refactor(ai): use completed response item finals

refactor(ai): simplify response finalization flow
fix(ai): respect response text and reasoning finals
2026-08-28 20:46:14 +00:00 · 2026-08-28 15:43:44 -05:00 · 2026-08-28 01:01:30 -05:00 · 2026-08-28 00:51:54 -05:00 · 2026-08-28 00:38:01 -05:00 · 2026-08-28 00:21:17 -05:00
233 changed files with 11418 additions and 7548 deletions
@@ -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
---
-
-Preserve prompt cache prefixes when sessions move between locations with unchanged instructions.
@@ -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/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
---
-
-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
---
-
-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.
@@ -1,6 +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.
@@ -2,7 +2,7 @@
 exact = true
 # Only install newly resolved package versions published at least 3 days ago.
 minimumReleaseAge = 259200
-minimumReleaseAgeExcludes = ["@ai-sdk/amazon-bedrock", "@ai-sdk/anthropic", "@brendonovich/vite-plugin-opencode", "@opencode-ai/sdk", "@opencode-ai/pty", "@opencode-ai/pty-darwin-arm64", "@opencode-ai/pty-darwin-x64", "@opencode-ai/pty-linux-arm64-gnu", "@opencode-ai/pty-linux-arm64-musl", "@opencode-ai/pty-linux-x64-gnu", "@opencode-ai/pty-linux-x64-musl", "@opentui/core", "@opentui/core-darwin-arm64", "@opentui/core-darwin-x64", "@opentui/core-linux-arm64", "@opentui/core-linux-arm64-musl", "@opentui/core-linux-x64", "@opentui/core-linux-x64-musl", "@opentui/core-win32-arm64", "@opentui/core-win32-x64", "@opentui/keymap", "@opentui/solid", "opentui-spinner", "gitlab-ai-provider", "opencode-gitlab-auth", "@ff-labs/fff-node", "@ff-labs/fff-bun", "@ff-labs/fff-bin-darwin-arm64", "@ff-labs/fff-bin-darwin-x64", "@ff-labs/fff-bin-linux-arm64-gnu", "@ff-labs/fff-bin-linux-arm64-musl", "@ff-labs/fff-bin-linux-x64-gnu", "@ff-labs/fff-bin-linux-x64-musl", "@ff-labs/fff-bin-win32-arm64", "@ff-labs/fff-bin-win32-x64", "@pierre/diffs", "@pierre/theming", "app-builder-lib", "dmg-builder", "electron", "electron-builder", "electron-publish", "blume"]
+minimumReleaseAgeExcludes = ["@ai-sdk/amazon-bedrock", "@ai-sdk/anthropic", "@brendonovich/vite-plugin-opencode", "@opencode-ai/sdk", "@opencode-ai/pty", "@opencode-ai/pty-darwin-arm64", "@opencode-ai/pty-darwin-x64", "@opencode-ai/pty-linux-arm64-gnu", "@opencode-ai/pty-linux-arm64-musl", "@opencode-ai/pty-linux-x64-gnu", "@opencode-ai/pty-linux-x64-musl", "@opentui/core", "@opentui/core-darwin-arm64", "@opentui/core-darwin-x64", "@opentui/core-linux-arm64", "@opentui/core-linux-arm64-musl", "@opentui/core-linux-x64", "@opentui/core-linux-x64-musl", "@opentui/core-win32-arm64", "@opentui/core-win32-x64", "@opentui/keymap", "@opentui/solid", "opentui-spinner", "gitlab-ai-provider", "opencode-gitlab-auth", "@ff-labs/fff-node", "@ff-labs/fff-bun", "@ff-labs/fff-bin-darwin-arm64", "@ff-labs/fff-bin-darwin-x64", "@ff-labs/fff-bin-linux-arm64-gnu", "@ff-labs/fff-bin-linux-arm64-musl", "@ff-labs/fff-bin-linux-x64-gnu", "@ff-labs/fff-bin-linux-x64-musl", "@ff-labs/fff-bin-win32-arm64", "@ff-labs/fff-bin-win32-x64", "@pierre/diffs", "@pierre/theming", "app-builder-lib", "dmg-builder", "electron", "electron-builder", "electron-publish", "blume", "mermaid"]

 [test]
 root = "./do-not-run-tests-from-root"
@@ -63,7 +63,8 @@ new sst.cloudflare.StaticSite("WebApp", {
  domain: "app." + domain,
  path: "packages/app",
  build: {
-    command: "bun turbo build",
+    // Preserve Sentry credentials and run source-map uploads on every deployment.
+    command: "bun run build",
    output: "./dist",
  },
 })
@@ -1,8 +1,8 @@
 {
  "nodeModules": {
-    "x86_64-linux": "sha256-agxF1Ab8P84tijHvw7jaG+9UZm/dJZhHw8CGNlQQqYc=",
-    "aarch64-linux": "sha256-Kg6CkhoEEsb+ZOGPN/rnNoirLdGSyQl6HU/Fy8t9Mqs=",
-    "aarch64-darwin": "sha256-SnxBpmcfPL2p3OYmSuG5Y/aFW8PeEOLhfQrxAs/53fs=",
-    "x86_64-darwin": "sha256-Dnxl1EcfiE7/rlHmPkko0BKc6hHVk6rQ/2h/PWuLfNo="
+    "x86_64-linux": "sha256-EtUp4pHl9TyPtRrLGvk/X7kd2LuIxNxCpUwF5aLtzN4=",
+    "aarch64-linux": "sha256-m0j/pMZCguclR3/T9JmzCfi11YzmIvBFyR2bVhIO37Y=",
+    "aarch64-darwin": "sha256-nqefk68ZTUfNU15q1WkXaGsFzPNwOjCtMHpp6WrpNqM=",
+    "x86_64-darwin": "sha256-syD7hX62E4yCDV/wux1QKw4q/zZr24f99Y2mmzMJo6o="
  }
 }
@@ -39,24 +39,24 @@
      "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",
      "@octokit/rest": "22.0.0",
      "@hono/standard-validator": "0.2.0",
      "@hono/zod-validator": "0.4.2",
-      "@opentui/core": "0.5.8",
-      "@opentui/keymap": "0.5.8",
-      "@opentui/solid": "0.5.8",
+      "@opentui/core": "0.5.9",
+      "@opentui/keymap": "0.5.9",
+      "@opentui/solid": "0.5.9",
      "@tanstack/solid-virtual": "3.13.37",
-      "@shikijs/stream": "4.2.0",
+      "@shikijs/stream": "4.4.3",
      "@standard-schema/spec": "1.1.0",
      "ulid": "3.0.1",
-      "@kobalte/core": "0.13.11",
+      "@kobalte/core": "0.13.13",
      "@corvu/drawer": "0.2.4",
      "@types/luxon": "3.7.1",
      "@types/node": "24.12.2",
@@ -67,13 +67,16 @@
      "@openauthjs/openauth": "0.0.0-20250322224806",
      "@pierre/diffs": "1.2.10",
      "opentui-spinner": "0.0.7",
-      "@solid-primitives/storage": "4.3.3",
+      "@solid-primitives/event-listener": "2.4.6",
+      "@solid-primitives/media": "2.3.6",
+      "@solid-primitives/resize-observer": "2.2.0",
+      "@solid-primitives/storage": "4.4.0",
      "@tailwindcss/vite": "4.1.11",
      "diff": "8.0.4",
      "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",
@@ -81,9 +84,9 @@
      "fuzzysort": "3.1.0",
      "get-east-asian-width": "1.6.0",
      "luxon": "3.6.1",
-      "marked": "18.0.7",
+      "marked": "18.0.11",
      "marked-shiki": "1.2.1",
-      "remend": "1.3.0",
+      "remend": "1.3.1",
      "@playwright/test": "1.59.1",
      "semver": "7.7.4",
      "typescript": "5.8.2",
@@ -92,17 +95,17 @@
      "remeda": "2.26.0",
      "resolve.exports": "2.0.3",
      "sst": "4.13.1",
-      "shiki": "4.2.0",
+      "shiki": "4.4.3",
      "solid-list": "0.3.0",
      "string-width": "7.2.0",
      "tailwindcss": "4.1.11",
-      "vite": "7.1.4",
+      "vite": "7.3.6",
      "@solidjs/meta": "0.29.4",
-      "@solidjs/router": "0.15.4",
+      "@solidjs/router": "1.0.0",
      "@solidjs/start": "https://pkg.pr.new/@solidjs/start@dfb2020",
-      "@sentry/solid": "10.36.0",
-      "@sentry/vite-plugin": "4.6.0",
-      "solid-js": "1.9.10",
+      "@sentry/solid": "10.71.0",
+      "@sentry/vite-plugin": "5.4.0",
+      "solid-js": "1.9.15",
      "solid-sonner": "0.3.1",
      "vite-plugin-solid": "2.11.10",
      "@lydell/node-pty": "1.2.0-beta.12"
@@ -158,7 +161,8 @@
    "@effect/platform-node-shared": "catalog:",
    "@types/bun": "catalog:",
    "@types/node": "catalog:",
-    "effect": "catalog:"
+    "effect": "catalog:",
+    "solid-js": "catalog:"
  },
  "patchedDependencies": {
    "@ai-sdk/openai-compatible@2.0.41": "patches/@ai-sdk%2Fopenai-compatible@2.0.41.patch",
@@ -166,7 +170,7 @@
    "@npmcli/agent@4.0.2": "patches/@npmcli%2Fagent@4.0.2.patch",
    "@silvia-odwyer/photon-node@0.3.4": "patches/@silvia-odwyer%2Fphoton-node@0.3.4.patch",
    "@standard-community/standard-openapi@0.2.9": "patches/@standard-community%2Fstandard-openapi@0.2.9.patch",
-    "solid-js@1.9.10": "patches/solid-js@1.9.10.patch",
+    "solid-js@1.9.15": "patches/solid-js@1.9.15.patch",
    "@ai-sdk/mistral@3.0.51": "patches/@ai-sdk%2Fmistral@3.0.51.patch",
    "gcp-metadata@8.1.2": "patches/gcp-metadata@8.1.2.patch",
    "pacote@21.5.0": "patches/pacote@21.5.0.patch",
@@ -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(),
@@ -1,4 +1,4 @@
-import { Effect, Schema } from "effect"
+import { Effect, Option, Schema } from "effect"
 import type { Content } from "@opencode-ai/schema/tool"
 import { HttpTransport } from "../route/transport/index.js"
 import { Protocol } from "../route/protocol.js"
@@ -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)
  }
@@ -843,21 +845,75 @@ const onOutputTextDone = (state: ParserState, event: Event, id: string): StepRes
  return [{ ...state, lifecycle: Lifecycle.textEnd(state.lifecycle, events, id) }, events]
 }

+const decodeMessagePart = Schema.decodeUnknownOption(
+  Schema.Union([OpenResponsesOutputText, Schema.Struct({ type: Schema.tag("refusal"), refusal: Schema.String })]),
+)
+
+const decodeSummaryPart = Schema.decodeUnknownOption(OpenResponsesReasoningSummaryText)
+
+const decodeReasoningPart = Schema.decodeUnknownOption(
+  Schema.Struct({ type: Schema.tag("reasoning_text"), text: Schema.String }),
+)
+
 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 +925,7 @@ 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 +934,48 @@ 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 +984,7 @@ 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 +996,8 @@ 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 +1018,14 @@ 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,
@@ -1041,28 +1075,32 @@ const onFunctionCallArgumentsDelta = Effect.fn("OpenResponses.onFunctionCallArgu
  return [{ ...state, lifecycle, tools: result.tools }, events] satisfies StepResult
 })

-const onOutputItemDone = Effect.fn("OpenResponses.onOutputItemDone")(function* (state: ParserState, event: Event) {
-  const item = event.item
+const onOutputItemDone = Effect.fn("OpenResponses.onOutputItemDone")(function* (
+  state: ParserState,
+  item: Event["item"],
+) {
  if (!item) return [state, NO_EVENTS] satisfies StepResult

  if (item.type === "message" && item.id !== undefined) {
+    const message = state.message?.id === item.id ? state.message : undefined
    const itemPhase = messagePhase(item.phase)
-    const phase = itemPhase === undefined ? state.messagePhases[item.id] : itemPhase
+    const phase = itemPhase === undefined ? message?.phase : itemPhase
+    const content = Array.isArray(item.content)
+      ? item.content.flatMap((part: unknown) => {
+          const decoded = Option.getOrUndefined(decodeMessagePart(part))
+          return decoded ? [decoded.type === "output_text" ? decoded.text : decoded.refusal] : []
+        })
+      : []
+    const text = content.length > 0 ? content.join("") : undefined
+    const metadata = providerMetadata(state, { itemId: item.id, ...(phase === undefined ? {} : { phase }) })
    const events: LLMEvent[] = []
-    const messageItems = new Set(state.messageItems)
-    messageItems.delete(item.id)
-    const { [item.id]: _phase, ...messagePhases } = state.messagePhases
+    const lifecycle =
+      message && text ? Lifecycle.textStart(state.lifecycle, events, item.id, metadata) : state.lifecycle
    return [
      {
        ...state,
-        lifecycle: Lifecycle.textEnd(
-          state.lifecycle,
-          events,
-          item.id,
-          providerMetadata(state, { itemId: item.id, ...(phase === undefined ? {} : { phase }) }),
-        ),
-        messageItems,
-        messagePhases,
+        lifecycle: Lifecycle.textEnd(lifecycle, events, item.id, metadata, text),
+        message: message ? undefined : state.message,
      },
      events,
    ] satisfies StepResult
@@ -1070,20 +1108,36 @@ 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 [
@@ -1094,30 +1148,87 @@ 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
  }

