feat(examples): add Worker-native Codex harness by mattzcarey · Pull Request #2208 · cloudflare/agents

mattzcarey · 2026-09-03T11:40:50Z

Summary

Adds examples/next/harnesses/codex, a Worker-native Codex harness composed as CodexHarness extends LifecycleCapability on a plain DurableObject. Example only: no package export, no changeset.

A static Codex-derived Rust/Wasm transition kernel runs in the owning isolate. Tasks delivers wakes and journals each model and tool effect with step.do, Streams records the kernel events, and a Shell Workspace holds the files.
The harness accepts an AI SDK LanguageModelV4 directly and runs Kimi K2.7 Code through workers-ai-provider@4, Workers AI, and AI Gateway. Every model-emitted tool call is preserved and settled sequentially before the next round.
The UI is served over the WebSockets capability. The client connects with useAgent from agents/react; a useCodexSession hook replays-then-tails each operation's Streams log, so the transcript and events reload from durable state on reconnect. A "Restart and verify" action aborts the Durable Object and shows the operation and file recovered.
Two RFCs record the target Codex architecture and the v1 model boundary (LanguageModelV4 for Codex, pi-ai for Pi).
OpenAI Codex source provenance and the pinned Apache-2.0 license are retained.

Known gaps

The harness uses the framework-internal Tasks apertures for a capability-owned driver; a public path is still to be designed.
A model step interrupted between completion and journal write is re-issued and the rare duplicate call accepted; the RFC records the policy.
The routes are unauthenticated, as with the other examples.

Run

Rust 1.95 with the wasm32-unknown-unknown target is required locally; pnpm run start builds the kernel first. CI does not build the kernel.

changeset-bot · 2026-09-03T11:40:57Z

⚠️ No Changeset found

Latest commit: dba8aec

Merging this PR will not cause a version bump for any packages. If these changes should not result in a new version, you're good to go. If these changes should result in a version bump, you need to add a changeset.

This PR includes no changesets

When changesets are added to this PR, you'll see the packages that this PR includes changesets for and the associated semver types

Click here to learn what changesets are, and how to add one.

Click here if you're a maintainer who wants to add a changeset to this PR

devin-ai-integration

Note

This report is out of date. Scroll down for Devin Review's latest report on this PR.

Devin Review found 8 potential issues.

4 flags not posted on this PR by your GitHub settings — view them in Devin Review. (Configure)

devin-ai-integration · 2026-09-03T11:43:13Z

+    const existing = this.#effect(operation.operation_id, action.effect_id);
+    if (existing?.status === "completed" && existing.result !== null) {
+      return parseEffectResult(existing.result);
+    }
+    if (!existing) {
+      this.lifecycle.storage.sql.exec(
+        `INSERT INTO cf_codex_effects
+         (operation_id, effect_id, kind, status, request, created_at)
+         VALUES (?, ?, ?, 'pending', ?, ?)`,
+        operation.operation_id,
+        action.effect_id,
+        action.type,
+        JSON.stringify(action),
+        Date.now()
+      );
+    }
+
+    const result =
+      action.type === "model"
+        ? await completeCodexModel(this.model, action)
+        : await performWorkspaceTool(this.workspace, action);


🔴 Interrupted model rounds replay inconsistently

If an attempt stops after transcript.record but before Tasks journals it, retrying can produce a different response. Stored history and replayed results then diverge.

Was this helpful? React with 👍 or 👎 to provide feedback.

devin-ai-integration · 2026-09-03T11:43:21Z

+    const [root, session] = url.pathname.split("/").filter(Boolean);
+    if (root !== "sessions" || session === undefined) {
+      return json({ error: "use /sessions/:session" }, { status: 404 });
+    }
+    return env.Coder.getByName(session).fetch(request);


🟥 Public session routes expose workspaces

Unauthenticated callers can read any named session's files, submit paid model work, cancel turns, and restart its Durable Object.

Was this helpful? React with 👍 or 👎 to provide feedback.

agent-think · 2026-09-03T11:44:16Z

⚪ agents import sizes

Measured 267 runtime imports as minified bundles. The primary size is gzip; raw minified size is included for diagnosis. An existing import growing by more than 10% is marked red. This report is informational.

Red	Yellow	Green	Unchanged	New	Removed
0	0	0	267	0	0

Compared ec93caf6 with dba8aec6. Open workflow run.

No import sizes changed.

