Documentation: Web Interface Client Interaction Architecture #8222

New Issue

2026-02-16T18:09:27-05:00

yindo commented

2026-02-16 18:09:27 -05:00

Originally created by @BenceBertalan on GitHub (Feb 1, 2026).

Originally assigned to: @jayair on GitHub.

Overview

This issue documents the architecture and implementation details of how the OpenCode web interface handles client interaction, including messaging, event handling, and real-time updates.

Architecture

The opencode web command starts a local Hono-based HTTP server that serves as the backend API for the web interface. The architecture follows a Local Server + Remote UI Proxy model:

Backend: Local Hono server running on the user's machine (default port 4096)
Frontend: Static UI assets proxied from https://app.opencode.ai
Communication: RESTful API + Server-Sent Events (SSE) for real-time updates

Key Files

packages/opencode/src/cli/cmd/web.ts - Web command entry point
packages/opencode/src/server/server.ts - Main server configuration and routing
packages/opencode/src/server/routes/session.ts - Session and message handling
packages/opencode/src/server/event.ts - Server event definitions
packages/opencode/src/bus/bus-event.ts - Event bus system
packages/opencode/src/server/routes/question.ts - Question handling
packages/opencode/src/server/routes/permission.ts - Permission handling

Message Handling

Sending Messages

The web client sends messages to sessions via HTTP POST requests:

Endpoint: POST /session/:sessionID/message

Request Body:

{
  text: string,
  files?: FilePart[],
  agent?: string,
  model?: { providerID: string, modelID: string },
  // ... other optional fields
}

Response: Streams the assistant's response as JSON

Implementation: packages/opencode/src/server/routes/session.ts:697-736

Related Endpoints:

POST /session/:sessionID/prompt_async - Asynchronous message sending (returns immediately)
POST /session/:sessionID/command - Send slash commands
POST /session/:sessionID/shell - Execute shell commands

Receiving Messages

Messages are received in two ways:

Initial Fetch: GET /session/:sessionID/message
- Returns all messages in a session with their parts
- Implementation: packages/opencode/src/server/routes/session.ts:546-583
Real-time Updates: Via SSE stream (see Event Handling below)

Message Structure

Messages follow a structured format:

type Message = {
  info: UserMessage | AssistantMessage,
  parts: Part[]
}

type Part = 
  | TextPart 
  | ToolPart 
  | FilePart 
  | ReasoningPart 
  | SnapshotPart
  | PatchPart
  | AgentPart
  | RetryPart
  | CompactionPart
  | SubtaskPart
  | StepStartPart
  | StepFinishPart

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

Event Handling (Real-time Updates)

Event Stream Connection

Endpoint: GET /event

Protocol: Server-Sent Events (SSE)

Implementation: packages/opencode/src/server/server.ts:474-529

The client establishes a persistent SSE connection to receive real-time updates. The server:

Immediately sends a server.connected event upon connection
Subscribes to all bus events and forwards them to the client
Sends heartbeat events every 30 seconds to prevent connection timeouts
Automatically closes the stream when the instance is disposed

Event Bus System

OpenCode uses a centralized event bus (BusEvent) to broadcast updates across the system:

// Event definition pattern
BusEvent.define("event.type", zodSchema)

Core Implementation: packages/opencode/src/bus/bus-event.ts

All events follow a discriminated union pattern:

type Event = {
  type: string,
  properties: { /* event-specific data */ }
}

Message Events

Event Types (from packages/opencode/src/session/message-v2.ts:401-430):

message.updated

{
  type: "message.updated",
  properties: {
    info: Message
  }
}

Fired when a message is created or modified
Contains the full message info

message.removed

{
  type: "message.removed",
  properties: {
    sessionID: string,
    messageID: string
  }
}

Fired when a message is deleted

message.part.updated
```
{
  type: "message.part.updated",
  properties: {
    part: Part,
    delta?: string
  }
}
```
- Fired when a message part is created or updated
- Used for streaming responses (text parts updated incrementally)
- The delta field contains incremental text updates

message.part.removed

{
  type: "message.part.removed",
  properties: {
    sessionID: string,
    messageID: string,
    partID: string
  }
}

Fired when a message part is deleted

Non-Message Event Handling

Todo Events

Event Type: todo.updated (from packages/opencode/src/session/todo.ts:18)

{
  type: "todo.updated",
  properties: {
    sessionID: string,
    todos: Todo[]
  }
}

REST Endpoints:

GET /session/:sessionID/todo - Fetch current todos

Implementation: packages/opencode/src/server/routes/session.ts:155-183

Question Events

Event Type: question.asked (from packages/opencode/src/question/index.ts:64)

{
  type: "question.asked",
  properties: {
    requestID: string,
    sessionID: string,
    questions: Question[]
  }
}

REST Endpoints:

GET /question/ - List all pending questions
POST /question/:requestID/reply - Answer a question
POST /question/:requestID/reject - Reject a question

Implementation: packages/opencode/src/server/routes/question.ts

When the AI needs user input, it:

Creates a question request with a unique requestID
Broadcasts question.asked event via SSE
Waits for client response via POST
Broadcasts question.replied or question.rejected event

Permission Events

Event Type: permission.asked (from packages/opencode/src/permission/next.ts:97)

{
  type: "permission.asked",
  properties: {
    requestID: string,
    sessionID: string,
    // ... permission details
  }
}

REST Endpoints:

GET /permission/ - List all pending permissions
POST /permission/:requestID/reply - Approve/deny permission

Implementation: packages/opencode/src/server/routes/permission.ts

The permission flow:

AI requests permission (e.g., to execute a command)
Server broadcasts permission.asked event
Client displays permission UI
User approves/denies via POST request
Server broadcasts permission.replied event

Session Events

Additional session-level events (from packages/opencode/src/session/index.ts:106-131):

session.created - New session created
session.updated - Session metadata updated
session.deleted - Session removed
session.diff - File changes summary
session.error - Session error occurred

Status Events

Event Type: session.status (from packages/opencode/src/session/status.ts:28)

{
  type: "session.status",
  properties: {
    sessionID: string,
    status: "idle" | "active" | "error"
  }
}

Indicates the current execution state of a session.