  if (isReasoningItem(item)) {
-    const events: LLMEvent[] = []
+    if (state.reasoningItems[item.id]?.open === false) return [state, NO_EVENTS] satisfies StepResult
    const metadata = reasoningMetadata(state, item)
+    const summary = Array.isArray(item.summary)
+      ? item.summary.map((part: unknown) => Option.getOrUndefined(decodeSummaryPart(part))?.text)
+      : []
+    const content = Array.isArray(item.content)
+      ? item.content.flatMap((part: unknown) => {
+          const decoded = Option.getOrUndefined(decodeReasoningPart(part))
+          return decoded ? [decoded.text] : []
+        })
+      : []
+    const text = summary.some(Boolean)
+      ? summary.filter((part) => part !== undefined).join("\n\n")
+      : content.some(Boolean)
+        ? content.join("\n\n")
+        : undefined
+    const events: LLMEvent[] = []
    const reasoningItem = state.reasoningItems[item.id]
    if (reasoningItem) {
-      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 parts = Object.entries(reasoningItem.summaryParts)
+      let lifecycle = state.lifecycle
+      // Once earlier summaries have closed, the whole item cannot replace the remaining fragment.
+      for (const [index, status] of parts) {
+        if (status === "concluded") continue
+        lifecycle = Lifecycle.reasoningEnd(
+          lifecycle,
+          events,
+          `${item.id}:${index}`,
+          metadata,
+          parts.length === 1 ? text : summary[Number(index)] || undefined,
        )
-      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
+      events.push(
+        LLMEvent.reasoningEnd({
+          id: item.id,
+          providerMetadata: metadata,
+          text,
+        }),
+      )
+      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) },
@@ -1129,32 +1240,27 @@ const onOutputItemDone = Effect.fn("OpenResponses.onOutputItemDone")(function* (
 })

 const onResponseFinish = Effect.fn("OpenResponses.onResponseFinish")(function* (state: ParserState, event: Event) {
-  const reconciled =
-    event.type === "response.completed"
-      ? yield* Effect.reduce(
-          event.response?.output ?? [],
-          () => [state, NO_EVENTS] satisfies StepResult,
-          ([current, events], item) => {
-            const id = item.id ?? (item.type === "function_call" ? item.call_id : undefined)
-            if (
-              id === undefined ||
-              ((item.type !== "function_call" || !current.tools[id]) &&
-                (item.type !== "reasoning" || !current.reasoningItems[id]))
-            )
-              return Effect.succeed([current, events] satisfies StepResult)
-            return onOutputItemDone(current, { type: "response.output_item.done", item }).pipe(
-              Effect.map(([next, emitted]) => [next, [...events, ...emitted]] satisfies StepResult),
-            )
-          },
-        )
-      : ([state, NO_EVENTS] satisfies StepResult)
-  const current = reconciled[0]
+  let current = state
+  const events: LLMEvent[] = []
+  if (event.type === "response.completed") {
+    for (const item of event.response?.output ?? []) {
+      const id = item.id ?? (item.type === "function_call" ? item.call_id : undefined)
+      if (id === undefined) continue
+      const tracked =
+        (item.type === "function_call" && current.tools[id]) ||
+        (item.type === "reasoning" && current.reasoningItems[id]?.open)
+      if (!tracked) continue
+      const [next, emitted] = yield* onOutputItemDone(current, item)
+      current = next
+      events.push(...emitted)
+    }
+  }
  // Some compatible providers omit output_item.done even after completing the response.
  const pending =
    event.type === "response.completed"
      ? yield* ToolStream.finishAll(current.id, current.tools)
      : { tools: current.tools, events: NO_EVENTS }
-  const events: LLMEvent[] = [...reconciled[1], ...pending.events]
+  events.push(...pending.events)
  const hasFunctionCall =
    pending.events.some((event) => LLMEvent.is.toolCall(event) || LLMEvent.is.toolInputError(event)) ||
    current.hasFunctionCall
@@ -1256,6 +1362,13 @@ 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(
@@ -1273,7 +1386,7 @@ export const step = (state: ParserState, input: Event) => {
  if (event.type === "response.output_item.done") {
    if (event.item?.type === "message" && event.item.id === undefined)
      return ProviderShared.eventError(state.id, `${event.type} message is missing id`)
-    return onOutputItemDone(state, event)
+    return onOutputItemDone(state, event.item)
  }
  if (event.type === "response.completed" || event.type === "response.incomplete") return onResponseFinish(state, event)
  if (event.type === "response.failed") return providerFailure(event, `${state.name} response failed`)
@@ -1305,10 +1418,10 @@ 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: {},
 })

@@ -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)
 }

@@ -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 }),
    })
  }
@@ -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 +1,209 @@
+import { describe, expect } from "bun:test"
+import { Effect } 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 generate = (...events: OpenResponses.Event[]) =>
+  LLMClient.generate(request).pipe(Effect.provide(fixedResponse(sseEvents(...events))))
+
+describe("Open Responses completed item text", () => {
+  ;["Draft expanded", "D", "Replacement", ""].forEach((text) => {
+    it.effect(`replaces streamed text with completed item text ${JSON.stringify(text)}`, () =>
+      Effect.gen(function* () {
+        const response = yield* generate(
+          { type: "response.output_item.added", item: { type: "message", id: "msg_1", phase: "commentary" } },
+          { type: "response.output_text.delta", item_id: "msg_1", delta: "Draft" },
+          { type: "response.output_text.done", item_id: "msg_1", text: "Part final" },
+          {
+            type: "response.output_item.done",
+            item: { type: "message", id: "msg_1", phase: "final_answer", content: [{ type: "output_text", text }] },
+          },
+          completed,
+        )
+        expect(response.text).toBe(text)
+        expect(response.events.filter(LLMEvent.is.textDelta).map((event) => event.text)).toEqual(["Draft"])
+        expect(response.events.filter(LLMEvent.is.textEnd)).toEqual([
+          {
+            type: "text-end",
+            id: "msg_1",
+            text,
+            providerMetadata: { "openai-compatible": { itemId: "msg_1", phase: "final_answer" } },
+          },
+        ])
+      }),
+    )
+  })
+
+  it.effect("joins completed text and refusal parts without streamed text", () =>
+    Effect.gen(function* () {
+      const response = yield* generate(
+        { type: "response.output_item.added", item: { type: "message", id: "msg_1" } },
+        {
+          type: "response.output_item.done",
+          item: {
+            type: "message",
+            id: "msg_1",
+            content: [
+              { type: "output_text", text: "Answer. " },
+              { type: "refusal", refusal: "Cannot help." },
+            ],
+          },
+        },
+        completed,
+      )
+      expect(response.text).toBe("Answer. Cannot help.")
+      expect(response.events.filter(LLMEvent.is.textStart)).toHaveLength(1)
+      expect(response.events.filter(LLMEvent.is.textEnd)).toHaveLength(1)
+    }),
+  )
+
+  it.effect("does not create an empty text fragment for an empty completed message", () =>
+    Effect.gen(function* () {
+      const response = yield* generate(
+        { type: "response.output_item.added", item: { type: "message", id: "msg_1" } },
+        { type: "response.output_text.done", item_id: "msg_1", text: "" },
+        {
+          type: "response.output_item.done",
+          item: { type: "message", id: "msg_1", content: [{ type: "output_text", text: "" }] },
+        },
+        completed,
+      )
+      expect(response.message.content).toEqual([])
+      expect(response.events.filter(LLMEvent.is.textStart)).toEqual([])
+    }),
+  )
+})
+
+describe("Open Responses completed item reasoning", () => {
+  ;[
+    {
+      name: "summary",
+      summary: [
+        { type: "summary_text", text: "Final" },
+        { type: "summary_text", text: "summary" },
+      ],
+      content: [{ type: "reasoning_text", text: "Raw" }],
+      text: "Final\n\nsummary",
+    },
+    {
+      name: "raw text",
+      summary: [
+        { type: "summary_text", text: "" },
+        { type: "summary_text", text: "" },
+      ],
+      content: [{ type: "reasoning_text", text: "Raw" }],
+      text: "Raw",
+    },
+    {
+      name: "streamed fallback",
+      summary: [
+        { type: "summary_text", text: "" },
+        { type: "summary_text", text: "" },
+      ],
+      content: [
+        { type: "reasoning_text", text: "" },
+        { type: "reasoning_text", text: "" },
+      ],
+      text: "Draft",
+    },
+  ].forEach((fixture) => {
+    it.effect(`uses ${fixture.name} at item completion`, () =>
+      Effect.gen(function* () {
+        const response = yield* generate(
+          { type: "response.output_item.added", item: { type: "reasoning", id: "rs_1" } },
+          { type: "response.reasoning_summary_text.delta", item_id: "rs_1", delta: "Draft" },
+          { type: "response.reasoning_summary_text.done", item_id: "rs_1", text: "Part final" },
+          {
+            type: "response.output_item.done",
+            item: {
+              type: "reasoning",
+              id: "rs_1",
+              summary: fixture.summary,
+              content: fixture.content,
+              encrypted_content: "encrypted",
+            },
+          },
+          completed,
+        )
+        expect(response.reasoning).toBe(fixture.text)
+        expect(response.events.filter(LLMEvent.is.reasoningEnd)).toHaveLength(1)
+        expect(response.message.content.find((part) => part.type === "reasoning")?.providerMetadata).toEqual({
+          "openai-compatible": { itemId: "rs_1", reasoningEncryptedContent: "encrypted" },
+        })
+      }),
+    )
+  })
+
+  it.effect("replaces only the still-open summary without repeating earlier text", () =>
+    Effect.gen(function* () {
+      const response = yield* generate(
+        { 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.reasoning_summary_part.added", item_id: "rs_1", summary_index: 1 },
+        { type: "response.reasoning_summary_text.delta", item_id: "rs_1", summary_index: 1, delta: "draft" },
+        {
+          type: "response.output_item.done",
+          item: {
+            type: "reasoning",
+            id: "rs_1",
+            summary: [
+              { type: "summary_text", text: "First " },
+              { type: "summary_text", text: "final" },
+            ],
+          },
+        },
+        completed,
+      )
+      expect(response.reasoning).toBe("First final")
+      expect(response.events.filter(LLMEvent.is.reasoningEnd).map((event) => event.text)).toEqual([undefined, "final"])
+    }),
+  )
+})
+;["response.completed", "response.incomplete"].forEach((type) => {
+  it.effect(`keeps streamed text when part finals are followed by ${type} without item completion`, () =>
+    Effect.gen(function* () {
+      const response = yield* generate(
+        { type: "response.output_item.added", item: { type: "message", id: "msg_1" } },
+        { type: "response.output_text.delta", item_id: "msg_1", content_index: 0, delta: "Hel" },
+        { type: "response.output_text.delta", item_id: "msg_1", content_index: 1, delta: "world" },
+        { type: "response.output_text.done", item_id: "msg_1", content_index: 0, text: "Hello " },
+        {
+          type: "response.content_part.done",
+          item_id: "msg_1",
+          content_index: 0,
+          part: { type: "output_text", text: "Hello " },
+        },
+        { type: "response.output_item.added", item: { type: "reasoning", id: "rs_1" } },
+        { type: "response.reasoning_summary_text.delta", item_id: "rs_1", delta: "Draft" },
+        { type: "response.reasoning_summary_text.done", item_id: "rs_1", text: "Part final" },
+        {
+          type: "response.reasoning_summary_part.done",
+          item_id: "rs_1",
+          summary_index: 0,
+          part: { type: "summary_text", text: "Part final" },
+        },
+        {
+          type,
+          response: {
+            id: "resp_1",
+            incomplete_details: type === "response.incomplete" ? { reason: "max_output_tokens" } : undefined,
+          },
+        },
+      )
+      expect(response.text).toBe("Helworld")
+      expect(response.reasoning).toBe("Draft")
+      expect(response.events.filter(LLMEvent.is.textEnd).map((event) => event.text)).toEqual([undefined])
+      expect(response.events.filter(LLMEvent.is.reasoningEnd).map((event) => event.text)).toEqual([undefined])
+    }),
+  )
+})
@@ -0,0 +1,468 @@
+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 reasoning text and encryption without replaying 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",
+          text: "Not streamed",
+          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 } },
+        },
+      ])
+    }),
+  )
+})
@@ -2599,6 +2599,7 @@ describe("OpenAI Responses route", () => {
          type: "reasoning-end",
          id: "rs_1:0",
          providerMetadata: { openai: { itemId: "rs_1", reasoningEncryptedContent: "terminal-state" } },
+          text: "Checked the diff.",
        },
      ])
      expect(response.message.content).toContainEqual({
@@ -2750,6 +2751,227 @@ 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(
@@ -2798,6 +3020,7 @@ describe("OpenAI Responses route", () => {
        {
          type: "reasoning-end",
          id: "rs_1:0",
+          text: "Checked the diff.",
          providerMetadata: { openai: { itemId: "rs_1", reasoningEncryptedContent: "encrypted-state" } },
        },
      ])
@@ -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" }),
@@ -209,6 +209,29 @@ test("appearance experimental setting switches tab orientation", async ({ page }
  await page.setViewportSize({ width: 390, height: 360 })
  await version.scrollIntoViewIfNeeded()
  await expect(version).toBeInViewport()
+
+  // Reload the UI-selected preference without seeding settings storage.
+  await page.reload()
+  const href = `/server/${base64Encode(server)}/session/${sessionA.id}`
+  await expect(
+    page
+      .locator('[data-slot="titlebar-tabs"]')
+      .locator(`[data-titlebar-tab-link][href="${href}"]`)
+      .getByText(sessionA.title, { exact: true }),
+  ).toBeVisible()
+  await expect(page.locator('[data-slot="vertical-tabs-sidebar"]')).toHaveCount(0)
+
+  await page.setViewportSize({ width: 1280, height: 720 })
+  await expect(
+    page
+      .locator('[data-slot="vertical-tabs-sidebar"]')
+      .locator(`[data-titlebar-tab-link][href="${href}"]`)
+      .getByText(sessionA.title, { exact: true }),
+  ).toBeVisible()
+  await expect(page.locator('[data-slot="titlebar-tabs"]')).toHaveCount(0)
+  await page.keyboard.press("Control+,")
+  await settings.getByRole("tab", { name: "Appearance" }).click()
+  await expect(layout).toContainText("Vertical")
 })

