kimaki 0.4.86 → 0.4.87

package/skills/critique/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: critique
 description: >
-  Git diff viewer and AI reviewer. Renders diffs as web pages, images, and PDFs
-  with syntax highlighting. Also provides AI-powered diff reviews via
-  `critique review --web`. Use this skill when working with critique for showing
-  diffs, generating diff URLs, selective hunk staging, or AI code reviews.
+  Git diff viewer. Renders diffs as web pages, images, and PDFs
+  with syntax highlighting. Use this skill when working with critique for showing
+  diffs, generating diff URLs, or selective hunk staging.
 ---
 
 # critique
@@ -89,39 +88,6 @@ critique hunks add 'file:@-10,6+10,7'       # stage only your hunks
 git commit -m "your changes"                 # commit separately
 ```
 
-## AI-powered diff review
-
-`critique review --web` spawns a separate opencode session that analyzes a diff, groups related
-changes, and produces a structured review with explanations, diagrams, and suggestions. Uploads
-the result as a shareable URL — much richer than a plain diff link.
-
-**This command is very slow (up to 20 minutes for large diffs).** Only run when the user
-explicitly asks for a code review or diff explanation. Warn the user it will take a while.
-Set Bash tool timeout to at least 25 minutes (`timeout: 1_500_000`).
-
-Always pass `--agent opencode` and `--session <current_session_id>` so the reviewer has context
-about why the changes were made. If you know other session IDs that produced the diff, pass them
-too with additional `--session` flags.
-
-```bash
-# Review working tree changes
-critique review --web --agent opencode --session <session_id>
-
-# Review a specific commit
-critique review --commit HEAD --web --agent opencode --session <session_id>
-
-# Review branch changes compared to main
-critique review main...HEAD --web --agent opencode --session <session_id>
-
-# Review with multiple session contexts
-critique review --commit abc1234 --web --agent opencode --session <session_id> --session <other_session_id>
-
-# Review only specific files
-critique review --web --agent opencode --session <session_id> --filter "src/**/*.ts"
-```
-
-The command prints a preview URL when done — share that URL with the user.
-
 ## Raw patch access
 
 Every `--web` upload also stores the raw unified diff. Append `.patch` to any critique URL to get it:

package/skills/gitchamber/SKILL.md

@@ -0,0 +1,93 @@
+---
+name: gitchamber
+description: CLI to download npm packages, PyPI packages, crates, or GitHub repo source code into node_modules/.gitchamber/ for analysis. Use when you need to read a package's inner workings, documentation, examples, or source code. Alternative to opensrc that stores in node_modules/ for zero-config gitignore/vitest/tsc compatibility. After fetching, analyze files with grep, read, and other tools.
+---
+
+# gitchamber
+
+CLI to download source code for npm packages, PyPI packages, crates.io crates, or GitHub repos into `node_modules/.gitchamber/`. After fetching, analyze the files using grep, read, glob, and other tools to understand inner workings, find usage examples, read documentation, or study the source code.
+
+Alternative to [opensrc](https://github.com/vercel-labs/opensrc) that stores in `node_modules/` instead of `opensrc/`.
+
+**Differences from opensrc:**
+
+- **Stores in `node_modules/.gitchamber/`** instead of `opensrc/` -- automatically ignored by git, vitest, tsc, linters, bundlers, and every other tool that skips `node_modules/`
+- **No file modification** -- removed all `.gitignore`, `tsconfig.json`, and `AGENTS.md` editing logic
+- **No `--modify` flag** or permission prompts
+- **Zero config** -- opensrc requires updating `.gitignore` and `tsconfig.json` excludes; gitchamber needs nothing
+
+Always run `gitchamber --help` first. The help output has all commands, options, and examples.
+
+## Install
+
+```bash
+npm install -g gitchamber
+```
+
+Aliases: `gitchamber`, `chamber`
+
+## Fetch packages
+
+```bash
+# npm
+chamber zod
+chamber @babel/core
+chamber react@18.2.0
+
+# PyPI
+chamber pypi:requests
+chamber pypi:flask==3.0.0
+
+# crates.io
+chamber crates:serde
+chamber crates:tokio@1.35.0
+
+# GitHub repos (owner/repo, with optional branch or tag)
+chamber vercel/ai
+chamber facebook/react#main
+chamber owner/repo@v1.0.0
+chamber https://github.com/denoland/deno
+```
+
+Multiple at once:
+
+```bash
+chamber zod react vercel/ai pypi:requests
+```
+
+## Other commands
+
+```bash
+# List fetched sources
+chamber list
+chamber list --json
+
+# Remove specific packages
+chamber remove zod
+chamber rm vercel/ai
+
+# Clean all
+chamber clean
+chamber clean --npm      # only npm
+chamber clean --pypi     # only PyPI
+chamber clean --crates   # only crates.io
+chamber clean --repos    # only repos
+```
+
+## Output location
+
+Source ends up in `node_modules/.gitchamber/<host>/<owner>/<repo>/`.
