield* semaphore.withPermit(
+            Effect.sync(() => {
+              transforms = [...transforms, transform]
            }),
          )
-          transforms.add(transform)
-          dirty = true
          yield* Scope.addFinalizer(scope, dispose)
-          yield* changed(false)
+          const batch = yield* CurrentBatch
+          if (batch?.active) batch.reloads.add(materializeReload)
+          else yield* materializeReload()
          return { dispose }
        }),
      )
    }),
-    reload: () => changed(true),
+    reload,
  }
 }
@@ -185,7 +185,7 @@ const layer = Layer.effect(
          draft.tools.delete(id)
        },
      }),
-      notify: () =>
+      finalize: () =>
        Effect.forEach(
          state.get().errors,
          ({ tool, error }) =>
@@ -19,7 +19,7 @@ export const name = "shell"
 export const DEFAULT_TIMEOUT_MS = 2 * 60 * 1_000

 const BACKGROUND_INSTRUCTION =
-  "You will be notified automatically when the command finishes. Avoid sleep commands or polling for completion; if you need the output before then, read the file directly."
+  "You will be notified automatically when the command finishes. The notification will include the command's output. DO NOT run sleep commands or poll the output file to check for completion. You can read from the file when its current output would be useful, such as when inspecting logs from a background server. Otherwise, continue with other work or end your response."
 const OS =
  process.platform === "darwin"
    ? "macOS"
@@ -1,7 +1,7 @@
 export * as Vcs from "./vcs.js"

 import path from "path"
-import { Cause, Context, Effect, Layer, Schema, Semaphore, Stream } from "effect"
+import { Cause, Context, Effect, Layer, Schema, Stream } from "effect"
 import type { VcsDefinition, VcsDraft } from "@opencode-ai/plugin/effect/vcs"
 import { FileDiff } from "@opencode-ai/schema/file-diff"
 import { FileSystem } from "@opencode-ai/schema/filesystem"
@@ -49,7 +49,6 @@ const layer = Layer.effect(
    const bus = yield* Bus.Service
    const vcs = location.vcs
    const current: { info: Info } = { info: { branch: {} } }
-    const refreshLock = Semaphore.makeUnsafe(1)
    const scope = {
      directory: location.directory,
      worktree: location.project.directory,
@@ -70,7 +69,7 @@ const layer = Layer.effect(
          set: (selection) => (draft.selection = selection),
        },
      }),
-      notify: () => refresh(),
+      finalize: () => refresh(),
    })
    const selected = () => {
      const value = state.get()
@@ -88,23 +87,13 @@ const layer = Layer.effect(
        ),
      )
    const refresh = Effect.fn("Vcs.refresh")(function* () {
-      const changed = yield* Effect.gen(function* () {
-        const provider = selected()
-        const next: Info = provider
-          ? yield* protect(provider, "info", provider.info(scope).pipe(Effect.flatMap(decodeInfo)), { branch: {} })
-          : { branch: {} }
-        const changed = current.info.branch.current !== next.branch.current
-        current.info = next
-        return changed
-      }).pipe(refreshLock.withPermit)
-      if (!changed) return
-      // Legacy listeners can publish nested updates before streams and SSE receive
-      // this event. Re-announce the latest branch if publication was overtaken.
-      while (true) {
-        const branch = current.info.branch.current
-        yield* bus.publish(VcsEvent.BranchUpdated, { branch })
-        if (branch === current.info.branch.current) return
-      }
+      const provider = selected()
+      const next: Info = provider
+        ? yield* protect(provider, "info", provider.info(scope).pipe(Effect.flatMap(decodeInfo)), { branch: {} })
+        : { branch: {} }
+      const changed = current.info.branch.current !== next.branch.current
+      current.info = next
+      if (changed) yield* bus.publish(VcsEvent.BranchUpdated, { branch: next.branch.current })
    })

    if (vcs) {
@@ -88,7 +88,7 @@ const layer = Layer.effect(
          set: (selection) => (draft.selection = selection),
        },
      }),
-      notify: () => bus.publish(WebSearch.Event.Updated, {}).pipe(Effect.asVoid),
+      finalize: () => bus.publish(WebSearch.Event.Updated, {}).pipe(Effect.asVoid),
    })

    const requireProvider = (providers: Map<ID, ProviderImplementation>, providerID: ID) => {
@@ -757,7 +757,7 @@ it.effect("classifies data-only AI SDK authentication errors", () =>
        data: { error: { code: "authentication_error" } },
      }),
    )
-    expect(error.reason).toMatchObject({ _tag: "Authentication", kind: "invalid" })
+    expect(error.reason).toMatchObject({ _tag: "Authentication" })
    expect(SessionRunnerRetry.isRetryable(error)).toBeFalse()
  }),
 )
@@ -776,7 +776,7 @@ Object.entries({
        responseBody,
      })
      const error = yield* streamFailure(cause)
-      expect(error.reason).toMatchObject({ _tag: "Authentication", kind: "invalid" })
+      expect(error.reason).toMatchObject({ _tag: "Authentication" })
      expect(SessionRunnerRetry.isRetryable(error)).toBeFalse()
      expect(error.reason.body).toBe(responseBody)
      expect(error.reason.cause).toBe(cause)
@@ -823,6 +823,55 @@ it.effect("retries status-less AI SDK transport failures", () =>
  }),
 )