All 267 current runtime imports

Status	Import	Gzip	Raw minified
⚪	`agents#__DO_NOT_USE_WILL_BREAK__agentContext`	258.6 KiB	1130.0 KiB
⚪	`agents#__DO_NOT_USE_WILL_BREAK__withInvocationScope`	258.6 KiB	1130.0 KiB
⚪	`agents#Agent`	258.6 KiB	1130.0 KiB
⚪	`agents#AGENT_TOOL_MILESTONE_PART`	258.6 KiB	1130.0 KiB
⚪	`agents#AGENT_TOOL_PROGRESS_PART`	258.6 KiB	1130.0 KiB
⚪	`agents#buildAgentPath`	259.1 KiB	1132.3 KiB
⚪	`agents#buildAgentUrl`	259.3 KiB	1132.7 KiB
⚪	`agents#callable`	258.6 KiB	1130.1 KiB
⚪	`agents#camelCaseToKebabCase`	258.6 KiB	1130.0 KiB
⚪	`agents#createHeaderBasedEmailResolver`	258.8 KiB	1130.4 KiB
⚪	`agents#DEFAULT_AGENT_STATIC_OPTIONS`	258.6 KiB	1130.0 KiB
⚪	`agents#DurableObjectOAuthClientProvider`	258.6 KiB	1130.0 KiB
⚪	`agents#getAgentByName`	258.6 KiB	1130.0 KiB
⚪	`agents#getCurrentAgent`	258.6 KiB	1130.0 KiB
⚪	`agents#getSubAgentByName`	258.9 KiB	1130.7 KiB
⚪	`agents#isDurableObjectCodeUpdateReset`	258.6 KiB	1130.0 KiB
⚪	`agents#isDurableObjectMemoryLimitReset`	258.6 KiB	1130.0 KiB
⚪	`agents#isDurableObjectStorageReset`	258.6 KiB	1130.1 KiB
⚪	`agents#isPlatformTransientError`	258.6 KiB	1130.0 KiB
⚪	`agents#MCP_SERVER_ID_MAX_LENGTH`	258.6 KiB	1130.0 KiB
⚪	`agents#MessageType`	258.8 KiB	1130.3 KiB
⚪	`agents#normalizeServerId`	258.6 KiB	1130.0 KiB
⚪	`agents#parseSubAgentPath`	258.6 KiB	1130.0 KiB
⚪	`agents#routeAgentEmail`	258.9 KiB	1130.7 KiB
⚪	`agents#routeAgentRequest`	259.2 KiB	1131.9 KiB
⚪	`agents#routeSubAgentRequest`	258.8 KiB	1130.6 KiB
⚪	`agents#SqlError`	258.6 KiB	1130.0 KiB
⚪	`agents#StreamingResponse`	258.6 KiB	1130.0 KiB
⚪	`agents#SUB_PREFIX`	258.6 KiB	1130.0 KiB
⚪	`agents#unstable_callable`	258.7 KiB	1130.2 KiB
⚪	`agents/agent-tools#agentTool`	112.5 KiB	538.2 KiB
⚪	`agents/browser#BrowserConnector`	50.5 KiB	176.6 KiB
⚪	`agents/browser#browserContent`	36.3 KiB	127.4 KiB
⚪	`agents/browser#browserExtract`	36.3 KiB	127.4 KiB
⚪	`agents/browser#browserLinks`	36.3 KiB	127.4 KiB
⚪	`agents/browser#browserMarkdown`	36.3 KiB	127.4 KiB
⚪	`agents/browser#browserPdf`	36.3 KiB	127.3 KiB
⚪	`agents/browser#BrowserRenderingError`	36.0 KiB	126.7 KiB
⚪	`agents/browser#browserScrape`	36.3 KiB	127.4 KiB
⚪	`agents/browser#browserScreenshot`	36.3 KiB	127.3 KiB
⚪	`agents/browser#browserSnapshot`	36.3 KiB	127.4 KiB
⚪	`agents/browser#CdpSession`	37.2 KiB	129.8 KiB
⚪	`agents/browser#CodemodeRuntime`	39.6 KiB	139.0 KiB
⚪	`agents/browser#connectBrowser`	37.8 KiB	131.4 KiB
⚪	`agents/browser#connectBrowserSession`	37.5 KiB	130.4 KiB
⚪	`agents/browser#connectUrl`	37.6 KiB	130.5 KiB
⚪	`agents/browser#createBrowserSession`	36.3 KiB	127.5 KiB
⚪	`agents/browser#DEFAULT_EXEC_SWEEP_IDLE_MS`	36.0 KiB	126.6 KiB
⚪	`agents/browser#DEFAULT_SWEEP_IDLE_MS`	36.0 KiB	126.6 KiB
⚪	`agents/browser#deleteBrowserSession`	36.1 KiB	126.9 KiB
⚪	`agents/browser#DurableBrowserSessionStore`	36.4 KiB	127.6 KiB
⚪	`agents/browser#getBrowserRecording`	36.2 KiB	127.1 KiB
⚪	`agents/browser#listBrowserTargets`	36.1 KiB	126.9 KiB
⚪	`agents/browser#loadCdpSpec`	36.6 KiB	128.3 KiB
⚪	`agents/browser#runQuickAction`	36.0 KiB	126.6 KiB
⚪	`agents/browser/ai#createBrowserRuntime`	146.0 KiB	630.3 KiB
⚪	`agents/browser/ai#createBrowserTools`	146.0 KiB	630.3 KiB
⚪	`agents/browser/ai#createQuickActionTools`	122.5 KiB	554.3 KiB
⚪	`agents/browser/tanstack-ai#createBrowserTools`	161.7 KiB	699.2 KiB
⚪	`agents/chat#AbortRegistry`	2.5 KiB	8.9 KiB
⚪	`agents/chat#AGENT_TOOL_STREAM_PROGRESS_BUMP_THROTTLE_MS`	2.3 KiB	8.2 KiB
⚪	`agents/chat#AgentToolProgressEmitter`	2.7 KiB	9.5 KiB
⚪	`agents/chat#AgentToolStreamProgressThrottle`	2.4 KiB	8.3 KiB
⚪	`agents/chat#aiSdkRecoveryCodec`	2.3 KiB	8.2 KiB
⚪	`agents/chat#applyAgentToolEvent`	3.2 KiB	11.0 KiB
⚪	`agents/chat#applyChunkToParts`	2.3 KiB	8.2 KiB
⚪	`agents/chat#applyToolUpdate`	2.4 KiB	8.4 KiB
⚪	`agents/chat#AutoContinuationController`	2.3 KiB	8.2 KiB
⚪	`agents/chat#awaitWithDeadline`	2.4 KiB	8.4 KiB
⚪	`agents/chat#broadcastTransition`	3.1 KiB	11.4 KiB
⚪	`agents/chat#buildChatRecoveringFrame`	2.4 KiB	8.4 KiB
⚪	`agents/chat#buildInClauseStrings`	2.4 KiB	8.4 KiB
⚪	`agents/chat#bumpChatRecoveryProgress`	2.4 KiB	8.3 KiB
⚪	`agents/chat#byteLength`	2.5 KiB	8.5 KiB
⚪	`agents/chat#CHAT_LAST_TERMINAL_KEY`	2.3 KiB	8.2 KiB
⚪	`agents/chat#CHAT_MESSAGE_TYPES`	2.3 KiB	8.2 KiB
⚪	`agents/chat#CHAT_RECOVERING_FLAG_TTL_MS`	2.3 KiB	8.2 KiB
⚪	`agents/chat#CHAT_RECOVERING_KEY`	2.3 KiB	8.2 KiB
⚪	`agents/chat#CHAT_RECOVERY_ALARM_DEBOUNCE_MS`	2.3 KiB	8.2 KiB
⚪	`agents/chat#CHAT_RECOVERY_INCIDENT_KEY_PREFIX`	2.3 KiB	8.2 KiB
⚪	`agents/chat#CHAT_RECOVERY_INCIDENT_TTL_MS`	2.3 KiB	8.2 KiB
⚪	`agents/chat#CHAT_RECOVERY_PROGRESS_KEY`	2.3 KiB	8.2 KiB
⚪	`agents/chat#CHAT_RECOVERY_STABLE_RETRY_DELAY_SECONDS`	2.3 KiB	8.2 KiB
⚪	`agents/chat#CHAT_RECOVERY_TASK_NAME`	2.3 KiB	8.2 KiB
⚪	`agents/chat#CHAT_STREAM_PROGRESS_CREDIT_THROTTLE_MS`	2.3 KiB	8.2 KiB
⚪	`agents/chat#ChatRecoveryEngine`	4.4 KiB	15.3 KiB
⚪	`agents/chat#chatRecoveryTaskRunOptions`	2.4 KiB	8.6 KiB
⚪	`agents/chat#ChatStreamStalledError`	2.4 KiB	8.3 KiB
