Merge multiclient: fan a chat session out to every client and answer approvals exactly once

Every client watching a session receives every frame any client's turn produces,
a prompt from any client is accepted and serialised per session (queued behind
the in-flight turn, acknowledged as queued), user messages are attributed to the
sending device's label, and a pending approval is a shared exactly-once object:
the first answer wins, is recorded, is pushed to every watching client, and a
later answer is refused. Supersedes the per-session claim and the Busy
read-only state.
This commit is contained in:
2026-10-18 00:10:23 +01:00
27 changed files with 1795 additions and 457 deletions
@@ -1,5 +1,6 @@
package net.awan.pipelines.data
import android.os.Build
import java.util.UUID
import java.util.concurrent.ConcurrentHashMap
import kotlinx.coroutines.flow.SharedFlow
@@ -27,6 +28,17 @@ import net.awan.pipelines.data.transport.PipelinesClient
import net.awan.pipelines.data.transport.ProtocolException
import net.awan.pipelines.data.transport.ServerUrl
/**
* The default label this device reports: its model name, so other clients can
* attribute a message to "Pixel 9 Pro XL". A build without a usable model (or a
* local unit test where the framework stub has none) falls back to a generic
* label rather than sending a blank one.
*/
private fun defaultClientLabel(): String {
val model = runCatching { Build.MODEL }.getOrNull()?.trim().orEmpty()
return model.ifBlank { "Android device" }
}
/** Run history plus the server's aggregate usage statistics. */
data class RunHistory(val runs: List<RunSummary>, val usage: UsageStats?)
@@ -38,6 +50,13 @@ data class RunHistory(val runs: List<RunSummary>, val usage: UsageStats?)
class PipelinesRepository(
private val client: PipelinesClient,
private val settings: SettingsRepository,
/**
* The label this device sends with its prompts and approval answers, so every
* other client can attribute a user message to the device that sent it and see
* which device answered an approval. Defaults to the device model; injectable
* so a unit test does not depend on the build.
*/
val clientLabel: String = defaultClientLabel(),
) {
val connectionState = client.state
@@ -241,9 +260,9 @@ class PipelinesRepository(
// directly and never holds its credentials. ----
/**
* Lists the sessions this server owns, with the `busy` flag the phone renders
* read-only. The server already returns operator sessions only, so the app
* never filters this list by ownership.
* Lists the sessions this server owns. The server already returns operator
* sessions only, so the app never filters this list by ownership; a session is
* never marked read-only.
*/
suspend fun chatSessions(): List<ChatSession> =
client.call(Message(type = Protocol.CHAT_SESSIONS)).chatSessions ?: emptyList()
@@ -284,15 +303,29 @@ class PipelinesRepository(
}
/**
* Sends one prompt with its attached file URIs; the server echoes an ack and
* then pushes chat_event frames. The attachments travel only here, with the
* prompt the operator actually sent — never on their own.
* Attaches this connection to [sessionId]'s shared live stream, so it sees
* every frame any client's turn produces — the other devices' prompts and the
* turn's streaming output — and can answer a shared approval. Best-effort: an
* older server that does not know `chat_subscribe` simply answers an error
* frame, which the caller ignores while history still loads.
*/
suspend fun chatPrompt(sessionId: String, text: String, files: List<String> = emptyList()) {
suspend fun chatSubscribe(sessionId: String) {
if (sessionId.isBlank()) return
client.call(ChatProtocol.subscribeRequest(sessionId))
}
/**
* Sends one prompt with its attached file URIs; the server echoes an ack and
* then pushes chat_event frames. The prompt carries this device's label so the
* other clients can attribute it. The attachments travel only here, with the
* prompt the operator actually sent — never on their own. Returns true when the
* server queued the prompt behind an in-flight turn.
*/
suspend fun chatPrompt(sessionId: String, text: String, files: List<String> = emptyList()): Boolean {
if (sessionId.isBlank()) throw ProtocolException("Select a chat session first.")
val trimmed = text.trim()
if (trimmed.isEmpty()) throw ProtocolException("Enter a message before sending.")
client.call(ChatProtocol.promptRequest(sessionId, trimmed, files))
return client.call(ChatProtocol.promptRequest(sessionId, trimmed, files, clientLabel)).chatQueued
}
suspend fun chatInterrupt(sessionId: String) {
@@ -304,7 +337,7 @@ class PipelinesRepository(
if (sessionId.isBlank() || requestId.isBlank()) {
throw ProtocolException("A pending permission request is required.")
}
client.call(ChatProtocol.replyRequest(sessionId, requestId, decision, message))
client.call(ChatProtocol.replyRequest(sessionId, requestId, decision, message, clientLabel))
}
private fun requireConfigured() {
@@ -30,8 +30,8 @@ data class ChatSession(
@SerialName("created_at") val createdAt: Long = 0,
@SerialName("updated_at") val updatedAt: Long = 0,
// Another client holds the session, or the server itself owns it as an active
// run: the phone shows it read-only instead of letting two clients write the
// same conversation.
// run. Kept for wire compatibility; the server no longer sets it, and a
// session is never read-only for a client.
val busy: Boolean = false,
)
@@ -55,6 +55,10 @@ data class ChatPromptRequest(
val model: String = "",
val agent: String = "",
val files: List<String> = emptyList(),
// The sending device's human-readable label (a device name), so every other
// client can attribute the message; the server sanitises it and falls back to
// a generic label when it is blank.
val client: String = "",
)
/** One stored turn: a user turn is a single text part, an assistant turn holds text/reasoning/tool parts. */
@@ -66,6 +70,9 @@ data class ChatMessage(
val model: String = "",
val agent: String = "",
@SerialName("created_at") val createdAt: Long = 0,
// The sending device's label on a user turn the server echoed, so a resumed
// transcript still says who sent the message. Empty on an assistant turn.
val client: String = "",
val parts: List<ChatPart> = emptyList(),
)
@@ -138,6 +145,9 @@ data class ChatEventFrame(
val part: ChatPart? = null,
val step: ChatStep? = null,
val usage: ChatUsage? = null,
// The sending device's label on a `user` frame (another client's prompt), so
// the transcript can say who sent it. Empty on the agent's own frames.
val client: String = "",
)
@Serializable
@@ -174,6 +184,9 @@ data class ChatPermissionFrame(
val message: String = "",
val resolved: Boolean = false,
val decision: String = "",
// The label of the client whose answer resolved the request, so every other
// client can show which device answered.
@SerialName("resolved_by") val resolvedBy: String = "",
)
@Serializable
@@ -189,6 +202,8 @@ data class ChatReplyRequest(
@SerialName("request_id") val requestId: String = "",
val decision: String = "",
val message: String = "",
// The answering device's label, recorded with the resolution.
val client: String = "",
)
/** Chat part/kind/state/reply constants, mirroring `internal/protocol/chat.go`. */
@@ -207,6 +222,13 @@ object ChatProtocol {
const val EVENT_STEP = "step"
const val EVENT_USAGE = "usage"
/**
* A prompt another client sent, echoed live to this client so it appears in
* the transcript attributed to the sending device. The sender never receives
* its own frame (it already has the message locally).
*/
const val EVENT_USER = "user"
const val STEP_STARTED = "started"
const val STEP_ENDED = "ended"
@@ -241,10 +263,21 @@ object ChatProtocol {
* shape a text-only prompt has always sent). Built here (not inline in the
* repository) so production and its unit test share the one wire shape.
*/
fun promptRequest(sessionId: String, text: String, files: List<String> = emptyList()): Message =
fun promptRequest(sessionId: String, text: String, files: List<String> = emptyList(), client: String = ""): Message =
Message(
type = Protocol.CHAT_PROMPT,
chatPrompt = ChatPromptRequest(sessionId = sessionId, text = text, files = files),
chatPrompt = ChatPromptRequest(sessionId = sessionId, text = text, files = files, client = client),
)
/**
* The `chat_subscribe` frame that attaches this connection to [sessionId]'s
* shared live stream, so the client sees every frame any client's turn
* produces. Built here so production and its unit test share the one shape.
*/
fun subscribeRequest(sessionId: String): Message =
Message(
type = Protocol.CHAT_SUBSCRIBE,
chatSubscribe = ChatQuery(sessionId = sessionId),
)
/**
@@ -261,7 +294,7 @@ object ChatProtocol {
* inline in the repository) so the approval card's actions and their unit
* test share the one wire shape.
*/
fun replyRequest(sessionId: String, requestId: String, decision: String, message: String = ""): Message =
fun replyRequest(sessionId: String, requestId: String, decision: String, message: String = "", client: String = ""): Message =
Message(
type = Protocol.CHAT_REPLY,
chatReply = ChatReplyRequest(
@@ -269,6 +302,7 @@ object ChatProtocol {
requestId = requestId,
decision = decision,
message = message,
client = client,
),
)
}
@@ -68,6 +68,9 @@ object Protocol {
const val CHAT_MESSAGES = "chat_messages"
const val CHAT_INTERRUPT = "chat_interrupt"
const val CHAT_REPLY = "chat_reply"
// Attaches this connection to one session's shared live stream, so every
// client watching a session receives every frame any client's turn produces.
const val CHAT_SUBSCRIBE = "chat_subscribe"
// The operator's directory choices for a new chat (home first, then the
// directories of previous operator sessions, most recently used first).
const val CHAT_DIRECTORIES = "chat_directories"
@@ -676,6 +679,11 @@ data class Message(
@SerialName("chat_create") val chatCreate: ChatCreateRequest? = null,
@SerialName("chat_query") val chatQuery: ChatQuery? = null,
@SerialName("chat_prompt") val chatPrompt: ChatPromptRequest? = null,
// A chat_prompt response with this set was accepted into the session's queue
// because a turn is already in flight; the composer shows queued/steering
// instead of blocking input.
@SerialName("chat_queued") val chatQueued: Boolean = false,
@SerialName("chat_subscribe") val chatSubscribe: ChatQuery? = null,
@SerialName("chat_messages") val chatMessages: List<ChatMessage>? = null,
@SerialName("chat_event") val chatEvent: ChatEventFrame? = null,
@SerialName("chat_permission") val chatPermission: ChatPermissionFrame? = null,
@@ -1078,6 +1078,10 @@ class AppViewModel(
fun loadChatHistory(sessionId: String) {
viewModelScope.launch {
// Watch the session's shared stream so frames from any client's turn
// arrive live. Best-effort: an older server answers an error frame,
// which must not stop the history from loading.
runCatching { repository.chatSubscribe(sessionId) }
chatStore.historyLoading(sessionId)
try {
chatStore.history(sessionId, repository.chatMessages(sessionId, CHAT_HISTORY_LIMIT))
@@ -1107,7 +1111,11 @@ class AppViewModel(
chatStore.running(sessionId, true)
viewModelScope.launch {
try {
repository.chatPrompt(sessionId, text, attachmentFiles(attachments))
val queued = repository.chatPrompt(sessionId, text, attachmentFiles(attachments))
// The server accepted the prompt (queued or sent); a queued prompt
// is one waiting behind an in-flight turn, and the composer says so
// instead of blocking input.
chatStore.setQueued(sessionId, queued)
} catch (t: Throwable) {
if (t is CancellationException) throw t
val message = ErrorMessages.describe(t)
@@ -1115,6 +1123,7 @@ class AppViewModel(
chatStore.failed(sessionId, message)
chatStore.restoreAttachments(sessionId, attachments, message)
chatStore.running(sessionId, false)
chatStore.setQueued(sessionId, false)
}
}
}
@@ -51,9 +51,9 @@ internal fun ChatComposer(
}
Surface(color = MaterialTheme.colorScheme.surfaceContainer) {
Column(Modifier.fillMaxWidth().padding(CHAT_GUTTER)) {
if (thread.readOnly) {
if (thread.queued) {
Text(
text = "Another client holds this session; it is read-only here.",
text = "Queued — it will send when the current turn finishes.",
style = MaterialTheme.typography.bodySmall,
color = MaterialTheme.colorScheme.onSurfaceVariant,
modifier = Modifier.padding(bottom = CHAT_ITEM_GAP),
@@ -65,14 +65,12 @@ internal fun ChatComposer(
Row(verticalAlignment = Alignment.Bottom, horizontalArrangement = Arrangement.spacedBy(CHAT_COMPOSER_GAP)) {
IconButton(
onClick = { picker.launch(arrayOf("*/*")) },
enabled = !thread.readOnly,
) {
Icon(Icons.Default.AttachFile, contentDescription = "Attach file")
}
OutlinedTextField(
value = thread.draft,
onValueChange = onDraft,
enabled = !thread.readOnly,
placeholder = { Text("Message the agent…") },
minLines = 1,
maxLines = 6,
@@ -213,11 +213,7 @@ internal fun ChatConversationPane(
onRetry = { vm.loadChatHistory(thread.sessionId) },
)
thread.messages.isEmpty() && !thread.running && approval == null -> EmptyState(
message = if (thread.readOnly) {
"This chat is read-only while another client holds the session."
} else {
"This chat has no messages yet. Ask something below."
},
message = "This chat has no messages yet. Ask something below.",
)
else -> ChatTranscript(
thread = thread,
@@ -246,23 +246,17 @@ internal fun chatHeaderMeta(thread: ChatThread): String = listOfNotNull(
private const val OPERATOR_TAG_LABEL = "Operator"
/**
* The status a session row shows. A locally-running turn is reported as
* `Running`; otherwise the server's `busy` flag is `Busy · read-only` (another
* client holds it, so the composer is disabled), else `Idle`.
*
* This is the same precedence [ChatThread.readOnly] applies: a turn we started is
* `Running` and writable, never the read-only the server's own `busy` flag alone
* would imply.
* The status a session row shows: `Running` while this client has a turn in
* flight, else `Idle`. A session is never reported `Busy` or read-only because
* another client is watching it — the server fans the stream out and accepts a
* prompt from any client, so the session stays writable everywhere.