+it.effect("classifies native fetch failures as request transport errors", () =>
+  Effect.gen(function* () {
+    const cause = Object.assign(new TypeError("fetch failed"), {
+      cause: Object.assign(new Error("connect ECONNREFUSED 127.0.0.1:443"), { code: "ECONNREFUSED" }),
+    })
+    const error = yield* streamFailure(cause)
+    expect(error.reason).toMatchObject({
+      _tag: "Transport",
+      transport: "http",
+      operation: "request",
+      code: "ECONNREFUSED",
+    })
+    expect(error.message).toBe("connect ECONNREFUSED 127.0.0.1:443")
+    expect(error.reason.cause).toBe(cause)
+    expect(SessionRunnerRetry.isRetryable(error)).toBeTrue()
+  }),
+)
+
+it.effect("classifies mid-stream socket drops as read transport errors", () =>
+  Effect.gen(function* () {
+    const cause = Object.assign(new Error("terminated"), {
+      cause: Object.assign(new Error("other side closed"), { code: "UND_ERR_SOCKET" }),
+    })
+    const error = yield* streamFailure(cause, true)
+    expect(error.reason).toMatchObject({
+      _tag: "Transport",
+      transport: "http",
+      operation: "read",
+      code: "UND_ERR_SOCKET",
+    })
+    expect(SessionRunnerRetry.isRetryable(error)).toBeTrue()
+  }),
+)
+
+it.effect("classifies the SSE chunk timeout as a read transport error", () =>
+  Effect.gen(function* () {
+    const error = yield* streamFailure(new Error("SSE read timed out"), true)
+    expect(error.reason).toMatchObject({ _tag: "Transport", transport: "http", operation: "read" })
+    expect(SessionRunnerRetry.isRetryable(error)).toBeTrue()
+  }),
+)
+
+it.effect("keeps unrecognized error codes on the unknown provider path", () =>
+  Effect.gen(function* () {
+    const error = yield* streamFailure(Object.assign(new Error("kaput"), { code: "E_SOMETHING_ELSE" }), true)
+    expect(error.reason).toBeInstanceOf(UnknownProviderError)
+  }),
+)
+
 it.effect("prefers a structured provider message over the code fallback", () =>
  Effect.gen(function* () {
    const error = yield* streamFailure(
@@ -1,5 +1,5 @@
 import { describe, expect } from "bun:test"
-import { Cause, Deferred, Effect, Exit, Fiber, Layer, Option, Ref, Schema, Stream } from "effect"
+import { Cause, Deferred, Effect, Exit, Fiber, Layer, Ref, Schema, Stream } from "effect"
 import { Bus } from "@opencode-ai/core/bus"
 import { Event } from "@opencode-ai/schema/event"
 import { Session } from "@opencode-ai/schema/session"
@@ -228,10 +228,10 @@ describe("Bus", () => {
      )

      const event = yield* bus.publish(SyncMessage, { id: "one", text: "hello" })
-      yield* bus.publish(SyncMessage, { id: "one", text: "after unsubscribe" })
+      yield* bus.publish(SyncMessage, { id: "one", text: "second event" })

      expect(received[0]).toEqual(event)
-      expect(received[1]?.data).toEqual({ id: "one", text: "after unsubscribe" })
+      expect(received[1]?.data).toEqual({ id: "one", text: "second event" })
    }),
  )

@@ -11,7 +11,6 @@ import { Location } from "@opencode-ai/core/location"
 import { Model } from "@opencode-ai/core/model"
 import { Provider } from "@opencode-ai/core/provider"
 import { AbsolutePath } from "@opencode-ai/core/schema"
-import { State } from "@opencode-ai/core/state"
 import { location } from "./fixture/location"
 import { testEffect } from "./lib/effect"

@@ -31,57 +30,6 @@ const catalogLayer = AppNodeBuilder.build(
 const it = testEffect(catalogLayer)

 describe("Catalog", () => {
-  it.effect("reads available and default models inside a batch before publishing", () =>
-    Effect.gen(function* () {
-      const catalog = yield* Catalog.Service
-      const bus = yield* Bus.Service
-      const observed: string[] = []
-      const unsubscribe = yield* bus.listen((event) =>
-        event.type === Catalog.Event.Updated.type
-          ? catalog.model.default().pipe(
-              Effect.map((model) => {
-                observed.push(model?.id ?? "none")
-              }),
-            )
-          : Effect.void,
-      )
-      yield* Effect.addFinalizer(() => unsubscribe)
-      const providerID = Provider.ID.make("test")
-      const old = Model.ID.make("old")
-      const newest = Model.ID.make("new")
-
-      yield* State.batch(
-        Effect.gen(function* () {
-          yield* catalog.transform((draft) => {
-            draft.provider.update(providerID, () => {})
-            draft.model.update(providerID, old, (model) => {
-              model.time.released = 1000
-            })
-            draft.model.update(providerID, newest, (model) => {
-              model.time.released = 2000
-            })
-            draft.model.default.set(providerID, old)
-          })
-          expect((yield* catalog.model.available()).map((model) => model.id)).toEqual([newest, old])
-          expect((yield* catalog.model.default())?.id).toBe(old)
-
-          const overlay = yield* catalog.transform((draft) =>
-            draft.model.update(providerID, old, (model) => {
-              model.enabled = false
-            }),
-          )
-          expect((yield* catalog.model.available()).map((model) => model.id)).toEqual([newest])
-          expect((yield* catalog.model.default())?.id).toBe(newest)
-          yield* overlay.dispose
-          expect((yield* catalog.model.default())?.id).toBe(old)
-          expect(observed).toEqual([])
-        }),
-      )
-
-      expect(observed).toEqual([old])
-    }),
-  )
-
  it.effect("publishes an updated event after catalog changes", () =>
    Effect.gen(function* () {
      const catalog = yield* Catalog.Service
@@ -343,7 +291,6 @@ describe("Catalog", () => {

      configured = false
      const reload = yield* catalog.reload().pipe(Effect.forkChild({ startImmediately: true }))
-      expect((yield* catalog.model.default())?.id).toBe(newest)
      yield* TestClock.adjust("500 millis")
      yield* Fiber.join(reload)
      expect((yield* catalog.model.default())?.id).toBe(newest)
@@ -13,7 +13,6 @@ import { LayerNode } from "@opencode-ai/util/effect/layer-node"
 import { Credential } from "@opencode-ai/core/credential"
 import { ConfigMigrateV1 } from "@opencode-ai/core/v1/config/migrate"
 import { ConfigV1 } from "@opencode-ai/core/v1/config/config"
-import { FSUtil } from "@opencode-ai/util/fs-util"
 import { Watcher } from "@opencode-ai/core/filesystem/watcher"
 import { Bus } from "@opencode-ai/core/bus"
 import { Global } from "@opencode-ai/util/global"
@@ -7,7 +7,7 @@ import { SqliteClient } from "@effect/sql-sqlite-bun"
 import { eq, sql } from "drizzle-orm"
 import { integer, sqliteTable, text } from "drizzle-orm/sqlite-core"
 import { Effect, Tracer } from "effect"
-import type { SqlClient as SqlClientService } from "effect/unstable/sql/SqlClient"
+import type { SqlClient } from "effect/unstable/sql/SqlClient"
 import { isSqlError } from "effect/unstable/sql/SqlError"
 import { EffectDrizzleSqlite } from "@opencode-ai/core/database/drizzle"

@@ -16,7 +16,7 @@ const users = sqliteTable("users", {
  name: text().notNull(),
 })