⚪	`agents/chat#classifyAgentToolChildRecovery`	2.4 KiB	8.5 KiB
⚪	`agents/chat#cleanupStreamBuffers`	2.3 KiB	8.2 KiB
⚪	`agents/chat#clearChatTerminal`	2.3 KiB	8.3 KiB
⚪	`agents/chat#clientResolvableToolNames`	2.3 KiB	8.3 KiB
⚪	`agents/chat#ContinuationState`	2.7 KiB	9.8 KiB
⚪	`agents/chat#createAgentToolEventState`	2.3 KiB	8.3 KiB
⚪	`agents/chat#createChatFiberSnapshot`	2.5 KiB	8.6 KiB
⚪	`agents/chat#createChatRecoveryTaskDefinition`	2.6 KiB	9.0 KiB
⚪	`agents/chat#createChatStreams`	5.5 KiB	19.3 KiB
⚪	`agents/chat#createChatTurnTaskDefinition`	2.7 KiB	8.9 KiB
⚪	`agents/chat#createToolsFromClientSchemas`	114.3 KiB	545.4 KiB
⚪	`agents/chat#crossMessageToolResultUpdate`	2.4 KiB	8.6 KiB
⚪	`agents/chat#DEFAULT_CHAT_RECOVERY_MAX_ATTEMPTS`	2.3 KiB	8.2 KiB
⚪	`agents/chat#DEFAULT_CHAT_RECOVERY_MAX_OOM_RETRIES`	2.3 KiB	8.2 KiB
⚪	`agents/chat#DEFAULT_CHAT_RECOVERY_MAX_WORK`	2.3 KiB	8.2 KiB
⚪	`agents/chat#DEFAULT_CHAT_RECOVERY_NO_PROGRESS_TIMEOUT_MS`	2.3 KiB	8.2 KiB
⚪	`agents/chat#DEFAULT_CHAT_RECOVERY_STABLE_TIMEOUT_MS`	2.3 KiB	8.2 KiB
⚪	`agents/chat#DEFAULT_CHAT_RECOVERY_TERMINAL_MESSAGE`	2.4 KiB	8.3 KiB
⚪	`agents/chat#dispatchChatRecoveryToHandoff`	3.0 KiB	9.9 KiB
⚪	`agents/chat#drainInteractionApplies`	2.3 KiB	8.3 KiB
⚪	`agents/chat#enforceRowSizeLimit`	3.5 KiB	11.2 KiB
⚪	`agents/chat#hasIncompleteToolBatch`	2.4 KiB	8.6 KiB
⚪	`agents/chat#interceptAgentToolBroadcast`	2.5 KiB	8.7 KiB
⚪	`agents/chat#isPlatformFailure`	2.6 KiB	8.9 KiB
⚪	`agents/chat#isReplayChunk`	2.4 KiB	8.7 KiB
⚪	`agents/chat#iterateWithStallWatchdog`	2.6 KiB	8.8 KiB
⚪	`agents/chat#KV_DELETE_MAX_KEYS`	2.3 KiB	8.2 KiB
⚪	`agents/chat#listActiveChatRecoveryIncidents`	2.4 KiB	8.4 KiB
⚪	`agents/chat#MAX_BOUND_PARAMS`	2.3 KiB	8.2 KiB
⚪	`agents/chat#MessageType`	2.4 KiB	9.0 KiB
⚪	`agents/chat#normalizeToolInput`	2.3 KiB	8.2 KiB
⚪	`agents/chat#parseProtocolMessage`	2.5 KiB	9.0 KiB
⚪	`agents/chat#partAwaitsClientInteraction`	2.4 KiB	8.6 KiB
⚪	`agents/chat#pausedExecutionUpdate`	2.4 KiB	8.4 KiB
⚪	`agents/chat#pendingChatTerminal`	2.3 KiB	8.3 KiB
⚪	`agents/chat#persistReconstructedOrphan`	3.1 KiB	11.0 KiB
⚪	`agents/chat#PreStreamTurns`	2.6 KiB	9.3 KiB
⚪	`agents/chat#readChatRecoveryProgress`	2.3 KiB	8.3 KiB
⚪	`agents/chat#reconcileMessages`	2.8 KiB	9.6 KiB
⚪	`agents/chat#reconcileOrphanPartial`	2.4 KiB	8.5 KiB
⚪	`agents/chat#recordChatTerminal`	2.4 KiB	8.3 KiB
⚪	`agents/chat#repairInterruptedToolParts`	2.6 KiB	9.1 KiB
⚪	`agents/chat#resolveChatRecoveryConfig`	2.6 KiB	8.9 KiB
⚪	`agents/chat#resolveToolMergeId`	2.4 KiB	8.5 KiB
⚪	`agents/chat#ResumableStream`	4.6 KiB	15.3 KiB
⚪	`agents/chat#ResumeHandshake`	3.0 KiB	10.4 KiB
⚪	`agents/chat#ROW_MAX_BYTES`	2.3 KiB	8.2 KiB
⚪	`agents/chat#runChatRecoveryExhaustion`	2.6 KiB	8.9 KiB
⚪	`agents/chat#sanitizeMessage`	2.5 KiB	8.8 KiB
⚪	`agents/chat#sendIfOpen`	2.4 KiB	8.4 KiB
⚪	`agents/chat#setChatRecovering`	2.5 KiB	8.5 KiB
⚪	`agents/chat#shouldCreditStreamProgress`	2.4 KiB	8.3 KiB
⚪	`agents/chat#STREAM_CLEANUP_DELAY_SECONDS`	2.3 KiB	8.2 KiB
⚪	`agents/chat#STREAM_RESUME_NONE_REASONS`	2.3 KiB	8.3 KiB
⚪	`agents/chat#StreamAccumulator`	2.9 KiB	10.7 KiB
⚪	`agents/chat#StreamProgressCreditThrottle`	2.4 KiB	8.3 KiB
⚪	`agents/chat#SubmitConcurrencyController`	2.9 KiB	10.3 KiB
⚪	`agents/chat#sweepStaleChatRecoveryIncidents`	2.4 KiB	8.5 KiB
⚪	`agents/chat#TextSegmentJoiner`	2.7 KiB	9.2 KiB
⚪	`agents/chat#TIMED_OUT`	2.3 KiB	8.2 KiB
⚪	`agents/chat#toolApprovalUpdate`	2.4 KiB	8.5 KiB
⚪	`agents/chat#toolPartHasSettledResult`	2.3 KiB	8.4 KiB
⚪	`agents/chat#toolResultUpdate`	2.4 KiB	8.5 KiB
⚪	`agents/chat#truncateOlderMessages`	3.2 KiB	10.4 KiB
⚪	`agents/chat#TurnQueue`	2.6 KiB	9.2 KiB
⚪	`agents/chat#unwrapChatFiberSnapshot`	2.4 KiB	8.5 KiB
⚪	`agents/chat#wrapChatFiberSnapshot`	2.3 KiB	8.2 KiB
⚪	`agents/chat-sdk#ChatSdkStateAdapter`	261.0 KiB	1141.6 KiB
⚪	`agents/chat-sdk#ChatSdkStateAgent`	260.4 KiB	1139.1 KiB
⚪	`agents/chat-sdk#createChatSdkState`	261.0 KiB	1141.6 KiB
⚪	`agents/chat-sdk#defaultKeyShard`	258.8 KiB	1130.2 KiB
⚪	`agents/chat-sdk#defaultThreadShard`	258.7 KiB	1130.1 KiB
⚪	`agents/chat/react#detectToolsRequiringConfirmation`	3.3 KiB	8.3 KiB
⚪	`agents/chat/react#extractClientToolSchemas`	3.2 KiB	8.3 KiB
⚪	`agents/chat/react#getAgentMessages`	3.4 KiB	8.6 KiB
⚪	`agents/chat/react#getToolApproval`	3.1 KiB	8.0 KiB
⚪	`agents/chat/react#getToolCallId`	3.1 KiB	8.0 KiB
⚪	`agents/chat/react#getToolInput`	3.1 KiB	8.0 KiB
⚪	`agents/chat/react#getToolOutput`	3.1 KiB	8.0 KiB
⚪	`agents/chat/react#getToolPartState`	3.2 KiB	8.2 KiB
⚪	`agents/chat/react#useAgentChat`	132.9 KiB	609.7 KiB
⚪	`agents/chat/react#WebSocketChatTransport`	5.7 KiB	17.1 KiB
⚪	`agents/chat/transport#WebSocketChatTransport`	2.8 KiB	9.2 KiB
⚪	`agents/client#AgentClient`	5.7 KiB	16.6 KiB
⚪	`agents/client#AgentConnectionError`	582 B	993 B
⚪	`agents/client#agentFetch`	4.2 KiB	12.3 KiB
⚪	`agents/client#createStubProxy`	638 B	1.0 KiB
⚪	`agents/client#DEFAULT_CALL_TIMEOUT_MS`	473 B	770 B