*/
internal fun sessionStatusLabel(session: ChatSession, runningLocally: Boolean): String =
sessionStatusLabel(session.busy, runningLocally)
sessionStatusLabel(runningLocally)
/** The status of a conversation from its own model flags (see [sessionStatusLabel]). */
internal fun sessionStatusLabel(busy: Boolean, runningLocally: Boolean): String = when {
runningLocally -> "Running"
busy -> "Busy · read-only"
else -> "Idle"
}
/** The status of a conversation from its own running flag (see [sessionStatusLabel]). */
internal fun sessionStatusLabel(runningLocally: Boolean): String =
if (runningLocally) "Running" else "Idle"
/**
* The activity a session row signals beyond its open/tag/directory state. An
@@ -304,7 +298,7 @@ internal data class ConversationHeader(
internal fun conversationHeader(thread: ChatThread): ConversationHeader = ConversationHeader(
title = sessionTitle(ChatSession(id = thread.sessionId, title = thread.title)),
kind = sessionTagLabel(thread.tag),
activity = sessionStatusLabel(thread.busy, thread.running),
activity = sessionStatusLabel(thread.running),
directory = thread.directory,
model = thread.model,
)
@@ -103,24 +103,26 @@ data class ChatThread(
* settle in place optimistically and survives a chat switch.
*/
val permissionAnswer: String = "",
/**
* The last prompt this client sent was accepted into the session's queue
* behind an in-flight turn (the server acknowledged it as queued), so the
* composer can say so instead of blocking. Cleared as soon as the turn's
* frames arrive or the thread settles.
*/
val queued: Boolean = false,
) {
/**
* Read-only while another client holds the session: the composer must never
* write to it. A turn we started ourselves keeps the session writable even
* though the server reports it busy (the server owns it as our active run),
* so the one rule here agrees with [sessionStatusLabel]'s `Running` case.
* At least one attachment is flagged; the prompt must not be sent with it.
*/
val readOnly: Boolean get() = busy && !running
/** At least one attachment is flagged; the prompt must not be sent with it. */
val hasAttachmentErrors: Boolean get() = attachments.any { it.error != null }
/**
* Whether the composer's send action is allowed. A message with a flagged
* attachment is never sent: the operator must remove or re-attach it first,
* so the file is never silently dropped.
* Whether the composer's send action is allowed. A session is never read-only:
* another client may watch the same conversation without blocking this one. A
* message with a flagged attachment is never sent, so the file is never
* silently dropped.
*/
val canSend: Boolean get() = !readOnly && draft.isNotBlank() && !hasAttachmentErrors
val canSend: Boolean get() = draft.isNotBlank() && !hasAttachmentErrors
/**
* Non-negative elapsed time of an in-flight turn at [nowMillis], or 0 once it
@@ -627,6 +629,13 @@ class ChatStore(
fun running(sessionId: String, running: Boolean) = update(sessionId) { setRunning(it, running) }
/**
* Records that the operator's last prompt was accepted into the session's
* queue (true) or sent immediately (false), so the composer can say "Queued"
* while it waits for the in-flight turn without blocking input.
*/
fun setQueued(sessionId: String, queued: Boolean) = update(sessionId) { it.copy(queued = queued) }
/**
* The stream resumed (the socket reconnected): every frame that was feeding an
* in-flight turn is gone, so no thread keeps claiming to run until a fresh
@@ -743,7 +752,11 @@ class ChatStore(
if (frame.sessionId.isBlank()) return
ensureThread(frame.sessionId)
markUnread(frame.sessionId)
// Any frame for the session means the turn has moved on, so a prompt we
// had queued is no longer waiting.
update(frame.sessionId) { if (it.queued) it.copy(queued = false) else it }
when (frame.kind) {
ChatProtocol.EVENT_USER -> applyRemoteUser(frame)
ChatProtocol.PART_TEXT, ChatProtocol.PART_REASONING -> applyDelta(frame)
ChatProtocol.PART_TOOL -> applyTool(frame)
ChatProtocol.EVENT_STEP -> {
@@ -754,6 +767,28 @@ class ChatStore(
}
}
/**
* Folds a user turn another client sent into the transcript, in place, once.
* The server never echoes this client's own prompts, so the sender's own
* message is never duplicated; the [ChatMessage.client] label says which
* device sent it.
*/
private fun applyRemoteUser(frame: ChatEventFrame) {
val text = frame.part?.text.orEmpty()
if (frame.messageId.isEmpty() || text.isEmpty()) return
update(frame.sessionId) { thread ->
if (thread.messages.any { it.id == frame.messageId }) return@update thread
val message = ChatMessage(
id = frame.messageId,
sessionId = frame.sessionId,
role = ChatProtocol.ROLE_USER,
client = frame.client,
parts = listOf(ChatPart(type = ChatProtocol.PART_TEXT, text = text)),
)
thread.copy(messages = thread.messages + message)
}
}
/**
* Creates a placeholder thread for a session that is not open, so a frame for
* a background chat is kept instead of dropped. A no-op when it already exists.
@@ -422,6 +422,16 @@ private fun MessageItem(
SelectionContainer {
Column(Modifier.padding(CHAT_GUTTER)) {
if (isUser) {
// A user turn another device sent is attributed to it, so
// the transcript says who sent the message. Our own
// messages carry no label.
if (message.client.isNotBlank()) {
Text(
text = message.client,
style = MaterialTheme.typography.labelSmall,
color = MaterialTheme.colorScheme.onSurfaceVariant,
)
}
UserParts(message.parts)
} else {
AssistantParts(
@@ -45,6 +45,45 @@ class ChatProtocolTest {
assertTrue(!sessions[1].busy)
}
@Test
fun chatMultiClientFieldsRoundTrip() {
// The client label the prompt carries, the queued acknowledgement, the
// subscribe request and the shared-answer fields of a permission frame.
val prompt = PipelinesJson.decodeFromString(
Message.serializer(),
"""{"type":"chat_prompt","chat_prompt":{"session_id":"ses_1","text":"hi","client":"Pixel 9 Pro XL"}}""",
)
assertEquals("Pixel 9 Pro XL", prompt.chatPrompt!!.client)
val ack = PipelinesJson.decodeFromString(
Message.serializer(),
"""{"type":"chat_prompt","id":"a1","chat_queued":true}""",
)
assertTrue(ack.chatQueued)
val subscribe = PipelinesJson.decodeFromString(
Message.serializer(),
"""{"type":"chat_subscribe","chat_subscribe":{"session_id":"ses_1"}}""",
)
assertEquals(Protocol.CHAT_SUBSCRIBE, subscribe.type)
assertEquals("ses_1", subscribe.chatSubscribe!!.sessionId)
val userFrame = PipelinesJson.decodeFromString(
Message.serializer(),
"""{"type":"chat_event","chat_event":{"session_id":"ses_1","message_id":"usr_1","kind":"user","client":"Pixel 10 Pro Fold","part":{"type":"text","text":"from the fold"}}}""",
)
assertEquals(ChatProtocol.EVENT_USER, userFrame.chatEvent!!.kind)
assertEquals("Pixel 10 Pro Fold", userFrame.chatEvent!!.client)
val resolved = PipelinesJson.decodeFromString(
Message.serializer(),
"""{"type":"chat_permission","chat_permission":{"session_id":"ses_1","request_id":"req_1","resolved":true,"decision":"once","resolved_by":"Pixel 9"}}""",
)
assertTrue(resolved.chatPermission!!.resolved)
assertEquals("once", resolved.chatPermission!!.decision)
assertEquals("Pixel 9", resolved.chatPermission!!.resolvedBy)
}
@Test
fun chatMessagesParseTextReasoningAndToolParts() {
val json = """
@@ -65,12 +65,11 @@ class ChatFormatTest {
}
@Test
fun sessionStatusReportsRunningBusyAndIdle() {
fun sessionStatusIsRunningOrIdleNeverReadOnly() {
assertEquals("Running", sessionStatusLabel(ChatSession(id = "s"), runningLocally = true))
assertEquals(
"Busy · read-only",
sessionStatusLabel(ChatSession(id = "s", busy = true), runningLocally = false),
)
// The server no longer marks a session Busy for another client, and a
// session is never read-only: the stale flag cannot produce that label.
assertEquals("Idle", sessionStatusLabel(ChatSession(id = "s", busy = true), runningLocally = false))
assertEquals("Idle", sessionStatusLabel(ChatSession(id = "s"), runningLocally = false))
}
@@ -113,19 +113,15 @@ class MultiChatStateTest {
}
@Test
fun busySessionIsReadOnlyAndCannotSend() {
fun busySessionStaysWritable() {
val store = ChatStore()
// Another client watching the session never makes it read-only: the
// server fans the stream out and accepts a prompt from any client.
store.open(session("a", busy = true))
store.draft("a", "unsent")
val thread = store.value.thread("a")!!
assertTrue(thread.readOnly)
assertFalse(thread.canSend)
// The server can clear busy later; the chat then becomes writable again.
store.sessionsLoaded(listOf(session("a", busy = false)))
store.draft("a", "unsent")
assertFalse(store.value.thread("a")!!.readOnly)
assertTrue(store.value.thread("a")!!.canSend)
assertTrue(thread.canSend)
assertTrue(thread.busy)
}
@Test
@@ -192,10 +188,9 @@ class MultiChatStateTest {
val store = ChatStore()
store.open(session("a", busy = true))
store.running("a", true)
// Our own turn keeps the session writable even though the server reports it busy.
// A turn in flight (ours or another client's) keeps the session writable.
store.draft("a", "next prompt")
val thread = store.value.thread("a")!!
assertFalse(thread.readOnly)
assertTrue(thread.canSend)
}
@@ -229,4 +224,78 @@ class MultiChatStateTest {
assertFalse(store.value.open.any { it.sessionId == "a" })
assertTrue(store.value.open.any { it.sessionId == "b" })
}
@Test
fun remoteUserFrameIsFoldedOnceAndAttributed() {
val store = ChatStore()
store.open(session("a"))
// The operator's own message, appended locally when sent.
store.appendLocalUserMessage("a", "mine")
// Another client's prompt arrives live, attributed to that device.
val frame = ChatEventFrame(
sessionId = "a",
messageId = "usr_7",
kind = ChatProtocol.EVENT_USER,
client = "Pixel 10 Pro Fold",
part = ChatPart(type = ChatProtocol.PART_TEXT, text = "from the fold"),
)
store.event(frame)
val messages = store.value.thread("a")!!.messages
assertEquals(2, messages.size)
assertEquals("mine", messages[0].parts.single().text)
assertEquals(ChatProtocol.ROLE_USER, messages[1].role)
assertEquals("Pixel 10 Pro Fold", messages[1].client)
assertEquals("from the fold", messages[1].parts.single().text)
// A replayed frame (e.g. after a reconnect) is folded once, not twice.
store.event(frame)
assertEquals(2, store.value.thread("a")!!.messages.size)
}
@Test
fun remoteAnswerClearsTheApprovalCard() {
val store = ChatStore()
store.open(session("a"))
store.permission(ChatPermissionFrame(sessionId = "a", requestId = "req_1", action = "bash"))
val open = approvalCard(store.value.thread("a")!!.permission, store.value.thread("a")!!.permissionAnswer)!!
assertTrue("the card is answerable while the request is open", open.actionable)
// Another client answered: the server pushes the resolved frame, which
// clears this client's card and shows the outcome without ever disabling
// it while the first answer was in flight.
store.permission(
ChatPermissionFrame(
sessionId = "a",
requestId = "req_1",
action = "bash",
resolved = true,
decision = ChatProtocol.DECISION_ONCE,
resolvedBy = "Pixel 9 Pro XL",
),
)
val thread = store.value.thread("a")!!
val cleared = approvalCard(thread.permission, thread.permissionAnswer)!!
assertFalse("a resolved request offers no controls", cleared.actionable)
assertEquals(ApprovalState.RESOLVED, cleared.state)
assertEquals(ChatProtocol.DECISION_ONCE, cleared.decision)
}
@Test
fun queuedPromptIsShownUntilTheTurnStreams() {
val store = ChatStore()
store.open(session("a"))
store.setQueued("a", true)
assertTrue(store.value.thread("a")!!.queued)
// The queued turn's first frame means it is running, so the marker clears.
store.event(
ChatEventFrame(
sessionId = "a",
messageId = "m1",
kind = ChatProtocol.PART_TEXT,
delta = "hi",
part = ChatPart(type = ChatProtocol.PART_TEXT, id = "m1#0"),
),
)
assertFalse(store.value.thread("a")!!.queued)
}
}
+27 -5
View File
@@ -304,12 +304,31 @@ The brokered OpenCode chat exposes the operator's own sessions, separate from th
sessions pipeline runs create. The protocol types are:
- `chat_sessions` lists the operator's own sessions only, ordered
most-recently-used first. Each carries its `directory`, its `tag`, its `busy`
state (another connection currently holds it) and its recency. A session with
most-recently-used first. Each carries its `directory`, its `tag` and its
recency. A session with
no recorded tag is never listed, and no pipeline stage session is ever listed:
stage sessions are still recorded in `run_steps`/`run_session_owners`
for the run that owns them. The list is fail-closed: with no registry and no
store it returns an empty list, never the endpoint's whole session list.
store it returns an empty list, never the endpoint's whole session list. A
session is never marked `busy`: any number of clients may watch and write one.
- `chat_subscribe` attaches a connection to one session's shared live stream (body
`session_id`) and replays the session's still-pending approval requests, so every
client that watches a session sees every frame any client's turn produces — the
other devices' prompts and the turn's streaming output — and can answer a shared
approval. Attaching is idempotent per connection; the subscription is released
when the connection ends.
- `chat_prompt` may come from any client. A prompt whose session already has a turn
in flight is accepted into that session's bounded queue (currently 8) and
acknowledged with `chat_queued: true`; the agent never receives two interleaved
turns. The prompt is echoed to the other watching clients as a `chat_event` of
kind `user`, carried with the sender's `client` label (a device name), while the
sender's own transcript keeps its local copy.
- `chat_reply` is exactly-once: the first answer to a pending request wins, is
recorded with the answering client's label and is pushed back to every watching
client as the same `chat_permission` frame with `resolved: true`, `decision` and
`resolved_by`, so each card clears and shows the outcome. A later answer is
refused as already answered (naming the client that won), never silently ignored
and never delivered to the agent twice.
- `chat_create` takes a `title` (default "New chat") and a `directory`
(default `~`, the operator's home; `~`, an omitted or empty value and a `~/...`
value all resolve to the home directory). A relative or missing directory is
@@ -357,8 +376,11 @@ password file as a reference).