Authentication

If OPENCODE_SERVER_PASSWORD is set, the server uses HTTP Basic Auth:

Username: OPENCODE_SERVER_USERNAME (default: "opencode")
Password: OPENCODE_SERVER_PASSWORD

Implementation: packages/opencode/src/server/server.ts:80-85

CORS Configuration

The server allows connections from:

localhost on any port
127.0.0.1 on any port
tauri://localhost (for desktop app)
*.opencode.ai (HTTPS only)
Custom origins via the --cors flag

Implementation: packages/opencode/src/server/server.ts:103-123

Client Implementation Pattern

A typical web client would:

Initialize:
- Connect to local server (detect via mDNS or user config)
- Establish SSE connection to /event

Handle Events:

const eventSource = new EventSource('/event');
eventSource.onmessage = (event) => {
  const { type, properties } = JSON.parse(event.data);
  switch(type) {
    case 'message.part.updated':
      // Update UI with new message part
      break;
    case 'question.asked':
      // Show question modal
      break;
    case 'permission.asked':
      // Show permission request
      break;
    // ... handle other events
  }
};

Send Messages:

await fetch(`/session/${sessionID}/message`, {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({ text: userInput })
});

Respond to Questions/Permissions:

await fetch(`/question/${requestID}/reply`, {
  method: 'POST',
  body: JSON.stringify({ answers: [...] })
});

Key Observations

Separation of Concerns: The backend logic runs locally while UI assets are served remotely, allowing UI updates without CLI updates
Event-Driven Architecture: All real-time updates flow through a centralized event bus with strong typing via Zod schemas
Streaming Support: Message parts can be streamed incrementally using the delta field in message.part.updated events
Type Safety: All API contracts are defined using Zod schemas and exposed via OpenAPI documentation at /doc
Flexible Deployment: Supports network access (0.0.0.0), mDNS discovery, and custom CORS origins for various deployment scenarios

Update: Quota and Rate Limit Detection

How OpenCode Detects Quota/Rate Limit Errors

OpenCode has sophisticated error detection and retry logic that identifies quota and rate limit issues from AI provider API responses. Here's how it works:

Detection Mechanism

File: packages/opencode/src/session/retry.ts:61-96

The retryable() function analyzes API errors to determine if they're quota/rate limit related:

export function retryable(error: ReturnType<NamedError["toObject"]>) {
  if (MessageV2.APIError.isInstance(error)) {
    if (!error.data.isRetryable) return undefined
    return error.data.message.includes("Overloaded") 
      ? "Provider is overloaded" 
      : error.data.message
  }

  // Parse error response body as JSON
  const json = JSON.parse(error.data.message)
  
  // Check for specific error patterns:
  
  // 1. Anthropic/Claude rate limit format
  if (json.type === "error" && json.error?.type === "too_many_requests") {
    return "Too Many Requests"
  }
  
  // 2. Generic quota exhaustion
  if (code.includes("exhausted") || code.includes("unavailable")) {
    return "Provider is overloaded"
  }
  
  // 3. Rate limit error codes
  if (json.type === "error" && json.error?.code?.includes("rate_limit")) {
    return "Rate Limited"
  }
}

Error Sources

File: packages/opencode/src/session/message-v2.ts:668-748

Errors are captured from the AI SDK's APICallError class and transformed into structured MessageV2.APIError objects:

{
  name: "APIError",
  data: {
    message: string,           // Human-readable error message
    statusCode?: number,       // HTTP status code (e.g., 429)
    isRetryable: boolean,      // Whether the error can be retried
    responseHeaders?: object,  // Raw response headers
    responseBody?: string,     // Raw response body (JSON)
    metadata?: object          // Additional metadata (e.g., URL)
  }
}

The isRetryable flag comes from the AI SDK and is provider-specific. OpenCode relies on:

The AI SDK's built-in retry detection (e.isRetryable)
HTTP status codes (some providers return 429, others use different codes)
Parsing the response body for known error patterns

Retry Logic with Exponential Backoff

File: packages/opencode/src/session/retry.ts:28-59

When a retryable error is detected, OpenCode calculates a delay before retrying:

export function delay(attempt: number, error?: MessageV2.APIError) {
  // 1. Check for Retry-After headers (preferred)
  if (error?.data.responseHeaders) {
    // Retry-After-Ms: milliseconds
    const retryAfterMs = headers["retry-after-ms"]
    if (retryAfterMs) return parseFloat(retryAfterMs)
    
    // Retry-After: seconds or HTTP date
    const retryAfter = headers["retry-after"]
    if (retryAfter) {
      // Try parsing as seconds
      const seconds = parseFloat(retryAfter)
      if (!isNaN(seconds)) return seconds * 1000
      
      // Try parsing as HTTP date
      const date = Date.parse(retryAfter) - Date.now()
      if (!isNaN(date) && date > 0) return date
    }
  }
  
  // 2. Fallback to exponential backoff
  return RETRY_INITIAL_DELAY * Math.pow(RETRY_BACKOFF_FACTOR, attempt - 1)
  // RETRY_INITIAL_DELAY = 2000ms
  // RETRY_BACKOFF_FACTOR = 2
  // Max delay = 30 seconds (without headers) or ~24 days (with headers)
}

Retry schedule: 2s → 4s → 8s → 16s → 30s (capped)

Communication to Web Client

When a retry occurs, the web client is notified via two mechanisms:

1. Session Status Event

Event: session.status (via SSE /event stream)

File: packages/opencode/src/session/status.ts:28-34

{
  type: "session.status",
  properties: {
    sessionID: string,
    status: {
      type: "retry",
      attempt: number,        // Which retry attempt (1, 2, 3, ...)
      message: string,        // User-friendly error message
      next: number           // Timestamp when next retry will occur
    }
  }
}

Trigger: packages/opencode/src/session/processor.ts:349-354

When the processor catches a retryable error, it immediately broadcasts a status update:

const retry = SessionRetry.retryable(error)
if (retry !== undefined) {
  attempt++
  const delay = SessionRetry.delay(attempt, error.name === "APIError" ? error : undefined)
  SessionStatus.set(input.sessionID, {
    type: "retry",
    attempt,
    message: retry,              // "Rate Limited", "Too Many Requests", etc.
    next: Date.now() + delay,    // When the retry will happen
  })
  await SessionRetry.sleep(delay, input.abort)
  continue  // Retry the request
}

2. Retry Part (Message History)

File: packages/opencode/src/session/message-v2.ts:184-194

If a retry occurs, a RetryPart is not automatically added to the message (based on code review). However, the error information is preserved in the assistant message:

type RetryPart = {
  type: "retry",
  id: string,
  sessionID: string,
  messageID: string,
  attempt: number,
  error: APIError,
  time: {
    created: number
  }
}

Note: The current implementation broadcasts retry status via session.status events but does not persist retry attempts as message parts. If the retry succeeds, the user never sees the error. If all retries fail, the final error is stored in the assistant message's error field.