⚪	`agents/client#isTerminalCloseEvent`	509 B	822 B
⚪	`agents/context#AgentContextProvider`	412 B	792 B
⚪	`agents/context#AgentSearchProvider`	640 B	1.3 KiB
⚪	`agents/context#ContextBlocks`	87.4 KiB	429.7 KiB
⚪	`agents/email#createAddressBasedEmailResolver`	193 B	227 B
⚪	`agents/email#createCatchAllEmailResolver`	110 B	97 B
⚪	`agents/email#createHeaderBasedEmailResolver`	334 B	492 B
⚪	`agents/email#createSecureReplyEmailResolver`	718 B	1.3 KiB
⚪	`agents/email#DEFAULT_MAX_AGE_SECONDS`	56 B	39 B
⚪	`agents/email#isAutoReplyEmail`	201 B	249 B
⚪	`agents/email#signAgentHeaders`	424 B	812 B
⚪	`agents/experimental/webmcp#registerWebMcp`	85.2 KiB	295.8 KiB
⚪	`agents/lifecycle#getCurrentAgent`	376 B	798 B
⚪	`agents/lifecycle#Lifecycle`	8.3 KiB	25.8 KiB
⚪	`agents/lifecycle#LifecycleCapability`	484 B	975 B
⚪	`agents/mcp#createLegacyMcpHandler`	375.9 KiB	1572.2 KiB
⚪	`agents/mcp#createMcpHandler`	388.2 KiB	1617.4 KiB
⚪	`agents/mcp#DurableObjectEventStore`	342.5 KiB	1430.7 KiB
⚪	`agents/mcp#ElicitRequestSchema`	342.5 KiB	1430.7 KiB
⚪	`agents/mcp#experimental_createMcpHandler`	376.1 KiB	1572.5 KiB
⚪	`agents/mcp#getMcpAuthContext`	342.5 KiB	1430.8 KiB
⚪	`agents/mcp#MCP_SERVER_ID_MAX_LENGTH`	342.5 KiB	1430.7 KiB
⚪	`agents/mcp#McpAgent`	342.5 KiB	1430.7 KiB
⚪	`agents/mcp#normalizeServerId`	342.5 KiB	1430.7 KiB
⚪	`agents/mcp#RPC_DO_PREFIX`	342.5 KiB	1430.7 KiB
⚪	`agents/mcp#RPCClientTransport`	342.5 KiB	1430.7 KiB
⚪	`agents/mcp#RPCServerTransport`	342.5 KiB	1430.7 KiB
⚪	`agents/mcp#SSEEdgeClientTransport`	342.6 KiB	1431.0 KiB
⚪	`agents/mcp#StreamableHTTPEdgeClientTransport`	342.6 KiB	1431.0 KiB
⚪	`agents/mcp#WorkerTransport`	345.8 KiB	1447.6 KiB
⚪	`agents/mcp/client#getNamespacedData`	62.9 KiB	240.0 KiB
⚪	`agents/mcp/client#MCP_SERVER_ID_MAX_LENGTH`	62.9 KiB	239.9 KiB
⚪	`agents/mcp/client#MCPClientManager`	158.6 KiB	702.6 KiB
⚪	`agents/mcp/client#normalizeServerId`	63.0 KiB	240.2 KiB
⚪	`agents/mcp/do-oauth-client-provider#DurableObjectOAuthClientProvider`	2.1 KiB	6.6 KiB
⚪	`agents/mcp/server#createMcpHandler`	80.5 KiB	307.2 KiB
⚪	`agents/mcp/server#getMcpAuthContext`	64.0 KiB	245.5 KiB
⚪	`agents/observability#channels`	259 B	549 B
⚪	`agents/observability#genericObservability`	470 B	1.2 KiB
⚪	`agents/observability#subscribe`	324 B	668 B
⚪	`agents/observability/ai#wrapAISDK`	8.8 KiB	30.5 KiB
⚪	`agents/react#_testUtils`	3.8 KiB	9.5 KiB
⚪	`agents/react#useAgent`	10.8 KiB	31.1 KiB
⚪	`agents/react#useAgentToolEvents`	5.6 KiB	16.8 KiB
⚪	`agents/routing#getAgentByName`	795 B	1.7 KiB
⚪	`agents/routing#routeAgentRequest`	1.6 KiB	3.6 KiB
⚪	`agents/routing#RoutedAgents`	2.4 KiB	6.2 KiB
⚪	`agents/schedule#getSchedulePrompt`	85.8 KiB	424.7 KiB
⚪	`agents/schedule#scheduleSchema`	85.3 KiB	423.6 KiB
⚪	`agents/schedule#unstable_getSchedulePrompt`	85.9 KiB	424.9 KiB
⚪	`agents/schedule#unstable_scheduleSchema`	85.3 KiB	423.6 KiB
⚪	`agents/schedules#Scheduler`	6.8 KiB	22.0 KiB
⚪	`agents/schedules/parser#getSchedulePrompt`	85.8 KiB	424.7 KiB
⚪	`agents/schedules/parser#scheduleSchema`	85.3 KiB	423.6 KiB
⚪	`agents/sessions#createCompactFunction`	1.7 KiB	4.0 KiB
⚪	`agents/sessions#Session`	1.9 KiB	5.4 KiB
⚪	`agents/sessions#Sessions`	8.8 KiB	31.2 KiB
⚪	`agents/skills#fromManifest`	309.8 KiB	1084.0 KiB
⚪	`agents/skills#parseSkillFrontmatter`	328.4 KiB	1146.2 KiB
⚪	`agents/skills#parseSkillMarkdown`	328.6 KiB	1146.5 KiB
⚪	`agents/skills#r2`	330.2 KiB	1150.4 KiB
⚪	`agents/skills#runner`	369.0 KiB	1297.8 KiB
⚪	`agents/skills#SkillRegistry`	416.4 KiB	1581.7 KiB
⚪	`agents/skills/compile#compileSkillScript`	15.4 KiB	43.4 KiB
⚪	`agents/skills/compile#isCompilableSkillScript`	15.4 KiB	43.3 KiB
⚪	`agents/streams#DEFAULT_MAX_CHUNK_BYTES`	83 B	81 B
⚪	`agents/streams#sseResponse`	843 B	1.6 KiB
⚪	`agents/streams#StreamClosedError`	161 B	197 B
⚪	`agents/streams#StreamNotFoundError`	201 B	261 B
⚪	`agents/streams#Streams`	3.4 KiB	11.1 KiB
⚪	`agents/streams#StreamSerializationError`	158 B	186 B
⚪	`agents/tasks#DuplicateTaskStepError`	328 B	463 B
⚪	`agents/tasks#MAX_SERIALIZED_BYTES`	190 B	232 B
⚪	`agents/tasks#MissingTaskDefinitionError`	358 B	536 B
⚪	`agents/tasks#NonRetryableError`	238 B	308 B
⚪	`agents/tasks#TaskReplayDivergedError`	341 B	483 B
⚪	`agents/tasks#Tasks`	8.9 KiB	31.8 KiB
⚪	`agents/tasks#TaskSerializationError`	258 B	339 B
⚪	`agents/types#MessageType`	211 B	365 B
⚪	`agents/vite#default`	353.8 KiB	1356.1 KiB
⚪	`agents/websockets#CALLABLES_RPC_QUERY`	12.4 KiB	43.3 KiB
⚪	`agents/websockets#CALLABLES_RPC_VALUE`	12.4 KiB	43.3 KiB
⚪	`agents/websockets#callablesFromDecorated`	12.7 KiB	44.3 KiB
⚪	`agents/websockets#callablesRpcUrl`	12.5 KiB	43.5 KiB
⚪	`agents/websockets#isCallablesRpcUpgrade`	12.4 KiB	43.4 KiB
⚪	`agents/websockets#WebSockets`	17.7 KiB	62.2 KiB
⚪	`agents/workflows#AgentWorkflow`	260.0 KiB	1134.8 KiB
⚪	`agents/workflows#WorkflowRejectedError`	258.7 KiB	1130.2 KiB
⚪	`agents/x402#normalizeNetwork`	14.7 KiB	61.1 KiB
⚪	`agents/x402#withX402`	23.0 KiB	89.2 KiB
⚪	`agents/x402#withX402Client`	104.1 KiB	346.5 KiB