The stored tag is exactly `operator`; the display label `Operator` is derived from
it, so there is no second tag vocabulary. Chat uses the server's one OpenCode
transport, and every existing chat guarantee (retained-state bounds, the
permission/approval flow, interruption, one broker call per list) is unchanged.
transport. A session's stream is fanned out to every client watching it, prompts
are serialised per session (queued behind the in-flight turn rather than
rejected), and approvals are shared and exactly-once; the retained-state bounds,
the resync-on-reconnect path, the exclusion of a run's own session and
per-connection write serialisation are unchanged.
The operator-session registry, filter, directory defaulting and the list bound are
covered by the `pipeline`, `opencode` and `server` unit tests. The live end-to-end
+48 -14
View File
@@ -26,6 +26,13 @@ const (
ChatMessages = "chat_messages"
ChatInterrupt = "chat_interrupt"
ChatReply = "chat_reply"
// ChatSubscribe attaches a connection to one session's shared live stream so
// it receives every frame any client's turn produces (its own and the other
// devices'), not only the frames of a turn it prompted itself. Any number of
// clients may watch one session; the session is never read-only. The request
// body is a ChatQuery naming the session and the response echoes the request
// id once the subscription is attached.
ChatSubscribe = "chat_subscribe"
// ChatDirectories is the request/response type for the operator's directory
// choices: the home directory plus the directories of previous operator
// sessions, most recently used first, deduplicated and bounded. It is a
@@ -49,13 +56,16 @@ const (
)
// ChatEvent.Kind values pushed on the chat_event stream. Step and usage carry
// no ChatPart; they report turn progress and the turn's totals.
// no ChatPart; they report turn progress and the turn's totals. User carries the
// text of a prompt another client sent, so a transcript can show it live; it is
// never sent back to the client that sent the prompt.
const (
ChatEventText = ChatPartText
ChatEventReasoning = ChatPartReasoning
ChatEventTool = ChatPartTool
ChatEventStep = "step"
ChatEventUsage = "usage"
ChatEventUser = "user"
)
// ChatStep.Status values, mirroring the OpenCode session.step events.
@@ -111,10 +121,11 @@ type ChatSession struct {
Tag string `json:"tag,omitempty"`
CreatedAt int64 `json:"created_at,omitempty"`
UpdatedAt int64 `json:"updated_at,omitempty"`
// Busy marks a session another client currently holds (or one the server
// itself owns as an active run), so the phone can show it read-only instead
// of letting two clients silently write the same conversation. It is
// additive and optional: older peers ignore it.
// Busy is retained for wire compatibility only: it is never set by this
// server. A session is never read-only, any number of clients may watch and
// write it, and only a turn is serialised (a waiting prompt is acknowledged
// as queued on its own client instead of marking the session Busy). Older
// peers still parse the field; newer ones ignore it.
Busy bool `json:"busy,omitempty"`
}
@@ -144,26 +155,34 @@ type ChatQuery struct {
// ChatPromptRequest is the chat_prompt request body: the text to send, with an
// optional model/agent override and attached file URIs. The matching response is
// the inbox envelope, which the server folds into a ChatMessage.
// the inbox envelope, which the server folds into a ChatMessage. Client is the
// sending device's human-readable label so every other client can attribute the
// message; the server sanitises it and falls back to a generic label when it is
// blank.
type ChatPromptRequest struct {
SessionID string `json:"session_id"`
Text string `json:"text"`
Model string `json:"model,omitempty"`
Agent string `json:"agent,omitempty"`
Files []string `json:"files,omitempty"`
Client string `json:"client,omitempty"`
}
// ChatMessage is one stored turn returned by chat_messages. A user turn is a
// single text part; an assistant turn holds the text, reasoning and tool parts
// the phone renders. Parts corresponds to the OpenCode content array.
type ChatMessage struct {
ID string `json:"id"`
SessionID string `json:"session_id"`
Role string `json:"role"`
Model string `json:"model,omitempty"`
Agent string `json:"agent,omitempty"`
CreatedAt int64 `json:"created_at,omitempty"`
Parts []ChatPart `json:"parts"`
ID string `json:"id"`
SessionID string `json:"session_id"`
Role string `json:"role"`
Model string `json:"model,omitempty"`
Agent string `json:"agent,omitempty"`
CreatedAt int64 `json:"created_at,omitempty"`
// Client is the sending device's label on a user turn the server echoed, so a
// resumed transcript still says who sent the message. It is empty on an
// assistant turn.
Client string `json:"client,omitempty"`
Parts []ChatPart `json:"parts"`
}
// ChatPart is one element of a ChatMessage. Type selects the meaning: text and
@@ -225,6 +244,9 @@ type ChatEventFrame struct {
Part *ChatPart `json:"part,omitempty"`
Step *ChatStep `json:"step,omitempty"`
Usage *ChatUsage `json:"usage,omitempty"`
// Client is the sending device's label on a user frame (ChatEventUser), so a
// transcript can say who sent the message. It is empty on assistant frames.
Client string `json:"client,omitempty"`
}
// ChatStep is a progress marker for the current step of a turn.
@@ -258,6 +280,15 @@ type ChatPermissionFrame struct {
Metadata map[string]any `json:"metadata,omitempty"`
Source *ChatPermissionSource `json:"source,omitempty"`
Message string `json:"message,omitempty"`
// Resolved, Decision and ResolvedBy report the shared, exactly-once outcome
// of a request any client may answer: once the first answer is recorded the
// server pushes the same frame back to every watching client with Resolved
// set, the Decision it recorded and the label of the client that gave it, so
// their cards clear and show the outcome instead of offering a stale choice.
// They are empty on a still-pending request.
Resolved bool `json:"resolved,omitempty"`
Decision string `json:"decision,omitempty"`
ResolvedBy string `json:"resolved_by,omitempty"`
}
// ChatPermissionSource identifies what raised a permission request, matching the
@@ -271,10 +302,13 @@ type ChatPermissionSource struct {
// ChatReplyRequest is the chat_reply request body: the phone's decision on a
// pending permission request, mirroring
// POST /api/session/{id}/permission/{requestID}/reply.
// POST /api/session/{id}/permission/{requestID}/reply. Client is the answering
// device's label, recorded with the resolution so every other client can see
// which device answered.
type ChatReplyRequest struct {
SessionID string `json:"session_id"`
RequestID string `json:"request_id"`
Decision string `json:"decision"`
Message string `json:"message,omitempty"`
Client string `json:"client,omitempty"`
}
+12 -2
View File
@@ -25,7 +25,13 @@ func chatSamples() []struct {
{"create", ChatCreateRequest{Title: "demo", Directory: "/work"}},
{"adopt", ChatAdoptRequest{SessionID: "ses_1"}},
{"query", ChatQuery{SessionID: "ses_1", Limit: 50}},
{"prompt", ChatPromptRequest{SessionID: "ses_1", Text: "hello", Model: "m", Agent: "build", Files: []string{"file:///tmp/a.png"}}},
{"prompt", ChatPromptRequest{SessionID: "ses_1", Text: "hello", Model: "m", Agent: "build", Files: []string{"file:///tmp/a.png"}, Client: "Pixel 9 Pro XL"}},
{"prompt_queued_ack", Message{Type: ChatPrompt, ID: "a1", ChatQueued: true}},
{"subscribe", ChatQuery{SessionID: "ses_1"}},
{"event_user", ChatEventFrame{
SessionID: "ses_1", MessageID: "usr_1", Kind: ChatEventUser, Client: "Pixel 10 Pro Fold",
Part: &ChatPart{Type: ChatPartText, ID: "usr", Text: "from the fold"},
}},
{"message", ChatMessage{
ID: "msg_1", SessionID: "ses_1", Role: ChatRoleAssistant, Model: "m", Agent: "build", CreatedAt: 1792112366711,
Parts: []ChatPart{
@@ -64,7 +70,11 @@ func chatSamples() []struct {
Source: &ChatPermissionSource{Type: "tool", MessageID: "msg_1", ID: "call_1"},
Message: "wants to run a command",
}},
{"reply", ChatReplyRequest{SessionID: "ses_1", RequestID: "req_1", Decision: ChatDecisionOnce, Message: "ok"}},
{"permission_resolved", ChatPermissionFrame{
SessionID: "ses_1", RequestID: "per_1", Action: "bash",
Resolved: true, Decision: ChatDecisionOnce, ResolvedBy: "Pixel 9 Pro XL",
}},
{"reply", ChatReplyRequest{SessionID: "ses_1", RequestID: "req_1", Decision: ChatDecisionOnce, Message: "ok", Client: "Pixel 9 Pro XL"}},
}
}
+6
View File
@@ -166,6 +166,12 @@ type Message struct {
ChatEvent *ChatEventFrame `json:"chat_event,omitempty"`
ChatPermission *ChatPermissionFrame `json:"chat_permission,omitempty"`
ChatReply *ChatReplyRequest `json:"chat_reply,omitempty"`
// ChatSubscribe attaches this connection to one session's shared stream; the
// body names the session like ChatQuery. A chat_prompt response sets
// ChatQueued when the prompt had to wait for an in-flight turn and was
// accepted into the session's queue instead of being sent immediately.
ChatSubscribe *ChatQuery `json:"chat_subscribe,omitempty"`
ChatQueued bool `json:"chat_queued,omitempty"`
// ChatDirectories carries the operator's directory choices on a
// chat_directories response (home first, then recent operator-session
// directories, deduplicated and bounded). Additive/omitempty so older peers
+8 -5
View File
@@ -46,10 +46,10 @@ type operatorRegistry interface {
OperatorDirectories(ctx context.Context, limit int) ([]string, error)
}
// chatClientToken returns an unguessable per-connection identity. It attributes
// a session claim so two clients on the same server cannot silently write the
// same conversation; a fresh token per connection means a reconnected client is
// a new writer and must re-claim.
// chatClientToken returns an unguessable per-connection identity. Its only role
// is to key a connection's chat-room subscriptions and to exclude the sender from
// its own fan-out; it carries no ownership. A fresh token per connection means a
// reconnected client is a new identity and simply reattaches.
func chatClientToken() string {
var b [8]byte
if _, err := rand.Read(b[:]); err != nil {
@@ -68,6 +68,9 @@ func handleChat(ctx context.Context, request protocol.Message, broker chatBroker
case protocol.ChatPrompt:
handleChatPrompt(ctx, request, broker, hub, registry, clientID, write)
return true
case protocol.ChatSubscribe:
handleChatSubscribe(request, broker, hub, clientID, write)
return true
case protocol.ChatMessages:
handleChatMessages(ctx, request, broker, hub, write)
return true
@@ -78,7 +81,7 @@ func handleChat(ctx context.Context, request protocol.Message, broker chatBroker
handleChatSimple(ctx, request, broker, hub, write)
return true
case protocol.ChatSessions:
handleChatSessions(ctx, request, broker, hub, registry, clientID, write)
handleChatSessions(ctx, request, broker, hub, registry, write)
return true
case protocol.ChatCreate:
handleChatCreate(ctx, request, broker, registry, write)
-65
View File
@@ -1,65 +0,0 @@
package server
// claim reserves sessionID for clientID. It reports true when the session is
// free or already held by the same client (so a client may re-prompt its own
// session) and false when another client holds it. The claim map is bounded by
// chatMaxTurns with oldest-eviction so a stuck client cannot grow it without
// limit.
func (h *chatHub) claim(sessionID, clientID string) bool {
if sessionID == "" || clientID == "" {
return false
}
h.mu.Lock()
defer h.mu.Unlock()
if h.claims == nil {
h.claims = map[string]string{}
}
if holder, ok := h.claims[sessionID]; ok {
return holder == clientID
}
h.evictClaimsLocked()
h.claims[sessionID] = clientID
h.claimOrder = append(h.claimOrder, sessionID)
return true
}
// release drops the same client's claim on sessionID; a claim held by a
// different client is left untouched so a stale release cannot free a live one.
func (h *chatHub) release(sessionID, clientID string) {
h.mu.Lock()
defer h.mu.Unlock()
if holder, ok := h.claims[sessionID]; !ok || holder != clientID {
return
}
delete(h.claims, sessionID)
for i, id := range h.claimOrder {
if id == sessionID {
h.claimOrder = append(h.claimOrder[:i], h.claimOrder[i+1:]...)
break
}
}
}
// busyForOther reports whether another client currently holds sessionID.
func (h *chatHub) busyForOther(sessionID, clientID string) bool {
h.mu.Lock()
defer h.mu.Unlock()
holder, ok := h.claims[sessionID]
return ok && holder != clientID
}
// evictClaimsLocked drops the oldest claim when the cap is reached, keeping the
// claim map bounded like the retained turns. Callers must hold h.mu.
func (h *chatHub) evictClaimsLocked() {
if len(h.claims) < chatMaxTurns {
return
}
for len(h.claimOrder) > 0 {
oldest := h.claimOrder[0]
h.claimOrder = h.claimOrder[1:]
if _, ok := h.claims[oldest]; ok {
delete(h.claims, oldest)
return
}
}
}
+18
View File
@@ -68,9 +68,27 @@ func handleChatSimple(ctx context.Context, request protocol.Message, broker chat
_ = write(protocol.Message{Type: protocol.Error, ID: request.ID, Error: "a valid permission decision is required"})
return
}
// A pending approval is shared and exactly-once: the first answer wins and is
// recorded with the client that gave it, and a later answer is refused as
// already answered rather than reaching the agent twice.
label := sanitizeChatClientLabel(reply.Client)
if hub != nil {
if prior, ok := hub.reservePermission(reply.SessionID, reply.RequestID, label); !ok {
_ = write(protocol.Message{Type: protocol.Error, ID: request.ID, Error: permissionRefusal(prior, reply.RequestID)})
return
}
}
if err := broker.Reply(ctx, *reply); err != nil {
if hub != nil {
hub.releasePermission(reply.SessionID, reply.RequestID)
}
_ = write(protocol.Message{Type: protocol.Error, ID: request.ID, Error: err.Error()})
return
}
_ = write(protocol.Message{Type: protocol.ChatReply, ID: request.ID})
if hub != nil {
// Push the resolution to every client watching the session so each card
// clears and shows the outcome and which device answered.
hub.confirmPermission(reply.SessionID, reply.RequestID, label, reply.Decision)
}
}
+73 -15
View File
@@ -1,7 +1,9 @@
package server
import (
"context"
"log"
"strconv"
"sync"
"time"
@@ -22,15 +24,18 @@ const chatMaxTurns = 128
// chatHub retains the accumulated turn state per session, independently of any
// single connection, so a reconnecting client can re-sync what it missed. State
// is keyed by session and then by message id (a session holds many turns), and
// is capped at chatRetainedLimit.