-const run = <A, E>(effect: Effect.Effect<A, E, SqlClientService>) =>
+const run = <A, E>(effect: Effect.Effect<A, E, SqlClient>) =>
  Effect.runPromise(
    effect.pipe(Effect.provide(SqliteClient.layer({ filename: ":memory:", disableWAL: true })), Effect.scoped),
  )
@@ -2,8 +2,7 @@ import { describe, expect } from "bun:test"
 import fs from "node:fs/promises"
 import os from "node:os"
 import path from "node:path"
-import { Effect, Exit, Stream } from "effect"
-import type * as PlatformError from "effect/PlatformError"
+import { Effect, Exit, PlatformError, Stream } from "effect"
 import { ChildProcess, ChildProcessSpawner } from "effect/unstable/process"
 import { CrossSpawnSpawner } from "@opencode-ai/util/cross-spawn-spawner"
 import { LayerNode } from "@opencode-ai/util/effect/layer-node"
@@ -1,5 +1,5 @@
 import { describe, expect, test } from "bun:test"
-import { Effect, Layer, Logger } from "effect"
+import { Effect, Logger } from "effect"
 import { AppNodeBuilder } from "@opencode-ai/core/effect/app-node-builder"
 import { LayerNode } from "@opencode-ai/util/effect/layer-node"
 import { Database } from "@opencode-ai/core/database/database"
@@ -1,127 +0,0 @@
-import { describe, expect } from "bun:test"
-import { Effect, Fiber, Scope } from "effect"
-import { TestClock } from "effect/testing"
-import { AppNodeBuilder } from "@opencode-ai/core/effect/app-node-builder"
-import { LocationWatcherPolicy } from "@opencode-ai/core/filesystem/location-watcher-policy"
-import { State } from "@opencode-ai/core/state"
-import { testEffect } from "../lib/effect"
-
-const it = testEffect(AppNodeBuilder.build(LocationWatcherPolicy.node))
-
-describe("LocationWatcherPolicy", () => {
-  it.effect("reads batched registrations and disposals without notifying observers", () =>
-    Effect.gen(function* () {
-      const policy = yield* LocationWatcherPolicy.Service
-      const observed: string[][] = []
-      yield* policy.observe((ignore) =>
-        Effect.sync(() => {
-          observed.push([...ignore])
-        }),
-      )
-
-      yield* State.batch(
-        Effect.gen(function* () {
-          yield* policy.transform((draft) => draft.add(["base"]))
-          const overlay = yield* policy.transform((draft) => draft.add(["overlay"]))
-          const snapshot = policy.current()
-          expect(snapshot).toEqual(["base", "overlay"])
-          expect(observed).toEqual([])
-
-          yield* overlay.dispose
-          expect(policy.current()).toEqual(["base"])
-          expect(snapshot).toEqual(["base", "overlay"])
-          expect(observed).toEqual([])
-        }),
-      )
-
-      expect(observed).toEqual([["base"]])
-    }),
-  )
-
-  it.effect("reads reloaded patterns before debounced observer reconciliation", () =>
-    Effect.gen(function* () {
-      const policy = yield* LocationWatcherPolicy.Service
-      const observed: string[][] = []
-      let ignore = ["first"]
-      yield* policy.observe((ignore) =>
-        Effect.sync(() => {
-          observed.push([...ignore])
-        }),
-      )
-      yield* policy.transform((draft) => draft.add(ignore))
-      const snapshot = policy.current()
-      observed.length = 0
-
-      ignore = ["second"]
-      const reload = yield* policy.reload().pipe(Effect.forkChild({ startImmediately: true }))
-      expect(policy.current()).toEqual(["second"])
-      expect(snapshot).toEqual(["first"])
-      expect(observed).toEqual([])
-
-      yield* TestClock.adjust("500 millis")
-      yield* Fiber.join(reload)
-      expect(observed).toEqual([["second"]])
-    }),
-  )
-
-  it.effect("passes the latest policy to later observers after a reentrant registration", () =>
-    Effect.gen(function* () {
-      const policy = yield* LocationWatcherPolicy.Service
-      const scope = yield* Scope.Scope
-      const observed: string[][] = []
-      let reentered = false
-      yield* policy.observe(() =>
-        Effect.gen(function* () {
-          if (reentered) return
-          reentered = true
-          yield* policy.transform((draft) => draft.add(["inner"])).pipe(Scope.provide(scope))
-        }),
-      )
-      yield* policy.observe((ignore) =>
-        Effect.sync(() => {
-          observed.push([...ignore])
-        }),
-      )
-
-      yield* policy.transform((draft) => draft.add(["outer"]))
-
-      expect(policy.current()).toEqual(["outer", "inner"])
-      expect(observed).toEqual([
-        ["outer", "inner"],
-        ["outer", "inner"],
-      ])
-    }),
-  )
-
-  it.effect("allows an observer to await a reload and keeps later observers current", () =>
-    Effect.gen(function* () {
-      const policy = yield* LocationWatcherPolicy.Service
-      const observed: string[][] = []
-      let ignore = ["first"]
-      let reentered = false
-      yield* policy.observe(() =>
-        Effect.gen(function* () {
-          if (reentered) return
-          reentered = true
-          ignore = ["second"]
-          yield* policy.reload()
-        }),
-      )
-      yield* policy.observe((ignore) =>
-        Effect.sync(() => {
-          observed.push([...ignore])
-        }),
-      )
-
-      const writer = yield* policy
-        .transform((draft) => draft.add(ignore))
-        .pipe(Effect.forkChild({ startImmediately: true }))
-      expect(policy.current()).toEqual(["second"])
-      expect(observed).toEqual([])
-
-      yield* TestClock.adjust("500 millis")
-      yield* Fiber.join(writer)
-      expect(observed).toEqual([["second"], ["second"]])
-    }),
-  )
-})
@@ -1,4 +1,4 @@
-import { Effect, Layer, Stream } from "effect"
+import { Effect, Layer } from "effect"
 import { Config } from "@opencode-ai/core/config"
 import { Location } from "@opencode-ai/core/location"
 import { Mcp } from "@opencode-ai/core/mcp/index"
@@ -1,25 +1,36 @@
 import fs from "fs/promises"
-import { tmpdir as osTmpdir } from "os"
+import os from "os"
 import path from "path"
 import { Effect } from "effect"

+type TempDir = { readonly path: string }
+
 export const tmpdir = async (prefix = "opencode-core-test-") => {
-  const dir = await fs.realpath(await fs.mkdtemp(path.join(osTmpdir(), prefix)))
+  const dir = await make(prefix)
  return {
    path: dir,
-    async [Symbol.asyncDispose]() {
-      await remove(dir)
+    [Symbol.asyncDispose]() {
+      return remove(dir)
    },
  }
 }