 test("vertical tab preference falls back to horizontal on mobile", async ({ page }) => {
@@ -198,6 +198,10 @@ fixture(
 fixture(
  "precaches public files of every type and size, excluding deployment metadata and source maps",
  async ({ page, site, builds, context }) => {
+    for (const output of Object.values(builds)) {
+      expect(output["/sw.js.map"]).toBeUndefined()
+      expect(Object.keys(output).some((path) => path.startsWith("/_assets/") && path.endsWith(".map"))).toBe(true)
+    }
    await install(page, site.url)
    const files = ["/nested/data.json", "/nested/font.woff2", "/nested/module.wasm", "/large.bin"]
    await context.setOffline(true)
@@ -42,21 +42,18 @@
    "@playwright/test": "catalog:",
    "@sentry/vite-plugin": "catalog:",
    "@tailwindcss/vite": "4.3.3",
-    "@tsconfig/bun": "1.0.9",
    "@types/bun": "catalog:",
    "@types/luxon": "catalog:",
    "@types/node": "catalog:",
    "@typescript/native-preview": "catalog:",
+    "diff": "catalog:",
    "happy-dom": "20.11.1",
    "tw-animate-css": "1.4.0",
-    "typescript": "catalog:",
-    "vite": "8.2.1",
-    "vite-plugin-icons-spritesheet": "3.0.1",
+    "vite": "8.2.2",
    "vite-plugin-pwa": "1.3.0",
    "vite-plugin-solid": "2.11.14"
  },
  "dependencies": {
-    "@corvu/drawer": "catalog:",
    "@dnd-kit/abstract": "0.5.0",
    "@dnd-kit/dom": "0.5.0",
    "@dnd-kit/helpers": "0.5.0",
@@ -71,28 +68,23 @@
    "@pierre/trees": "1.0.0-beta.4",
    "@sentry/solid": "catalog:",
    "@solid-primitives/event-bus": "1.1.2",
-    "@solid-primitives/event-listener": "2.4.5",
+    "@solid-primitives/event-listener": "catalog:",
    "@solid-primitives/i18n": "2.2.1",
    "@solid-primitives/keyed": "1.5.3",
-    "@solid-primitives/media": "2.3.3",
-    "@solid-primitives/resize-observer": "2.1.5",
+    "@solid-primitives/media": "catalog:",
+    "@solid-primitives/resize-observer": "catalog:",
    "@solid-primitives/scheduled": "1.5.3",
    "@solid-primitives/storage": "catalog:",
    "@solidjs/meta": "catalog:",
    "@solidjs/router": "catalog:",
    "@tanstack/solid-query": "5.91.4",
    "@tanstack/solid-virtual": "catalog:",
-    "diff": "catalog:",
    "effect": "catalog:",
    "fuzzysort": "catalog:",
    "ghostty-web": "github:anomalyco/ghostty-web#83c0a07b8628b748aed073b232cb4b52a6ca11c1",
    "luxon": "catalog:",
-    "marked": "catalog:",
-    "marked-shiki": "catalog:",
    "remeda": "catalog:",
-    "shiki": "catalog:",
    "solid-js": "catalog:",
-    "solid-list": "catalog:",
    "solid-presence": "0.2.0",
    "tailwindcss": "4.3.3"
  }
@@ -644,7 +644,7 @@ export function persisted<T>(
      : undefined
  if (channel) onCleanup(() => channel.close())

-  const [state, setState, init] = makePersisted(store, {
+  const [state, setState, init] = makePersisted<T, typeof store>(store, {
    name: config.key,
    storage,
    sync: channel ? messageSync(channel) : undefined,
@@ -0,0 +1,135 @@
+import { describe, expect, test } from "bun:test"
+import { createApiForServer } from "./api"
+import { readLocalImage } from "./image"
+
+function setup(
+  respond: (init?: RequestInit) => Response | Promise<Response> = () => new Response(new Uint8Array([0, 127, 255])),
+) {
+  const requests: Array<{ url: URL; init?: RequestInit }> = []
+  const api = createApiForServer({
+    server: { url: "https://server.example:4096", username: "image-user", password: "secret" },
+    fetch: (async (input: string | URL | Request, init?: RequestInit) => {
+      requests.push({ url: new URL(input instanceof Request ? input.url : input), init })
+      return respond(init)
+    }) as typeof fetch,
+  })
+  return { api, requests }
+}
+
+describe("readLocalImage", () => {
+  test.each([
+    ["images/screen #1 + 50% ?.PNG", "/workspace/project", "images/screen%20%231%20%2B%2050%25%20%3F.PNG"],
+    ["C:/tmp/opencode/screen #1.png", "C:/tmp/opencode/", "screen%20%231.png"],
+    ["d:/screen.png", "d:/", "screen.png"],
+    ["D:/charts/screen.png", "D:/charts/", "screen.png"],
+    ["Z:/charts/screen.png", "Z:/charts/", "screen.png"],
+    ["/tmp/opencode/screen #1.png", "/tmp/opencode/", "screen%20%231.png"],
+    ["/screen.png", "/", "screen.png"],
+  ])("reads %s with the correct location and authentication", async (path, directory, encoded) => {
+    const { api, requests } = setup()
+    const signal = new AbortController().signal
+    const blob = await readLocalImage(api, "/workspace/project", path, signal)
+
+    expect(blob).toBeInstanceOf(Blob)
+    expect(blob?.type).toBe("image/png")
+    expect(new Uint8Array(await blob!.arrayBuffer())).toEqual(new Uint8Array([0, 127, 255]))
+    expect(requests).toHaveLength(1)
+    expect(requests[0].url.origin).toBe("https://server.example:4096")
+    expect(requests[0].url.pathname).toBe(`/api/fs/read/${encoded}`)
+    expect([...requests[0].url.searchParams]).toEqual([["location[directory]", directory]])
+    expect(requests[0].init?.method).toBe("GET")
+    expect(new Headers(requests[0].init?.headers).get("authorization")).toBe(`Basic ${btoa("image-user:secret")}`)
+    expect(requests[0].init?.signal).toBe(signal)
+  })
+
+  test("preserves literal percent escapes and encodes the supplied relative location", async () => {
+    const { api, requests } = setup()
+    await readLocalImage(api, "C:/project #1 + 50%", "images/literal%20name.png", new AbortController().signal)
+
+    expect(requests[0].url.href).toBe(
+      "https://server.example:4096/api/fs/read/images/literal%2520name.png?location%5Bdirectory%5D=C%3A%2Fproject+%231+%2B+50%25",
+    )
+  })
+
+  test.each([
+    ["png", "image/png"],
+    ["jpeg", "image/jpeg"],
+    ["JPG", "image/jpeg"],
+    ["gif", "image/gif"],
+    ["webp", "image/webp"],
+    ["SVG", "image/svg+xml"],
+    ["avif", "image/avif"],
+    ["bmp", "image/bmp"],
+    ["ico", "image/x-icon"],
+  ])("uses the MIME type for .%s rather than the response header", async (extension, type) => {
+    const { api } = setup(
+      () => new Response("image bytes", { headers: { "content-type": "application/octet-stream" } }),
+    )
+    const blob = await readLocalImage(api, "/repo", `image.${extension}`, new AbortController().signal)
+    expect(blob?.type).toBe(type)
+    expect(await blob?.text()).toBe("image bytes")
+  })
+
+  test.each([
+    "https://example.com/image.png",
+    "HTTP://example.com/image.png",
+    "file:///tmp/image.png",
+    "data:image/png;base64,image.png",
+    "blob:https://example.com/image.png",
+    "custom+scheme:image.png",
+    "C:image.png",
+    "//server/share/image.png",
+    "\\\\server\\share\\image.png",
+    "//?/C:/image.png",
+    "///server/share/image.png",
+    "image.txt",
+    "image.html",
+    "image.constructor",
+    "image.png.txt",
+    "image",
+    "images.png/image",
+    "image.png/",
+    "",
+  ])("does not request unsupported input %s", async (path) => {
+    const { api, requests } = setup()
+    expect(await readLocalImage(api, "/repo", path, new AbortController().signal)).toBeUndefined()
+    expect(requests).toHaveLength(0)
+  })
+
+  test.each([400, 401])("propagates declared API errors (%s)", async (status) => {
+    const error = { _tag: "RequestError", message: "Cannot read image" }
+    const { api } = setup(() => Response.json(error, { status }))
+    await expect(readLocalImage(api, "/repo", "image.png", new AbortController().signal)).rejects.toEqual(error)
+  })
+
+  test.each([404, 500])("does not turn an unexpected HTTP status (%s) into a Blob", async (status) => {
+    const { api } = setup(() => new Response("Not an image", { status }))
+    await expect(readLocalImage(api, "/repo", "image.png", new AbortController().signal)).rejects.toMatchObject({
+      reason: "UnexpectedStatus",
+      cause: { status },
+    })
+  })
+
+  test("propagates transport failures", async () => {
+    const error = new Error("Connection lost")
+    const { api } = setup(() => Promise.reject(error))
+    await expect(readLocalImage(api, "/repo", "image.png", new AbortController().signal)).rejects.toMatchObject({
+      reason: "Transport",
+      cause: error,
+    })
+  })
+
+  test("forwards cancellation to an in-flight fetch", async () => {
+    const controller = new AbortController()
+    const { api, requests } = setup(
+      (init) =>
+        new Promise((_resolve, reject) => {
+          init?.signal?.addEventListener("abort", () => reject(init.signal?.reason), { once: true })
+        }),
+    )
+    const result = readLocalImage(api, "/repo", "image.png", controller.signal)
+    expect(requests[0].init?.signal).toBe(controller.signal)
+    controller.abort()
+    await expect(result).rejects.toMatchObject({ reason: "Transport", cause: controller.signal.reason })
+  })
+})
@@ -0,0 +1,36 @@
+import { getDirectory, getFilename } from "@opencode-ai/util/path"
+import type { OpenCodeClient } from "@opencode-ai/client/promise"
+
+const types = new Map([
+  ["png", "image/png"],
+  ["jpeg", "image/jpeg"],
+  ["jpg", "image/jpeg"],
+  ["gif", "image/gif"],
+  ["webp", "image/webp"],
+  ["svg", "image/svg+xml"],
+  ["avif", "image/avif"],
+  ["bmp", "image/bmp"],
+  ["ico", "image/x-icon"],
+])
+
+export async function readLocalImage(
+  api: Pick<OpenCodeClient, "file">,
+  directory: string,
+  path: string,
+  signal: AbortSignal,
+): Promise<Blob | undefined> {
+  const drive = /^[a-z]:\//i.test(path)
+  if (/^[\\/]{2}/.test(path) || (!drive && /^[a-z][a-z\d+.-]*:/i.test(path))) return
+  const type = types.get(path.match(/\.([^./]+)$/)?.[1]?.toLowerCase() ?? "")
+  if (!type) return
+  const absolute = drive || path.startsWith("/")
+  // Scope absolute images to their parent, including files outside the project.
+  const bytes = await api.file.read(
+    {
+      path: absolute ? getFilename(path) : path,
+      location: { directory: absolute ? getDirectory(path) : directory },
+    },
+    { signal },
+  )
+  return new Blob([new Uint8Array(bytes)], { type })
+}
@@ -1,4 +1,5 @@
 import { DataProvider } from "@opencode-ai/session-ui/context"
+import { MarkdownProvider, type ReadMarkdownImage } from "@opencode-ai/session-ui/context/markdown"
 import { useNavigate, useParams } from "@solidjs/router"
 import { createMemo, type ParentProps } from "solid-js"
 import { useProviders } from "@/providers/catalog/providers"
@@ -8,6 +9,7 @@ import { sessionHref } from "@/shell/routes/session"
 import { useData } from "@/runtime/server/current"
 import { useServerSDK } from "@/runtime/server/client"
 import { useTabs } from "@/shell/tabs/tabs"
+import { readLocalImage } from "@/runtime/server/image"