// is capped at chatRetainedLimit. It also owns the per-session live rooms: the
// one broker stream, the prompt queue and the fan-out to every attached client.
type chatHub struct {
mu sync.Mutex
turns map[string]*chatTurn
now func() time.Time
// claims maps a session to the client currently writing it so a second
// client is rejected; claimOrder bounds the map like chatMaxTurns.
claims map[string]string
claimOrder []string
mu sync.Mutex
turns map[string]*chatTurn
rooms map[string]*chatRoom
baseCtx context.Context
registry operatorRegistry
now func() time.Time
// userSeq is a monotonic source of ids for the user turns the server echoes
// to the other clients, so each retained user message has a stable id.
userSeq int
}
// chatPart is the retained form of one part. Text and reasoning deltas append to
@@ -40,12 +45,16 @@ type chatPart struct {
text []byte
}
// chatMessage is one retained assistant turn. Its parts keep the exact ids the
// supporting chat_event frames carried, so a resume preserves attribution.
// chatMessage is one retained turn. Its parts keep the exact ids the supporting
// chat_event frames carried, so a resume preserves attribution. Role and client
// are carried for a user turn the server echoed (a prompt another client sent),
// so a resumed transcript still says who sent it.
type chatMessage struct {
id string
order []string
parts map[string]*chatPart
id string
role string
client string
order []string
parts map[string]*chatPart
}
type chatTurn struct {
@@ -62,10 +71,33 @@ type chatTurn struct {
// bounds it to chatPermissionRetainedLimit.
permissions map[string]struct{}
permissionOrder []string
// resolutions records the shared exactly-once answers to permission requests,
// keyed by request id, so a second answer is refused and the recorded outcome
// survives the clients that gave it; resolutionOrder bounds it to
// chatPermissionRetainedLimit like the dedup set above.
resolutions map[string]*chatResolution
resolutionOrder []string
}
// chatResolution is the shared answer to one permission request. answered is
// false while the first answer is still being delivered to the agent, so a
// concurrent second answer is refused without ever reaching the agent twice.
type chatResolution struct {
client string
decision string
answered bool
}
func newChatHub() *chatHub {
return &chatHub{turns: map[string]*chatTurn{}, now: time.Now}
return &chatHub{turns: map[string]*chatTurn{}, rooms: map[string]*chatRoom{}, baseCtx: context.Background(), now: time.Now}
}
// nextUserMessageID mints a stable id for one echoed user turn.
func (h *chatHub) nextUserMessageID() string {
h.mu.Lock()
defer h.mu.Unlock()
h.userSeq++
return "usr_" + strconv.Itoa(h.userSeq)
}
func (h *chatHub) clock() time.Time {
@@ -100,11 +132,33 @@ func (h *chatHub) apply(frame protocol.ChatEventFrame) {
}
message := turn.messages[frame.MessageID]
if message == nil {
message = &chatMessage{id: frame.MessageID, parts: map[string]*chatPart{}}
role := protocol.ChatRoleAssistant
client := ""
if frame.Kind == protocol.ChatEventUser {
role = protocol.ChatRoleUser
client = frame.Client
}
message = &chatMessage{id: frame.MessageID, role: role, client: client, parts: map[string]*chatPart{}}
turn.order = append(turn.order, frame.MessageID)
turn.messages[frame.MessageID] = message
} else if message.client == "" && frame.Kind == protocol.ChatEventUser {
message.client = frame.Client
}
switch frame.Kind {
case protocol.ChatEventUser:
if frame.Part == nil || frame.Part.ID == "" || frame.Part.Text == "" || turn.overflow {
return
}
if !turn.retain(len(frame.Part.Text)) {
return
}
part, ok := message.parts[frame.Part.ID]
if !ok {
part = &chatPart{part: protocol.ChatPart{Type: protocol.ChatPartText, ID: frame.Part.ID}}
message.order = append(message.order, frame.Part.ID)
message.parts[frame.Part.ID] = part
}
part.text = append(part.text, frame.Part.Text...)
case protocol.ChatEventText, protocol.ChatEventReasoning:
id := ""
if frame.Part != nil {
@@ -255,6 +309,10 @@ func (h *chatHub) snapshot(sessionID string) []protocol.ChatMessage {
continue
}
out := protocol.ChatMessage{ID: id, SessionID: sessionID, Role: protocol.ChatRoleAssistant}
if message.role != "" {
out.Role = message.role
}
out.Client = message.client
for _, partID := range message.order {
if part, ok := message.parts[partID]; ok {
piece := part.part
+472
View File
@@ -0,0 +1,472 @@
package server
import (
"context"
"errors"
"net/http/httptest"
"strings"
"sync"
"testing"
"time"
"github.com/coder/websocket"
"github.com/coder/websocket/wsjson"
"git.a-wan.net/alan/pipelines/internal/protocol"
)
// channelChat is a broker whose stream is driven frame-by-frame from a channel,
// so a test can hold a turn in flight and prove prompt serialisation, fan-out and
// exactly-once approval behaviour without a real OpenCode service.
type channelChat struct {
mu sync.Mutex
prompts []string
perm []protocol.ChatPermissionFrame
replies []protocol.ChatReplyRequest
frames chan protocol.ChatEventFrame
ready chan struct{}
once sync.Once
// promptErrAt, when nonzero, is the 1-based index of the Prompt call that
// fails, so a test can prove a broker failure is reported to the client that
// sent the prompt.
promptErrAt int
}
func newChannelChat() *channelChat {
return &channelChat{frames: make(chan protocol.ChatEventFrame, 32), ready: make(chan struct{})}
}
func (c *channelChat) Prompt(_ context.Context, _, text string) error {
c.mu.Lock()
c.prompts = append(c.prompts, text)
fail := c.promptErrAt != 0 && len(c.prompts) == c.promptErrAt
c.mu.Unlock()
if fail {
return errors.New("broker rejected the prompt")
}
return nil
}
func (c *channelChat) Stream(ctx context.Context, _ string, ready func(), emit func(protocol.ChatEventFrame) error) error {
c.once.Do(func() {
close(c.ready)
if ready != nil {
ready()
}
})
for {
select {
case <-ctx.Done():
return ctx.Err()
case frame := <-c.frames:
if err := emit(frame); err != nil {
return err
}
}
}
}
func (c *channelChat) Interrupt(context.Context, string) error { return nil }
func (c *channelChat) Messages(context.Context, string, int) ([]protocol.ChatMessage, error) {
return nil, nil
}
func (c *channelChat) Sessions(context.Context) ([]protocol.ChatSession, error) { return nil, nil }
func (c *channelChat) Create(_ context.Context, title, directory string) (protocol.ChatSession, error) {
return protocol.ChatSession{ID: "ses_created", Title: title, Directory: directory}, nil
}
func (c *channelChat) Session(context.Context, string) (protocol.ChatSession, bool, error) {
return protocol.ChatSession{}, false, nil
}
func (c *channelChat) Permissions(context.Context, string) ([]protocol.ChatPermissionFrame, error) {
c.mu.Lock()
defer c.mu.Unlock()
return append([]protocol.ChatPermissionFrame(nil), c.perm...), nil
}
func (c *channelChat) Reply(_ context.Context, request protocol.ChatReplyRequest) error {
c.mu.Lock()
c.replies = append(c.replies, request)
c.mu.Unlock()
return nil
}
func (c *channelChat) push(frame protocol.ChatEventFrame) {
c.frames <- frame
}
func (c *channelChat) promptCount() int {
c.mu.Lock()
defer c.mu.Unlock()
return len(c.prompts)
}
func (c *channelChat) promptTexts() []string {
c.mu.Lock()
defer c.mu.Unlock()
return append([]string(nil), c.prompts...)
}
func (c *channelChat) replyCount() int {
c.mu.Lock()
defer c.mu.Unlock()
return len(c.replies)
}
// dialChatServer starts one server and dials n connections, returning the server
// so a test can reconnect a dropped client to the same hub.
func dialChatServer(t *testing.T, options Options, n int) (context.Context, context.CancelFunc, *httptest.Server, []*websocket.Conn) {
t.Helper()
ctx, cancel := context.WithTimeout(context.Background(), 15*time.Second)
srv := httptest.NewServer(HandlerWithOptions(ctx, options))
t.Cleanup(func() { srv.Close(); cancel() })
conns := make([]*websocket.Conn, 0, n)
for i := 0; i < n; i++ {
conns = append(conns, dialChatConn(t, ctx, srv))
}
return ctx, cancel, srv, conns
}
func dialChatConn(t *testing.T, ctx context.Context, srv *httptest.Server) *websocket.Conn {
t.Helper()
conn, _, err := websocket.Dial(ctx, "ws"+strings.TrimPrefix(srv.URL, "http")+"/connect", nil)
if err != nil {
t.Fatal(err)
}
t.Cleanup(func() { conn.CloseNow() })
return conn
}
// readUntil reads messages until one of type want arrives, failing on a server
// error frame; interleaved push frames are skipped.
func readUntil(t *testing.T, ctx context.Context, conn *websocket.Conn, want string) protocol.Message {
t.Helper()
for {
var message protocol.Message
if err := wsjson.Read(ctx, conn, &message); err != nil {
t.Fatalf("read (waiting for %s): %v", want, err)
}
if message.Type == protocol.Error {
t.Fatalf("server error frame while waiting for %s: %s", want, message.Error)
}
if message.Type == want {
return message
}
}
}
// nextEvent reads the next chat_event frame strictly, so a test can assert the
// order of the turn's frames.
func nextEvent(t *testing.T, ctx context.Context, conn *websocket.Conn) protocol.ChatEventFrame {
t.Helper()
for {
var message protocol.Message
if err := wsjson.Read(ctx, conn, &message); err != nil {
t.Fatalf("read event: %v", err)
}
if message.Type == protocol.Error {
t.Fatalf("server error frame: %s", message.Error)
}
if message.Type == protocol.ChatEvent && message.ChatEvent != nil {
return *message.ChatEvent
}
}
}
// nextPermission reads the next chat_permission frame for requestID.
func nextPermission(t *testing.T, ctx context.Context, conn *websocket.Conn, requestID string) protocol.ChatPermissionFrame {
t.Helper()
for {
var message protocol.Message
if err := wsjson.Read(ctx, conn, &message); err != nil {
t.Fatalf("read permission: %v", err)
}
if message.Type == protocol.Error {
t.Fatalf("server error frame: %s", message.Error)
}
if message.Type == protocol.ChatPermission && message.ChatPermission != nil && message.ChatPermission.RequestID == requestID {
return *message.ChatPermission
}
}
}
func writeChat(t *testing.T, ctx context.Context, conn *websocket.Conn, message protocol.Message) {
t.Helper()
if err := wsjson.Write(ctx, conn, message); err != nil {
t.Fatal(err)
}
}
// TestChatFanoutToSeveralClients is the multi-client acceptance test: a prompt
// from one client is accepted, its user turn is pushed live to the other client
// attributed to the sending device, and the turn's streaming frames reach every
// watching client, not only the one that prompted.
func TestChatFanoutToSeveralClients(t *testing.T) {
broker := newChannelChat()
ctx, _, _, conns := dialChatServer(t, Options{Chat: broker}, 2)
phone, tablet := conns[0], conns[1]
// The tablet watches the session before anything is sent.
writeChat(t, ctx, tablet, protocol.Message{Type: protocol.ChatSubscribe, ID: "s1", ChatSubscribe: &protocol.ChatQuery{SessionID: "ses_1"}})
readUntil(t, ctx, tablet, protocol.ChatSubscribe)
// The phone prompts. Its ack is not a queue acknowledgement.
writeChat(t, ctx, phone, protocol.Message{Type: protocol.ChatPrompt, ID: "p1", ChatPrompt: &protocol.ChatPromptRequest{SessionID: "ses_1", Text: "from the phone", Client: "Pixel 9"}})
ack := readUntil(t, ctx, phone, protocol.ChatPrompt)
if ack.ID != "p1" || ack.ChatQueued {
t.Fatalf("phone prompt ack = %+v, want accepted (not queued)", ack)
}
// The tablet sees the phone's message, attributed to the phone.
userFrame := nextEvent(t, ctx, tablet)
if userFrame.Kind != protocol.ChatEventUser || userFrame.Client != "Pixel 9" || userFrame.Part == nil || userFrame.Part.Text != "from the phone" {
t.Fatalf("tablet user frame = %+v, want the phone's message attributed to Pixel 9", userFrame)
}
// The turn's streaming output reaches both clients in order.
broker.push(protocol.ChatEventFrame{SessionID: "ses_1", MessageID: "msg_1", Kind: protocol.ChatEventText, Delta: "hel", Part: &protocol.ChatPart{Type: protocol.ChatPartText, ID: "msg_1#0"}})
broker.push(protocol.ChatEventFrame{SessionID: "ses_1", MessageID: "msg_1", Kind: protocol.ChatEventText, Delta: "lo", Part: &protocol.ChatPart{Type: protocol.ChatPartText, ID: "msg_1#0"}})
broker.push(protocol.ChatEventFrame{SessionID: "ses_1", MessageID: "msg_1", Kind: protocol.ChatEventStep, Step: &protocol.ChatStep{Status: protocol.ChatStepEnded, Index: 1}})
for _, client := range []struct {
name string
conn *websocket.Conn
}{{"phone", phone}, {"tablet", tablet}} {
var text strings.Builder
for i := 0; i < 2; i++ {
frame := nextEvent(t, ctx, client.conn)
if frame.Kind != protocol.ChatEventText {
t.Fatalf("%s frame %d = %+v, want text", client.name, i, frame)
}
text.WriteString(frame.Delta)
}
if text.String() != "hello" {
t.Fatalf("%s saw %q, want the streamed turn output", client.name, text.String())
}
if end := nextEvent(t, ctx, client.conn); end.Kind != protocol.ChatEventStep || end.Step == nil || end.Step.Status != protocol.ChatStepEnded {
t.Fatalf("%s step frame = %+v, want ended", client.name, end)
}
}
}
// TestChatPromptSerialisedPerSession pins that two prompts for one session never
// interleave: the second is accepted as queued and only posted once the first
// turn ends.