-export const withTempDir = <A, E, R>(body: (tmp: Awaited<ReturnType<typeof tmpdir>>) => Effect.Effect<A, E, R>) =>
+export const tmpdirScoped = (prefix = "opencode-core-test-") =>
+  Effect.acquireRelease(
+    Effect.tryPromise(() => make(prefix)),
+    (dir) => Effect.tryPromise(() => remove(dir)).pipe(Effect.orDie),
+  ).pipe(Effect.map((path) => ({ path })))
+
+export const withTempDir = <A, E, R>(body: (tmp: TempDir) => Effect.Effect<A, E, R>) =>
  Effect.acquireUseRelease(
-    Effect.promise(() => tmpdir()),
-    body,
-    (tmp) => Effect.promise(() => tmp[Symbol.asyncDispose]()),
+    Effect.tryPromise(() => make("opencode-core-test-")),
+    (path) => body({ path }),
+    (dir) => Effect.tryPromise(() => remove(dir)).pipe(Effect.orDie),
  )

+const make = async (prefix: string) => fs.realpath(await fs.mkdtemp(path.join(os.tmpdir(), prefix)))
+
+// Bun's callback APIs expose short paths and can hang during recursive removal on Windows.
 async function remove(dir: string, retries = 30): Promise<void> {
  try {
    await fs.rm(dir, { recursive: true, force: true })
@@ -7,7 +7,6 @@ import { Bus } from "@opencode-ai/core/bus"
 import { ConfigInstructionPlugin } from "@opencode-ai/core/config/plugin/instruction"
 import { Watcher } from "@opencode-ai/core/filesystem/watcher"
 import { InstructionDiscovery } from "@opencode-ai/core/instruction-discovery"
-import { Instructions } from "@opencode-ai/core/instructions/index"
 import { Location } from "@opencode-ai/core/location"
 import { AbsolutePath } from "@opencode-ai/core/schema"
 import { FSUtil } from "@opencode-ai/util/fs-util"
@@ -1,7 +1,7 @@
 import { describe, expect } from "bun:test"
 import os from "os"
 import { Effect, Layer } from "effect"
-import * as TestClock from "effect/testing/TestClock"
+import { TestClock } from "effect/testing"
 import { AppNodeBuilder } from "@opencode-ai/core/effect/app-node-builder"
 import { Location } from "@opencode-ai/core/location"
 import { FSUtil } from "@opencode-ai/util/fs-util"
@@ -1,73 +0,0 @@
-import { describe, expect } from "bun:test"
-import { Cause, Effect, Exit, Fiber } from "effect"
-import { TestClock } from "effect/testing"
-import { Credential } from "@opencode-ai/core/credential"
-import { AppNodeBuilder } from "@opencode-ai/core/effect/app-node-builder"
-import { Integration } from "@opencode-ai/core/integration"
-import { LayerNode } from "@opencode-ai/util/effect/layer-node"
-import { testEffect } from "./lib/effect"
-
-const it = testEffect(AppNodeBuilder.build(LayerNode.group([Integration.node, Credential.node])))
-
-describe("Integration replay", () => {
-  it.effect("fails and closes an OAuth attempt when fresh implementation replay throws", () =>
-    Effect.gen(function* () {
-      const integrations = yield* Integration.Service
-      const credentials = yield* Credential.Service
-      const integrationID = Integration.ID.make("replay-test")
-      const methodID = Integration.MethodID.make("code")
-      const source = { fail: false, closed: false }
-      const failure = new Error("integration transform replay failed")
-      yield* integrations.transform((editor) => {
-        if (source.fail) throw failure
-        editor.method.update({
-          integrationID,
-          method: { id: methodID, type: "oauth", label: "Fixture" },
-          authorize: () =>
-            Effect.addFinalizer(() => Effect.sync(() => (source.closed = true))).pipe(
-              Effect.as({
-                mode: "code" as const,
-                url: "https://example.com/authorize",
-                instructions: "Enter the fixture code",
-                callback: () =>
-                  Effect.succeed(
-                    Credential.OAuth.make({
-                      type: "oauth",
-                      methodID,
-                      access: "dummy-access",
-                      refresh: "dummy-refresh",
-                      expires: Number.MAX_SAFE_INTEGER,
-                    }),
-                  ),
-              }),
-            ),
-        })
-      })
-
-      const attempt = yield* integrations.oauth.connect({ integrationID, methodID, label: "Fixture" })
-      source.fail = true
-      const reload = yield* integrations.reload().pipe(Effect.exit, Effect.forkChild({ startImmediately: true }))
-      yield* Effect.addFinalizer(() =>
-        Effect.gen(function* () {
-          source.fail = false
-          yield* TestClock.adjust("500 millis")
-          yield* Fiber.join(reload)
-        }),
-      )
-
-      const exit = yield* integrations.oauth
-        .complete({ integrationID, attemptID: attempt.attemptID, code: "dummy-code" })
-        .pipe(Effect.exit)
-
-      expect(Exit.isFailure(exit) && Cause.hasDies(exit.cause)).toBe(true)
-      expect(Exit.isFailure(exit) && Cause.squash(exit.cause)).toBe(failure)
-      expect(yield* integrations.oauth.status({ integrationID, attemptID: attempt.attemptID })).toEqual({
-        status: "failed",
-        message: failure.message,
-        time: attempt.time,
-      })
-      expect(source.closed).toBe(true)
-      expect(yield* credentials.list(integrationID)).toEqual([])
-    }),
-  )
-})
@@ -1,13 +1,12 @@
 import { describe, expect } from "bun:test"
 import { Cause, Clock, Duration, Effect, Exit, Fiber, Layer, Scope, Stream } from "effect"
-import * as TestClock from "effect/testing/TestClock"
+import { TestClock } from "effect/testing"
 import { Credential } from "@opencode-ai/core/credential"
 import { AppNodeBuilder } from "@opencode-ai/core/effect/app-node-builder"
 import { makeGlobalNode } from "@opencode-ai/util/effect/app-node"
 import { LayerNode } from "@opencode-ai/util/effect/layer-node"
 import { Bus } from "@opencode-ai/core/bus"
 import { Integration } from "@opencode-ai/core/integration"
-import { State } from "@opencode-ai/core/state"
 import { testEffect } from "./lib/effect"

 const it = testEffect(AppNodeBuilder.build(LayerNode.group([Integration.node, Credential.node, Bus.node])))
@@ -263,102 +262,6 @@ describe("Integration", () => {
    }),
  )