Client UI Handling Example

From the TUI implementation (packages/opencode/src/cli/cmd/tui/component/prompt/index.tsx:1044-1084):

const retry = createMemo(() => {
  const s = status()
  if (s.type !== "retry") return
  return s
})

const message = createMemo(() => {
  const r = retry()
  if (!r) return
  
  // Special case for Gemini quota errors
  if (r.message.includes("exceeded your current quota") && r.message.includes("gemini"))
    return "gemini is way too hot right now"
    
  // Truncate long messages
  if (r.message.length > 80) return r.message.slice(0, 80) + "..."
  return r.message
})

// Calculate countdown timer
const seconds = Math.round((retry.next - Date.now()) / 1000)

// Display: "Rate Limited [retrying in 8s attempt #2]"

Web Client Implementation Pattern

To handle quota/rate limit errors, a web client should:

Listen for session.status events:

eventSource.onmessage = (event) => {
  const { type, properties } = JSON.parse(event.data);
  
  if (type === 'session.status' && properties.status.type === 'retry') {
    const { attempt, message, next } = properties.status;
    
    // Show retry notification
    showRetryBanner({
      message,                           // "Rate Limited", "Too Many Requests"
      attempt,                           // 1, 2, 3...
      retryIn: next - Date.now()        // Milliseconds until retry
    });
  }
  
  if (type === 'session.status' && properties.status.type === 'idle') {
    // Retry succeeded or session completed
    hideRetryBanner();
  }
};

Check for final errors in assistant messages:

if (message.role === 'assistant' && message.error) {
  if (message.error.name === 'APIError') {
    const { message: errorMsg, statusCode, isRetryable } = message.error.data;
    
    if (statusCode === 429 || errorMsg.includes('quota') || errorMsg.includes('rate limit')) {
      showQuotaError(errorMsg);
    }
  }
}

Known Provider Error Patterns

Based on the code, OpenCode detects these patterns:

Provider	Error Pattern	Detection Method
Anthropic/Claude	`{"type":"error","error":{"type":"too_many_requests"}}`	JSON parsing
OpenAI	Status 429, `rate_limit_exceeded` error code	Status code + AI SDK
Google Gemini	"exceeded your current quota" in message	String matching
Generic	`exhausted`, `unavailable` in error code	String matching
Any	`Overloaded` in error message	String matching

REST API for Status Checking

Clients can also poll session status via:

Endpoint: GET /session/status

Response:

{
  "session_abc123": {
    "type": "retry",
    "attempt": 2,
    "message": "Rate Limited",
    "next": 1738435200000
  },
  "session_xyz789": {
    "type": "idle"
  }
}

Implementation: packages/opencode/src/server/routes/session.ts:70-90

This allows clients to check retry status without maintaining a persistent SSE connection.

@BenceBertalan commented on GitHub (Feb 1, 2026): ## Update: Quota and Rate Limit Detection ### How OpenCode Detects Quota/Rate Limit Errors OpenCode has sophisticated error detection and retry logic that identifies quota and rate limit issues from AI provider API responses. Here's how it works: ### Detection Mechanism **File**: `packages/opencode/src/session/retry.ts:61-96` The `retryable()` function analyzes API errors to determine if they're quota/rate limit related: ```typescript export function retryable(error: ReturnType<NamedError["toObject"]>) { if (MessageV2.APIError.isInstance(error)) { if (!error.data.isRetryable) return undefined return error.data.message.includes("Overloaded") ? "Provider is overloaded" : error.data.message } // Parse error response body as JSON const json = JSON.parse(error.data.message) // Check for specific error patterns: // 1. Anthropic/Claude rate limit format if (json.type === "error" && json.error?.type === "too_many_requests") { return "Too Many Requests" } // 2. Generic quota exhaustion if (code.includes("exhausted") || code.includes("unavailable")) { return "Provider is overloaded" } // 3. Rate limit error codes if (json.type === "error" && json.error?.code?.includes("rate_limit")) { return "Rate Limited" } } ``` ### Error Sources **File**: `packages/opencode/src/session/message-v2.ts:668-748` Errors are captured from the AI SDK's `APICallError` class and transformed into structured `MessageV2.APIError` objects: ```typescript { name: "APIError", data: { message: string, // Human-readable error message statusCode?: number, // HTTP status code (e.g., 429) isRetryable: boolean, // Whether the error can be retried responseHeaders?: object, // Raw response headers responseBody?: string, // Raw response body (JSON) metadata?: object // Additional metadata (e.g., URL) } } ``` The `isRetryable` flag comes from the AI SDK and is provider-specific. OpenCode relies on: 1. The AI SDK's built-in retry detection (`e.isRetryable`) 2. HTTP status codes (some providers return 429, others use different codes) 3. Parsing the response body for known error patterns ### Retry Logic with Exponential Backoff **File**: `packages/opencode/src/session/retry.ts:28-59` When a retryable error is detected, OpenCode calculates a delay before retrying: ```typescript export function delay(attempt: number, error?: MessageV2.APIError) { // 1. Check for Retry-After headers (preferred) if (error?.data.responseHeaders) { // Retry-After-Ms: milliseconds const retryAfterMs = headers["retry-after-ms"] if (retryAfterMs) return parseFloat(retryAfterMs) // Retry-After: seconds or HTTP date const retryAfter = headers["retry-after"] if (retryAfter) { // Try parsing as seconds const seconds = parseFloat(retryAfter) if (!isNaN(seconds)) return seconds * 1000 // Try parsing as HTTP date const date = Date.parse(retryAfter) - Date.now() if (!isNaN(date) && date > 0) return date } } // 2. Fallback to exponential backoff return RETRY_INITIAL_DELAY * Math.pow(RETRY_BACKOFF_FACTOR, attempt - 1) // RETRY_INITIAL_DELAY = 2000ms // RETRY_BACKOFF_FACTOR = 2 // Max delay = 30 seconds (without headers) or ~24 days (with headers) } ``` **Retry schedule**: 2s → 4s → 8s → 16s → 30s (capped) ### Communication to Web Client When a retry occurs, the web client is notified via **two mechanisms**: #### 1. Session Status Event **Event**: `session.status` (via SSE `/event` stream) **File**: `packages/opencode/src/session/status.ts:28-34` ```typescript { type: "session.status", properties: { sessionID: string, status: { type: "retry", attempt: number, // Which retry attempt (1, 2, 3, ...) message: string, // User-friendly error message next: number // Timestamp when next retry will occur } } } ``` **Trigger**: `packages/opencode/src/session/processor.ts:349-354` When the processor catches a retryable error, it immediately broadcasts a status update: ```typescript const retry = SessionRetry.retryable(error) if (retry !== undefined) { attempt++ const delay = SessionRetry.delay(attempt, error.name === "APIError" ? error : undefined) SessionStatus.set(input.sessionID, { type: "retry", attempt, message: retry, // "Rate Limited", "Too Many Requests", etc. next: Date.now() + delay, // When the retry will happen }) await SessionRetry.sleep(delay, input.abort) continue // Retry the request } ``` #### 2. Retry Part (Message History) **File**: `packages/opencode/src/session/message-v2.ts:184-194` If a retry occurs, a `RetryPart` is **not** automatically added to the message (based on code review). However, the error information is preserved in the assistant message: ```typescript type RetryPart = { type: "retry", id: string, sessionID: string, messageID: string, attempt: number, error: APIError, time: { created: number } } ``` **Note**: The current implementation broadcasts retry status via `session.status` events but does not persist retry attempts as message parts. If the retry succeeds, the user never sees the error. If all retries fail, the final error is stored in the assistant message's `error` field. ### Client UI Handling Example From the TUI implementation (`packages/opencode/src/cli/cmd/tui/component/prompt/index.tsx:1044-1084`): ```typescript const retry = createMemo(() => { const s = status() if (s.type !== "retry") return return s }) const message = createMemo(() => { const r = retry() if (!r) return // Special case for Gemini quota errors if (r.message.includes("exceeded your current quota") && r.message.includes("gemini")) return "gemini is way too hot right now" // Truncate long messages if (r.message.length > 80) return r.message.slice(0, 80) + "..." return r.message }) // Calculate countdown timer const seconds = Math.round((retry.next - Date.now()) / 1000) // Display: "Rate Limited [retrying in 8s attempt #2]" ``` ### Web Client Implementation Pattern To handle quota/rate limit errors, a web client should: 1. **Listen for `session.status` events**: ```javascript eventSource.onmessage = (event) => { const { type, properties } = JSON.parse(event.data); if (type === 'session.status' && properties.status.type === 'retry') { const { attempt, message, next } = properties.status; // Show retry notification showRetryBanner({ message, // "Rate Limited", "Too Many Requests" attempt, // 1, 2, 3... retryIn: next - Date.now() // Milliseconds until retry }); } if (type === 'session.status' && properties.status.type === 'idle') { // Retry succeeded or session completed hideRetryBanner(); } }; ``` 2. **Check for final errors** in assistant messages: ```javascript if (message.role === 'assistant' && message.error) { if (message.error.name === 'APIError') { const { message: errorMsg, statusCode, isRetryable } = message.error.data; if (statusCode === 429 || errorMsg.includes('quota') || errorMsg.includes('rate limit')) { showQuotaError(errorMsg); } } } ``` ### Known Provider Error Patterns Based on the code, OpenCode detects these patterns: | Provider | Error Pattern | Detection Method | |----------|--------------|------------------| | **Anthropic/Claude** | `{"type":"error","error":{"type":"too_many_requests"}}` | JSON parsing | | **OpenAI** | Status 429, `rate_limit_exceeded` error code | Status code + AI SDK | | **Google Gemini** | "exceeded your current quota" in message | String matching | | **Generic** | `exhausted`, `unavailable` in error code | String matching | | **Any** | `Overloaded` in error message | String matching | ### REST API for Status Checking Clients can also poll session status via: **Endpoint**: `GET /session/status` **Response**: ```json { "session_abc123": { "type": "retry", "attempt": 2, "message": "Rate Limited", "next": 1738435200000 }, "session_xyz789": { "type": "idle" } } ``` **Implementation**: `packages/opencode/src/server/routes/session.ts:70-90` This allows clients to check retry status without maintaining a persistent SSE connection.