 export function SessionUIProvider(
  props: ParentProps<{
@@ -21,6 +23,10 @@ export function SessionUIProvider(
  const serverSDK = useServerSDK()
  const tabs = useTabs()
  const directory = () => props.directory
+  const readImage = createMemo<ReadMarkdownImage>(() => {
+    const dir = directory()
+    return (path, signal) => readLocalImage(serverSDK.api, dir, path, signal)
+  })
  const href = (sessionID: string) => sessionHref(props.server, sessionID)
  const navigateToSession = async (sessionID: string) => {
    const tab = tabs.store.find(
@@ -60,7 +66,9 @@ export function SessionUIProvider(
      onNavigateToSession={navigateToSession}
      onSessionHref={href}
    >
-      <LocalProvider>{props.children}</LocalProvider>
+      <MarkdownProvider readImage={readImage()}>
+        <LocalProvider>{props.children}</LocalProvider>
+      </MarkdownProvider>
    </DataProvider>
  )
 }
@@ -0,0 +1,85 @@
+import { expect, test } from "bun:test"
+import { MemoryRouter, Route, createMemoryHistory, useNavigate, useParams } from "@solidjs/router"
+import { createEffect, onCleanup } from "solid-js"
+import { createComponent, render } from "solid-js/web"
+import { createSessionOwnership } from "@/session/session-ownership"
+
+test("session ownership follows navigation, back, forward, replacement, and route disposal", async () => {
+  const host = document.createElement("div")
+  const history = createMemoryHistory()
+  history.set({ value: "/session/A", replace: true, scroll: false })
+  const captured: ReturnType<ReturnType<typeof createSessionOwnership>["capture"]>[] = []
+  const navigate: ReturnType<typeof useNavigate>[] = []
+  const cleaned: string[] = []
+  const settle = () => new Promise((resolve) => setTimeout(resolve, 0))
+
+  const Session = () => {
+    const params = useParams<{ id: string }>()
+    const ownership = createSessionOwnership(() => params.id)
+    const label = document.createElement("div")
+    navigate.push(useNavigate())
+    createEffect(() => {
+      label.textContent = params.id
+      captured.push(ownership.capture())
+    })
+    onCleanup(() => cleaned.push("session"))
+    return label
+  }
+
+  const dispose = render(
+    () =>
+      createComponent(MemoryRouter, {
+        history,
+        get children() {
+          return [
+            createComponent(Route, { path: "/", component: () => "Home" }),
+            createComponent(Route, { path: "/session/:id", component: Session }),
+          ]
+        },
+      }),
+    host,
+  )
+
+  try {
+    expect(host.textContent).toBe("A")
+    expect(captured[0].current()).toBe(true)
+
+    navigate[0]("/session/B")
+    await settle()
+    expect(host.textContent).toBe("B")
+    expect(captured[0].current()).toBe(false)
+    expect(captured[1].current()).toBe(true)
+
+    history.back()
+    await settle()
+    expect(host.textContent).toBe("A")
+    expect(captured[0].current()).toBe(false)
+    expect(captured[1].current()).toBe(false)
+    expect(captured[2].current()).toBe(true)
+
+    history.forward()
+    await settle()
+    expect(host.textContent).toBe("B")
+    expect(captured[2].current()).toBe(false)
+    expect(captured[3].current()).toBe(true)
+    expect(navigate).toHaveLength(1)
+    expect(cleaned).toEqual([])
+
+    navigate[0]("/", { replace: true })
+    await settle()
+    expect(host.textContent).toBe("Home")
+    expect(captured.every((owner) => !owner.current())).toBe(true)
+    expect(cleaned).toEqual(["session"])
+
+    history.back()
+    await settle()
+    expect(host.textContent).toBe("A")
+    expect(captured[4].current()).toBe(true)
+    expect(navigate).toHaveLength(2)
+  } finally {
+    dispose()
+  }
+
+  expect(captured.every((owner) => !owner.current())).toBe(true)
+  expect(cleaned).toEqual(["session", "session"])
+})
@@ -0,0 +1,89 @@
+import { expect, test } from "bun:test"
+import {
+  createComputed,
+  createMemo,
+  createResource,
+  createRoot,
+  createSignal,
+  onCleanup,
+  startTransition,
+  Suspense,
+  type Accessor,
+  type JSX,
+} from "solid-js"
+import { createComponent, render } from "solid-js/web"
+
+// Solid 1.9.15 includes the former transition patch for solidjs/solid#2046.
+test("a memo created during a paused transition has a committed value", async () => {
+  const host = document.createElement("div")
+  const loaded = Promise.withResolvers<string>()
+  const started = Promise.withResolvers<void>()
+  const memos: Accessor<string>[] = []
+  const [session, setSession] = createSignal(false)
+  const dispose = render(
+    () =>
+      createComponent(Suspense, {
+        fallback: "Loading",
+        get children() {
+          return createMemo(() => {
+            if (!session()) return "Home"
+            memos.push(createMemo(() => "Session"))
+            const [data] = createResource(() => loaded.promise)
+            started.resolve()
+            return createMemo(() => data() ?? "")
+          }) as unknown as JSX.Element
+        },
+      }),
+    host,
+  )
+
+  try {
+    expect(host.textContent).toBe("Home")
+    const pending = startTransition(() => setSession(true))
+    await started.promise
+    expect(host.textContent).toBe("Home")
+    expect(memos).toHaveLength(1)
+    expect(memos[0]()).toBe("Session")
+
+    loaded.resolve("Session loaded")
+    await pending
+    expect(host.textContent).toBe("Session loaded")
+    expect(memos[0]()).toBe("Session")
+  } finally {
+    loaded.resolve("Session loaded")
+    dispose()
+  }
+})
+
+// Exercise each patched bundle independently; importing both dev formats emits Solid's duplicate-runtime warning.
+test.each(["solid.js", "solid.cjs", "dev.js", "dev.cjs", "server.js", "server.cjs"])(
+  "%s reentrant disposal cleans owned computations and callbacks exactly once",
+  async (file) => {
+    const runtime: {
+      createRoot: typeof createRoot
+      createComputed: typeof createComputed
+      onCleanup: typeof onCleanup
+    } = await import(`solid-js/dist/${file}`)
+    const cleaned: string[] = []
+    const dispose = runtime.createRoot((dispose) => {
+      runtime.onCleanup(() => cleaned.push("root"))
+      runtime.createComputed(() => {
+        runtime.onCleanup(() => cleaned.push("first"))
+      })
+      runtime.createComputed(() => {
+        runtime.onCleanup(() => cleaned.push("second"))
+        runtime.onCleanup(() => {
+          cleaned.push("reentrant")
+          // Bound the regression so an unpatched runtime fails without overflowing the stack.
+          if (cleaned.filter((item) => item === "reentrant").length === 1) dispose()
+        })
+      })
+      return dispose
+    })
+
+    expect(dispose).not.toThrow()
+    expect(cleaned.toSorted()).toEqual(["first", "reentrant", "root", "second"])
+    dispose()
+    expect(cleaned).toHaveLength(4)
+  },
+)
@@ -10,6 +10,8 @@ export function serviceWorker(directory: string) {
    injectRegister: false,
    manifest: false,
    workbox: {
+      // Workbox runs after Sentry's upload and cleanup, so do not publish an unuploaded map.
+      sourcemap: false,
      globDirectory: directory,
      clientsClaim: false,
      // Keep each open tab on its complete build until all old clients close.
@@ -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": {
@@ -183,6 +183,7 @@ export type SessionCreateInput = {
  readonly agent?: Agent.ID | undefined
  readonly model?: Model.Ref | undefined
  readonly location?: Location.Ref | undefined
+  readonly metadata?: Session.Metadata | undefined
 }
 export type SessionCreateOutput = Session.Info
 export type SessionCreateOperation<E = never> = (input?: SessionCreateInput) => Effect.Effect<SessionCreateOutput, E>
@@ -410,6 +411,7 @@ export type SessionLogOutput =
            readonly title?: string | undefined
            readonly agent?: Agent.ID | undefined
            readonly model?: Model.Ref | undefined
+            readonly metadata?: Session.Metadata | undefined
            readonly version: string
          }
        }
@@ -360,6 +360,7 @@ const EndpointSessionCreate = (raw: RawClient["server.session"]) => (input?: Ses
        agent: input?.["agent"],
        model: input?.["model"],
        location: input?.["location"],
+        metadata: input?.["metadata"],
      },
    }).pipe(
      Effect.mapError(mapClientError),
@@ -513,6 +513,7 @@ export function make(options: ClientOptions) {
              agent: input?.["agent"],
              model: input?.["model"],
              location: input?.["location"],
+              metadata: input?.["metadata"],
            },
            successStatus: 200,
            declaredStatuses: [401, 400],
@@ -29,6 +29,8 @@ export type TokenUsageInfo = {

 export type LocationRef = { directory: string; workspaceID?: string }

+export type SessionMetadata = { [x: string]: JsonValue }
+
 export type FileDiffInfo = {
  file: string
  patch: string
@@ -548,6 +550,7 @@ export type SessionCreated = {
    title?: string
    agent?: string
    model?: ModelRef
+    metadata?: SessionMetadata
    version: string
  }
 }
@@ -1642,6 +1645,7 @@ export type SessionInfo = {
  title?: string
  location: LocationRef
  subpath?: string
+  metadata?: SessionMetadata
  revert?: SessionRevert
 }

@@ -2687,6 +2691,7 @@ export type SessionCreateInput = {
    readonly agent?: string | null
    readonly model?: { readonly id: string; readonly providerID: string; readonly variant?: string } | null
    readonly location?: { readonly directory: string; readonly workspaceID?: string } | null
+    readonly metadata?: { readonly [x: string]: JsonValue } | null
  }["id"]
  readonly title?: {
    readonly id?: string | null
@@ -2694,6 +2699,7 @@ export type SessionCreateInput = {
    readonly agent?: string | null
    readonly model?: { readonly id: string; readonly providerID: string; readonly variant?: string } | null
    readonly location?: { readonly directory: string; readonly workspaceID?: string } | null
+    readonly metadata?: { readonly [x: string]: JsonValue } | null
  }["title"]
  readonly agent?: {
    readonly id?: string | null
@@ -2701,6 +2707,7 @@ export type SessionCreateInput = {
    readonly agent?: string | null
    readonly model?: { readonly id: string; readonly providerID: string; readonly variant?: string } | null
    readonly location?: { readonly directory: string; readonly workspaceID?: string } | null
+    readonly metadata?: { readonly [x: string]: JsonValue } | null
  }["agent"]
  readonly model?: {
    readonly id?: string | null
@@ -2708,6 +2715,7 @@ export type SessionCreateInput = {
    readonly agent?: string | null
    readonly model?: { readonly id: string; readonly providerID: string; readonly variant?: string } | null
    readonly location?: { readonly directory: string; readonly workspaceID?: string } | null
+    readonly metadata?: { readonly [x: string]: JsonValue } | null
  }["model"]
  readonly location?: {
    readonly id?: string | null
@@ -2715,7 +2723,16 @@ export type SessionCreateInput = {
    readonly agent?: string | null
    readonly model?: { readonly id: string; readonly providerID: string; readonly variant?: string } | null
    readonly location?: { readonly directory: string; readonly workspaceID?: string } | null
+    readonly metadata?: { readonly [x: string]: JsonValue } | null
  }["location"]
+  readonly metadata?: {
+    readonly id?: string | null
+    readonly title?: string | null
+    readonly agent?: string | null
+    readonly model?: { readonly id: string; readonly providerID: string; readonly variant?: string } | null
+    readonly location?: { readonly directory: string; readonly workspaceID?: string } | null
+    readonly metadata?: { readonly [x: string]: JsonValue } | null
+  }["metadata"]
 }

 export type SessionCreateOutput = { data: SessionInfo }["data"]
@@ -2752,6 +2769,7 @@ export type SessionImportInput = {
      readonly title?: string
      readonly location: { readonly directory: string; readonly workspaceID?: string }
      readonly subpath?: string
+      readonly metadata?: { readonly [x: string]: JsonValue }
      readonly revert?: {
        readonly messageID: string
        readonly partID?: string
@@ -3028,6 +3046,7 @@ export type SessionImportInput = {
      readonly title?: string
      readonly location: { readonly directory: string; readonly workspaceID?: string }
      readonly subpath?: string
+      readonly metadata?: { readonly [x: string]: JsonValue }
      readonly revert?: {
        readonly messageID: string
        readonly partID?: string
@@ -3304,6 +3323,7 @@ export type SessionImportInput = {
      readonly title?: string
      readonly location: { readonly directory: string; readonly workspaceID?: string }
      readonly subpath?: string
+      readonly metadata?: { readonly [x: string]: JsonValue }
      readonly revert?: {
        readonly messageID: string
        readonly partID?: string
@@ -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" },
    ])
  })

@@ -514,7 +514,7 @@ function userPart(part: ContentPart): UserContent {
 function assistantPart(part: ContentPart): AssistantContent {
  switch (part.type) {
    case "text":
-      return [{ type: "text", text: part.text }]
+      return [{ type: "text", text: part.text, providerOptions: metadataProviderOptions(part.providerMetadata) }]
    case "media":
      return [{ type: "file", mediaType: part.mediaType, data: part.data, filename: part.filename }]
    case "reasoning":
@@ -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),
@@ -3,7 +3,7 @@ export * as CodeModeTool from "./tool.js"
 import { CodeMode, Tool, toolError } from "@opencode-ai/codemode"
 import type { Content, Context, Error, Info, Metadata, Result } from "@opencode-ai/schema/tool"
 import { Effect, Ref, Schema, Semaphore } from "effect"
-import { definition } from "../tool/runtime.js"
+import { definition, normalizedName } from "../tool/runtime.js"

 const ExecuteFile = Schema.Struct({
  data: Schema.String,
@@ -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 }]
@@ -165,7 +163,7 @@ function runtime(
 }

 function qualifiedName(registration: Info) {
-  const normalized = registration.name.replace(/[^a-zA-Z0-9_-]/g, "_")
+  const normalized = normalizedName(registration)
  if (registration.options?.namespace === undefined) return normalized
  return `${registration.options.namespace}.${normalized}`
 }
@@ -53,6 +53,9 @@ export class UpdateError extends Schema.TaggedError<UpdateError>()("Config.Updat

 export const Options = Schema.Struct({
  project: Schema.optional(Schema.Boolean),
+  // false skips the global config dir, ~/.claude, and ~/.agents; wellknown,
+  // file, and content entries still load.
+  global: Schema.optional(Schema.Boolean),
  file: Schema.optional(Schema.String),
  content: Schema.optional(Schema.String),
 })
@@ -84,7 +87,10 @@ export const testLayer = (initial: Entry[] = []) =>
            const entry = current[index]
            if (!entry || entry.type !== "document")
              return yield* Effect.fail(new UpdateError({ message: "No editable config document found" }))
-            const info = produce(entry.info, update)
+            const info = yield* Effect.try({
+              try: () => produce(entry.info, update),
+              catch: (cause) => new UpdateError({ message: "Config update failed", cause }),
+            })
            yield* Ref.set(entries, current.with(index, new Document({ type: "document", path: entry.path, info })))
            return info
          }),
@@ -217,28 +223,39 @@ export const layer = (options?: Options) =>
                })
                .pipe(Effect.orDie)

+        const globalEnabled = options?.global !== false
+        // A walked path that resolves into a global root is global config
+        // however the walk reached it (home above the project, or a location
+        // beneath the global config dir), so global: false excludes it
+        // uniformly — classified once here, not per consumer below.
+        const globalRoots = [globalDirectory, globalClaudeDirectory, globalAgentsDirectory].map((item) =>
+          path.resolve(item),
+        )
+        const visible = globalEnabled
+          ? discovered
+          : discovered.filter((item) => {
+              const resolved = path.resolve(item)
+              return !globalRoots.some((root) => resolved === root || resolved.startsWith(root + path.sep))
+            })
        // We load certain files from a few other folders in the ecosystem
        const claude = [
          ...new Set([
-            ...((yield* fs.isDir(globalClaudeDirectory)) ? [globalClaudeDirectory] : []),
-            ...discovered.filter((item) => path.basename(item) === ".claude").toReversed(),
+            ...(globalEnabled && (yield* fs.isDir(globalClaudeDirectory)) ? [globalClaudeDirectory] : []),
+            ...visible.filter((item) => path.basename(item) === ".claude").toReversed(),
          ]),
        ].map((directory) => new ClaudeDirectory({ type: "claude", path: AbsolutePath.make(directory) }))
        const agents = [
          ...new Set([
-            ...((yield* fs.isDir(globalAgentsDirectory)) ? [globalAgentsDirectory] : []),
-            ...discovered.filter((item) => path.basename(item) === ".agents").toReversed(),
+            ...(globalEnabled && (yield* fs.isDir(globalAgentsDirectory)) ? [globalAgentsDirectory] : []),
+            ...visible.filter((item) => path.basename(item) === ".agents").toReversed(),
          ]),
        ].map((directory) => new AgentsDirectory({ type: "agents", path: AbsolutePath.make(directory) }))