Reported by agent-think[bot].

The example is the demo: remove smoke.mjs, the node:test adapter suite and its tsx tsconfig, the /health, results and abort routes, and the "static-wasm" mode/metadata leftovers. Remove the nx `build` script so CI does not need a Rust toolchain; `start` and `deploy` still build the kernel. Fix recovery after a Durable Object restart: a stored terminal action now settles the operation instead of failing it, a replayed terminal operation closes its stream, and an identical resubmit of a still-queued operation re-syncs its Tasks wake. Join text blocks before trimming so boundary whitespace survives, and stop gating UI completion on the demo file. Trim deployment URLs and smoke timing tables from the RFCs. Claude-Session: https://claude.ai/code/session_01KEFnjoMnZBMewsuD9qxGrL

Drop the harness's own cf_codex_effects table and run each model or Workspace effect as a named Tasks step keyed by its effect ID. Tasks replays settled results on later attempts and hands the step's AbortSignal to the model call, so cancellation reaches in-flight work. Document the interrupted step policy in the RFC: tools re-run idempotently, model rounds re-issue and accept a rare duplicate call. Claude-Session: https://claude.ai/code/session_01KEFnjoMnZBMewsuD9qxGrL

devin-ai-integration

Note

This report is out of date. Scroll down for Devin Review's latest report on this PR.

Devin Review found 2 new potential issues.

4 flags not posted on this PR by your GitHub settings — view them in Devin Review. (Configure)

devin-ai-integration · 2026-09-03T13:11:10Z

+    if (operation.status === "completed" || operation.status === "failed") {
+      // Replayed after settling: make sure the stream is closed and finish.
+      await this.#flushEvents(operation, true);
+      return projectTaskResult(operation);


🟡 Terminal recovery reopens closed streams

A restart after stream settlement makes replay call #flushEvents on a closed stream. Streams.open() throws, so the task cannot finish recovery.