yindo commented

2026-02-16 18:09:27 -05:00

@BenceBertalan commented on GitHub (Feb 1, 2026):

This issue has been moved to BenceBertalan/octools#1 where it will be maintained as part of the OpenCode documentation repository.

@BenceBertalan commented on GitHub (Feb 1, 2026): This issue has been moved to BenceBertalan/octools#1 where it will be maintained as part of the OpenCode documentation repository.

yindo referenced this issue

2026-02-16 18:10:17 -05:00

[FEATURE]: JSX and TSX syntax highlighting for markdown-injected #8561

yindo referenced this issue

2026-02-16 18:10:51 -05:00

OpenCode unable to display valid JSON #8789

yindo referenced this issue

2026-02-16 18:11:05 -05:00

[FEATURE]: Beautified Question Tool Text Display #8877

Sign in to join this conversation.

Branches Tags

dev

mini-terminal-title

location-wait-api

mini-project-commands

resume-prompt

alibaba-images

item-reference-investigation

ai-pdf-support

beta

v2

production

wsl-shell-env

fork-once

wsl-env-load

stream-eof-finish

nvidia-minimax-thinking

pr-38231-assets

shell-mode-style

pr-38224-assets

reject-malformed-hunks

tool-progress-live

codemode-catalog-diffs

model-flicker

default-background

terminal-queries

event-batching

port-plugins

gemini-thinking-level

patch-symlink-policy

session-version-sentinel

client-service

service-channel-config

webfetch-images

search-integration

billing-details

shell-exit-grace

desktop-image-backgrounds

copilot-endpoint

migrate-select-theme

bound-tool-output

workspace-model-block

remove-promo

collapse-model-providers

review-sidebar-hydration

collapse-questions

location-startup-timing

remove-output-paths

shell-output-preview

quark-timeline

raw-tool-recovery

dialog-hover-fix

server-profiles

server-switcher

kimi-mfjs-schema

session-options-hook

interleaved-fields

remote-workspaces-plan

fix-initial-message

undo-git-guard

pr-37575-assets

opentui-binary-repro

startup-lock-release

system-theme-v2

llm-error-types

tui-plugin-load

external-defaults

productionclear

pr-37513-assets

console-auth-refresh

v2-app-api

backend-adapter-v2

oc-clipboard-and-paste

test/hot-reload-regressions

provider-benchmark

shell-progress-tail

model-cycle-palette

theme-toggle-copy

flaky-provider-tests

permission-modal-keyboard

shell-output-alignment

session-http-hook

permission-highlight

activity-panel

workspace-copy

interrupt-not-found

device-org-select

v2-subagent-limit

vertex-xai-default

reasoning-replay

agent-picker-custom

effect-dynamic-tools

patch-empty-hang

fix/empty-assistant-output

favorites-cli-config

simulated-tools

console-analytics-logger

simulation-terminal-frame-capture

feature-defaults

free-model-logo

service-restart

interrupt-stop-race

xai-oauth

background-indicator-inline

home-shortcut-align

compaction-model-marker

provider-config-shape

interface-toggle

install-layout-eligibility

tools-menu

mcp-location-refresh

session-picker-crash

optimistic-submit

dialog-action-focus

llm-terminal-contract

llm-remove-provider-error

remove-subtle-syntax

title-small-model

dialog-empty-states

permission-panel

api-dsl-cleanup

app-backend-v2

free-model-badge

compaction-percent

thought-toggle

home-session-scroll

llm-error-redesign

luna-oauth-fix

tool-flat-draft

v2-shell-utf8

remove-starptech

effort-values-none

config-dialog

update-tsgo

bounded-compaction-prod

stale-form-submit

dismiss-stale-form

bounded-compaction

agent-picker-variants

config-dir-repro

shell-tail-output

v2-integrations

quick-undo

startup-error-cause

subagent-panel-ui

lazy-fff

optimistic-input

zsh-positional

v2-diff-route

plugin-session-rename

gpt56-max

shortcut-screenshots

service-status

context-overflow

random-tool-catalog

review-nav-spacing

architecture-review

duplicate-event-logs

fix-shell-tab

v2-agent-env

plugin-watch-fix

compaction-cleanup

fix-compaction

genai-observability

agent-permission-order

tui-pending

catalog-repros

catalog-cold-start

console-login-logs

fix/tui-fresh-session-prompt

review-terminal

model-reset-repro

reasoning-variants

improve-caching

team-members

promise-chaining

tabs-launch-screenshots

compaction-steer

agent-env-markers

daemon-election

retry-layout

bash-streaming-fix

bash-tool-crash

restore-session-paging

provider-entrypoints

model-input-defaults

fix-initial-message-page-size

background-return

model-capability-defaults

runner-scenario-dsl

location-watch-guard

fix-shell-count

session-model-sync

new-session-commands

interrupt-tool-hang

codemode-service

mcp-attachments

stdlib-gaps

codemode-object-delete

json-callbacks

code-mode-opencode

drive-manifest

firecrawl-search

persisted-suspense

mcp-resource-app

mcp-resource-ui

mcp-resource-api

media-attachment

instruction-rename

destructuring-assign

codemode-audit

schema-reexports

event-subscribe

nxl/vcs-plugin-api

global-forms

revert-prompt

fix-stale-tools

service-version-guard

partial-refund-ledger

sdk-js-imports

jlongster/simulation-improvements

promise-named-types

tool-output

execute-code-mode-v2

compaction-indicator

subagent-command

catalog-readiness

pending-tool-error

zen-body-limit

form-tui

step-settlement

settlement-ledger

provider-packages

elicitation-timeout

codemode-opencode-adapter

optimize-hooks

models-log-leak

zen-accounting-latency

form-elicitation

codemode-opencode-wiring

codemode-opencode-integration

models-refresh-daemon

v2-model-refresh

filesystem-simulation

context-checkpoint

system-context

subagent-notify

subagent-resume

simulation-spec-v2

directory-attachment-expansion

zen-headers-timeout

config-effect-v2

embedded-config-seam

config-ownership

shell-background-notice

compaction-idle-status

session-tab-remount

publish-server

directory-attachments

content-filter-notice

settings-model-clipping

home-autocomplete-location

tabs-restore

plugin-runtime-bridge

simulation-spec

optimistic-prompt

reasoning-model-api

tool-result-api

beta-badge

prompt-submit-clear

prompt-attachments

mcp-prompts

background-shortcut

debug-windows-opentui-standalone-repro-release

fix-empty-sessions-list

core-node-consumers

model-selection

snapshot-otui

pty-env-route

status-frame-fix

daxbox-servers

shell-output-flush

shell-tool-test

auth-list

remove-default-layers

jlongster/opencode-all-tests-more

native-provider-clean

context-tooltip-v2

native-provider-core

native-provider-stack

deferred-tools

delete-email-action

poll-updates