-        const directories = [
-          globalDirectory,
-          ...discovered
-            .filter((item) => path.basename(item) === ".opencode")
-            .toReversed()
-            .map((directory) => AbsolutePath.make(directory)),
-        ]
-        const directPaths = discovered
+        const projectDirectories = visible
+          .filter((item) => path.basename(item) === ".opencode")
+          .toReversed()
+          .map((directory) => AbsolutePath.make(directory))
+        const directPaths = visible
          .filter((item) => ![".agents", ".claude", ".opencode"].includes(path.basename(item)))
          .toReversed()
        fileTargets.clear()
@@ -270,15 +287,21 @@ export const layer = (options?: Options) =>
              )
            : []

-        const supplementary = yield* Effect.forEach(directories, loadDirectory).pipe(Effect.orDie)
+        // Global entries sit below explicit and direct files; project
+        // directories rank above them.
+        const globalSupplementary = globalEnabled ? yield* loadDirectory(globalDirectory).pipe(Effect.orDie) : []
+        const projectSupplementary = yield* Effect.forEach(projectDirectories, loadDirectory).pipe(
+          Effect.orDie,
+          Effect.map((entries) => entries.flat()),
+        )
        return [
          ...(yield* loadWellknown().pipe(Effect.orDie)),
          ...claude,
          ...agents,
-          ...(supplementary[0] ?? []),
+          ...globalSupplementary,
          ...explicit,
          ...direct,
-          ...supplementary.slice(1).flat(),
+          ...projectSupplementary,
          ...content,
        ]
      })
@@ -19,6 +19,9 @@ export const Plugin = define({
  id: "opencode.config.instruction",
  effect: Effect.fn(function* () {
    const discovery = yield* InstructionDiscovery.Service
+    // Nothing this plugin watches or loads can contribute when both scopes
+    // are disabled; skip the resolves, the watcher fiber, and the transform.
+    if (!discovery.project && !discovery.global) return
    yield* Effect.gen(function* () {
      const fs = yield* FSUtil.Service
      const global = yield* Global.Service
@@ -35,9 +38,15 @@ export const Plugin = define({
      const loaded: { current: Loaded } = { current: { type: "available", files: [] } }

      const publish = (update: Watcher.Update) => PubSub.publish(changes, update.path).pipe(Effect.asVoid)
+      // The ancestor walk can reach the global file when the location sits
+      // beneath the global config dir; global: false excludes it there too.
      const candidates = [
-        globalFile,
-        ...(project ? ancestorDirectories(start, stop).map((directory) => join(directory, "AGENTS.md")) : []),
+        ...(discovery.global ? [globalFile] : []),
+        ...(project
+          ? ancestorDirectories(start, stop)
+              .map((directory) => join(directory, "AGENTS.md"))
+              .filter((file) => discovery.global || file !== globalFile)
+          : []),
      ]
      for (const path of new Set(candidates)) {
        const updates = yield* watcher.subscribe({ path, type: "file" })
@@ -51,15 +60,15 @@ export const Plugin = define({
      })

      const globalSource = Effect.fn("ConfigInstructionPlugin.globalSource")(function* () {
+        if (!discovery.global) return []
        const file = yield* read(globalFile)
        return file ? [file] : []
      })

      const projectSource = Effect.fn("ConfigInstructionPlugin.projectSource")(function* () {
        if (!project) return []
-        const discovered = new Set(
-          yield* Effect.forEach(yield* fs.up({ targets: ["AGENTS.md"], start, stop }), fs.resolve),
-        )
+        const walked = yield* Effect.forEach(yield* fs.up({ targets: ["AGENTS.md"], start, stop }), fs.resolve)
+        const discovered = new Set(walked.filter((file) => discovery.global || file !== globalFile))
        const files = yield* Effect.forEach(discovered, read, { concurrency: "unbounded" })
        if (files.some((file) => file === undefined)) return Instructions.unavailable
        return files.filter((file): file is InstructionDiscovery.File => file !== undefined)
@@ -7,16 +7,16 @@ import { FileSystem } from "@opencode-ai/schema/filesystem"
 import { makeGlobalNode } from "@opencode-ai/util/effect/app-node"
 import { Cause, Context, Effect, Layer, PubSub, RcMap, Schema, Stream } from "effect"
 import { lazy } from "../util/lazy.js"
-import { watch as watchFileSystem } from "node:fs"
+import { watch } from "node:fs"
 import path from "path"
 import loadBinding from "./watcher-binding.js"

 const SUBSCRIBE_TIMEOUT_MS = 10_000
 export const Event = { Updated: FileSystem.Event.Changed }

-const watcher = lazy((): typeof import("@parcel/watcher") | undefined => {
+const watcher = lazy((): typeof ParcelWatcher | undefined => {
  try {
-    return createWrapper(loadBinding()) as typeof import("@parcel/watcher")
+    return createWrapper(loadBinding()) as typeof ParcelWatcher
  } catch {
    return
  }
@@ -192,7 +192,7 @@ export const nativeLayer = Layer.succeed(
      if (input.type === "file") {
        return Effect.sync(() => {
          const directory = path.dirname(input.target)
-          const subscription = watchFileSystem(directory, { recursive: false }, (_event, file) => {
+          const subscription = watch(directory, { recursive: false }, (_event, file) => {
            if (file && path.resolve(directory, file.toString()) !== input.target) return
            input.publish({ path: input.target, type: "update" } satisfies Update)
          })
@@ -218,7 +218,7 @@ export function configured(options?: Options) {
 export const node = configured()

 function subscribeDirectory(
-  native: typeof import("@parcel/watcher") | undefined,
+  native: typeof ParcelWatcher | undefined,
  backend: ParcelWatcher.BackendType | undefined,
  directory: string,
  ignore: readonly string[],
@@ -311,7 +311,7 @@ function validateField(field: InputField, value: Form.Value): string | undefined
    }
    if (field.format === "email" && !/^[^\s@]+@[^\s@]+\.[^\s@]+$/.test(value))
      return `Expected email for form field: ${field.key}`
-    if (field.format === "uri" && !isUri(value)) return `Expected URI for form field: ${field.key}`
+    if (field.format === "uri" && !URL.canParse(value)) return `Expected URI for form field: ${field.key}`
    if (field.format === "date" && !isDate(value)) return `Expected date for form field: ${field.key}`
    if (field.format === "date-time" && !isDateTime(value)) return `Expected date-time for form field: ${field.key}`
    if (field.options && !field.custom && !field.options.some((option) => option.value === value)) {
@@ -347,15 +347,6 @@ function isStringArray(value: Form.Value): value is ReadonlyArray<string> {
  return Array.isArray(value) && value.every((item): item is string => typeof item === "string")
 }

-function isUri(value: string) {
-  try {
-    new URL(value)
-    return true
-  } catch {
-    return false
-  }
-}
-
 function isDate(value: string) {
  if (!/^\d{4}-\d{2}-\d{2}$/.test(value)) return false
  const date = new Date(`${value}T00:00:00.000Z`)
@@ -37,20 +37,19 @@ export const layer = Layer.effect(

    const runText = Effect.fn("Generate.text")(function* (input: TextInput) {
      const resolved = yield* resolver.resolve(input.model).pipe(
-        Effect.catchTags({
-          "SessionRunnerModel.VariantUnavailableError": (error) =>
-            input.model
+        Effect.catchTag(
+          [
+            "SessionRunnerModel.VariantUnavailableError",
+            "SessionRunnerModel.UnsupportedPackageError",
+            "SessionRunnerModel.UnresolvedProviderVariablesError",
+          ],
+          (error) => {
+            const mapped: Error = input.model
              ? new ModelSelectionError({ message: error.message })
-              : new UnavailableError({ message: error.message, service: error.providerID }),
-          "SessionRunnerModel.UnsupportedPackageError": (error) =>
-            input.model
-              ? new ModelSelectionError({ message: error.message })
-              : new UnavailableError({ message: error.message, service: error.providerID }),
-          "SessionRunnerModel.UnresolvedProviderVariablesError": (error) =>
-            input.model
-              ? new ModelSelectionError({ message: error.message })
-              : new UnavailableError({ message: error.message, service: error.providerID }),
-        }),
+              : new UnavailableError({ message: error.message, service: error.providerID })
+            return Effect.fail(mapped)
+          },
+        ),
      )
      if (!resolved)
        return yield* new ModelSelectionError({
@@ -47,7 +47,7 @@ export function prepareResponsesTools({
          name: tool.name,
          description: tool.description,
          parameters: tool.inputSchema,
-          strict: strictJsonSchema,
+          strict: tool.strict ?? strictJsonSchema,
        })
        break
      case "provider": {
@@ -23,6 +23,7 @@ import { Mcp } from "./mcp/index.js"
 import { Permission } from "./permission.js"
 import { Plugin } from "./plugin.js"
 import { PluginHooks } from "./plugin/hooks.js"
+import { InstancePlugins } from "./plugin/instance.js"
 import { PluginSupervisor } from "./plugin/supervisor.js"
 import { Worktree } from "./worktree.js"
 import { Pty } from "./pty.js"
@@ -66,6 +67,7 @@ const nodes = [
  AISDK.node,
  Plugin.node,
  PluginHooks.node,
+  InstancePlugins.node,
  PluginSupervisor.node,
  Worktree.refreshNode,
  FileSystemSearch.node,
@@ -109,10 +111,45 @@ export const graph = LayerNode.group<typeof nodes>(nodes)
 export type Services = LayerNode.Output<typeof graph>
 export type Error = LayerNode.Error<typeof graph>

+export interface Options {
+  // Plugins this instance is born with; empty and absent are equivalent.
+  readonly plugins?: InstancePlugins.List
+  // Filesystem config discovery; true (default) is today's behavior. When
+  // false the instance boots vanilla: no upward config scan, no global config
+  // dir, no plugin-dir loading or ambient plugin module imports, no boot-time
+  // AGENTS.md discovery. Wellknown integration config and host-injected values
+  // still apply, and a config value that explicitly names something
+  // file-backed (a skill path, an MCP command) is a request, not discovery.
+  // Use-triggered behavior also stays: reading a file still injects nested
+  // AGENTS.md instructions — that is session-time context, not boot-time
+  // population.
+  readonly discovery?: boolean
+  readonly replacements?: LayerNode.Replacements
+}
+
+// Vanilla neutralizes the discovery inputs; the plugin list stays untouched.
+// These are defaults ahead of caller replacements: a host that replaces a
+// gated node itself owns that node's discovery flags. Plugin-directory
+// discovery needs no swap here — implicit scanning only triggers on Directory
+// config entries, which a no-scan Config never produces, and the default
+// source still honors explicit plugin operations from wellknown and
+// host-injected config.
+const vanillaReplacements: LayerNode.Replacements = [
+  [Config.node, Config.configured({ project: false, global: false })],
+  [InstructionDiscovery.node, InstructionDiscovery.configured({ project: false, global: false })],
+]
+
 // One instance is one compiled, fresh copy of the graph standing on a directory.
-export function layer(ref: Location.Ref, replacements: LayerNode.Replacements = []) {
+export function layer(ref: Location.Ref, options: Options = {}) {
  const startedAt = performance.now()
-  const allReplacements = replacements.concat([[Location.node, Location.boundNode(ref)]])
+  // Ordered: vanilla defaults, then caller replacements (which win over the
+  // defaults), then bound pairs (which win over everything).
+  const allReplacements: LayerNode.Replacements = [
+    ...(options.discovery === false ? vanillaReplacements : []),
+    ...(options.replacements ?? []),
+    [Location.node, Location.boundNode(ref, { discovery: options.discovery })],
+    [InstancePlugins.node, InstancePlugins.bound(options.plugins ?? [])],
+  ]
  // Apply replacements during hoist, not afterward: replacements can
  // introduce new tagged dependencies (Location.boundNode depends on
  // Project), and the hoist walk is the only pass that can still slice
@@ -39,12 +39,14 @@ export interface Interface extends State.Transformable<Draft> {
  // Discovery policy lives here because internal plugins have no per-composition options channel.
  // Move it into plugin config once plugins can consume their own options.
  readonly project: boolean
+  readonly global: boolean
  readonly list: () => Effect.Effect<File[] | Instructions.Unavailable>
  readonly load: () => Effect.Effect<Instructions.List>
 }

 export const Options = Schema.Struct({
  project: Schema.optional(Schema.Boolean),
+  global: Schema.optional(Schema.Boolean),
 })
 export type Options = typeof Options.Type

@@ -95,6 +97,7 @@ export const layer = (options?: Options) =>

      return Service.of({
        project: options?.project !== false,
+        global: options?.global !== false,
        transform: state.transform,
        reload: state.reload,
        list,
@@ -16,7 +16,8 @@ export type Kind = typeof Kind.Type
 /**
 * Mutation paths do not accept project references. A leading `~` expands to
 * the home directory; other relative paths resolve from the active Location.
- * Paths outside it require separate `external_directory` approval.
+ * Paths outside it and its non-root project worktree require separate
+ * `external_directory` approval.
 */
 export const ResolveInput = Schema.Struct({
  path: Schema.String,
@@ -52,22 +53,24 @@ export interface Interface {
  /**
   * Resolve a path and derive its permission resources. A leading `~` expands
   * to the home directory; other relative paths resolve from the Location.
-   * Paths outside it require separate `external_directory` approval. This does
-   * not approve the mutation.
+   * Paths outside it and its non-root project worktree require separate
+   * `external_directory` approval. This does not approve the mutation.
   */
  readonly resolve: (input: ResolveInput) => Effect.Effect<Target, FSUtil.Error>
 }