-  it.effect("resolves stored OAuth with refresh registrations made inside a batch", () =>
-    Effect.gen(function* () {
-      const integrations = yield* Integration.Service
-      const credentials = yield* Credential.Service
-      const integrationID = Integration.ID.make("acme")
-      const method = Integration.OAuthMethod.make({
-        id: Integration.MethodID.make("browser"),
-        type: "oauth",
-        label: "Browser",
-      })
-      const expired = Credential.OAuth.make({
-        type: "oauth",
-        methodID: method.id,
-        access: "expired",
-        refresh: "refresh",
-        expires: 0,
-      })
-      const fresh = Credential.OAuth.make({
-        ...expired,
-        access: "fresh",
-        refresh: "fresh-refresh",
-        expires: (yield* Clock.currentTimeMillis) + Duration.toMillis(Duration.hours(1)),
-      })
-      const stored = yield* credentials.create({ integrationID, label: "Personal", value: expired })
-      const connection = { type: "credential" as const, id: stored.id, label: stored.label }
-      const calls: string[] = []
-      const implementation = {
-        integrationID,
-        method,
-        authorize: () => Effect.die("unexpected authorization"),
-        refresh: (value: Credential.OAuth) =>
-          Effect.sync(() => {
-            expect(value).toEqual(expired)
-            calls.push("original")
-            return fresh
-          }),
-      }
-
-      yield* State.batch(
-        Effect.gen(function* () {
-          yield* integrations.transform((editor) => editor.method.update(implementation))
-          expect(yield* integrations.connection.resolve(connection)).toEqual(fresh)
-          expect((yield* credentials.get(stored.id))?.value).toEqual(fresh)
-          expect(calls).toEqual(["original"])
-
-          expect(yield* integrations.connection.resolve(connection)).toEqual(fresh)
-          expect(calls).toEqual(["original"])
-
-          yield* credentials.update(stored.id, { value: expired })
-          const overridden = Credential.OAuth.make({ ...fresh, access: "override" })
-          const override = yield* integrations.transform((editor) =>
-            editor.method.update({
-              ...implementation,
-              refresh: (value) =>
-                Effect.sync(() => {
-                  expect(value).toEqual(expired)
-                  calls.push("override")
-                  return overridden
-                }),
-            }),
-          )
-          expect(yield* integrations.connection.resolve(connection)).toEqual(overridden)
-          expect((yield* credentials.get(stored.id))?.value).toEqual(overridden)
-
-          yield* override.dispose
-          yield* credentials.update(stored.id, { value: expired })
-          expect(yield* integrations.connection.resolve(connection)).toEqual(fresh)
-          expect(calls).toEqual(["original", "override", "original"])
-
-          yield* credentials.update(stored.id, { value: expired })
-          const removal = yield* integrations.transform((editor) => editor.method.remove(integrationID, method))
-          expect(yield* integrations.connection.resolve(connection)).toEqual(expired)
-          expect((yield* credentials.get(stored.id))?.value).toEqual(expired)
-          expect(calls).toEqual(["original", "override", "original"])
-
-          yield* removal.dispose
-          expect(yield* integrations.connection.resolve(connection)).toEqual(fresh)
-          yield* credentials.update(stored.id, { value: expired })
-          yield* integrations.transform((editor) => editor.method.update({ ...implementation, refresh: undefined }))
-          expect(yield* integrations.connection.resolve(connection)).toEqual(expired)
-          expect((yield* credentials.get(stored.id))?.value).toEqual(expired)
-          expect(calls).toEqual(["original", "override", "original", "original"])
-
-          const failure = new Error("refresh failed")
-          yield* integrations.transform((editor) =>
-            editor.method.update({ ...implementation, refresh: () => Effect.fail(failure) }),
-          )
-          expect(yield* integrations.connection.resolve(connection).pipe(Effect.flip)).toEqual(
-            new Integration.AuthorizationError({ cause: failure }),
-          )
-          expect((yield* credentials.get(stored.id))?.value).toEqual(expired)
-        }),
-      )
-    }),
-  )
-
  it.effect("completes code OAuth once and stores the credential", () =>
    Effect.gen(function* () {
      const integrations = yield* Integration.Service
@@ -1,7 +1,6 @@
 import { test, type TestOptions } from "bun:test"
-import { Cause, Effect, Exit, Layer, Scope } from "effect"
-import * as TestClock from "effect/testing/TestClock"
-import * as TestConsole from "effect/testing/TestConsole"
+import { Cause, Effect, Exit, Layer, type Scope } from "effect"
+import { TestClock, TestConsole } from "effect/testing"

 type Body<A, E, R> = Effect.Effect<A, E, R> | (() => Effect.Effect<A, E, R>)

@@ -4,7 +4,7 @@ import { SessionMessage } from "@opencode-ai/core/session/message"
 import { toSessionError } from "@opencode-ai/core/session/to-session-error"
 import type { SessionError } from "@opencode-ai/schema/session-error"
 import { Tool } from "@opencode-ai/core/tool"
-import type { Context as PluginContext } from "@opencode-ai/plugin/effect/plugin"
+import type { Context } from "@opencode-ai/plugin/effect/plugin"
 import { Effect, type Scope } from "effect"
 import { host } from "../plugin/host"

@@ -52,7 +52,7 @@ export function waitForCodeModeTool(
 export const registerToolPlugin = <R>(
  plugin: {
    readonly id: string
-    readonly effect: (context: PluginContext) => Effect.Effect<void, never, R>
+    readonly effect: (context: Context) => Effect.Effect<void, never, R>
  },
  overrides: Parameters<typeof host>[0] = {},
 ): Effect.Effect<void, never, R | Tool.Service | Scope.Scope> =>
@@ -33,25 +33,9 @@ import { McpStdio } from "@opencode-ai/core/mcp/stdio"
 import { Permission } from "@opencode-ai/core/permission"
 import { AbsolutePath } from "@opencode-ai/core/schema"
 import { Session } from "@opencode-ai/core/session"
-import { State } from "@opencode-ai/core/state"
 import { McpTool } from "@opencode-ai/core/tool/mcp"
 import { Tool } from "@opencode-ai/core/tool"
-import {
-  Context,
-  DateTime,
-  Deferred,
-  Effect,
-  Exit,
-  Fiber,
-  Layer,
-  PubSub,
-  Ref,
-  Schedule,
-  Schema,
-  Scope,
-  Sink,
-  Stream,
-} from "effect"
+import { Deferred, Effect, Exit, Fiber, Layer, PubSub, Ref, Schedule, Schema, Sink, Stream } from "effect"
 import { TestClock } from "effect/testing"
 import { ChildProcess, ChildProcessSpawner } from "effect/unstable/process"
 import { ExitCode, makeHandle, ProcessId } from "effect/unstable/process/ChildProcessSpawner"
@@ -82,7 +66,7 @@ function resourceServer(
    listChanged?: boolean
    emptyElicitation?: boolean
    urlElicitation?: boolean
-    respond?: (request: Request) => Response | undefined | Promise<Response | undefined>
+    respond?: (request: Request) => Response | undefined
  } = {},
 ) {
  return Effect.acquireRelease(
@@ -174,7 +158,7 @@ function resourceServer(
          if (typeof body === "object" && body !== null && "method" in body && body.method === "initialize") {
            state.initializations += 1
          }
-          return (await input.respond?.(request)) ?? transport.handleRequest(request)
+          return input.respond?.(request) ?? transport.handleRequest(request)
        },
      })
      return {
@@ -1341,121 +1325,6 @@ test("reconciles only changed MCP server config", async () => {
  )
 })