jlongster/test-batch

session-forking

plugin-patterns

anthropic-thinking-variants

merge-dev-into-v2

fix-windows-abbreviate-home

project-edit-update

streaming-prd

zen-refund-accounting

fish-completion

cache-code-highlights

review-session-pane

sdk-generation-dev-check

clean-desktop-deps

clean-http-recorder-deps

clean-opencode-deps

clean-session-ui-deps

clean-stats-app-deps

clean-ui-deps

clean-web-deps

clean-app-deps

clean-cli-deps

clean-console-app-deps

clean-console-core-deps

clean-console-function-deps

clean-console-mail-deps

clean-console-support-deps

clean-core-deps

clean-root-deps

tui-child-picker

core-project-relocation

complete-client

open-auth-url

desktop-relocated

child-session-picker

fix-event-type

typecheck-28263387070

refresh-singleflight

jlongster/location-nodes

home-active-indicator

session-step-interrupted

interrupt-loading

fix/tui-preserve-renderer-error

fix/provider-session-failures

frank-production-validation-20260626

embedded-live-tail

fix/openai-stateless-reasoning-continuation

session-event-stream

responses-stream-retry

mcp-core-skeleton

server-auto-approve

opentui-retry

timeline-scroll-state

protocol-events

published-events

native-provider-config

native-provider-packages

oc-1.17.10-hotfix

new-session-model

tab-custom-color

feat/tui-render-state-dump

fix/tui-palette-question-mode

otui-native-yoga

feature/expand-paste-summary

todo-dock-motion

mcp-search-tool

tab-shrink

session-provider-errors

isolate-oauth-headers

verify-mcp-auth

secure-oauth-api

mcp-reconnect

restrict-mcp-env

redact-config-secrets

atomic-oauth-callback

native-provider-schema

add-model-comparison-pages

question-paste

simplify-target-layouts

fix-mention-mime

tagged-error-lint

websocket-auth

headless-console-login

mobile-utility-ui

ios-pwa-shell

mobile-bottom-nav

mobile-session-layout

mobile-home-layout

plugin-internal

fix/v2-queue-after-terminal-failure

http-recorder-release

custom-image-defaults

consolidate-todo-event

normalize-step-event-versions

fix-session-subpath

simplify/v2-runner-transitions

run-core-tests

feat/v2-terminal-run-failures-dev

filesystem-errors

hide-read-arguments

layer-node-permit

layer-node-projector

layer-node-repocache

layer-node-sprompt

layer-node-projcopy

layer-node-location

layer-node-movesess

layer-node-locfs

layer-node-models

layer-node-locmut

layer-node-instruct

layer-node-cconfig

layer-node-watcher

layer-node-fmutation

layer-node-integrate

layer-node-cevent

layer-node-cspawn

layer-node-cagent

layer-node-cproject

layer-node-command

yolo-flag

layer-node-extdir

layer-node-cprocess

layer-node-cgit

layer-node-cripgrep

layer-node-csearch

figma-mcp-client

stabilize-ci-tests

core-tests-ci

project-copy-migration

mcp-prompt-refresh

mcp-oauth-refresh

workerd

share-listener-runtime

v2-global-nodes

server-node-graph

mcp-resource-content

fix/command-double-file

background-model-refresh

jlongster/project-copy-config

demo/pr-31617-session-location

feat/tui-copy-session-location

reasoning-options

reasoning-options-support

fix/opencode-bundle-fff

refactor/mcp-connection-results

refactor/reference-directory-parts

feat/mcp-resource-updated

fix/mcp-prompts-list-changed

feat/mcp-resource-list-changed

docs-go-pricing-explanation

refactor/tui-http-sdk

fix/v2-read-validation-failure

refactor/v2-session-run-coordinator

refactor/core-provider-turn

feat/v2-terminal-run-failures

fix/v2-session-wake-retry-dev

feat/core-v2-background-agent

fix/http-recorder-release

fix/v2-session-wake-retry

fix/bash-tool-settlement

fix/v2-headless-permission-policy

fix/v2-binary-detection

fix/v2-read-images

fix/v2-read-errors

feat/core-v2-overflow-recovery

feat/jsonl-log-file

feat/core-v2-session-context-epoch

fix-bedrock-1

fix/session-metadata-migration-repair

pr-30929-demo-video

nexxeln-copy-git-worktree-path

fix/tui-worker-rpc-errors

refactor/core-v2-message-identity

fix/core-v2-sequence-index-invariants

refactor/core-account-file-agents

feat/core-command-registry

fix/tui-rpc-errors

fix/openai-codex-route-timeouts

fix/openai-websocket-header-timeout

refactor/remove-aisdk-option-fields

dustin/improve-memory-usage

feat/sdk-oagen-effect-emitter

nxl/consolidate-project-references

fix/prompt-loop-shutdown

feat/stripe-lake-ingest

kit/tui-scenario-frames

test/core-location-filesystem-canonical-paths

fix/zen-provider-sse-errors

dustin/clickable-titles

fix/free-tier-limit-cta

fix-model-selection

kit/pr-30051-screenshots

fix/xai-provider-upstream-pdf-support

chore/opencode-ai-provider-updates

feat/mcp-add-inline-args

refactor/provider-inline-local-helpers

fix/tui-syntax-builtins

fix/tui-question-keybindings

nxl/session-status-parent-id

feat/core-config-service

fix/free-model-sort

jlongster/workspace-v2

server-discovery

nxl/tui-message-keyboard-nav

fix-github-links-and-star

kit/tui-pending-tool-spinner

fix/task-running-continuation-feedback

fix-leader-none

fix/google-vertex-anthropic-auth-message

worktree-fork-toast

feat/request-aware-provider-fetch

fix/session-project-migration-time

kit/tui-optimistic-prompt-render

issue-13770-tool-output-docs

fix/google-vertex-metadata-warning

brendan/fix-e2e

question-endpoint

test/config-effect-dsl

fix-native-llm-options

compaction-adjustments

fix/app-v2-channel-gate

feat/core-database-schema-sync

fix/mcp-oauth-scope-and-callback-port

dustin/fix-structured-output-fields

kit/repro-zod-schema-leak

worktree-dead-exports

worktree-dead-files

nxl/fix-permission-specificity

jlongster/diff-viewer

nxl/v2-deferred-prompt

fix-retries

nxl/compaction-args

dustin/tool-choice-capability-support

cooper/opencode-codex-refresh-dedupe

refactor/native-runtime-prepared-request

storage-v2-service

drop-app-runtime-instance

worktree-test-port-audit

worktree-cli-effect-harness-2

worktree-cli-prewarm

refactor/session-prompt-parts

image-paths

test/config-instance-opencode-files

fix-env-json-parse-guards

test/config-instance-save-update

extract-part-text-helper

test/config-instance-template-loads

test/config-instance-first-slice

test/config-instance-agent-command

test/provider-instance-custom-models

test/provider-instance-model-lookup

worktree-global-bus-unify

test/provider-instance-first-slice

oc-issue-question-stuck

oc-snapshot-subdir

nxl/fix-auto-compaction-progress

fix/edit-project-dialog

brendan/message-timeline-scroll-virtualiser

jlongster/simulation-rebase