-/** Lexical absolute path, expanding a leading `~` before resolving against `directory`. */
-export const resolvePath = (directory: string, input: string, home = Global.Path.home) =>
-  path.resolve(
+/** Lexical absolute path, normalizing Windows shell paths and expanding `~` before resolution. */
+export const resolvePath = (directory: string, input: string, home = Global.Path.home) => {
+  const normalized = FSUtil.windowsPath(input)
+  return path.resolve(
    directory,
-    input === "~"
+    normalized === "~"
      ? home
-      : input.startsWith("~/") || (process.platform === "win32" && input.startsWith("~\\"))
-        ? path.join(home, input.slice(2))
-        : input,
+      : normalized.startsWith("~/") || (process.platform === "win32" && normalized.startsWith("~\\"))
+        ? path.join(home, normalized.slice(2))
+        : normalized,
  )
+}

 export class Service extends Context.Service<Service, Interface>()("@opencode/LocationMutation") {}

@@ -82,7 +85,11 @@ const layer = Layer.effect(

    const resolve = Effect.fnUntraced(function* (input: ResolveInput) {
      const absolute = resolvePath(location.directory, input.path)
-      if (FSUtil.contains(location.directory, absolute)) {
+      const worktree = path.resolve(location.project.directory)
+      const internal =
+        FSUtil.contains(location.directory, absolute) ||
+        (worktree !== path.parse(worktree).root && FSUtil.contains(worktree, absolute))
+      if (internal) {
        return {
          absolute,
          resource: slash(path.relative(location.directory, absolute) || "."),
@@ -120,6 +127,6 @@ const layer = Layer.effect(

 export const node = makeLocationNode({
  service: Service,
-  layer: layer.pipe(Layer.orDie),
+  layer,
  deps: [FSUtil.node, Location.node, ProjectMarkers.node],
 })
@@ -25,7 +25,7 @@ export function buildLocationServiceMap(
  return Layer.effect(
    LocationServiceMap.Service,
    Effect.map(
-      LayerMap.make((ref: Location.Ref) => Instance.layer(ref, replacements), {
+      LayerMap.make((ref: Location.Ref) => Instance.layer(ref, { replacements }), {
        // Workspace-placed directories exist only inside the workspace, so a
        // local stat consults the wrong filesystem. Workspace liveness is
        // owned by placement; do not probe the sandbox here, which would
@@ -17,12 +17,12 @@ export class Service extends Context.Service<Service, Interface>()("@opencode/Lo

 export const node = LayerNode.unbound(Service, tags.values.location)

-const layer = (ref: Ref) =>
+const layer = (ref: Ref, options?: { readonly discovery?: boolean }) =>
  Layer.effect(
    Service,
    Effect.gen(function* () {
      const project = yield* Project.Service
-      const resolved = yield* project.resolve(ref.directory)
+      const resolved = yield* project.resolve(ref.directory, options)
      return Service.of({
        directory: ref.directory,
        workspaceID: ref.workspaceID,
@@ -33,9 +33,9 @@ const layer = (ref: Ref) =>
    }),
  )

-export const boundNode = (ref: Ref) =>
+export const boundNode = (ref: Ref, options?: { readonly discovery?: boolean }) =>
  makeLocationNode({
    service: Service,
-    layer: layer(ref),
+    layer: layer(ref, options),
    deps: [Project.node],
  })
@@ -19,7 +19,7 @@ async function install(
  const directory = path.join(root, `${input.version}-${input.sha256.slice(0, 16)}`)
  await privateDirectory(directory)
  const destination = path.join(directory, "opencode-pty")
-  if (await exists(destination, input.sha256)) return destination
+  if (await validateIfPresent(destination, input.sha256)) return destination

  const bytes = new Uint8Array(await Bun.file(input.path).arrayBuffer())
  if (sha256(bytes) !== input.sha256) throw new Error("Embedded opencode-pty checksum mismatch")
@@ -34,7 +34,7 @@ async function install(
    }
    await chmod(temporary, 0o755)
    await rename(temporary, destination).catch(async (error) => {
-      if (!(await exists(destination, input.sha256))) throw error
+      if (!(await validateIfPresent(destination, input.sha256))) throw error
    })
  } finally {
    await rm(temporary, { force: true })
@@ -52,7 +52,7 @@ async function privateDirectory(directory: string) {
  await chmod(directory, 0o700)
 }

-async function exists(file: string, expected: string) {
+async function validateIfPresent(file: string, expected: string) {
  try {
    await validate(file, expected)
    return true
@@ -62,14 +62,13 @@ async function exists(file: string, expected: string) {
  }
 }

-async function validate(file: string, expected?: string) {
+async function validate(file: string, expected: string) {
  const info = await lstat(file)
  if (!info.isFile() || info.isSymbolicLink()) throw new Error(`Unsafe opencode-pty executable: ${file}`)
  const uid = typeof process.getuid === "function" ? process.getuid() : undefined
  if (uid !== undefined && info.uid !== uid)
    throw new Error(`opencode-pty executable is owned by another user: ${file}`)
-  if (expected && sha256(await readFile(file)) !== expected)
-    throw new Error(`Cached opencode-pty checksum mismatch: ${file}`)
+  if (sha256(await readFile(file)) !== expected) throw new Error(`Cached opencode-pty checksum mismatch: ${file}`)
  await chmod(file, 0o755)
  return file
 }
@@ -91,16 +91,11 @@ const layer = Layer.effect(

      yield* lock.withPermit(
        Effect.gen(function* () {
-          const next = definitions.map((definition) => ({ id: definition.id, version: definition.version }))
-          const current = Array.from(active.values(), (entry) => ({
-            id: entry.plugin.id,
-            version: entry.plugin.version,
-          }))
          if (
-            current.length === next.length &&
-            current.every((definition, index) => {
-              const candidate = next[index]
-              return definition.id === candidate?.id && definition.version === candidate.version
+            active.size === definitions.length &&
+            Array.from(active.values()).every((entry, index) => {
+              const definition = definitions[index]
+              return entry.plugin.id === definition?.id && entry.plugin.version === definition.version
            })
          ) {
            const nextInventory = [...Array.from(active.values(), (entry) => activeInfo(entry.plugin)), ...failures]
@@ -83,7 +83,7 @@ Use best judgement when processing input.
 Use these to inform your review:

 - **Explore agent** - Find how existing code handles similar problems. Check patterns, conventions, and prior art before claiming something doesn't fit.
- **Exa Code Context** - Verify correct usage of libraries/APIs before flagging something as wrong.
+- **Available documentation and code-search tools** - Verify correct usage of libraries/APIs before flagging something as wrong.
 - **Web Search** - Research best practices if you're unsure about a pattern.

 If you're uncertain about something and can't verify it with these tools, say "I'm not sure about X" rather than flagging it as a definite issue.
@@ -0,0 +1,50 @@
+export * as InstancePlugins from "./instance.js"
+
+import type { Plugin } from "@opencode-ai/plugin/effect/plugin"
+import { Context, Layer } from "effect"
+import { makeLocationNode } from "@opencode-ai/util/effect/app-node"
+import type { Versioned } from "../plugin.js"
+
+/**
+ * Holds the plugins one instance is born with. Unlike the host-global
+ * `SdkPlugins` store, this list is a birth argument of a single instance:
+ * `Instance.layer` binds it through the replacement mechanism, so two
+ * instances in one process can carry different plugins. The list is immutable
+ * for the instance's lifetime; runtime dynamism lives inside plugins through
+ * the container transform/reload APIs.
+ *
+ * Limitations: `vcs` marker declarations in an instance list are not seen by
+ * `ProjectMarkers` (it is global and runs during project resolution, before
+ * the instance exists — unlike `SdkPlugins`, whose declarations it consumes
+ * directly), and config plugin operations may disable instance plugins by id,
+ * matching `SdkPlugins` behavior.
+ */
+export type List = readonly Plugin[]
+
+export interface Interface {
+  readonly all: () => readonly Versioned[]
+}
+
+export class Service extends Context.Service<Service, Interface>()("@opencode/InstancePlugins") {}
+
+export const node = makeLocationNode({
+  service: Service,
+  layer: bound([]),
+  deps: [],
+})
+
+// The constant version is load-bearing: the plugin registry treats an
+// unchanged (id, version) pair as the same plugin across activations, which
+// is only correct because a bound list never changes after creation.
+// `source: "sdk"` means host-contributed; an instance list is the
+// per-instance form of the same channel.
+export function bound(plugins: List) {
+  const duplicates = plugins.filter((plugin, index) => plugins.findIndex((other) => other.id === plugin.id) !== index)
+  if (duplicates.length > 0) {
+    throw new Error(`duplicate instance plugin ids: ${duplicates.map((plugin) => plugin.id).join(", ")}`)
+  }
+  const stamped = plugins.map(
+    (plugin): Versioned => ({ ...plugin, version: "instance", source: { type: "sdk" } }),
+  )
+  return Layer.succeed(Service, Service.of({ all: () => stamped }))
+}
@@ -1,5 +1,5 @@
 import { Effect, Option } from "effect"
-import type { Document } from "@opencode-ai/schema/config"
+import type { Document, Entry } from "@opencode-ai/schema/config"
 import { Catalog } from "../../catalog.js"
 import { Config } from "../../config.js"
 import { Provider } from "../../provider.js"
@@ -9,7 +9,11 @@ export const configuredSettings = Effect.fn("ProviderPlugin.configuredSettings")
  const current = (yield* catalog.provider.get(id))?.settings
  const service = yield* Effect.serviceOption(Config.Service)
  const entries = Option.isSome(service) ? yield* service.value.entries() : []
+  return foldSettings(entries, id, current)
+})
+
+export function foldSettings(entries: readonly Entry[], id: string, initial: Provider.Settings | undefined) {
  return entries
    .filter((entry): entry is Document => entry.type === "document")
-    .reduce((settings, entry) => Provider.mergeOverlay(settings, entry.info.providers?.[id]?.settings), current)
-})
+    .reduce((settings, entry) => Provider.mergeOverlay(settings, entry.info.providers?.[id]?.settings), initial)
+}
@@ -81,9 +81,6 @@ export const GoogleVertexPlugin = define({
            ...(typeof provider.settings?.baseURL === "string"
              ? { baseURL: replaceVertexVars(provider.settings.baseURL, project, location) }
              : {}),
-            ...(Provider.packageName(provider.package)?.includes("@ai-sdk/openai-compatible")
-              ? { fetch: authFetch(provider.settings?.fetch) }
-              : {}),
          }
        })
      }
@@ -1,11 +1,11 @@
 import { define } from "@opencode-ai/plugin/effect/plugin"
-import { Document, type Entry } from "@opencode-ai/schema/config"
+import type { Entry } from "@opencode-ai/schema/config"
 import { Duration, Effect, Schedule, Schema, Semaphore, Stream } from "effect"
 import { HttpClient, HttpClientRequest, HttpClientResponse } from "effect/unstable/http"
 import { Config } from "../../config.js"
 import { Model } from "../../model.js"
-import { Provider } from "../../provider.js"
 import type { PluginInternal } from "../internal.js"
+import { foldSettings } from "./configured.js"

 const providerID = "lmstudio"

@@ -150,13 +150,7 @@ export function make(origin = "http://127.0.0.1:1234", interval: Duration.Input
 export const LMStudioPlugin = make()

 function configured(entries: readonly Entry[], origin: string) {
-  const settings = entries
-    .filter((entry): entry is Document => entry.type === "document")
-    .flatMap((entry) => {
-      const settings = entry.info.providers?.[providerID]?.settings
-      return settings ? [settings] : []
-    })
-    .reduce<Provider.Settings | undefined>((result, item) => Provider.mergeOverlay(result, item), undefined)
+  const settings = foldSettings(entries, providerID, undefined)
  const baseURL = (
    typeof settings?.baseURL === "string" ? settings.baseURL : `${origin.replace(/\/+$/, "")}/v1`
  ).replace(/\/+$/, "")
@@ -1,11 +1,11 @@
 import { define } from "@opencode-ai/plugin/effect/plugin"
-import { Document, type Entry } from "@opencode-ai/schema/config"
+import type { Entry } from "@opencode-ai/schema/config"
 import { Duration, Effect, Schedule, Schema, Semaphore, Stream } from "effect"
 import { HttpClient, HttpClientRequest, HttpClientResponse } from "effect/unstable/http"
 import { Config } from "../../config.js"
 import { Model } from "../../model.js"
-import { Provider } from "../../provider.js"
 import type { PluginInternal } from "../internal.js"
+import { foldSettings } from "./configured.js"

 const providerID = "ollama"

@@ -206,13 +206,7 @@ export function make(origin = "http://127.0.0.1:11434", interval: Duration.Input
 export const OllamaPlugin = make()

 function configured(entries: readonly Entry[], origin: string) {
-  const settings = entries
-    .filter((entry): entry is Document => entry.type === "document")
-    .flatMap((entry) => {
-      const settings = entry.info.providers?.[providerID]?.settings
-      return settings ? [settings] : []
-    })
-    .reduce<Provider.Settings | undefined>((result, item) => Provider.mergeOverlay(result, item), undefined)
+  const settings = foldSettings(entries, providerID, undefined)
  const baseURL = (
    typeof settings?.baseURL === "string" ? settings.baseURL : `${origin.replace(/\/+$/, "")}/v1`
  ).replace(/\/+$/, "")
@@ -1,11 +1,11 @@
 import { define } from "@opencode-ai/plugin/effect/plugin"
-import { Document, type Entry } from "@opencode-ai/schema/config"
+import type { Entry } from "@opencode-ai/schema/config"
 import { Duration, Effect, Schedule, Schema, Semaphore, Stream } from "effect"
 import { HttpClient, HttpClientRequest, HttpClientResponse } from "effect/unstable/http"
 import { Config } from "../../config.js"
 import { Model } from "../../model.js"
-import { Provider } from "../../provider.js"
 import type { PluginInternal } from "../internal.js"
+import { foldSettings } from "./configured.js"

 const providerID = "vllm"