-testEffect(Layer.empty).live("serializes MCP config restoration behind an in-flight replacement", () =>
-  Effect.gen(function* () {
-    const started = yield* Deferred.make<void>()
-    const release = yield* Deferred.make<void>()
-    const accepted = yield* Deferred.make<void>()
-    const server = yield* resourceServer({
-      respond: (request) =>
-        request.method !== "POST"
-          ? undefined
-          : Effect.runPromise(
-              Deferred.succeed(started, undefined).pipe(Effect.andThen(Deferred.await(release)), Effect.as(undefined)),
-            ),
-    })
-
-    yield* Effect.gen(function* () {
-      const service = yield* Mcp.Service
-      expect((yield* service.servers())[0]?.status).toEqual({ status: "disabled" })
-      const replacing = yield* service
-        .transform((draft) => draft.update("resources", (config) => (config.disabled = false)))
-        .pipe(Effect.forkScoped({ startImmediately: true }))
-      yield* Deferred.await(started)
-
-      const restoring = yield* State.batch(
-        Effect.gen(function* () {
-          yield* service.transform((draft) => draft.update("resources", (config) => (config.disabled = true)))
-          yield* Deferred.succeed(accepted, undefined)
-        }),
-      ).pipe(Effect.forkScoped({ startImmediately: true }))
-      yield* Deferred.await(accepted)
-      expect((yield* service.servers())[0]?.status).toEqual({ status: "pending" })
-
-      yield* Deferred.succeed(release, undefined)
-      yield* Fiber.join(replacing)
-      yield* Fiber.join(restoring)
-      expect((yield* service.servers())[0]?.status).toEqual({ status: "disabled" })
-      expect(yield* service.tools()).toEqual([])
-      expect(server.state.initializations).toBe(1)
-    }).pipe(
-      Effect.ensuring(Deferred.succeed(release, undefined)),
-      Effect.provide(
-        resourceMcpLayer(new ConfigMCP.Remote({ type: "remote", url: server.url, oauth: false, disabled: true })),
-      ),
-    )
-  }),
-)
-
-testEffect(
-  AppNodeBuilder.build(
-    LayerNode.group([Bus.node, Integration.node, Credential.node, Form.node, Environment.node, Location.node]),
-    [
-      [
-        Location.node,
-        Layer.succeed(
-          Location.Service,
-          Location.Service.of(location({ directory: AbsolutePath.make(import.meta.dir) })),
-        ),
-      ],
-      [Environment.node, hostEnvironmentLayer],
-    ],
-  ),
-).effect("discards queued MCP notifications after its layer closes", () =>
-  Effect.gen(function* () {
-    const bus = yield* Bus.Service
-    const entered = yield* Deferred.make<void>()
-    const release = yield* Deferred.make<void>()
-    const root = yield* Scope.make()
-    yield* Effect.addFinalizer(() =>
-      Deferred.succeed(release, undefined).pipe(
-        Effect.andThen(State.batch(Scope.close(root, Exit.void), { flush: false })),
-        Effect.andThen(TestClock.adjust("500 millis")),
-      ),
-    )
-    const context = yield* Layer.build(Mcp.layer()).pipe(Scope.provide(root))
-    const service = Context.get(context, Mcp.Service)
-    const observed: string[] = []
-    let block = false
-    const unsubscribe = yield* bus.listen((event) =>
-      Effect.gen(function* () {
-        if (event.type !== McpEvent.StatusChanged.type) return
-        observed.push(Schema.decodeUnknownSync(McpEvent.StatusChanged.data)(event.data).server)
-        if (!block) return
-        block = false
-        yield* Deferred.succeed(entered, undefined)
-        yield* Deferred.await(release)
-      }),
-    )
-    yield* Effect.addFinalizer(() => unsubscribe)
-    const source = { url: "https://example.com/initial", added: false }
-    yield* service
-      .transform((draft) => {
-        draft.set("fixture", { type: "remote", url: source.url, oauth: false, disabled: true })
-        if (source.added) draft.set("queued", { type: "local", command: ["unused"], disabled: true })
-      })
-      .pipe(Scope.provide(root))
-
-    block = true
-    source.url = "https://example.com/first"
-    const first = yield* service.reload().pipe(Effect.forkChild({ startImmediately: true }))
-    yield* TestClock.adjust("500 millis")
-    yield* Deferred.await(entered)
-    source.url = "https://example.com/second"
-    source.added = true
-    const second = yield* service.reload().pipe(Effect.forkChild({ startImmediately: true }))
-    yield* TestClock.adjust("500 millis")
-
-    yield* State.batch(Scope.close(root, Exit.void), { flush: false })
-    observed.length = 0
-    yield* Deferred.succeed(release, undefined)
-    yield* Fiber.join(first)
-    yield* Fiber.join(second)
-    expect(observed).toEqual([])
-    expect((yield* service.servers()).map((server) => server.name)).toEqual([Mcp.ServerName.make("fixture")])
-  }),
-)
-
 test("serializes concurrent MCP lifecycle operations", async () => {
  await Effect.runPromise(
    Effect.scoped(
@@ -5,7 +5,6 @@ import { Database } from "@opencode-ai/core/database/database"
 import { AppNodeBuilder } from "@opencode-ai/core/effect/app-node-builder"
 import { LayerNode } from "@opencode-ai/util/effect/layer-node"
 import { Bus } from "@opencode-ai/core/bus"
-import { Job } from "@opencode-ai/core/job"
 import { Location } from "@opencode-ai/core/location"
 import { Permission } from "@opencode-ai/core/permission"
 import { PermissionTable } from "@opencode-ai/core/permission/sql"
@@ -122,7 +121,7 @@ describe("Permission", () => {
    }),
  )