thdxr/auth-well-known-service

models-dev-global-snapshot

tui-markdown-h3-muted

debug-windows-opentui-bun-1.3.14

debug-windows-opentui-crash

serve-socket-mode

fix-event-sync

kit/delete-instance-local-context

upgrade-otui-0212

snapshot-npm-native-binary-install

emdash/27458-h7lu6

session-next-delta-events

new-colors

fix/event-stream-context-capture

fix/event-stream-context-27391

effect/session-transport-service

effect/config-paths-service

adjust-perm-array-logic

nxl/remove-http-notfound-fallback

nxl/render-config-json-diagnostics

nxl/render-tagged-config-errors

effect-test-permission-next

fix/desktop-session-status-tui-20260513090340

opencode/storage-engine-repository

effect/define-service-helper

disable-image-resizing-default

effect/util-process-effect-returning

effect-test-plugin-auth-override

effect/kill-tuiconfig-installation-facades

effect/unwrap-run-runtime-facades

effect-test-project-project

jlongster/fuzz-backend

fix-aws-issue

llm-native-inject-client

llm-native-runtime-openai

llm-native-prepare-tests

llm-native-request-adapter

llm-native-event-adapter

effect-test-provider-cluster1

brendan/lazy-init-plugins

kit/drop-project-sandboxes

claude/learn-new-skill-Ji0dn

fix/windows-instance-fixture-cleanup

worktree-draft+llm-usage-additive

styled-skill-errors

cleanup/effectify-remaining-compaction-tests

draft/session-timeline-rewind

worktree-http-recorder-cassette-seam

claude/review-recent-issues-Ck5UO

opencode/happy-cabin

cleanup/localize-id-prefixes

cleanup/openapi-workspace-path-pattern

llm-service-event-seam

kit/config-field-tolerant

kit/migrate-drift-tests-into-exerciser

kit/httpapi-exercise-via-sdk

kit/mcp-tolerate-bad-output-schemas

refactor-provider-model-status-schema

fix/httpapi-query-schema-drift

kit/fix-26435-legacy-session-model

kit/plugin-mutation-reproducers

kit/fix-workspace-time-used-migration

kit/revert-26550-fallback

kit/restore-hono-temporary

kit/fix-empty-bad-request-normalization

nxl/reference-file-mentions

fix/composer-image-preview-click

kit/httpapi-project-skill-repro

kit/httpapi-total-coverage

kit/httpapi-auth-cleanup-base

jlongster/workspace-external

fix-reasoning-efforts

fix/session-negative-output-tokens

make-review-normal

nxl/fix-anthropic-provider-tools

brendan/desktop-electron-refactor

fix/workspace-warp-typecheck

jlongster/warp

nxl/background-subagents

kit/pty-no-auth-parity

thdxr/v2-message-model-failures

kit/server-listen-native

kit/httpapi-listener-proxy-ws

kit/typed-session-not-found-sketch

fix-wellknown-down

kit/httpapi-not-found-shape

effect-drizzle-sqlite

question-lifecycle-effect-tests

kit/instance-loader-service

kit/effect-workspace-adapters

docs-sdk

kit/llm-approval-instance-ref

kit/session-llm-instance-state

effect-sync-event-service

jlongster/pin-session

azure-cognitive-improvements

adapter-rename

nxl/runtime-aware-search-service

deflake-test

moonshot-mfjs

nxl/small-model-subagents

brendan/new-composer-design

kit/httpapi-sdk-smoke-test

simon-reject-failure

kit/httpapi-json-shape-parity

kit/fix-httpapi-session-list-main

kit/httpapi-route-parity

fix-deepseek-reasoner

kit/httpapi-experimental-tools

deepseek-anthropic

fix/usage-chart-local-time

fix-shell-test

fix-config-ordering-issue

fix/beta-lazy-assistant-error

fix/session-event-typecheck-ci-shell

kit/httpapi-route-inventory-current

shell-test

simon-thread-network-defaults

fix-hover-selected

kit/schema-native-cleanup-ts

adjust-retry-logic

kit/session-schema-events

kit/config-permission-effect

Cramer/2026-03-25/bare-repo-bug

opencode-remote-voice

core

fix-zen-2

kit/multiedit-schema-fix-ts

kit/fix-release-publish-effect

kit/file-instance-context

kit/lsp-effect-refactor

kit/tui-terminal-notifications

tui-favorite-sort-on-query

openai-compaction

fix-copilot

opencode/swift-nebula

fix/project-worktree-external-directory-default

kit/tui-go-upsell-shimmer

kit/httpapi-workspace-schema-migration

kit/ns-plugin-loader-redo

kit/ns-plugin-loader

kit/ns-file-watcher

kit/repro-write-lsp-hang

kit/collapse-session

kit/collapse-patch

kit/retrofit-plugin-main

kit/retrofit-skill-main

kit/retrofit-permission-main

kit/retrofit-mcp-main

kit/retrofit-config-main

kit/unwrap-plugin-siblings

kit/unwrap-small-standalone

kit/unwrap-mcp-siblings

kit/unwrap-config-siblings

kit/self-reexport-migration-tooling

claude/verify-pr-comment-UuyAZ

claude/debug-e2e-tests-Hkgdb

kit/ns-heap

kit/ns-bus-event

kit/ns-standalone

kit/config-httpapi

kit/ns-file-3

kit/ns-session-3

kit/project-httpapi-reads

kit/ns-session

kit/ns-share

kit/ns-project

kit/ns-util-color

kit/ns-lsp

kit/ns-util-local-context

jlongster/sync-fenc

anthropic-fixes

feat/request-route-spans

kit/fs-search

kit/fs-tui-state

example-tui-plugin

cli-perf/tui-config

kit/fs-cli-io

kit/fs-plugin-npm

kit/llm-facade-cleanup

fix/snapshot-gitignored-index

kit/tui-facade-cleanup

kit/config-providers-httpapi-spike

kit/file-httpapi-spike

kit/workspace-httpapi-reads

nxl/mount-question-server

fix/session-prompt-permission-draft

fix-effect-context-bridges

followup-question-reply-inline

kit/fix-session-prompt-logger-interop

kit/question-httpapi-spike

kit/httpapi-route-inventory

kit/facade-session-prompt

jlongster/wip

nxl/fff-search-service

brendan/effect-env

kit/facade-project-20260413

kit/ripgrep-schema-source

kit/shell-job-service

fix/lsp-dead-root-prune

2.0

foo

facade/config

facade/lsp

facade/file

facade/provider

kit/ai-sdk-motel-bridge

oc-run

kit/e2e-seed-runtime-scope

brendan/electron-window-state

go-hero-banner-glm51-promo

snapshot-node-shim-stuff

fix/tui-session-diff-summary

oc-release-0.1.98

fix/snapshot-gitignore-respect

oc-basecode

worktree-agent-ab6ff98a

layered-deferred-comp

oc-startup

feat/tui-logo-radial-pulse

claude/effect-migration-review-Qyu6m

fix-anthropic-transform

kit/effect-sync-event

kit/effect-workspace

kit/eliminate-message-v2-roundtrips

worktree-agent-ab5855c0

kit/motel-session-telemetry

kit/tool-effect-multiedit

task-spec-executor-split

kit/tool-effect-invalid

worktree-feat+otel-bridge

kit/effect-native-tool-interrupt

jlongster/tui-workspaces-ux

kit/permission-flow-ux

nxl/deflake-webfetch-memory-test

npmcli-config

brendan/node-server-types

pr-21017

app/startup-splash

no-diff-virtualization

opencode/shiny-cactus

nxl/fix-diffs-header-sticky

nxl/shell-mode-tray

message-v3

opencode/gentle-pixel

oc-run-pinned

kit/prompt-abort-cleanup

opencode-suggest