Was this helpful? React with 👍 or 👎 to provide feedback.

Replace the HTTP polling routes with a WebSocket protocol on the WebSockets capability: a session snapshot on connect, subscribe to replay-then-tail an operation's Streams log, and submit and restart commands. Operation state changes broadcast to every connection. The client connects with useAgent from agents/react and a small useCodexSession hook layers the protocol on that socket, so the whole transcript and every operation's events reload from durable state on reconnect. The worker routes with routeAgentRequest. Claude-Session: https://claude.ai/code/session_01KEFnjoMnZBMewsuD9qxGrL

devin-ai-integration

Note

This report is out of date. Scroll down for Devin Review's latest report on this PR.

Devin Review found 4 new potential issues.

4 flags not posted on this PR by your GitHub settings — view them in Devin Review. (Configure)

devin-ai-integration · 2026-09-03T13:19:30Z

+    if (block.type === "text") continue;
+    if (!block.complete) continue;
+    frames.push({
+      type: "response.output_item.done",
+      item: {
+        type: "function_call",
+        call_id: block.id,
+        name: block.name,
+        arguments: block.input
+      }
+    });
+  }
+  if (text.length > 0) {
+    frames.push(
+      { type: "response.output_text.delta", delta: text },
+      {
+        type: "response.output_item.done",
+        item: {
+          type: "message",
+          role: "assistant",
+          content: [{ type: "output_text", text }]
+        }
+      }
+    );
+  }


🟡 Model content order is reversed

blocksToFrames moves every text block behind all tool calls. Responses with interleaved text and tools enter the next model round in a different order.

Was this helpful? React with 👍 or 👎 to provide feedback.

devin-ai-integration · 2026-09-03T13:19:32Z

+function isClientMessage(value: unknown): value is CodexClientMessage {
+  return (
+    typeof value === "object" &&
+    value !== null &&
+    "type" in value &&
+    typeof value.type === "string"
+  );
+}


🟨 WebSocket payloads lack validation

isClientMessage validates only the discriminator. Oversized prompts and malformed identifiers reach storage and model execution, enabling resource exhaustion and unexpected failures.

Was this helpful? React with 👍 or 👎 to provide feedback.

devin-ai-integration · 2026-09-03T13:19:33Z

+  const path = action.arguments.path;
+  if (typeof path !== "string") {
+    return { type: "error", message: `${action.name} requires a path` };
+  }
+  if (action.name === "workspace_write") {
+    const content = action.arguments.content;
+    if (typeof content !== "string") {
+      return { type: "error", message: "workspace_write requires content" };
+    }
+    await workspace.writeFile(path, content);


🟨 Workspace tools lack path confinement

Model-provided paths reach readFile and writeFile without a permitted-root check. Adversarial prompts can access any path exposed by the workspace.

Was this helpful? React with 👍 or 👎 to provide feedback.

pkg-pr-new · 2026-09-03T13:28:00Z

Open in StackBlitz

agents

npm i https://pkg.pr.new/agents@2208

@cloudflare/ai-chat

npm i https://pkg.pr.new/@cloudflare/ai-chat@2208

@cloudflare/codemode

npm i https://pkg.pr.new/@cloudflare/codemode@2208

hono-agents

npm i https://pkg.pr.new/hono-agents@2208

@cloudflare/shell

npm i https://pkg.pr.new/@cloudflare/shell@2208

@cloudflare/think

npm i https://pkg.pr.new/@cloudflare/think@2208

@cloudflare/voice

npm i https://pkg.pr.new/@cloudflare/voice@2208

@cloudflare/worker-bundler

npm i https://pkg.pr.new/@cloudflare/worker-bundler@2208

commit: dba8aec

Deploy as codex-harness-example, give the Vite dev server its own inspector port so it can run beside the other harness examples, and document setting CLOUDFLARE_ACCOUNT_ID for logins with several accounts.

agents/react resolved a second React copy from the agents package, which broke every hook call in the browser.

A closed stream ends as soon as it is replayed, and every stream end asked for a snapshot that resubscribed to every operation. Subscribe to each operation once per connection and refresh only after a live tail ends, and scroll to the bottom only when content is added.

Add a synthetic-model stress worker (src/stress) with a driver and a CDP heap profiler (scripts/) so the kernel, Tasks, Streams, and SQLite paths can be pushed without Workers AI. Fix what the runs broke: - the 16-transition cap failed any turn with more than six tool calls; cap model rounds at 24 and transitions at 256 instead - the stored model action repeated the checkpoint's input, halving the transcript a turn could hold before SQLITE_TOOBIG; store it without the input and rehydrate on read - a 1 MB tool argument could not be journaled as a Tasks step result; bound prompts, tool arguments, and tool outputs at 256 KB, replacing oversized arguments with an error the model sees - session listings carried every checkpoint; omit kernel state from listings and let the UI read one checkpoint on demand Record the results and limits in the README and RFC.

devin-ai-integration

Note

This report is out of date. Scroll down for Devin Review's latest report on this PR.

Devin Review found 1 new potential issue.

4 flags not posted on this PR by your GitHub settings — view them in Devin Review. (Configure)

devin-ai-integration · 2026-09-04T11:43:14Z

+    await this.streams.open(streamId, { tag: operationId });
+    this.lifecycle.storage.sql.exec(
+      `INSERT INTO cf_codex_operations
+       (operation_id, stream_id, status, prompt, started_at)
+       VALUES (?, ?, 'queued', ?, ?)`,
+      operationId,
+      streamId,
+      prompt,
+      Date.now()
+    );


🟡 Concurrent retries reject accepted operations

Concurrent submissions sharing an operationId can both pass the existing-row check before streams.open yields. The later insert throws instead of returning the receipt.

Was this helpful? React with 👍 or 👎 to provide feedback.