@@ -136,13 +136,7 @@ export function make(origin = "http://127.0.0.1:8000", interval: Duration.Input
 export const VLLMPlugin = make()

 function configured(entries: readonly Entry[], origin: string) {
-  const settings = entries
-    .filter((entry): entry is Document => entry.type === "document")
-    .flatMap((entry) => {
-      const settings = entry.info.providers?.[providerID]?.settings
-      return settings ? [settings] : []
-    })
-    .reduce<Provider.Settings | undefined>((result, item) => Provider.mergeOverlay(result, item), undefined)
+  const settings = foldSettings(entries, providerID, undefined)
  const baseURL = (
    typeof settings?.baseURL === "string" ? settings.baseURL : `${origin.replace(/\/+$/, "")}/v1`
  ).replace(/\/+$/, "")
@@ -76,7 +76,7 @@ export const layerWithCell = (cell: Cell) =>
        resume: (sessionID) => require(cell, (runtime) => runtime.session.resume(sessionID)),
        switchAgent: (input) => require(cell, (runtime) => runtime.session.switchAgent(input)),
        switchModel: (input) => require(cell, (runtime) => runtime.session.switchModel(input)),
-        interrupt: (sessionID) => require(cell, (runtime) => runtime.session.interrupt(sessionID)),
+        interrupt: (sessionID, options) => require(cell, (runtime) => runtime.session.interrupt(sessionID, options)),
        synthetic: (input) => require(cell, (runtime) => runtime.session.synthetic(input)),
        wait: (sessionID) => require(cell, (runtime) => runtime.session.wait(sessionID)),
        context: (sessionID) => require(cell, (runtime) => runtime.session.context(sessionID)),
@@ -9,6 +9,7 @@ import { makeLocationNode } from "@opencode-ai/util/effect/app-node"
 import { Bus } from "../bus.js"
 import { Npm } from "@opencode-ai/util/npm"
 import { Plugin } from "../plugin.js"
+import { InstancePlugins } from "./instance.js"
 import { PluginInternal } from "./internal.js"
 import { PluginModule } from "./module.js"
 import { SdkPlugins } from "./sdk.js"
@@ -85,6 +86,7 @@ export const layer = Layer.effect(
  Effect.gen(function* () {
    const registry = yield* Plugin.Service
    const sdk = yield* SdkPlugins.Service
+    const instance = yield* InstancePlugins.Service
    const sources = yield* ConfigPluginSource.Service
    const bus = yield* Bus.Service
    const ready = yield* Latch.make()
@@ -93,10 +95,13 @@ export const layer = Layer.effect(
    const activate = Effect.fn("PluginSupervisor.activate")(function* () {
      // Resolve OpenCode's internal plugins with their privileged Location services.
      const internal = yield* PluginInternal.list()
-      // Combine internal plugins with host-contributed SDK plugins in boot order.
+      // Combine internal plugins with host-contributed plugins in boot order.
+      // Instance-bound plugins come last: later activation can override earlier
+      // container writes, so the instance's explicit choices win over globals.
      const pre = [
        ...internal.pre.map((plugin) => ({ ...plugin, version: "internal", source: { type: "builtin" as const } })),
        ...sdk.all(),
+        ...instance.all(),
      ]
      const post = internal.post.map((plugin) => ({
        ...plugin,
@@ -125,9 +130,9 @@ export const layer = Layer.effect(
      Stream.debounce("100 millis"),
      Stream.runForEach((target) =>
        Effect.gen(function* () {
-          yield* activate()
+          yield* activate().pipe(Effect.catchCause((cause) => Effect.logError("failed to reload plugins", { cause })))
          if (observed === target) yield* ready.open
-        }).pipe(Effect.catchCause((cause) => Effect.logError("failed to reload plugins", { cause }))),
+        }),
      ),
      Effect.forkScoped({ startImmediately: true }),
    )
@@ -138,6 +143,7 @@ export const layer = Layer.effect(
 const nodeDeps = [
  Plugin.node,
  SdkPlugins.node,
+  InstancePlugins.node,
  ConfigPluginSource.node,
  Bus.node,
  Npm.node,
@@ -49,7 +49,7 @@ Use the instructions below and the tools available to assist the user.

 # Tool Use - OpenCode Specifics
 - When `webfetch` returns a message about a redirect to a different host, you should immediately make a new `webfetch` request with the redirect URL provided in the response.
- When `plan` mode is active, you will see a <system-reminder> about this. `plan` mode is for planning, not editing. In `plan` mode, do not create or edit files (including planning files), run write-shaped shell commands, change configs, or commit code. If the user is asking you to perform edit operations in `plan` mode, inform them that `plan` mode is active and that they need to switch to build mode.
+- When `plan` mode is active, you will see a <system-reminder> about this. Follow that reminder for the files you may edit and all other Plan mode restrictions. If the user asks you to implement changes, inform them that `plan` mode is active and that they need to switch to build mode.

 # Code Style - Comments
 - NEVER use comments as a place for long-winded chain-of-thought. Long thinking texts must be generated as private reasoning. Comments in code must be appropriately concise.
@@ -109,25 +109,14 @@ function make(
      return []
    }),
    status: Effect.fn("VcsHg.status")(function* () {
-      const [items, batch] = yield* Effect.all(
-        // Zero-context patches are enough to count changed lines.
-        [hg.status(undefined, scope), hg.diff(undefined, scope, { context: 0 })],
-        { concurrency: 2 },
-      )
-      const chunks = chunksByFile(batch, () => undefined)
-      return yield* Effect.forEach(
-        items.toSorted((a, b) => a.file.localeCompare(b.file)),
+      return (yield* diffAgainst(undefined, { context: 0 })).map(
        (item) =>
-          Effect.gen(function* () {
-            const patch = yield* patchFor(item, undefined, chunks.get(item.file))
-            const counts = countPatch(patch)
-            return {
-              file: item.file,
-              additions: counts.additions,
-              deletions: counts.deletions,
-              status: item.status,
-            } satisfies FileStatus
-          }),
+          ({
+            file: item.file,
+            additions: item.additions,
+            deletions: item.deletions,
+            status: item.status,
+          }) satisfies FileStatus,
      )
    }),
    diff: Effect.fn("VcsHg.diff")(function* (mode: Mode, options?: DiffOptions) {
@@ -62,7 +62,7 @@ export const root = Effect.fn("Project.root")(function* (
 export interface Interface {
  readonly list: () => Effect.Effect<ReadonlyArray<Info>>
  readonly update: (input: UpdateInput) => Effect.Effect<Info, NotFoundError>
-  readonly resolve: (input: AbsolutePath) => Effect.Effect<Resolved>
+  readonly resolve: (input: AbsolutePath, options?: { readonly discovery?: boolean }) => Effect.Effect<Resolved>
 }

 export class Service extends Context.Service<Service, Interface>()("@opencode/Project") {}
@@ -256,15 +256,14 @@ const layer = Layer.effect(
      const value = input.trim()
      if (!value) return undefined

-      try {
-        const parsed = new URL(value)
+      const parsed = URL.parse(value)
+      if (parsed) {
        if (parsed.protocol === "file:") return undefined
        return parts(parsed.hostname, parsed.pathname)
-      } catch {
-        const scp = value.match(/^([^@/:]+@)?([^/:]+):(.+)$/)
-        if (scp) return parts(scp[2], scp[3])
-        return undefined
      }
+      const scp = value.match(/^([^@/:]+@)?([^/:]+):(.+)$/)
+      if (scp) return parts(scp[2], scp[3])
+      return undefined
    }

    function parts(host: string, name: string) {
@@ -317,9 +316,12 @@ const layer = Layer.effect(
      }
    })

-    const resolve = Effect.fn("Project.resolve")(function* (input: AbsolutePath) {
+    const resolve = Effect.fn("Project.resolve")(function* (
+      input: AbsolutePath,
+      options?: { readonly discovery?: boolean },
+    ) {
      const directory = AbsolutePath.make(yield* fs.resolve(input))
-      const marker = yield* markers.discover(directory)
+      const marker = yield* markers.discover(directory, options)
      const native = yield* fs.up({ targets: [".git", ".hg"], start: directory, mode: "first" }).pipe(
        Effect.map((matches) => matches[0]),
        Effect.orElseSucceed(() => undefined),
@@ -22,7 +22,10 @@ export interface Match {
 }

 export interface Interface {
-  readonly discover: (directory: AbsolutePath) => Effect.Effect<Match | undefined>
+  readonly discover: (
+    directory: AbsolutePath,
+    options?: { readonly discovery?: boolean },
+  ) => Effect.Effect<Match | undefined>
  readonly targets: () => readonly string[]
 }

@@ -38,7 +41,10 @@ const layer = Layer.effect(
    const known = new Set([".git", ".hg"])
    const loaded = new Map<string, Versioned | undefined>()

-    const discover = Effect.fn("ProjectMarkers.discover")(function* (directory: AbsolutePath) {
+    // The filesystem half of discovery: walk up for config, scan plugin
+    // directories, and read configured plugin operations. This is the part a
+    // no-discovery caller must skip — it imports plugin modules.
+    const scanOperations = Effect.fnUntraced(function* (directory: AbsolutePath) {
      const found = yield* fs
        .up({ targets: [".opencode", "opencode.json", "opencode.jsonc"], start: directory })
        .pipe(Effect.orElseSucceed(() => []))
@@ -54,7 +60,7 @@ const layer = Layer.effect(
      const configured = yield* Effect.forEach([...new Set(files)], (file) => read(fs, file)).pipe(
        Effect.map((entries) => entries.flat()),
      )
-      const operations = yield* Effect.forEach(
+      return yield* Effect.forEach(
        [
          ...automatic.map((target): ConfigPluginSource.Operation => ({ type: "add", target, options: {} })),
          ...configured,
@@ -70,6 +76,15 @@ const layer = Layer.effect(
          )
        },
      )
+    })
+
+    const discover = Effect.fn("ProjectMarkers.discover")(function* (
+      directory: AbsolutePath,
+      options?: { readonly discovery?: boolean },
+    ) {
+      // discovery: false skips the config scan and its plugin module loading;
+      // sdk-declared vcs markers are host-explicit, not ambient, so they stay.
+      const operations = options?.discovery === false ? [] : yield* scanOperations(directory)
      const declarations = new Map<string, { readonly id: string; readonly markers: readonly string[] }>()

      for (const plugin of sdk.all()) {
@@ -1,14 +1,15 @@
 import { createRequire } from "node:module"
 import { isSea } from "node:sea"
+import type { spawn } from "@lydell/node-pty"
 import type { Opts, Proc } from "./pty.js"

 export type { Disp, Exit, Opts, Proc } from "./pty.js"

-const pty = createRequire(import.meta.url)(
-  process.env.OPENCODE_NODE_PTY_PATH ?? "@lydell/node-pty",
-) as typeof import("@lydell/node-pty")
+const pty = createRequire(import.meta.url)(process.env.OPENCODE_NODE_PTY_PATH ?? "@lydell/node-pty") as {
+  spawn: typeof spawn
+}

-export function spawn(file: string, args: string[], opts: Opts): Proc {
+function spawnPty(file: string, args: string[], opts: Opts): Proc {
  const proc = pty.spawn(file, args, process.platform === "win32" && isSea() ? { ...opts, useConptyDll: true } : opts)
  return {
    pid: proc.pid,
@@ -29,3 +30,5 @@ export function spawn(file: string, args: string[], opts: Opts): Proc {
    },
  }
 }
+
+export { spawnPty as spawn }
@@ -1,6 +1,6 @@
 import path from "path"
 import { Context, Effect, Layer, Stream } from "effect"
-import { FetchHttpClient, HttpClient, HttpClientRequest } from "effect/unstable/http"
+import { HttpClient, HttpClientRequest } from "effect/unstable/http"
 import { ChildProcess } from "effect/unstable/process"
 import { ChildProcessSpawner } from "effect/unstable/process/ChildProcessSpawner"
 import { CrossSpawnSpawner } from "@opencode-ai/util/cross-spawn-spawner"
@@ -41,7 +41,7 @@ export type DeepMutable<T> = T extends string | number | boolean | bigint | symb

 /**
 * Nominal wrapper for scalar types. The class itself is a valid schema —
- * pass it directly to `Schema.decode`, `Schema.decodeEffect`, etc.
+ * pass it directly to `Schema.decodeUnknownSync`, `Schema.decodeEffect`, etc.
 *
 * The runtime value remains an unwrapped primitive. `Schema.brand` supplies
 * the primitive schema behavior and constructor validation, while the class
@@ -98,6 +98,7 @@ type CreateBaseInput = {
  title?: string
  agent?: Agent.ID
  model?: Model.Ref
+  metadata?: SessionSchema.Metadata
 }
 type CreateInput = CreateBaseInput &
  ({ location: Location.Ref; parentID?: never } | { parentID: SessionSchema.ID; location?: never })
@@ -409,6 +410,9 @@ const layer = Layer.effect(
              subpath: RelativePath.make(path.relative(project.directory, location.directory).replaceAll("\\", "/")),
              title: input.title,
              agent: input.agent,
+              // Children inherit metadata the way they inherit location, so
+              // host policies that read it treat the family uniformly.
+              metadata: input.metadata ?? parent?.metadata,
              model: input.model
                ? {
                    id: Model.ID.make(input.model.id),
@@ -1209,7 +1213,7 @@ const SHELL_MAX_CAPTURE_BYTES = 1024 * 1024