func TestChatPromptSerialisedPerSession(t *testing.T) {
broker := newChannelChat()
ctx, _, _, conns := dialChatServer(t, Options{Chat: broker}, 2)
phone, tablet := conns[0], conns[1]
writeChat(t, ctx, phone, protocol.Message{Type: protocol.ChatPrompt, ID: "p1", ChatPrompt: &protocol.ChatPromptRequest{SessionID: "ses_1", Text: "one"}})
if ack := readUntil(t, ctx, phone, protocol.ChatPrompt); ack.ChatQueued {
t.Fatalf("first prompt should start immediately: %+v", ack)
}
// The tablet's prompt while the turn is in flight is queued, and it is told so.
writeChat(t, ctx, tablet, protocol.Message{Type: protocol.ChatPrompt, ID: "p2", ChatPrompt: &protocol.ChatPromptRequest{SessionID: "ses_1", Text: "two"}})
if ack := readUntil(t, ctx, tablet, protocol.ChatPrompt); !ack.ChatQueued {
t.Fatalf("second prompt should be acknowledged as queued: %+v", ack)
}
if broker.promptCount() != 1 {
t.Fatalf("prompts forwarded = %d, want 1 while the first turn is in flight", broker.promptCount())
}
// End the first turn; the queued prompt is then posted.
broker.push(protocol.ChatEventFrame{SessionID: "ses_1", MessageID: "msg_1", Kind: protocol.ChatEventStep, Step: &protocol.ChatStep{Status: protocol.ChatStepEnded, Index: 1}})
deadline := time.Now().Add(3 * time.Second)
for broker.promptCount() < 2 {
if time.Now().After(deadline) {
t.Fatalf("queued prompt was never posted: %v", broker.promptTexts())
}
time.Sleep(5 * time.Millisecond)
}
if got := broker.promptTexts(); len(got) != 2 || got[0] != "one" || got[1] != "two" {
t.Fatalf("prompts = %v, want [one two] in order", got)
}
}
// TestChatApprovalFirstAnswerWins is the exactly-once acceptance test: a pending
// approval is shared, the first answer is recorded with the client that gave it
// and broadcast to every client, and a later answer is refused.
func TestChatApprovalFirstAnswerWins(t *testing.T) {
broker := newChannelChat()
broker.perm = []protocol.ChatPermissionFrame{{SessionID: "ses_1", RequestID: "req_1", Action: "bash", Resources: []string{"rm -rf /tmp"}}}
ctx, _, _, conns := dialChatServer(t, Options{Chat: broker}, 2)
phone, tablet := conns[0], conns[1]
// A turn starts so the poller runs and pushes the pending request.
writeChat(t, ctx, phone, protocol.Message{Type: protocol.ChatPrompt, ID: "p1", ChatPrompt: &protocol.ChatPromptRequest{SessionID: "ses_1", Text: "run it"}})
readUntil(t, ctx, phone, protocol.ChatPrompt)
pending := nextPermission(t, ctx, phone, "req_1")
if pending.Resolved {
t.Fatalf("request already marked resolved: %+v", pending)
}
// A second client attaches and is replayed the still-pending request, so its
// card is answerable too.
writeChat(t, ctx, tablet, protocol.Message{Type: protocol.ChatSubscribe, ID: "s1", ChatSubscribe: &protocol.ChatQuery{SessionID: "ses_1"}})
readUntil(t, ctx, tablet, protocol.ChatSubscribe)
replay := nextPermission(t, ctx, tablet, "req_1")
if replay.Resolved || replay.Action != "bash" {
t.Fatalf("replayed permission = %+v, want the pending request", replay)
}
// The phone answers first.
writeChat(t, ctx, phone, protocol.Message{Type: protocol.ChatReply, ID: "a1", ChatReply: &protocol.ChatReplyRequest{SessionID: "ses_1", RequestID: "req_1", Decision: protocol.ChatDecisionOnce, Client: "Pixel 9"}})
readUntil(t, ctx, phone, protocol.ChatReply)
// Both clients see the resolution, with the answering device recorded.
for _, client := range []struct {
name string
conn *websocket.Conn
}{{"phone", phone}, {"tablet", tablet}} {
resolution := nextPermission(t, ctx, client.conn, "req_1")
if !resolution.Resolved || resolution.Decision != protocol.ChatDecisionOnce || resolution.ResolvedBy != "Pixel 9" {
t.Fatalf("%s resolution = %+v, want resolved once by Pixel 9", client.name, resolution)
}
}
// The tablet's later answer is refused, and it never reaches the agent.
writeChat(t, ctx, tablet, protocol.Message{Type: protocol.ChatReply, ID: "a2", ChatReply: &protocol.ChatReplyRequest{SessionID: "ses_1", RequestID: "req_1", Decision: protocol.ChatDecisionAlways, Client: "Pixel 10 Pro Fold"}})
var refused protocol.Message
if err := wsjson.Read(ctx, tablet, &refused); err != nil {
t.Fatal(err)
}
if refused.Type != protocol.Error || !strings.Contains(refused.Error, "already answered by Pixel 9") {
t.Fatalf("second answer was not refused as already answered: %+v", refused)
}
if broker.replyCount() != 1 {
t.Fatalf("broker replies = %d, want the agent to receive exactly one answer", broker.replyCount())
}
}
// TestChatSubscribeWireShape pins the exact wire body the Android app sends for
// chat_subscribe (ChatProtocol.subscribeRequest): the session id travels in the
// chat_subscribe field, not chat_query. The handler once read chat_query, so the
// unit tests passed while the shipped app's subscribe was silently rejected; this
// test writes the raw JSON, attaches the connection and proves a prompt from
// another client reaches it.
func TestChatSubscribeWireShape(t *testing.T) {
broker := newChannelChat()
ctx, _, _, conns := dialChatServer(t, Options{Chat: broker}, 2)
phone, watch := conns[0], conns[1]
if err := watch.Write(ctx, websocket.MessageText, []byte(`{"type":"chat_subscribe","id":"s1","chat_subscribe":{"session_id":"ses_1"}}`)); err != nil {
t.Fatal(err)
}
if ack := readUntil(t, ctx, watch, protocol.ChatSubscribe); ack.ID != "s1" {
t.Fatalf("subscribe ack = %+v, want id s1", ack)
}
// The watcher is attached: another client's prompt is fanned out to it.
writeChat(t, ctx, phone, protocol.Message{Type: protocol.ChatPrompt, ID: "p1", ChatPrompt: &protocol.ChatPromptRequest{SessionID: "ses_1", Text: "ping", Client: "Pixel 9"}})
readUntil(t, ctx, phone, protocol.ChatPrompt)
frame := nextEvent(t, ctx, watch)
if frame.Kind != protocol.ChatEventUser || frame.Client != "Pixel 9" || frame.Part == nil || frame.Part.Text != "ping" {
t.Fatalf("watcher frame = %+v, want the phone's message (subscribe did not attach)", frame)
}
}
// TestChatQueuedPromptFailureSurfaced pins that a prompt accepted as queued whose
// delivery to the agent later fails is reported to the client that sent it,
// instead of leaving its composer showing "Queued" with no error.
func TestChatQueuedPromptFailureSurfaced(t *testing.T) {
broker := newChannelChat()
broker.promptErrAt = 2 // the queued (second) prompt fails to reach the agent
ctx, _, _, conns := dialChatServer(t, Options{Chat: broker}, 2)
phone, tablet := conns[0], conns[1]
// The phone's prompt starts a turn held in flight.
writeChat(t, ctx, phone, protocol.Message{Type: protocol.ChatPrompt, ID: "p1", ChatPrompt: &protocol.ChatPromptRequest{SessionID: "ses_1", Text: "one"}})
if ack := readUntil(t, ctx, phone, protocol.ChatPrompt); ack.ChatQueued {
t.Fatalf("first prompt should start immediately: %+v", ack)
}
// The tablet's prompt is accepted as queued and acknowledged as such.
writeChat(t, ctx, tablet, protocol.Message{Type: protocol.ChatPrompt, ID: "p2", ChatPrompt: &protocol.ChatPromptRequest{SessionID: "ses_1", Text: "two"}})
if ack := readUntil(t, ctx, tablet, protocol.ChatPrompt); !ack.ChatQueued {
t.Fatalf("second prompt should be acknowledged as queued: %+v", ack)
}
// End the first turn; the queued prompt is posted and the broker rejects it.
broker.push(protocol.ChatEventFrame{SessionID: "ses_1", MessageID: "msg_1", Kind: protocol.ChatEventStep, Step: &protocol.ChatStep{Status: protocol.ChatStepEnded, Index: 1}})
for {
var message protocol.Message
if err := wsjson.Read(ctx, tablet, &message); err != nil {
t.Fatalf("read (waiting for the queued prompt failure): %v", err)
}
if message.Type != protocol.Error {
continue
}
if message.ID != "p2" || !strings.Contains(message.Error, "broker rejected the prompt") {
t.Fatalf("queued prompt failure = %+v, want an error for p2 naming the broker failure", message)
}
break
}
}
// TestChatPendingApprovalsAllReplayed pins that every unresolved approval request
// a room holds is replayed to a client that attaches afterwards, not only the
// most recent one, so both cards are answerable on the late client.
func TestChatPendingApprovalsAllReplayed(t *testing.T) {
broker := newChannelChat()
broker.perm = []protocol.ChatPermissionFrame{
{SessionID: "ses_1", RequestID: "req_1", Action: "bash", Resources: []string{"rm -rf /tmp"}},
{SessionID: "ses_1", RequestID: "req_2", Action: "write", Resources: []string{"/etc/hosts"}},
}
ctx, _, _, conns := dialChatServer(t, Options{Chat: broker}, 2)
phone, tablet := conns[0], conns[1]
// A turn starts so the poller pushes both pending requests to the phone.
writeChat(t, ctx, phone, protocol.Message{Type: protocol.ChatPrompt, ID: "p1", ChatPrompt: &protocol.ChatPromptRequest{SessionID: "ses_1", Text: "run them"}})
readUntil(t, ctx, phone, protocol.ChatPrompt)
nextPermission(t, ctx, phone, "req_1")
nextPermission(t, ctx, phone, "req_2")
// A client that attaches afterwards is replayed both.
writeChat(t, ctx, tablet, protocol.Message{Type: protocol.ChatSubscribe, ID: "s1", ChatSubscribe: &protocol.ChatQuery{SessionID: "ses_1"}})
readUntil(t, ctx, tablet, protocol.ChatSubscribe)
first := nextPermission(t, ctx, tablet, "req_1")
second := nextPermission(t, ctx, tablet, "req_2")
if first.Resolved || second.Resolved || first.Action != "bash" || second.Action != "write" {
t.Fatalf("replayed permissions = %+v / %+v, want both still-pending requests", first, second)
}
}
// TestChatResyncAfterReconnect is the resync acceptance test: a client that drops
// and reconnects re-syncs the whole conversation from retained state, including
// the user turn and who sent it.
func TestChatResyncAfterReconnect(t *testing.T) {
broker := scriptedChat()
ctx, _, srv, conns := dialChatServer(t, Options{Chat: broker}, 1)
phone := conns[0]
writeChat(t, ctx, phone, protocol.Message{Type: protocol.ChatPrompt, ID: "p1", ChatPrompt: &protocol.ChatPromptRequest{SessionID: "ses_1", Text: "hi", Client: "Pixel 9"}})
readUntil(t, ctx, phone, protocol.ChatPrompt)
readChatTurn(t, ctx, phone)
// The phone's socket drops.
phone.CloseNow()
// A fresh connection re-syncs from retained state.
reconnected := dialChatConn(t, ctx, srv)
writeChat(t, ctx, reconnected, protocol.Message{Type: protocol.ChatMessages, ID: "m1", ChatQuery: &protocol.ChatQuery{SessionID: "ses_1"}})
response := readUntil(t, ctx, reconnected, protocol.ChatMessages)
if len(response.ChatMessages) != 2 {
t.Fatalf("resync returned %d messages, want user+assistant: %+v", len(response.ChatMessages), response.ChatMessages)
}
user := response.ChatMessages[0]
if user.Role != protocol.ChatRoleUser || user.Client != "Pixel 9" || len(user.Parts) != 1 || user.Parts[0].Text != "hi" {
t.Fatalf("resynced user turn = %+v", user)
}
assistant := response.ChatMessages[1]
if assistant.Role != protocol.ChatRoleAssistant || assistant.ID != "msg_1" {
t.Fatalf("resynced assistant turn = %+v", assistant)
}
}
+69 -8
View File
@@ -1,5 +1,7 @@
package server
import "git.a-wan.net/alan/pipelines/internal/protocol"
// chatPermissionRetainedLimit bounds the dedup set of already-pushed permission
// request ids one session retains, so a long turn cannot grow it without limit.
const chatPermissionRetainedLimit = 256
@@ -31,24 +33,83 @@ func (h *chatHub) seenPermission(sessionID, requestID string) bool {
return true
}
// forgetPermission releases a request id reserved by seenPermission when its
// frame could not be written, so a later poll re-pushes it instead of the id
// staying "seen" while the phone never received the request.
func (h *chatHub) forgetPermission(sessionID, requestID string) {
// reservePermission claims the shared right to answer requestID for client. It
// returns true when this caller is the first to answer (the only caller allowed
// to reach the agent), and false with the recorded resolution when the request is
// already answered or is already being answered, so a later answer is refused
// rather than delivered twice. The reservation is bounded like the dedup set.
func (h *chatHub) reservePermission(sessionID, requestID, client string) (*chatResolution, bool) {
if sessionID == "" || requestID == "" {
return
return nil, false
}
h.mu.Lock()
defer h.mu.Unlock()
turn := h.turnLocked(sessionID)
if turn.resolutions == nil {
turn.resolutions = map[string]*chatResolution{}
}
if prior, ok := turn.resolutions[requestID]; ok {
return prior, false
}
turn.resolutions[requestID] = &chatResolution{client: client}
turn.resolutionOrder = append(turn.resolutionOrder, requestID)
if len(turn.resolutionOrder) > chatPermissionRetainedLimit {
oldest := turn.resolutionOrder[0]
turn.resolutionOrder = turn.resolutionOrder[1:]
delete(turn.resolutions, oldest)
}
return nil, true
}
// releasePermission drops a reservation whose answer never reached the agent, so
// a later attempt can win instead of the request staying permanently refused.