…ample # Conflicts: # design/AGENTS.md # examples/next/README.md

…e limits The kernel checkpoint no longer carries the transcript. It is a cursor over one turn: phase, round, and pending tool calls, a few hundred bytes however long the conversation is. Everything with size moves to the SDK's durable primitives: - prompts, assistant messages, and tool outputs are Sessions messages, so large ones chunk across rows; each round hydrates a byte-budgeted window and Sessions compacts the branch past a token threshold - tool calls reach the kernel as a pointer to the stored assistant message and tool outputs are stored as tool messages, so Tasks journals effects by id instead of by value - events append to the operation's Streams log in the same transaction as the checkpoint; the journal table is gone - workspace_read takes offset and max_bytes, and the Workspace spills large files to an R2 bucket - the prompt shows a marker for any tool input or output over 64 KB, with a ranged read to page it back, so one large write cannot evict the rest of the turn from the context window Remove the 256 KB payload caps and the transition cap; the round cap is a configurable option. The stress suite now completes 8 MB prompts, 8 MB tool payloads, 60-round turns, 200 calls in a round, 200 turns on one object, and 32 concurrent objects with a 0.5 KB checkpoint throughout.

A transient Workers AI capacity error failed the whole turn. A round that returns no usable response now throws inside its Tasks step, which retries with backoff before the turn fails. Nothing is stored for a failed round, so a retry starts clean.

devin-ai-integration

Note

This report is out of date. Scroll down for Devin Review's latest report on this PR.

Devin Review found 8 new potential issues.

4 flags not posted on this PR by your GitHub settings — view them in Devin Review. (Configure)

devin-ai-integration · 2026-09-04T12:24:33Z

+    await this.session.appendMessage({
+      id: userMessageId(operationId),
+      role: "user",
+      parts: [{ type: "text", text: prompt }],
+      metadata: { operationId }
+    });


🔴 Concurrent turns contaminate each other

When prompts overlap, appendMessage puts them on one shared branch. Each model can consume another operation’s prompt or output.

Was this helpful? React with 👍 or 👎 to provide feedback.

devin-ai-integration · 2026-09-04T12:24:34Z

+  if (action.name === "workspace_read") {
+    const content = await workspace.readFile(path);
+    if (content === null)
+      return { success: false, output: { path, found: false } };
+    // Files have no size limit; the model pages through big ones by range.
+    const bytes = new TextEncoder().encode(content);
+    const offset = clampInteger(input.offset, 0, bytes.byteLength);
+    const maxBytes = clampInteger(input.max_bytes, 1, DEFAULT_READ_BYTES);
+    const end = Math.min(bytes.byteLength, offset + maxBytes);


🔴 Ranged reads load whole files

workspace_read loads and re-encodes the entire file before slicing. A small range from a large R2 file can exhaust Worker memory.

Was this helpful? React with 👍 or 👎 to provide feedback.

devin-ai-integration · 2026-09-04T12:24:36Z

+    const existing = this.#operation(operationId);
+    if (existing) {
+      if (existing.prompt !== promptPreview(prompt)) {
+        throw new Error(
+          `Codex operation ${operationId} already exists with different input`
+        );
+      }


🟡 Long prompt conflicts go undetected

promptPreview compares only the first 4,096 characters of long prompts. Different requests sharing that prefix reuse the earlier operation.

Was this helpful? React with 👍 or 👎 to provide feedback.

devin-ai-integration · 2026-09-04T12:24:37Z

+    const end = Math.min(bytes.byteLength, offset + maxBytes);
+    return {
+      success: true,
+      output: {
+        path,
+        content: new TextDecoder().decode(bytes.subarray(offset, end)),
+        offset,
+        end,
+        total_bytes: bytes.byteLength,
+        ...(end < bytes.byteLength ? { next_offset: end } : {})


🟡 Paged reads corrupt Unicode

When a byte range splits a multibyte character, decode replaces both fragments. Paged reads permanently corrupt that character.

Was this helpful? React with 👍 or 👎 to provide feedback.

devin-ai-integration · 2026-09-04T12:24:38Z

+  const text = blocks
+    .filter((block) => block.type === "text")
+    .map((block) => block.value)
+    .join("")
+    .trim();


🟡 Model output loses whitespace

trim removes intentional edge whitespace before events and final output are generated. Code blocks and whitespace-sensitive answers change.

Suggested change

const text = blocks

.filter((block) => block.type === "text")

.map((block) => block.value)

.join("")

.trim();

const text = blocks

.filter((block) => block.type === "text")

.map((block) => block.value)

.join("");

Was this helpful? React with 👍 or 👎 to provide feedback.

devin-ai-integration · 2026-09-04T12:24:39Z

+    this.lifecycle.storage.transactionSync(() => {
+      for (const event of transition.events) {
+        if (event.seq < writer.cursor) continue;
+        if (event.seq !== writer.cursor) {
+          throw new Error(
+            `Codex event gap for ${operation.operation_id}: expected ${writer.cursor}, got ${event.seq}`
+          );
+        }
+        writer.append(event);
+      }


🟡 Large response blocks fail turns

When a text or reasoning block exceeds Streams’ 1 MiB limit, append throws. The otherwise valid model turn is marked failed.

Was this helpful? React with 👍 or 👎 to provide feedback.

devin-ai-integration · 2026-09-04T12:24:40Z

+    return step.do(
+      `effect:${action.effect_id}`,
+      { retries: MODEL_ROUND_RETRIES, timeout: "10 minutes" },
+      ({ signal }) => this.#runEffect(operation, checkpoint, action, signal)


🟡 Long tool IDs fail turns

A tool-call ID above 244 characters makes step.do reject the effect. Valid provider tool calls then fail the turn.

Was this helpful? React with 👍 or 👎 to provide feedback.

devin-ai-integration · 2026-09-04T12:24:41Z

+        submit: (input) => this.submit(input),
+        operation: (operationId) => this.snapshot(operationId),
+        message: (id) => this.message(id),
+        readFile: (path) => this.readFile(path),


🟥 Clients can read arbitrary workspace files

A client-controlled path reaches readFile without an allowlist. Any connected client can retrieve every file stored in that session’s workspace.

Was this helpful? React with 👍 or 👎 to provide feedback.

…hink

devin-ai-integration

Devin Review found 3 new potential issues.

5 flags not posted on this PR by your GitHub settings — view them in Devin Review. (Configure)

devin-ai-integration · 2026-09-04T12:49:39Z

+      if (
+        !(error instanceof Error) ||
+        error.name === "AttemptSupersededError"
+      ) {
+        throw error;
+      }
+      this.#settleFailed(input.operationId, errorMessage(error));


🔴 Platform failures become terminal turns

When a step exhausts transient platform retries, #drive converts the propagated error into a terminal turn failure. Tasks cannot defer recovery to a fresh invocation.