-  it.effect("evaluates against an explicit provider-turn agent", () =>
+  it.effect("evaluates against an explicit agent", () =>
    Effect.gen(function* () {
      yield* setup([{ action: "read", resource: "*", effect: "allow" }])
      const agents = yield* Agent.Service
@@ -1,12 +1,10 @@
 import { describe, expect } from "bun:test"
 import { ToolFailure } from "@opencode-ai/ai"
-import { Clock, Context, Duration, Effect, Exit, Fiber, Schema, Stream } from "effect"
+import { Context, Effect, Exit, Fiber, Schema, Stream } from "effect"
 import { Plugin as EffectPlugin } from "@opencode-ai/plugin/effect"
 import { Config as ConfigSchema } from "@opencode-ai/schema/config"
 import { Agent } from "@opencode-ai/core/agent"
 import { Bus } from "@opencode-ai/core/bus"
-import { Credential } from "@opencode-ai/core/credential"
-import { Integration } from "@opencode-ai/core/integration"
 import { Plugin } from "@opencode-ai/core/plugin"
 import { PluginHost } from "@opencode-ai/core/plugin/host"
 import { PluginRuntime } from "@opencode-ai/core/plugin/runtime"
@@ -55,64 +53,6 @@ describe("Plugin", () => {
    }),
  )

-  it.effect("refreshes its own stored OAuth connection during plugin activation", () =>
-    Effect.gen(function* () {
-      const plugins = yield* Plugin.Service
-      const credentials = yield* Credential.Service
-      const integrationID = Integration.ID.make("acme")
-      const methodID = Integration.MethodID.make("browser")
-      const expired = Credential.OAuth.make({
-        type: "oauth",
-        methodID,
-        access: "expired",
-        refresh: "refresh",
-        expires: 0,
-      })
-      const fresh = Credential.OAuth.make({
-        ...expired,
-        access: "fresh",
-        refresh: "fresh-refresh",
-        expires: (yield* Clock.currentTimeMillis) + Duration.toMillis(Duration.hours(1)),
-      })
-      const stored = yield* credentials.create({ integrationID, label: "Personal", value: expired })
-      const resolved: (Credential.Value | undefined)[] = []
-      const refreshed: Credential.OAuth[] = []
-
-      yield* plugins.activate([
-        versioned(
-          EffectPlugin.define({
-            id: "oauth-refresh",
-            effect: (ctx) =>
-              Effect.gen(function* () {
-                yield* ctx.integration.transform((editor) =>
-                  editor.method.update({
-                    integrationID,
-                    method: { id: methodID, type: "oauth", label: "Browser" },
-                    authorize: () => Effect.die("unexpected authorization"),
-                    refresh: (value) =>
-                      Effect.sync(() => {
-                        refreshed.push(value)
-                        return fresh
-                      }),
-                  }),
-                )
-                const connection = yield* ctx.integration.connection.active(integrationID)
-                if (!connection) return yield* Effect.die("stored connection missing")
-                resolved.push(yield* ctx.integration.connection.resolve(connection).pipe(Effect.orDie))
-              }),
-          }),
-        ),
-      ])
-
-      expect(resolved).toEqual([fresh])
-      expect(refreshed).toEqual([expired])
-      expect((yield* credentials.get(stored.id))?.value).toEqual(fresh)
-      expect(yield* plugins.list()).toEqual([
-        { id: Plugin.ID.make("oauth-refresh"), source: { type: "builtin" }, status: "active", tui: false },
-      ])
-    }),
-  )
-
  it.live("exposes public events through the plugin context", () =>
    Effect.gen(function* () {
      const plugins = yield* Plugin.Service
@@ -915,7 +915,7 @@ describe("fromPromise", () => {
    }),
  )

-  it.effect("returns content-only plugin results through Code Mode", () =>
+  it.effect("returns content-only plugin results and rejected Promises through Code Mode", () =>
    Effect.gen(function* () {
      const plugins = yield* Plugin.Service
      const registry = yield* Tool.Service
@@ -927,8 +927,11 @@ describe("fromPromise", () => {
            tools.add({
              name: "demo_status",
              description: "Returns a status string",
-              input: Schema.Struct({}),
-              execute: async () => ({ content: [{ type: "text", text: "hello" }] }),
+              input: Schema.Struct({ fail: Schema.optionalKey(Schema.Boolean) }),
+              execute: async ({ fail }) => {
+                if (fail) await ctx.session.create({ agent: undefined })
+                return { content: [{ type: "text", text: "hello" }] }
+              },
              options: { codemode: true },
            })
          })
@@ -953,6 +956,22 @@ describe("fromPromise", () => {
        output: { output: "hello", toolCalls: [{ tool: "demo_status", status: "completed" }] },
        content: [{ type: "text", text: "hello" }],
      })
+      expect(
+        yield* toolSet.execute({
+          sessionID: Session.ID.make("ses_content_only_tool"),
+          agent: Agent.ID.make("build"),
+          messageID: SessionMessage.ID.make("msg_content_only_tool"),
+          call: {
+            type: "tool-call",
+            id: "call_failed_tool",
+            name: "execute",
+            input: { code: "return await tools.demo_status({ fail: true })" },
+          },
+        }),
+      ).toMatchObject({
+        content: [{ type: "text", text: 'Expected string | null\n  at ["agent"]' }],
+        metadata: { error: true },
+      })
    }),
  )
 })
@@ -1,10 +1,7 @@
 import { describe, expect } from "bun:test"
 import { Effect, Exit, Layer, Scope } from "effect"
 import { AppNodeBuilder } from "@opencode-ai/core/effect/app-node-builder"
-import { LayerNode } from "@opencode-ai/util/effect/layer-node"
-import { Bus } from "@opencode-ai/core/bus"
 import { AbsolutePath } from "@opencode-ai/core/schema"
-import { State } from "@opencode-ai/core/state"
 import { Global } from "@opencode-ai/util/global"
 import { Reference } from "@opencode-ai/core/reference"
 import { Repository } from "@opencode-ai/core/repository"
@@ -14,128 +11,9 @@ import { it } from "./lib/effect"
 const cache = Layer.mock(RepositoryCache.Service, {
  ensure: () => Effect.die("unexpected Git materialization"),
 })
-const referenceLayer = AppNodeBuilder.build(LayerNode.group([Reference.node, Bus.node]), [
-  [RepositoryCache.node, cache],
-])
+const referenceLayer = AppNodeBuilder.build(Reference.node, [[RepositoryCache.node, cache]])