func (h *chatHub) releasePermission(sessionID, requestID string) {
h.mu.Lock()
defer h.mu.Unlock()
turn := h.turns[sessionID]
if turn == nil {
return
}
delete(turn.permissions, requestID)
for i, id := range turn.permissionOrder {
delete(turn.resolutions, requestID)
for i, id := range turn.resolutionOrder {
if id == requestID {
turn.permissionOrder = append(turn.permissionOrder[:i], turn.permissionOrder[i+1:]...)
turn.resolutionOrder = append(turn.resolutionOrder[:i], turn.resolutionOrder[i+1:]...)
break
}
}
}
// confirmPermission records the delivered answer and pushes the resolution to
// every watching client, so each one's approval card clears and shows the
// outcome and which client gave it.
func (h *chatHub) confirmPermission(sessionID, requestID, client, decision string) {
h.mu.Lock()
if turn := h.turns[sessionID]; turn != nil {
if resolution, ok := turn.resolutions[requestID]; ok {
resolution.decision = decision
resolution.answered = true
}
}
frame := protocol.ChatPermissionFrame{SessionID: sessionID, RequestID: requestID}
var targets []*chatSub
if room := h.rooms[sessionID]; room != nil {
for i := range room.pending {
if room.pending[i].RequestID == requestID {
frame = room.pending[i]
room.pending = append(room.pending[:i], room.pending[i+1:]...)
break
}
}
for _, sub := range room.subs {
targets = append(targets, sub)
}
}
h.mu.Unlock()
frame.Resolved = true
frame.Decision = decision
frame.ResolvedBy = client
msg := protocol.Message{Type: protocol.ChatPermission, ChatPermission: &frame}
for _, sub := range targets {
sub.send(msg)
}
}
+662
View File
@@ -0,0 +1,662 @@
package server
import (
"context"
"errors"
"fmt"
"log"
"strings"
"sync"
"time"
"git.a-wan.net/alan/pipelines/internal/opencode"
"git.a-wan.net/alan/pipelines/internal/protocol"
)
// The chat room is one session's shared live channel. Many clients attach to it
// (the operator's phone, tablet and terminal) and every frame any turn produces
// is fanned out to all of them, so each device sees the same conversation
// including the other devices' prompts and the turn's streaming output. The room
// owns the session's one broker stream and its one prompt queue, so a session is
// never read-only for a client and two turns never interleave: a prompt that
// arrives while a turn is in flight is queued (bounded) and its client is told so
// in the ack.
const (
// chatRoomSubscriberBuffer bounds one attached client's pending frames. A
// client that falls this far behind is dropped rather than blocking the turn
// or the other clients; it re-syncs from history when it reattaches.
chatRoomSubscriberBuffer = 64
// chatRoomQueueLimit bounds the prompts one session may hold while a turn is
// in flight. A prompt that would exceed it is refused with a visible error
// instead of being silently dropped.
chatRoomQueueLimit = 8
// chatClientLabelMax bounds the human-readable client label the server stores
// and echoes, so a long device name cannot grow a frame without limit.
chatClientLabelMax = 48
// chatClientLabelFallback labels a prompt whose sender did not name itself, so
// a transcript always has something to attribute the message to.
chatClientLabelFallback = "Another device"
// chatRoomPendingLimit bounds how many unresolved approval requests one room
// retains for replay to a client that attaches after they were raised, so a
// long turn cannot grow the replay state without limit.
chatRoomPendingLimit = 16
)
// chatSub is one client's attachment to a session's shared stream. Frames reach
// it through a dedicated writer goroutine so a slow or broken client never stalls
// the turn or the other subscribers; the buffered channel bounds how far behind
// it may fall.
type chatSub struct {
hub *chatHub
room *chatRoom
clientID string
label string
ch chan protocol.Message
done chan struct{}
once sync.Once
write func(protocol.Message) error
}
func (s *chatSub) run() {
for {
select {
case <-s.done:
return
case msg := <-s.ch:
if err := s.write(msg); err != nil {
s.close()
return
}
}
}
}
func (s *chatSub) send(msg protocol.Message) {
select {
case <-s.done:
return
default:
}
select {
case s.ch <- msg:
default:
// The client is not draining: drop it rather than block the fan-out. Its
// next attach re-syncs from history.
s.close()
}
}
// close detaches the subscription and stops its writer goroutine exactly once.
func (s *chatSub) close() {
s.once.Do(func() {
close(s.done)
s.hub.detach(s.room.sessionID, s)
})
}
// chatQueuedPrompt is one prompt waiting for the session's in-flight turn to
// finish. acked marks a prompt the handler already acknowledged as queued, so the
// turn runner does not send a second (success) acknowledgement for the same
// request id; write is kept either way so a later broker failure is still
// reported to the client that sent it.
type chatQueuedPrompt struct {
text string
requestID string
write func(protocol.Message) error
acked bool
}
// chatRoom is one session's shared live channel. Every field is guarded by the
// owning chatHub's mutex.
type chatRoom struct {
sessionID string
broker chatBroker
ctx context.Context
cancel context.CancelFunc
subs map[string]*chatSub
queue []*chatQueuedPrompt
running bool
streaming bool
// buffering holds the turn's frames until the prompting client's ack has been
// written, so the ack always precedes the frames it acknowledges. It is set
// only while the very first turn subscribes to the firehose.
buffering bool
buffered []protocol.ChatEventFrame
// pending holds the room's unresolved approval requests, in the order they
// were raised, replayed to a client that attaches after they were raised. A
// request is removed once it is resolved.
pending []protocol.ChatPermissionFrame
pollerStarted bool
wake chan struct{}
turnDone chan struct{}
}
func newChatRoom(base context.Context, sessionID string) *chatRoom {
if base == nil {
base = context.Background()
}
roomCtx, cancel := context.WithCancel(base)
return &chatRoom{
sessionID: sessionID,
ctx: roomCtx,
cancel: cancel,
subs: map[string]*chatSub{},
wake: make(chan struct{}, 1),
}
}
// roomLocked returns the session's room, creating it (and its turn runner) when
// it is the first client to watch the session. Callers must hold h.mu.
func (h *chatHub) roomLocked(sessionID string) *chatRoom {
if h.rooms == nil {
h.rooms = map[string]*chatRoom{}
}
if room := h.rooms[sessionID]; room != nil {
return room
}
room := newChatRoom(h.baseCtx, sessionID)
h.rooms[sessionID] = room
go h.runRoom(room)
return room
}
// attach registers write as one client's subscription to sessionID's stream and
// returns it, or the existing subscription when the same connection has already
// attached. It is idempotent so a client may prompt and subscribe without
// registering twice.
func (h *chatHub) attach(sessionID, clientID, label string, broker chatBroker, write func(protocol.Message) error) *chatSub {
if sessionID == "" || clientID == "" || write == nil {
return nil
}
h.mu.Lock()
room := h.roomLocked(sessionID)
if room.broker == nil {
room.broker = broker
}
if sub, ok := room.subs[clientID]; ok {
if label != "" {
sub.label = label
}
h.mu.Unlock()
return sub
}
sub := &chatSub{
hub: h,
room: room,
clientID: clientID,
label: label,
ch: make(chan protocol.Message, chatRoomSubscriberBuffer),
done: make(chan struct{}),
write: write,
}
room.subs[clientID] = sub
h.mu.Unlock()
go sub.run()
return sub
}
// detach drops one subscription. The room (and its broker stream and queue) is
// released once its last client leaves, so a session with no watchers holds no
// goroutine.
func (h *chatHub) detach(sessionID string, sub *chatSub) {
h.mu.Lock()
room := h.rooms[sessionID]
if room == nil || room.subs[sub.clientID] != sub {
h.mu.Unlock()
return
}
delete(room.subs, sub.clientID)
if len(room.subs) == 0 {
delete(h.rooms, sessionID)
room.cancel()
}
h.mu.Unlock()
}
// detachClient drops every chat subscription one connection holds; the read loop
// calls it when the connection ends so no subscriber goroutine outlives it.
func (h *chatHub) detachClient(clientID string) {
if clientID == "" {
return
}
h.mu.Lock()
var subs []*chatSub
for _, room := range h.rooms {
if sub, ok := room.subs[clientID]; ok {
subs = append(subs, sub)
}
}
h.mu.Unlock()
for _, sub := range subs {
sub.close()
}
}
// fanout delivers one frame to every client watching sessionID except the one
// named by except (the sender, who already has it locally).
func (h *chatHub) fanout(sessionID string, msg protocol.Message, except string) {
h.mu.Lock()
var targets []*chatSub
if room := h.rooms[sessionID]; room != nil {
for id, sub := range room.subs {
if id == except {
continue
}
targets = append(targets, sub)
}
}
h.mu.Unlock()
for _, sub := range targets {
sub.send(msg)
}
}
// broadcastUser retains a prompt as a user turn and pushes it live to every other
// client watching the session, attributed to the sending client's label. The
// sender already has the message locally, so it is excluded to keep its own
// transcript from duplicating it.
func (h *chatHub) broadcastUser(frame protocol.ChatEventFrame, exceptClientID string) {
h.apply(frame)
h.fanout(frame.SessionID, protocol.Message{Type: protocol.ChatEvent, ChatEvent: &frame}, exceptClientID)
}
// emit folds one broker frame into the retained state and fans it out. While the
// first turn's ack is still pending the frames are buffered and flushed in order
// once it is written. A step-ended frame finishes the turn, letting the queue
// advance.
func (h *chatHub) emit(frame protocol.ChatEventFrame) {
h.apply(frame)
h.mu.Lock()
room := h.rooms[frame.SessionID]
buffered := false
var targets []*chatSub
if room != nil {
if room.buffering {
room.buffered = append(room.buffered, frame)
buffered = true
} else {
for _, sub := range room.subs {
targets = append(targets, sub)
}
}
}
if room != nil && frame.Kind == protocol.ChatEventStep && frame.Step != nil && frame.Step.Status == protocol.ChatStepEnded {
h.finishTurnLocked(room)
}
h.mu.Unlock()
if buffered {
return
}
msg := protocol.Message{Type: protocol.ChatEvent, ChatEvent: &frame}
for _, sub := range targets {
sub.send(msg)
}
}
// finishTurnLocked marks the room's turn finished and releases the turn runner's
// wait. Callers must hold h.mu.
func (h *chatHub) finishTurnLocked(room *chatRoom) {
room.running = false
if room.turnDone != nil {
close(room.turnDone)
room.turnDone = nil
}
}
// flushBuffered releases the frames held while the ack was pending and delivers
// them in order. It is a no-op once the room is no longer buffering.
func (h *chatHub) flushBuffered(sessionID string) {
h.mu.Lock()
room := h.rooms[sessionID]
var pending []protocol.ChatEventFrame
var targets []*chatSub
if room != nil && room.buffering {
room.buffering = false
pending = room.buffered
room.buffered = nil
for _, sub := range room.subs {
targets = append(targets, sub)
}
}
h.mu.Unlock()
for i := range pending {
frame := pending[i]
msg := protocol.Message{Type: protocol.ChatEvent, ChatEvent: &frame}
for _, sub := range targets {
sub.send(msg)
}
}
}
// submitPrompt accepts one prompt: it starts the turn runner immediately when no
// turn is in flight, or queues it (bounded) when one is. It returns whether the
// prompt was queued or refused.
func (h *chatHub) submitPrompt(sessionID string, p *chatQueuedPrompt) (queued bool, refused bool) {
h.mu.Lock()
room := h.roomLocked(sessionID)
if room.running || len(room.queue) > 0 {
if len(room.queue) >= chatRoomQueueLimit {
h.mu.Unlock()
return false, true
}
// The client is acknowledged as queued by the handler, so the turn runner
// must not acknowledge the same request again once it runs. The write is
// still kept so a later broker failure reaches the client that sent it.
p.acked = true
room.queue = append(room.queue, p)
signalWake(room.wake)
h.mu.Unlock()
return true, false
}
room.queue = append(room.queue, p)
signalWake(room.wake)
h.mu.Unlock()
return false, false
}
// pendingFrames returns a copy of the room's unresolved approval requests so a
// client that attaches after they were raised can be shown every one of them. It
// returns nil when the room holds none.
func (h *chatHub) pendingFrames(sessionID string) []protocol.ChatPermissionFrame {
h.mu.Lock()
defer h.mu.Unlock()
room := h.rooms[sessionID]
if room == nil || len(room.pending) == 0 {
return nil
}
frames := make([]protocol.ChatPermissionFrame, len(room.pending))
copy(frames, room.pending)
return frames
}
// pushPermission publishes one newly seen pending approval request to every
// client watching the session and remembers it (bounded) for a client that
// attaches later. A request already seen (or already resolved) is not pushed
// again.
func (h *chatHub) pushPermission(sessionID string, frame protocol.ChatPermissionFrame) {
if frame.RequestID == "" || frame.Resolved {
return
}
if !h.seenPermission(sessionID, frame.RequestID) {
return
}
h.mu.Lock()
var targets []*chatSub
if room := h.rooms[sessionID]; room != nil {
known := false
for i := range room.pending {
if room.pending[i].RequestID == frame.RequestID {
room.pending[i] = frame
known = true
break
}
}
if !known {
room.pending = append(room.pending, frame)
if len(room.pending) > chatRoomPendingLimit {
room.pending = room.pending[len(room.pending)-chatRoomPendingLimit:]
}
}
for _, sub := range room.subs {
targets = append(targets, sub)
}
}
h.mu.Unlock()
msg := protocol.Message{Type: protocol.ChatPermission, ChatPermission: &frame}
for _, sub := range targets {
sub.send(msg)
}
}
// runRoom is the session's turn runner: it takes queued prompts one at a time,
// posts each to the broker and waits for the turn to end, so two prompts of one
// session can never interleave.