 export const node = makeGlobalNode({
  service: Service,
-  layer: layer.pipe(Layer.orDie),
+  layer,
  deps: [
    Job.node,
    SessionEnvironment.node,
@@ -215,7 +215,7 @@ const select = (
 export const buildPrompt = (input: { readonly previousSummary?: string; readonly context: readonly string[] }) =>
  [
    input.previousSummary
-      ? `Update the anchored summary below using the conversation history above.\nPreserve still-true details, remove stale details, and merge in the new facts.\n<previous-summary>\n${input.previousSummary}\n</previous-summary>`
+      ? `Update the anchored summary below using the conversation history below.\nPreserve still-true details, remove stale details, and merge in the new facts.\n<previous-summary>\n${input.previousSummary}\n</previous-summary>`
      : "Create a new anchored summary from the conversation history.",
    SUMMARY_TEMPLATE,
    "The following is the conversation history:",
@@ -98,6 +98,7 @@ export const layer = (options?: Options) =>
      const recoverShell = Effect.fnUntraced(function* (
        background: Job.Background,
        recovery: Extract<Job.Recovery, { kind: "shell" }>,
+        suspended: ReadonlySet<SessionSchema.ID>,
      ) {
        const state = background.status === "running" ? "cancelled" : background.status
        const text =
@@ -121,7 +122,7 @@ export const layer = (options?: Options) =>
              shellID: recovery.shellID,
              state,
            },
-            resume: false,
+            ...(suspended.has(recovery.sessionID) ? { resume: false } : {}),
          })
          .pipe(
            Effect.catchTag("Session.NotFoundError", () => Effect.void),
@@ -211,23 +212,25 @@ export const layer = (options?: Options) =>
      return Service.of({
        resumeSuspendedSessions: Effect.gen(function* () {
          const active = yield* execution.active
-          // Early notices wait for root recovery's accounting, including roots that exhaust their budget.
-          const suspended = new Set((yield* store.listSuspended()).filter((sessionID) => !active.has(sessionID)))
          const pending = yield* jobs.pendingBackground
-          yield* store.releaseChildClaims(
-            pending.flatMap((background) =>
-              background.status === "running" && background.recovery.kind === "subagent"
-                ? [background.recovery.childSessionID]
-                : [],
-            ),
+          const children = pending.flatMap((background) =>
+            background.status === "running" && background.recovery.kind === "subagent"
+              ? [background.recovery.childSessionID]
+              : [],
          )
+          // Early notices wait for recovery's accounting, including Sessions that exhaust their budget.
+          const suspended = new Set(
+            [...(yield* store.listSuspended()), ...children].filter((sessionID) => !active.has(sessionID)),
+          )
+          yield* store.releaseChildClaims(children)
          yield* Effect.forEach(
-            pending,
+            // Admit shell outcomes before a recovered child can start its first model request.
+            pending.toSorted((a, b) => Number(a.recovery.kind === "subagent") - Number(b.recovery.kind === "subagent")),
            Effect.fnUntraced(function* (background) {
              if ((yield* jobs.get(background.id))?.status === "running") return
              const recovery = background.recovery
              yield* recovery.kind === "shell"
-                ? recoverShell(background, recovery)
+                ? recoverShell(background, recovery, suspended)
                : recoverSubagent(background, recovery, suspended)
            }),
            { discard: true },
@@ -49,6 +49,7 @@ export function fromRow(row: typeof SessionTable.$inferSelect): SessionSchema.In
      workspaceID: row.workspace_id ? Workspace.ID.make(row.workspace_id) : undefined,
    }),
    subpath: row.path ? RelativePath.make(row.path) : undefined,
+    metadata: row.metadata ?? undefined,
    revert: row.revert ? decodeRevert(row.revert) : undefined,
    outcome: row.idle_outcome ?? undefined,
    time: {
@@ -202,7 +202,7 @@ export const preview = Effect.fn("InstructionState.preview")(function* (
    update: Instructions.renderUpdate(
      instructions,
      dereference(state.current_values, stored),
-      dereferenceDelta(result.delta, new Map([...stored, ...observedBlobs])),
+      dereferenceDelta(result.delta, observedBlobs),
    ),
  }
 })
@@ -41,7 +41,6 @@ interface Channel {
  readonly openedAt: number
  active?: Active
  closing: boolean
-  poisoned: boolean
  checkpoint?: ChannelCheckpoint
  pending?: { readonly token: object; readonly checkpoint: ChannelCheckpoint }
  reader?: Fiber.Fiber<unknown, unknown>
@@ -150,7 +149,6 @@ export const makeLayer = (connector: WebSocketConnector) =>
        channel: Channel,
        error: AIError,
      ) {
-        channel.poisoned = true
        if (owner.channel === channel) owner.channel = undefined
        if (channel.closing) return
        channel.closing = true
@@ -187,7 +185,6 @@ export const makeLayer = (connector: WebSocketConnector) =>
              connection,
              openedAt: yield* Clock.currentTimeMillis,
              closing: false,
-              poisoned: false,
            }
            owner.channel = channel
            channel.reader = yield* connection.messages.pipe(
@@ -274,13 +271,11 @@ export const makeLayer = (connector: WebSocketConnector) =>
        const current = owner.channel
        const rotateAfterMs = exchange.connect.rotateAfterMs ?? ROTATE_AFTER_MS
        const rotation = current
-          ? current.poisoned
-            ? "poisoned"
-            : current.affinity !== key
-              ? "affinity"
-              : now - current.openedAt >= rotateAfterMs
-                ? "age"
-                : undefined
+          ? current.affinity !== key
+            ? "affinity"
+            : now - current.openedAt >= rotateAfterMs
+              ? "age"
+              : undefined
          : undefined
        if (current && rotation) {
          yield* Effect.logDebug("session websocket rotating", {
@@ -361,7 +356,6 @@ export const makeLayer = (connector: WebSocketConnector) =>

        let terminal: ChannelObservation | undefined
        const token = {}
-        let staged: ChannelCheckpoint | undefined
        const frames = Stream.fromQueue(active.queue).pipe(
          Stream.timeoutOrElse({
            duration: IDLE_TIMEOUT,
@@ -382,7 +376,7 @@ export const makeLayer = (connector: WebSocketConnector) =>
              if (!observationTerminal(observation)) return
              terminal = observation
              lifecycle.delivery = "terminal"
-              staged = observation.type === "completed" ? observation.checkpoint : undefined
+              const staged = observation.type === "completed" ? observation.checkpoint : undefined
              if (staged) channel.pending = { token, checkpoint: staged }
              if (observation.type !== "completed" || !staged) channel.checkpoint = undefined
            }),
@@ -157,6 +157,7 @@ const projectFork = Effect.fn("SessionProjector.projectFork")(function* (
      title: forkTitle(parent.title ?? undefined),
      agent: parent.agent,
      model: parent.model,
+      metadata: parent.metadata,
      version: parent.version,
      cost: 0,
      tokens_input: 0,
@@ -446,6 +447,7 @@ const layer = Layer.effectDiscard(
            title: event.data.title,
            agent: event.data.agent,
            model: event.data.model,
+            metadata: event.data.metadata,
            version: event.data.version,
            time_created: event.created,
            time_updated: event.created,
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Aiden Cline	0b0e24ada7	refactor(ai): use completed response item finals	2026-08-28 15:43:44 -05:00
Aiden Cline	1a1aa97235	refactor(ai): simplify response finalization flow	2026-08-28 01:01:30 -05:00
Aiden Cline	b1f29c83f8	fix(ai): respect response text and reasoning finals	2026-08-28 00:51:54 -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
Kit Langton	a065ad4ba7	feat(core): vanilla instance discovery option (#45752 )	2026-08-28 03:16:29 +00:00
Kit Langton	048aec32e7	refactor(core): share local provider settings fold (#45645 )	2026-08-27 23:13:13 -04:00
Kit Langton	a258b17fac	test(core): use partial service mocks (#45703 )	2026-08-27 23:13:04 -04:00
Kit Langton	07facd2086	refactor(util): share process stop policy (#45725 )	2026-08-27 23:12:57 -04:00
Kit Langton	6bf342a861	refactor(core): consolidate HTML inline handling (#45649 )	2026-08-27 23:12:50 -04:00
Kit Langton	2cca1ae860	refactor(core): use nonthrowing URL parsing (#45726 )	2026-08-27 23:12:43 -04:00
Kit Langton	becf5bf482	refactor(core): retain changed worktrees directly (#45709 )	2026-08-27 23:12:36 -04:00
Kit Langton	afe9e579d6	refactor(core): simplify instruction preview blobs (#45702 )	2026-08-27 23:12:28 -04:00
Kit Langton	0b82fe60ea	refactor(core): consolidate model error mapping (#45722 )	2026-08-27 23:12:19 -04:00
Luke Parker	6fad330efc	chore(deps): upgrade Solid and Router (#45808 )	2026-08-28 03:03:08 +00:00
Kit Langton	87f21a301d	fix(core): forward plugin interrupt options (#45632 )	2026-08-27 23:01:57 -04:00
Kit Langton	0123fed65d	fix(core): preserve Responses tool strictness (#45663 )	2026-08-27 23:01:43 -04:00
Kit Langton	64ef85159d	fix(core): preserve assistant text metadata (#45650 )	2026-08-27 23:01:33 -04:00
Kit Langton	e63779d9e1	fix(core): keep vertex settings serializable (#45704 )	2026-08-27 23:01:20 -04:00
Kit Langton	ac55c05c30	fix(core): correct compaction history direction (#45698 )	2026-08-27 23:01:07 -04:00
Dax Raad	8fa672ed71	docs: document diagnostic profile signals	2026-08-27 22:53:28 -04:00
Kit Langton	d84d1421ae	test(core): bind acquired test services (#45711 )	2026-08-27 22:43:09 -04:00
Kit Langton	dd2674e9c4	refactor(core): reuse Mercurial diff preparation (#45652 )	2026-08-27 22:42:47 -04:00
Kit Langton	ade8175ad8	refactor(core): use environment driver namespace (#45707 )	2026-08-27 22:42:36 -04:00
Kit Langton	b0db52da6f	refactor(tui): remove inert diff viewer setup (#45687 )	2026-08-27 22:42:29 -04:00
Kit Langton	9d673d7fb3	docs(core): align built-in prompt guidance (#45642 )	2026-08-27 22:42:19 -04:00
Kit Langton	9cab8b45b2	refactor(core): remove unreachable transport state (#45628 )	2026-08-27 22:42:11 -04:00
Kit Langton	17aa942541	refactor(core): reuse tool name normalization (#45644 )	2026-08-27 22:42:00 -04:00
Kit Langton	cbc3e63869	refactor(core): simplify skill discovery validation (#45729 )	2026-08-27 22:41:51 -04:00
Kit Langton	2ce126e2df	test(core): simplify runner scenario fixtures (#45440 )	2026-08-27 22:37:07 -04:00
Aiden Cline	1faba03cfe	fix(core): normalize Windows tool paths (#45806 )	2026-08-27 21:36:22 -05:00
Kit Langton	09b0edd662	refactor(core): compare plugin generations directly (#45728 )	2026-08-27 22:31:42 -04:00
Kit Langton	0c75b7b3c7	feat(core): per-instance plugin input (#45732 )	2026-08-28 02:31:36 +00:00
Kit Langton	fd77a721ac	test(core): align session test vocabulary (#45670 )	2026-08-27 22:31:33 -04:00
Kit Langton	11aab207f0	test(core): remove dead test setup (#45669 )	2026-08-27 22:31:26 -04:00
Kit Langton	04c9e01dad	refactor: normalize filesystem boundary imports (#45730 )	2026-08-27 22:31:15 -04:00
Kit Langton	762291b2a8	feat(core): durable session metadata at creation (#45805 )	2026-08-28 02:30:55 +00:00
Kit Langton	e0bad10065	test(core): exercise fsutil passthroughs (#45667 )	2026-08-27 22:30:43 -04:00
Kit Langton	e6d656dec1	refactor(core): clarify PTY binary validation (#45715 )	2026-08-27 22:30:35 -04:00
Kit Langton	d34dd6c14a	refactor(core): type native PTY import explicitly (#45710 )	2026-08-27 22:30:15 -04:00
Kit Langton	43c8690c14	docs(core): correct newtype decoding guidance (#45736 )	2026-08-27 22:30:07 -04:00
Kit Langton	35d681afab	test(core): make test sentinels effective (#45706 )	2026-08-27 22:29:59 -04:00
Kit Langton	8ab08f7fc9	refactor(core): remove infallible layer conversion (#45672 )	2026-08-27 22:29:44 -04:00
Luke Parker	c5113ee74a	chore(desktop): trim external dependency archives (#45804 )	2026-08-28 02:24:46 +00:00
Kit Langton	88988b8c12	fix(core): preserve typed config test-layer errors (#45778 )	2026-08-27 22:13:34 -04:00
opencode-agent[bot]	2389111bf6	chore: update nix node_modules hashes	2026-08-28 02:08:36 +00:00
Luke Parker	b92b84f33d	chore(deps): refresh markdown dependencies (#45793 )	2026-08-28 01:45:46 +00:00
opencode-agent[bot]	078522e534	chore: update nix node_modules hashes	2026-08-28 01:28:15 +00:00
Aiden Cline	7111e71528	fix(core): treat project paths as internal (#45799 )	2026-08-27 20:26:25 -05:00
Luke Parker	0ce3214844	chore(deps): upgrade Sentry and verify reporting (#45796 )	2026-08-28 01:13:17 +00:00
Luke Parker	132ec56fda	chore(ui): refresh Kobalte and Solid primitives (#45794 )	2026-08-28 01:08:44 +00:00
opencode-agent[bot]	216af25ecc	chore: update nix node_modules hashes	2026-08-28 01:00:46 +00:00
Luke Parker	6881cffc41	chore(deps): refresh Vite and Electron Builder tooling (#45790 )	2026-08-28 00:46:32 +00:00
opencode-agent[bot]	aecea54e95	chore: update nix node_modules hashes	2026-08-28 00:37:45 +00:00
Luke Parker	c0fa9aff72	fix(app): render local Markdown images through the server (#45780 )	2026-08-28 00:30:00 +00:00
opencode-agent[bot]andrekram1-node	d5be4cf888	fix(core): share native model defaults with v1 config migration (#45760 ) Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>	2026-08-27 19:25:56 -05:00
Aiden Cline	7b6b0f2717	fix(core): cap provider retry-after delays at fifteen minutes (#45787 )	2026-08-27 19:23:06 -05:00
James Long	a03a1dd854	chore: upgrade opentui to 0.5.9 (#45785 )	2026-08-27 20:20:59 -04:00
Luke Parker	8f350df392	chore(deps): remove unused frontend dependencies (#45779 )	2026-08-28 00:19:57 +00:00
Luke Parker	4cecfe8e79	chore(desktop): remove stale native packaging (#45786 )	2026-08-28 10:18:53 +10:00
Kit Langton	89ca9fc641	fix(core): complete supervisor flush when plugin activation fails (#45783 )	2026-08-28 00:16:25 +00:00
Kit Langton	a2dcf2dff0	fix(core): wake sessions for recovered shell outcomes (#45781 )	2026-08-27 20:11:56 -04:00