 describe("Reference", () => {
-  it.effect("prepares batched references before cache work or update events", () => {
-    const operations: RepositoryCache.EnsureInput[] = []
-    const cache = Layer.mock(RepositoryCache.Service, {
-      ensure: (input) =>
-        Effect.sync(() => {
-          operations.push(input)
-          return {
-            repository: input.reference.label,
-            host: input.reference.host,
-            remote: input.reference.remote,
-            localPath: Repository.cachePath(Global.Path.repos, input.reference, input.branch),
-            status: "cached",
-          } satisfies RepositoryCache.Result
-        }),
-    })
-    const referenceLayer = AppNodeBuilder.build(LayerNode.group([Reference.node, Bus.node]), [
-      [RepositoryCache.node, cache],
-    ])
-
-    return Effect.gen(function* () {
-      const references = yield* Reference.Service
-      const bus = yield* Bus.Service
-      const observed: string[][] = []
-      const unsubscribe = yield* bus.listen((event) =>
-        event.type === Reference.Event.Updated.type
-          ? references.list().pipe(
-              Effect.map((infos) => {
-                observed.push(infos.map((info) => info.name))
-              }),
-            )
-          : Effect.void,
-      )
-      yield* Effect.addFinalizer(() => unsubscribe)
-
-      yield* State.batch(
-        Effect.gen(function* () {
-          yield* references.transform((draft) => {
-            draft.add("docs", Reference.LocalSource.make({ type: "local", path: AbsolutePath.make("/docs") }))
-            draft.add(
-              "sdk",
-              Reference.GitSource.make({
-                type: "git",
-                repository: "owner/repo",
-                branch: "feature/docs",
-                description: "SDK documentation",
-                hidden: true,
-              }),
-            )
-            draft.add("invalid", Reference.GitSource.make({ type: "git", repository: "invalid" }))
-            draft.add(
-              "invalid-branch",
-              Reference.GitSource.make({ type: "git", repository: "owner/repo", branch: "../escape" }),
-            )
-            draft.add("file", Reference.GitSource.make({ type: "git", repository: "file:///docs" }))
-          })
-          const infos = yield* references.list()
-          expect(infos.map((info) => info.name)).toEqual(["docs", "sdk"])
-          expect(infos[1]).toMatchObject({
-            path: Repository.cachePath(Global.Path.repos, Repository.parseRemote("owner/repo"), "feature/docs"),
-            description: "SDK documentation",
-            hidden: true,
-          })
-          expect(operations).toEqual([])
-          expect(observed).toEqual([])
-        }),
-      )
-
-      expect(observed).toEqual([["docs", "sdk"]])
-      yield* Effect.yieldNow
-      expect(
-        operations.map((input) => ({
-          repository: input.reference.label,
-          branch: input.branch,
-          refresh: input.refresh,
-        })),
-      ).toEqual([{ repository: "owner/repo", branch: "feature/docs", refresh: true }])
-    }).pipe(Effect.provide(referenceLayer))
-  })
-
-  it.effect("lets update listeners replace references and refetch the latest projection", () =>
-    Effect.gen(function* () {
-      const references = yield* Reference.Service
-      const bus = yield* Bus.Service
-      const scope = yield* Scope.Scope
-      const observed: string[][] = []
-      let reentered = false
-      const first = yield* bus.listen((event) =>
-        Effect.gen(function* () {
-          if (event.type !== Reference.Event.Updated.type || reentered) return
-          reentered = true
-          yield* references
-            .transform((draft) =>
-              draft.add("docs", Reference.LocalSource.make({ type: "local", path: AbsolutePath.make("/new") })),
-            )
-            .pipe(Scope.provide(scope))
-        }),
-      )
-      const second = yield* bus.listen((event) =>
-        event.type === Reference.Event.Updated.type
-          ? references.list().pipe(
-              Effect.map((infos) => {
-                observed.push(infos.map((info) => info.path))
-              }),
-            )
-          : Effect.void,
-      )
-      yield* Effect.addFinalizer(() => first.pipe(Effect.andThen(second)))
-
-      yield* references.transform((draft) =>
-        draft.add("docs", Reference.LocalSource.make({ type: "local", path: AbsolutePath.make("/old") })),
-      )
-
-      expect((yield* references.list()).map((info) => info.path)).toEqual([AbsolutePath.make("/new")])
-      expect(observed).toEqual([["/new"], ["/new"]])
-    }).pipe(Effect.provide(referenceLayer)),
-  )
-
  it.effect("registers normalized sources for the owning scope", () =>
    Effect.gen(function* () {
      const references = yield* Reference.Service
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Aiden Cline	634e085ca8	fix(ai): keep chat reasoning in one lifecycle	2026-08-28 01:46:25 -05:00
Aiden Cline	11ca603490	fix(ai): finish chat streams at done sentinel (#45850 )	2026-08-28 00:53:53 -05:00
Aiden Cline	85d8b07f09	fix(ai): ignore late converse tool deltas (#45847 )	2026-08-28 00:38:01 -05:00
Aiden Cline	d2ee536c16	fix(core): classify AISDK network failures as transport errors (#45840 )	2026-08-28 00:21:17 -05:00
Aiden Cline	e12e04f482	fix(core): strengthen background shell guidance (#45843 )	2026-08-28 00:19:15 -05:00
Kit Langton	5743537945	test(core): use effectful temp fixtures (#45637 )	2026-08-28 01:01:04 -04:00
Aiden Cline	18e22cd82e	refactor(ai): simplify response stream state (#45835 )	2026-08-27 23:56:42 -05:00
Aiden Cline	bdf019a9ac	fix(ai): detect DashScope input length overflow errors (#45834 )	2026-08-27 23:43:14 -05:00
Aiden Cline	5cbafc57c0	refactor(ai): default unrecognized provider failures to retry (#45825 )	2026-08-27 23:40:52 -05:00
Aiden Cline	55674b858b	fix(ai): make final snapshots authoritative for text and reasoning (#45831 )	2026-08-27 23:38:19 -05:00
Luke Parker	bb390f435c	fix(session-ui): enable word diffs in unified view (#45833 )	2026-08-28 04:31:18 +00:00
Kit Langton	92b9eebab2	feat(tui): streamline diff review workflow (#45817 )	2026-08-28 00:11:29 -04:00
Aiden Cline	074413a96d	fix(ai): normalize response item boundaries (#45789 )	2026-08-27 23:08:50 -05:00
opencode-agent[bot]	4685ba8d3e	chore: update nix node_modules hashes	2026-08-28 04:03:16 +00:00
Kit Langton	d2c307ab30	test(core): remove unused test imports (#45674 )	2026-08-27 23:58:41 -04:00
Kit Langton	a5193634d0	test(core): use direct test imports (#45683 )	2026-08-27 23:58:34 -04:00
Kit Langton	95725d121a	chore: remove unused changesets (#45827 )	2026-08-27 23:55:57 -04:00
Aiden Cline	56f2559798	fix(codemode): report original tool errors (#45820 )	2026-08-27 22:54:36 -05:00
Kit Langton	38bffc9db1	chore(deps): upgrade Effect to rc.112 (#45819 )	2026-08-27 23:43:37 -04:00
Kit Langton	1d3308d904	test(core): refresh test vocabulary (#45714 )	2026-08-27 23:26:45 -04:00
opencode-agent[bot]	3c9e5adefa	chore: update nix node_modules hashes	2026-08-28 03:23:31 +00:00