func (h *chatHub) runRoom(room *chatRoom) {
for {
p, done, ok := h.nextPrompt(room)
if !ok {
return
}
h.runTurn(room, p, done)
}
}
// nextPrompt pops the next queued prompt, blocking until one arrives or the room
// is released. It marks the room running and creates the turn's completion
// channel so a stale signal from a previous turn can never end the next one.
func (h *chatHub) nextPrompt(room *chatRoom) (*chatQueuedPrompt, chan struct{}, bool) {
for {
h.mu.Lock()
if len(room.queue) > 0 {
p := room.queue[0]
room.queue = room.queue[1:]
room.running = true
room.turnDone = make(chan struct{})
done := room.turnDone
h.mu.Unlock()
return p, done, true
}
h.mu.Unlock()
select {
case <-room.ctx.Done():
return nil, nil, false
case <-room.wake:
}
}
}
// runTurn subscribes to the broker stream when needed, posts one prompt, writes
// its ack and waits for the turn to end.
func (h *chatHub) runTurn(room *chatRoom, p *chatQueuedPrompt, done chan struct{}) {
broker := h.roomBroker(room)
first := false
h.mu.Lock()
if !room.streaming {
first = true
room.buffering = true
}
h.mu.Unlock()
defer h.flushBuffered(room.sessionID)
if broker == nil {
h.failPrompt(room, p, errors.New("chat is not configured on this server"))
return
}
if first {
if err := h.startStream(room, broker); err != nil {
h.failPrompt(room, p, err)
h.endRoomTurn(room)
return
}
}
if err := broker.Prompt(room.ctx, room.sessionID, p.text); err != nil {
h.failPrompt(room, p, err)
h.endRoomTurn(room)
return
}
if h.registry != nil {
if err := h.registry.TouchOperatorSession(room.ctx, room.sessionID); err != nil {
log.Printf("touch operator session %s: %v", room.sessionID, err)
}
}
if p.write != nil && !p.acked {
_ = p.write(protocol.Message{Type: protocol.ChatPrompt, ID: p.requestID})
}
h.flushBuffered(room.sessionID)
// Start the approval poller once, after the first ack, so a pending request
// is surfaced after the prompt is acknowledged and shared with every client.
h.mu.Lock()
startPoller := !room.pollerStarted
room.pollerStarted = true
h.mu.Unlock()
if startPoller {
go h.pollRoom(room, broker)
}
select {
case <-done:
case <-room.ctx.Done():
}
}
// endRoomTurn releases the turn slot after a prompt that never entered flight,
// so the queue advances immediately instead of waiting for a step that never
// comes.
func (h *chatHub) endRoomTurn(room *chatRoom) {
h.mu.Lock()
h.finishTurnLocked(room)
h.mu.Unlock()
}
// failPrompt reports a refused prompt to the client that sent it, so a prompt
// that never reached the agent is visible on the device that sent it rather than
// leaving its composer waiting. It is reported for a queued prompt too, whose
// success ack was already sent but whose delivery may still fail.
func (h *chatHub) failPrompt(room *chatRoom, p *chatQueuedPrompt, err error) {
if p.write == nil || err == nil {
return
}
_ = p.write(protocol.Message{Type: protocol.Error, ID: p.requestID, Error: err.Error()})
}
// roomBroker returns the broker bound to the room.
func (h *chatHub) roomBroker(room *chatRoom) chatBroker {
h.mu.Lock()
defer h.mu.Unlock()
return room.broker
}
// startStream attaches the room to the broker firehose, waiting until the
// subscription is ready so no delta emitted between subscribing and posting a
// prompt is lost. The permission poller starts alongside it.
func (h *chatHub) startStream(room *chatRoom, broker chatBroker) error {
attached := make(chan struct{})
var once sync.Once
result := make(chan error, 1)
ctx := room.ctx
go func() {
result <- broker.Stream(ctx, room.sessionID, func() {
once.Do(func() { close(attached) })
}, func(frame protocol.ChatEventFrame) error {
h.emit(frame)
return nil
})
}()
select {
case <-attached:
case err := <-result:
if err == nil {
err = errors.New("chat stream ended before it was subscribed")
}
return err
case <-ctx.Done():
return ctx.Err()
}
h.mu.Lock()
room.streaming = true
h.mu.Unlock()
go h.drainStream(room, result)
return nil
}
// drainStream reports the terminal error of a room's subscription and clears the
// streaming flag so a later turn re-subscribes; it also releases a turn still
// waiting on a stream that ended.
func (h *chatHub) drainStream(room *chatRoom, result <-chan error) {
err := <-result
h.mu.Lock()
room.streaming = false
h.finishTurnLocked(room)
h.mu.Unlock()
if err != nil && room.ctx.Err() == nil {
log.Printf("chat stream session=%s: %v", room.sessionID, err)
}
}
// pollRoom polls the broker's pending-approval list for the room on a fixed
// interval and pushes each newly seen request to every attached client. The
// first poll runs immediately; the loop stops with the room's context.
func (h *chatHub) pollRoom(room *chatRoom, broker chatBroker) {
ticker := time.NewTicker(chatPermissionPollInterval)
defer ticker.Stop()
reported := false
for {
if err := h.pollPermissionsOnce(room.ctx, broker, room.sessionID); err != nil {
if room.ctx.Err() != nil {
return
}
if errors.Is(err, opencode.ErrPermissionUnsupported) {
log.Printf("chat permission poll session=%s: %v", room.sessionID, err)
return
}
if reported {
log.Printf("chat permission poll session=%s: %v", room.sessionID, err)
} else {
reported = true
h.fanout(room.sessionID, protocol.Message{Type: protocol.Error, Error: "chat permission poll: " + err.Error()}, "")
}
}
select {
case <-room.ctx.Done():
return
case <-ticker.C:
}
}
}
// pollPermissionsOnce performs one poll and pushes each newly seen request of the
// session to every client watching it.
func (h *chatHub) pollPermissionsOnce(ctx context.Context, broker chatBroker, sessionID string) error {
pending, err := broker.Permissions(ctx, sessionID)
if err != nil {
return err
}
for _, request := range pending {
if request.SessionID != sessionID || request.RequestID == "" {
continue
}
h.pushPermission(sessionID, request)
}
return nil
}
// signalWake nudges a room's turn runner without blocking. The channel is
// buffered, so a signal already pending is enough.
func signalWake(ch chan struct{}) {
select {
case ch <- struct{}{}:
default:
}
}
// sanitizeChatClientLabel cleans a client-supplied device label for storage and
// echo: control characters are dropped, the length is bounded and a blank label
// becomes the generic fallback, so a transcript can always attribute a message.
func sanitizeChatClientLabel(label string) string {
var b strings.Builder
for _, r := range label {
if r < 0x20 || r == 0x7f {
continue
}
b.WriteRune(r)
}
out := strings.TrimSpace(b.String())
if len(out) > chatClientLabelMax {
out = strings.TrimSpace(out[:chatClientLabelMax])
}
if out == "" {
return chatClientLabelFallback
}
return out
}
// permissionRefusal explains why a second answer to an already-answered request
// is refused, naming the client that won so the operator sees what happened.
func permissionRefusal(prior *chatResolution, requestID string) string {
if prior == nil {
return "permission request " + requestID + " is already resolved"
}
if prior.answered {
return fmt.Sprintf("permission request %s was already answered by %s", requestID, prior.client)
}
return fmt.Sprintf("permission request %s is already being answered by %s", requestID, prior.client)
}
+9 -10
View File
@@ -17,15 +17,15 @@ import (
// fixed list bounds.
const operatorDirectoryLimit = 8
// handleChatSessions answers chat_sessions with the operator's own sessions,
// marking any another client currently holds as Busy. The registry is the single
// source of truth for which sessions are listed and for their directory, tag,
// created/recency, so a pipeline stage session (recorded in run_steps, never in
// the operator registry) is always excluded and a session with no recorded tag
// is never listed. FAIL-CLOSED: when no registry is configured the result is
// empty, never the whole endpoint list. broker.Sessions is called at most once
// per request, and the registry once.
func handleChatSessions(ctx context.Context, request protocol.Message, broker chatBroker, hub *chatHub, registry operatorRegistry, clientID string, write func(protocol.Message) error) {
// handleChatSessions answers chat_sessions with the operator's own sessions. The
// registry is the single source of truth for which sessions are listed and for
// their directory, tag, created/recency, so a pipeline stage session (recorded
// in run_steps, never in the operator registry) is always excluded and a session
// with no recorded tag is never listed. FAIL-CLOSED: when no registry is
// configured the result is empty, never the whole endpoint list. broker.Sessions
// is called at most once per request, and the registry once. A session is never
// marked Busy: any number of clients may watch and write one session.
func handleChatSessions(ctx context.Context, request protocol.Message, broker chatBroker, hub *chatHub, registry operatorRegistry, write func(protocol.Message) error) {
if broker == nil {
_ = write(protocol.Message{Type: protocol.Error, ID: request.ID, Error: "chat is not configured on this server"})
return
@@ -74,7 +74,6 @@ func handleChatSessions(ctx context.Context, request protocol.Message, broker ch
session.Tag = operator.Tag
session.CreatedAt = operator.CreatedAt
session.UpdatedAt = operator.UpdatedAt
session.Busy = hub.busyForOther(operator.ID, clientID)
response.ChatSessions = append(response.ChatSessions, session)
}
_ = write(response)
+67 -156
View File
@@ -2,10 +2,7 @@ package server
import (
"context"
"errors"
"log"
"strings"
"sync"
"time"
"git.a-wan.net/alan/pipelines/internal/opencode"
@@ -14,10 +11,16 @@ import (
// chatPermissionPollInterval is the fixed interval between permission polls: one
// GET per poll through the shared Connection bounds, never a busy loop. The first
// poll runs immediately so a request pending when the prompt is sent is surfaced
// poll runs immediately so a request pending when a turn starts is surfaced
// without waiting a full interval.
const chatPermissionPollInterval = 2 * time.Second
// handleChatPrompt accepts a prompt from any client. It never rejects a prompt
// because another client is watching the session: the client attaches to the
// session's shared room and the prompt either starts a turn or is queued behind
// the one in flight, with the ack saying which. The prompt is echoed live to
// every other client, attributed to the sending device's label, and the turn's
// output is fanned out to all of them.
func handleChatPrompt(ctx context.Context, request protocol.Message, broker chatBroker, hub *chatHub, registry operatorRegistry, clientID string, write func(protocol.Message) error) {
if broker == nil {
_ = write(protocol.Message{Type: protocol.Error, ID: request.ID, Error: "chat is not configured on this server"})
@@ -42,170 +45,78 @@ func handleChatPrompt(ctx context.Context, request protocol.Message, broker chat
_ = write(protocol.Message{Type: protocol.Error, ID: request.ID, Error: "chat prompt exceeds 64 KiB"})
return
}
// Claim the session before subscribing or prompting: a second client must be
// rejected here, before any broker call, so two clients cannot silently write
// the same conversation. The same client may re-prompt its own session.
sessionID := prompt.SessionID
if !hub.claim(sessionID, clientID) {
_ = write(protocol.Message{Type: protocol.Error, ID: request.ID, Error: "session " + sessionID + " is busy with another client"})
sub := hub.attach(sessionID, clientID, sanitizeChatClientLabel(prompt.Client), broker, write)
if sub == nil {
_ = write(protocol.Message{Type: protocol.Error, ID: request.ID, Error: "could not attach to session " + sessionID})
return
}
// Subscribe to the OpenCode firehose before posting the prompt: the stream
// has no replay cursor (research 2.4), so a delta emitted between the POST
// and the subscription would otherwise be lost. Frames that arrive before the
// ack is written are buffered and flushed in order after it.
streamCtx, streamCancel := context.WithCancel(ctx)
attached := make(chan struct{})
var attachOnce sync.Once
streamResult := make(chan error, 1)
var bufferMu sync.Mutex
buffering := true
var buffered []protocol.ChatEventFrame
go func() {
streamResult <- broker.Stream(streamCtx, sessionID, func() {
attachOnce.Do(func() { close(attached) })
}, func(frame protocol.ChatEventFrame) error {
bufferMu.Lock()
if buffering {
buffered = append(buffered, frame)
bufferMu.Unlock()
return nil
}
bufferMu.Unlock()
hub.apply(frame)
return write(protocol.Message{Type: protocol.ChatEvent, ChatEvent: &frame})
})
}()
select {
case <-attached:
case err := <-streamResult:
streamCancel()
hub.release(sessionID, clientID)
if err != nil && ctx.Err() == nil {
_ = write(protocol.Message{Type: protocol.Error, ID: request.ID, Error: "chat stream: " + err.Error()})
}
return
case <-ctx.Done():
streamCancel()
hub.release(sessionID, clientID)
// The user turn every *other* client sees, carrying the sender's label. The
// sender's own client appended it locally, so it is excluded below.
userFrame := protocol.ChatEventFrame{
SessionID: sessionID,
MessageID: hub.nextUserMessageID(),
Kind: protocol.ChatEventUser,
Part: &protocol.ChatPart{Type: protocol.ChatPartText, ID: "usr", Text: prompt.Text},
Client: sub.label,
}
queued, refused := hub.submitPrompt(sessionID, &chatQueuedPrompt{
text: prompt.Text,
requestID: request.ID,
write: write,
})
if refused {
_ = write(protocol.Message{Type: protocol.Error, ID: request.ID, Error: "session " + sessionID + " already has the maximum number of prompts queued"})
return
}
if err := broker.Prompt(ctx, sessionID, prompt.Text); err != nil {
streamCancel()
hub.release(sessionID, clientID)
_ = write(protocol.Message{Type: protocol.Error, ID: request.ID, Error: err.Error()})
return
// Publish the user turn to every other client; the sender already has it.
hub.broadcastUser(userFrame, clientID)
if queued {
// The client that sent it is told the prompt is waiting for the in-flight
// turn, so it shows queued/steering instead of blocking or silently
// dropping the message. The turn runner acknowledges it once it runs, so
// clear the ack on the queued entry to avoid a second ack for the same id.