Prompt for agents

Preserve Tasks control-flow and platform-failure semantics in CodexHarness.#drive. The catch in examples/next/harnesses/codex/src/codex-harness.ts currently rethrows non-Error controls and AttemptSupersededError only. ReplayStep also intentionally propagates code-update resets, memory-limit resets, and exhausted transient platform failures so Tasks can defer or apply breaker policy. Use the Tasks/retries predicates or a framework-supported error classifier to rethrow every control/platform failure, and settle the Codex operation only for terminal application errors.

Was this helpful? React with 👍 or 👎 to provide feedback.

devin-ai-integration · 2026-09-04T12:49:40Z

+        case "stream_end": {
+          // Only an operation we were tailing live needs its settled state
+          // and file; a replayed closed stream ends immediately.
+          const operation = stateRef.current.operations.find(
+            (candidate) => candidate.operationId === message.operationId
+          );
+          if (operation && isActive(operation)) {
+            sendRef.current({ type: "snapshot", id: crypto.randomUUID() });
+          }


🟡 Completed turns leave workspace view stale

After completion, isActive suppresses the snapshot request at stream end. The sidebar keeps the file state captured before the turn.

Suggested change

case "stream_end": {

// Only an operation we were tailing live needs its settled state

// and file; a replayed closed stream ends immediately.

const operation = stateRef.current.operations.find(

(candidate) => candidate.operationId === message.operationId

);

if (operation && isActive(operation)) {

sendRef.current({ type: "snapshot", id: crypto.randomUUID() });

}

case "stream_end": {

sendRef.current({ type: "snapshot", id: crypto.randomUUID() });

return;

}

Was this helpful? React with 👍 or 👎 to provide feedback.

devin-ai-integration · 2026-09-04T12:49:42Z

+        const result = await this.#performEffect(
+          operation,
+          transition.checkpoint,
+          transition.action,
+          step
+        );
+        command = {
+          type: "resolve_effect",
+          checkpoint: transition.checkpoint,
+          effect_id: transition.action.effect_id,
+          result
+        };


🟡 Round limit permits extra call

When the kernel emits the first disallowed round, #performEffect calls the model before checking the limit. The operation pays for an unused response.

Prompt for agents

Enforce maxRounds before dispatching each model action, including the model action emitted after the last tool in a batch. Do not call the provider or append an assistant message for a round that the next loop iteration will reject. Clarify whether maxRounds counts model calls or completed continuations and test small limits such as 1.

Was this helpful? React with 👍 or 👎 to provide feedback.

feat(examples): add Worker-native Codex harness

362574a

devin-ai-integration Bot reviewed Sep 3, 2026

View reviewed changes

mattzcarey added 2 commits September 3, 2026 13:00

devin-ai-integration Bot reviewed Sep 3, 2026

View reviewed changes

mattzcarey added 4 commits September 3, 2026 15:19

chore(codex-harness): rename the worker and pin a dev inspector port

de001c6

Deploy as codex-harness-example, give the Vite dev server its own inspector port so it can run beside the other harness examples, and document setting CLOUDFLARE_ACCOUNT_ID for logins with several accounts.

fix(codex-harness): dedupe React so the client renders

69dda74

agents/react resolved a second React copy from the agents package, which broke every hook call in the browser.

chore(codex-harness): shorten the empty-state copy

8b6316c

This comment was marked as resolved.

Sign in to view

devin-ai-integration Bot reviewed Sep 4, 2026

View reviewed changes

mattzcarey added 3 commits September 4, 2026 12:55

Merge remote-tracking branch 'origin/main' into feat/codex-harness-ex…

361a125

…ample # Conflicts: # design/AGENTS.md # examples/next/README.md

devin-ai-integration Bot reviewed Sep 4, 2026

View reviewed changes

mattzcarey added 3 commits September 4, 2026 13:31

chore(codex-harness): hydrate 32 MiB of history per round, matching T…

015f49e

…hink

chore(codex-harness): drop the run details panel from the UI

00fb9fb

feat(codex-harness): tools and workspace sidebar

dba8aec

devin-ai-integration Bot reviewed Sep 4, 2026

View reviewed changes

Uh oh!

Conversation

mattzcarey commented Sep 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Known gaps

Run

Uh oh!

changeset-bot Bot commented Sep 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

⚠️ No Changeset found

Uh oh!

devin-ai-integration Bot left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

devin-ai-integration Bot Sep 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

devin-ai-integration Bot Sep 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

agent-think Bot commented Sep 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

⚪ agents import sizes

Uh oh!

devin-ai-integration Bot left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

devin-ai-integration Bot Sep 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

devin-ai-integration Bot left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

devin-ai-integration Bot Sep 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

devin-ai-integration Bot Sep 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

devin-ai-integration Bot Sep 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

pkg-pr-new Bot commented Sep 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

This comment was marked as resolved.

Uh oh!

devin-ai-integration Bot left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

devin-ai-integration Bot Sep 4, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

devin-ai-integration Bot left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

devin-ai-integration Bot Sep 4, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

mattzcarey commented Sep 3, 2026 •

edited

Loading

changeset-bot Bot commented Sep 3, 2026 •

edited

Loading

devin-ai-integration Bot left a comment •

edited

Loading

devin-ai-integration Bot Sep 3, 2026 •

edited

Loading

devin-ai-integration Bot Sep 3, 2026 •

edited

Loading

agent-think Bot commented Sep 3, 2026 •

edited

Loading

devin-ai-integration Bot left a comment •

edited

Loading

devin-ai-integration Bot Sep 3, 2026 •

edited

Loading

devin-ai-integration Bot left a comment •

edited

Loading

devin-ai-integration Bot Sep 3, 2026 •

edited

Loading

devin-ai-integration Bot Sep 3, 2026 •

edited

Loading

devin-ai-integration Bot Sep 3, 2026 •

edited

Loading

pkg-pr-new Bot commented Sep 3, 2026 •

edited

Loading

devin-ai-integration Bot left a comment •

edited

Loading

devin-ai-integration Bot Sep 4, 2026 •

edited

Loading

devin-ai-integration Bot left a comment •

edited

Loading

devin-ai-integration Bot Sep 4, 2026 •

edited

Loading

devin-ai-integration Bot Sep 4, 2026 •

edited

Loading

devin-ai-integration Bot Sep 4, 2026 •

edited

Loading

devin-ai-integration Bot Sep 4, 2026 •

edited

Loading

devin-ai-integration Bot Sep 4, 2026 •

edited

Loading

devin-ai-integration Bot Sep 4, 2026 •

edited

Loading

devin-ai-integration Bot Sep 4, 2026 •

edited

Loading