rankings

copilot/research-opencode-server-plugin-api

kit/console-org-switcher

kit/ci-unit-reporting

figma-tokens

copilot/fix-spawn-error-windows

kit/dev-memory-observe

kit/remove-e2e-url-repro

effect-sync-event

effect/summary

pr-18308

worktree-audit-effect-services

test/processor-mock-server

fix/session-tool-metadata

opencode/glowing-tiger

claude/variant-popover-number-keys-gc6Bo

kit/format-child-process-spawner

jlongster/flaky-plugin-test

timeline-spacing-cleanup

feat/fff-search-tools

pr-18335

refactor/server-route-organization

jlongster/remove-workspace-server

kit/zen-stream-diagnostics

worktree-agent-a682f34a

spinner-concepts

openai-websocket

brendan-cli-codesign

brendan/cli-codesign

kit/windows-session-restore

opencode/cosmic-mountain

opencode/quick-orchid

perf/tool-memory

input-cleanup

opencode/sunny-comet

log-worktree-error-details

remove-context-tooltip-from-tab

tui-experimental-design

kit/effectify-command-review

brendan/better-session-id-handling

fix/lazy-facades

fix/insufferable-cycle-cyclone

kit/effectify-worktree

kit/effectify-tool-registry

kit/effectify-plugin

kit/effectify-pty

kit/effectify-command

kit/effectify-session-status

feat/auto-accept-permissions

kit/skill-lazy-init

fix-plugin-provider-behavior

fix/stale-running-session-ui

opencode-2-0

opencode/quiet-pixel

enterprise-lead-tracking

fix-e2e

kit/effect-bus

gitlab-version

add-model-reconciliation

jlongster/effectify-event-route

fix/zen-openai-response-usage

refactor/effect-pattern-migration

no-projects-empty-state

nexxeln/readme-small-tweak

test-branch

refactor/delete-scheduler

fix/shell-tab-shell-mode

effectify-skill

rhys/fast-mode-toggle

fix/flaky-question-dock-e2e

no-project-empty-state

fix/webkit-diff-viewer-crash

repro/watcher-als-bug

kit/repro-interrupted-text

startup

revert-17354-opencode/mighty-garden

move-status

perf/tui-session-history-cursor

effect-auth-foundation

console-subcommands

title-bar-cleanup

effect-log-compat

node-pty

fix/interrupt-idle-reason-poc

fix/interrupt-double-sound

opencode/proud-rocket

jlongster/automatic-session-routing

refactor/node-server-adapter

add-api-shape

node-build

jlongster/revert-sighup

fix/memory-tui-cache-listeners

auto-accept-permissions

pr-16286

default-explore-models

kit-pr

kit-pr-ahhhh

fix/16323-keyed-show-callbacks

feat/hashline-edit-experimental-v2

fix/git-fsmonitor-cleanup

snapshot-spawn-server-logs

implement-background-agents

opencode/happy-planet

fix/subagent-navigation-inline-click

go-page

fix/daytona-plugin-link-15976

opencode/hidden-orchid

tweaks

sidebar-fade-scroll

migrate-enterprise-to-nextjs

migrate-web-to-nextjs

migrate-app-to-nextjs

migrate-console-app-to-nextjs

fix/beta-stack-aware-sync

feature/tui-assistant-tokens-per-second

opencode/misty-falcon

snapshot-node-pty

update-stats

legal-req

commit-history

mhart/fix-cloning-slowness

chore/duplicate-issues-agent-dev

chore/duplicate-issues-agent

migrate-skill-discovery

migrate-mcp

migrate-config

optimize-apply-patch

temp

test-fields

brendan/nsis-vc-redistributables

chore-cleanup

feat/reference-agent

fix/attach-default-cwd

clean-modified-files

feat/discord-bot

v5-v6

feat/fff-file-search

snapshot-windows-desktop

fix-read-tool-for-webfetch

K-Mistele/dev

provider-optional-fields

feature/session-handoff

models-endpoint

opencode/sunny-harbor

utilize-family-in-dialog

review

tui-claude-style

rm-footer

fix/shiki-highlight-engine

fix/plugin-install-config

fix/plugin-install-location

feat/update-to-include-discord

git-slop-v2

docs-export

app/open-button

feature/workspace-domain

redesign-run-command

git-slop

opencode/clever-falcon

ripgrep-tree-paths

adjust-instructions-logic

fix-tool-ordering

workflow/publish-updates

chore-update-deps

feat/turborepo-caching

trigger-publish-on-beta

add-beta-branch-trigger

remove/nix-desktop-workflow

ci

fix-markdown-parsing

remove-highlights-template

update-to-add-learn-script

release-highlights-template

fixing-changelog-spacing

fixing-changelog-ui

fix-changelog-json

changelog-swr-caching

add-dynamic-agents-resolving

release-notes

fix/claude-pro-max-docs-warning

web-fixing-download-buton-on-changelog

fix/google-vertex-anthropic-thinking

sqlite

fix-azure-issue

desktop-poilsh-styles-ui-ux

desktop-shortcuts-panel

scheduler-module

apply-patch

cleanup-server-routes

fix-tool-outputs

fix-ai-message-issue

updated-black-page-performance

fix-black-page-view-transition-safari

update-design-subscriptions

fix-markdown-parser

fix/mcp-timeout

fix-id-issue

upgrade-bun

black-page-transitions-design-updates

official-copilot-plugin

plan-mode

read-plurals

cli-run-improvements

style-new-tips-layout

codex-auth

disable-auto-server

fix-model-dialog

fix-plugin-hook

feat/question-multiselect

new-toolbar-layout

feature/tui-sidebar-overlay

ui-improvements-some-animations

ask-question-tool

truncate-to-file

update-perms

truncation

snaphot-style-multiple-commands-input

experimental-mentions

queue-on-track

add-ignored

rename-repo-sst-to-anomalyco

permission-rework

ripgrep-tests

variants-docs

fix-custom-model-variants

read-global-claude-skills

changelog-updates

thinking-toggle-wip

style-current-todo

tui-shortcuts-panel

update-toggle-and-model-selection

small-screens

feature/skill-tool

feature/agent-skills

add-tests

llm-centralization

interleaved-fixes

interleaved-thinking

docs

sdk

bash-tweaks

provider-cleanup

fix-issue

blacksmith-migration-0ddfdb5

fix/cli-clean-exit-on-model-errors

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: anomalyco/opencode#8222

Documentation: Web Interface Client Interaction Architecture #8222

Overview

Architecture

Key Files

Message Handling

Sending Messages

Receiving Messages

Message Structure

Event Handling (Real-time Updates)

Event Stream Connection

Event Bus System

Message Events

Non-Message Event Handling

Todo Events

Question Events

Permission Events

Session Events

Status Events

Authentication

CORS Configuration

Client Implementation Pattern

Key Observations

Related Documentation

Update: Quota and Rate Limit Detection

How OpenCode Detects Quota/Rate Limit Errors

Detection Mechanism

Error Sources

Retry Logic with Exponential Backoff

Communication to Web Client

1. Session Status Event

2. Retry Part (Message History)

Client UI Handling Example

Web Client Implementation Pattern

Known Provider Error Patterns

REST API for Status Checking