_ = write(protocol.Message{Type: protocol.ChatPrompt, ID: request.ID, ChatQueued: true})
}
// Recency is one UPDATE: it moves the operator session to the front of
// chat_sessions. A session id that is not an operator session updates no row
// and is not an error, so pipeline stage prompts are unaffected.
if registry != nil {
// Recency is one UPDATE: it moves the operator session to the front of
// chat_sessions. A session id that is not an operator session updates no
// row and is not an error, so pipeline stage prompts are unaffected.
if err := registry.TouchOperatorSession(ctx, sessionID); err != nil {
log.Printf("touch operator session %s: %v", sessionID, err)
// Best-effort; the turn runner also touches on delivery.
_ = err
}
}
// Acknowledge the accepted prompt with the echoed request id, then stream the
// reply. The prompt is sent exactly once and never re-sent on resume.
if err := write(protocol.Message{Type: protocol.ChatPrompt, ID: request.ID}); err != nil {
streamCancel()
hub.release(sessionID, clientID)
}
// handleChatSubscribe attaches one connection to a session's shared stream so it
// receives every frame any client's turn produces, its own or another device's.
// It replays the session's still-pending approval requests, if the room holds
// any, so a device that joins late still shows the cards.
func handleChatSubscribe(request protocol.Message, broker chatBroker, hub *chatHub, clientID string, write func(protocol.Message) error) {
// The wire body of chat_subscribe is the chat_subscribe field (the app's
// subscribeRequest and docs/cli.md both use it), not the chat_query body the
// other session-scoped commands carry.
query := request.ChatSubscribe
if query == nil || !opencode.ValidSessionID(query.SessionID) {
_ = write(protocol.Message{Type: protocol.Error, ID: request.ID, Error: "a valid OpenCode session id is required"})
return
}
// Flush frames buffered while the prompt was accepted, then resume live
// delivery. Holding bufferMu preserves order: the stream goroutine either
// buffered before this flush or waits and writes after it.
bufferMu.Lock()
buffering = false
pending := buffered
buffered = nil
for _, frame := range pending {
hub.apply(frame)
if err := write(protocol.Message{Type: protocol.ChatEvent, ChatEvent: &frame}); err != nil {
bufferMu.Unlock()
streamCancel()
hub.release(sessionID, clientID)
return
}
if broker == nil {
_ = write(protocol.Message{Type: protocol.Error, ID: request.ID, Error: "chat is not configured on this server"})
return
}
bufferMu.Unlock()
go drainChatStream(ctx, streamResult, streamCancel, hub, sessionID, clientID, write)
// Poll for pending approval requests alongside the event stream, sharing
// streamCtx so the poller stops when the stream ends or the client
// disconnects. The first poll runs immediately.
go pollChatPermissions(streamCtx, broker, hub, sessionID, write)
}
// pollChatPermissions polls the broker's pending-approval list on a fixed
// interval, sharing the chat subscription's context so it stops on disconnect or
// when the turn's stream ends. The hub dedups the request ids, so each pending
// request is pushed at most once; a poll failure is surfaced once through the
// same write closure instead of staying silent. A backend that does not expose
// the approval surface (opencode.ErrPermissionUnsupported) stops the poller
// quietly, so the documented limitation is not reported as a per-prompt error.
func pollChatPermissions(ctx context.Context, broker chatBroker, hub *chatHub, sessionID string, write func(protocol.Message) error) {
ticker := time.NewTicker(chatPermissionPollInterval)
defer ticker.Stop()
reported := false
for {
if err := pushChatPermissions(ctx, broker, hub, sessionID, write); err != nil {
if ctx.Err() != nil {
return
}
if errors.Is(err, opencode.ErrPermissionUnsupported) {
log.Printf("chat permission poll session=%s: %v", sessionID, err)
return
}
if reported {
log.Printf("chat permission poll session=%s: %v", sessionID, err)
} else {
reported = true
_ = write(protocol.Message{Type: protocol.Error, Error: "chat permission poll: " + err.Error()})
}
}
select {
case <-ctx.Done():
return
case <-ticker.C:
}
}
}
// pushChatPermissions performs one poll and writes a chat_permission frame for
// every newly seen request of the session, through the same connection-scoped
// write closure as the chat stream. It never re-pushes a request id, and releases
// the reservation on a write failure so the frame is not silently dropped.
func pushChatPermissions(ctx context.Context, broker chatBroker, hub *chatHub, sessionID string, write func(protocol.Message) error) error {
pending, err := broker.Permissions(ctx, sessionID)
if err != nil {
return err
}
for _, request := range pending {
if request.SessionID != sessionID || request.RequestID == "" {
continue
}
if !hub.seenPermission(sessionID, request.RequestID) {
continue
}
frame := request
if err := write(protocol.Message{Type: protocol.ChatPermission, ChatPermission: &frame}); err != nil {
hub.forgetPermission(sessionID, request.RequestID)
return err
}
}
return nil
}
// drainChatStream reports the terminal error of a chat subscription and releases
// its context and the session claim once the stream has ended, so a later client
// is no longer blocked and nothing leaks.
func drainChatStream(ctx context.Context, result <-chan error, cancel context.CancelFunc, hub *chatHub, sessionID, clientID string, write func(protocol.Message) error) {
defer cancel()
defer hub.release(sessionID, clientID)
if err := <-result; err != nil && ctx.Err() == nil {
log.Printf("chat stream session=%s: %v", sessionID, err)
_ = write(protocol.Message{Type: protocol.Error, Error: "chat stream: " + err.Error()})
sub := hub.attach(query.SessionID, clientID, "", broker, write)
if sub == nil {
_ = write(protocol.Message{Type: protocol.Error, ID: request.ID, Error: "could not attach to session " + query.SessionID})
return
}
_ = write(protocol.Message{Type: protocol.ChatSubscribe, ID: request.ID})
// Replay every still-unresolved approval request the room holds, not only the
// most recent one, so a client that attaches after two requests were raised
// still sees both cards.
for _, pending := range hub.pendingFrames(query.SessionID) {
frame := pending
sub.send(protocol.Message{Type: protocol.ChatPermission, ChatPermission: &frame})
}
}
+29 -111
View File
@@ -436,10 +436,18 @@ func TestChatMessagesResumesRetainedState(t *testing.T) {
if err := wsjson.Read(ctx, conn, &response); err != nil {
t.Fatal(err)
}
if response.Type != protocol.ChatMessages || response.ID != "r2" || len(response.ChatMessages) != 1 {
if response.Type != protocol.ChatMessages || response.ID != "r2" || len(response.ChatMessages) != 2 {
t.Fatalf("resume response = %+v", response)
}
message := response.ChatMessages[0]
// The prompt is retained as a user turn and the assistant reply beside it, so
// a reconnecting client re-syncs a conversation that still says who sent
// what. The user turn carries the sending client's label (the generic
// fallback when the prompt did not name one).
user := response.ChatMessages[0]
if user.Role != protocol.ChatRoleUser || len(user.Parts) != 1 || user.Parts[0].Type != protocol.ChatPartText || user.Parts[0].Text != "hi" || user.Client != chatClientLabelFallback {
t.Fatalf("resumed user turn = %+v", user)
}
message := response.ChatMessages[1]
if message.ID != "msg_1" || message.Role != protocol.ChatRoleAssistant || len(message.Parts) != 2 {
t.Fatalf("resumed message = %+v", message)
}
@@ -1361,88 +1369,6 @@ func TestChatSessionsFailsClosedWithoutOwnership(t *testing.T) {
}
}
// TestChatSessionsBusyRejectsSecondClient is the task evidence for busy state:
// while client A holds ses_1 with a blocking prompt, client B's chat_sessions
// reports ses_1 Busy=true and B's chat_prompt for ses_1 is rejected before any
// broker.Prompt call; after A disconnects the claim is released and a later list
// is no longer busy.
func TestChatSessionsBusyRejectsSecondClient(t *testing.T) {
ctx := context.Background()
store := newOperatorStore(t)
if err := store.RecordOperatorSession(ctx, "ses_1", "/work", "operator chat", protocol.ChatSessionTagOperator); err != nil {
t.Fatal(err)
}
broker := scriptedChat()
broker.block = true
broker.done = make(chan struct{})
broker.sessions = []protocol.ChatSession{{ID: "ses_1"}}
ctx, _, conns := dialChatConns(t, Options{Chat: broker, OperatorRegistry: store}, 2)
connA, connB := conns[0], conns[1]
if err := wsjson.Write(ctx, connA, protocol.Message{Type: protocol.ChatPrompt, ID: "a1", ChatPrompt: &protocol.ChatPromptRequest{SessionID: "ses_1", Text: "hi"}}); err != nil {
t.Fatal(err)
}
var ack protocol.Message
if err := wsjson.Read(ctx, connA, &ack); err != nil {
t.Fatal(err)
}
if ack.Type != protocol.ChatPrompt || ack.ID != "a1" {
t.Fatalf("prompt ack = %+v", ack)
}
if err := wsjson.Write(ctx, connB, protocol.Message{Type: protocol.ChatSessions, ID: "b1"}); err != nil {
t.Fatal(err)
}
var listing protocol.Message
if err := wsjson.Read(ctx, connB, &listing); err != nil {
t.Fatal(err)
}
if listing.Type != protocol.ChatSessions || len(listing.ChatSessions) != 1 || !listing.ChatSessions[0].Busy {
t.Fatalf("held session not marked busy: %+v", listing)
}
if err := wsjson.Write(ctx, connB, protocol.Message{Type: protocol.ChatPrompt, ID: "b2", ChatPrompt: &protocol.ChatPromptRequest{SessionID: "ses_1", Text: "hello"}}); err != nil {
t.Fatal(err)
}
var rejected protocol.Message
if err := wsjson.Read(ctx, connB, &rejected); err != nil {
t.Fatal(err)
}
if rejected.Type != protocol.Error || !strings.Contains(rejected.Error, "busy") {
t.Fatalf("second client's prompt was not rejected as busy: %+v", rejected)
}
if prompts, _, _ := broker.counts(); prompts != 1 {
t.Fatalf("busy prompt reached OpenCode: %d prompt calls, want 1", prompts)
}
// Disconnecting A releases the claim so a later client is no longer blocked.
if err := connA.Close(websocket.StatusNormalClosure, ""); err != nil {
t.Fatal(err)
}
select {
case <-broker.done:
case <-time.After(5 * time.Second):
t.Fatal("stream did not stop after disconnect")
}
deadline := time.Now().Add(5 * time.Second)
for {
if err := wsjson.Write(ctx, connB, protocol.Message{Type: protocol.ChatSessions, ID: "b3"}); err != nil {
t.Fatal(err)
}
var after protocol.Message
if err := wsjson.Read(ctx, connB, &after); err != nil {
t.Fatal(err)
}
if after.Type == protocol.ChatSessions && len(after.ChatSessions) == 1 && !after.ChatSessions[0].Busy {
return
}
if time.Now().After(deadline) {
t.Fatalf("claim not released after disconnect: %+v", after)
}
time.Sleep(10 * time.Millisecond)
}
}
// TestChatPromptPushesPermissionAndForwardsReply is the task evidence: with a
// blocking scripted stream keeping the subscription open, a seeded pending
// approval request is pushed as a chat_permission frame carrying the seeded
@@ -1522,11 +1448,29 @@ func TestChatPermissionDedupesRepeatedPolls(t *testing.T) {
mu.Unlock()
return nil
}
if sub := hub.attach("ses_1", "c1", "phone", broker, write); sub == nil {
t.Fatal("attach returned nil")
}
for i := 0; i < 3; i++ {
if err := pushChatPermissions(context.Background(), broker, hub, "ses_1", write); err != nil {
if err := hub.pollPermissionsOnce(context.Background(), broker, "ses_1"); err != nil {
t.Fatal(err)
}
}
deadline := time.Now().Add(2 * time.Second)
for {
mu.Lock()
count := len(pushed)
mu.Unlock()
if count > 0 {
break
}
if time.Now().After(deadline) {
t.Fatal("no permission frame was pushed")
}
time.Sleep(5 * time.Millisecond)
}
// Give a duplicate a chance to arrive before asserting there is none.
time.Sleep(50 * time.Millisecond)
mu.Lock()
defer mu.Unlock()
if len(pushed) != 1 {
@@ -1684,32 +1628,6 @@ func TestChatPermissionUnsupportedBackendIsQuiet(t *testing.T) {
}
}
// TestChatPermissionWriteFailureDoesNotDropRequest pins that a request id is not
// retained as "seen" when its frame could not be written, so the next poll
// re-pushes it instead of silently dropping the approval request.
func TestChatPermissionWriteFailureDoesNotDropRequest(t *testing.T) {
broker := scriptedChat()
broker.permissions = []protocol.ChatPermissionFrame{{SessionID: "ses_1", RequestID: "req_1", Action: "bash"}}
hub := newChatHub()
attempts := 0
write := func(protocol.Message) error {
attempts++
if attempts == 1 {
return fmt.Errorf("connection closed")
}
return nil
}
if err := pushChatPermissions(context.Background(), broker, hub, "ses_1", write); err == nil {
t.Fatal("a failed write must surface an error")
}
if err := pushChatPermissions(context.Background(), broker, hub, "ses_1", write); err != nil {
t.Fatalf("retry after a failed write: %v", err)
}
if attempts != 2 {
t.Fatalf("push attempts = %d, want the request re-pushed after the failure", attempts)
}
}
// TestChatAdoptRecordsEndpointSession is the chat_adopt acceptance test: the
// endpoint's own record supplies the directory and title, the handler records
// the row with the operator tag, and the response echoes the session and its
+5
View File
@@ -86,6 +86,8 @@ func HandlerWithOptions(ctx context.Context, options Options, stores ...*pipelin
if registry == nil && len(stores) > 0 {
registry = stores[0]
}
hub.baseCtx = ctx
hub.registry = registry
mux.HandleFunc("GET /artifacts/{run}/{step}/{name...}", func(w http.ResponseWriter, r *http.Request) {
if runs == nil {
http.NotFound(w, r)
@@ -139,6 +141,9 @@ func HandlerWithOptions(ctx context.Context, options Options, stores ...*pipelin
// Drop every run subscription this connection holds when the read loop
// returns, so no subscriber, goroutine or timer outlives the connection.
defer events.unsubscribeClient(clientID)
// Drop every chat subscription too, so a chat room held only by this
// connection releases its broker stream and turn runner.
defer hub.detachClient(clientID)
if len(stores) > 0 {
items, err := stores[0].List(ctx)
if err != nil {