+
+Tracked in `node_modules/.gitchamber/sources.json`.
+
+## How it works
+
+1. Resolves package via registry API (npm, PyPI, crates.io)
+2. Extracts `repository` URL from metadata
+3. Shallow-clones at the matching version tag
+4. Strips `.git` directory
+5. For npm: auto-detects installed version from lockfiles
+
+## When to use
+
+Use gitchamber (or its alias `chamber`) instead of manually cloning repos into tmp directories. Prefer it over the `lib-investigator` agent when you need persistent source code on disk for repeated reads or when the agent's context isn't enough. When the user refers to opensrc, always use gitchamber instead.

package/skills/goke/SKILL.md

@@ -178,9 +178,11 @@ Without a schema, all values stay as strings. `--port 3000` → `"3000"` (string
 | `[name]` in command | Optional argument |
 | `[...files]` in command | Variadic (collects remaining args into array) |
 | `<value>` in option | Required value (error if missing) |
-| `[value]` in option | Optional value (`true` if flag present without value) |
+| `[value]` in option | Optional value (`undefined` if flag present without value) |
 | no brackets in option | Boolean flag (`undefined` if not passed, `true` if passed) |
 
+**Optionality is determined solely by bracket syntax, not by the schema.** `[square brackets]` makes an option optional regardless of whether the schema is `z.string()` or `z.string().optional()`. The schema's `.optional()` is never consulted for this — it only affects type coercion. So `z.string()` with `[--name]` is treated as optional: if the flag is omitted, `options.name` is `undefined` even though the schema has no `.optional()`.
+
 ## Global Options and Middleware
 
 Global options apply to all commands. Use `.use()` to register middleware that runs before any command action — for reacting to global options (logging, state init, auth).

package/src/agent-model.e2e.test.ts

@@ -398,7 +398,8 @@ describe('agent model resolution', () => {
         Reply with exactly: agent-model-check
         --- from: assistant (TestBot)
         ⬥ ok
-        *project ⋅ main ⋅ Ns ⋅ N% ⋅ agent-model-v2 ⋅ **test-agent***"
+        *project ⋅ main ⋅ Ns ⋅ N% ⋅ agent-model-v2 ⋅ **test-agent***
+        ⬥ ok"
       `)
       expect(footerMessage).toBeDefined()
       if (!footerMessage) {
@@ -454,7 +455,7 @@ describe('agent model resolution', () => {
         Reply with exactly: system-context-check
         --- from: assistant (TestBot)
         ⬥ system-context-ok
-        *project ⋅ main ⋅ Ns ⋅ N% ⋅ agent-model-v2 ⋅ **test-agent***"
+        *project ⋅ Ns ⋅ N% ⋅ agent-model-v2 ⋅ **test-agent***"
       `)
     },
     15_000,

package/src/commands/btw.ts

@@ -0,0 +1,158 @@
+// /btw command - Fork the current session with full context and send a new prompt.
+// Unlike /fork, this does not replay past messages in Discord. It just creates
+// a new thread, forks the entire session (no messageID), and immediately
+// dispatches the user's prompt so the forked session starts working right away.
+
+import {
+  ChannelType,
+  ThreadAutoArchiveDuration,
+  type ThreadChannel,
+  MessageFlags,
+} from 'discord.js'
+import { getThreadSession, setThreadSession } from '../database.js'
+import { initializeOpencodeForDirectory } from '../opencode.js'
+import {
+  resolveWorkingDirectory,
+  resolveTextChannel,
+  sendThreadMessage,
+} from '../discord-utils.js'
+import { getOrCreateRuntime } from '../session-handler/thread-session-runtime.js'
+import { createLogger, LogPrefix } from '../logger.js'
+import type { CommandContext } from './types.js'
+
+const logger = createLogger(LogPrefix.FORK)
+
+export async function handleBtwCommand({
+  command,
+  appId,
+}: CommandContext): Promise<void> {
+  const channel = command.channel
+
+  if (!channel) {
+    await command.reply({
+      content: 'This command can only be used in a channel',
+      flags: MessageFlags.Ephemeral,
+    })
+    return
+  }
+
+  const isThread = [
+    ChannelType.PublicThread,
+    ChannelType.PrivateThread,
+    ChannelType.AnnouncementThread,
+  ].includes(channel.type)
+
+  if (!isThread) {
+    await command.reply({
+      content:
+        'This command can only be used in a thread with an active session',
+      flags: MessageFlags.Ephemeral,
+    })
+    return
+  }
+
+  const prompt = command.options.getString('prompt', true)
+
+  const resolved = await resolveWorkingDirectory({
+    channel: channel as ThreadChannel,
+  })
+
+  if (!resolved) {
+    await command.reply({
+      content: 'Could not determine project directory for this channel',
+      flags: MessageFlags.Ephemeral,
+    })
+    return
+  }
+
+  const { projectDirectory } = resolved
+
+  const sessionId = await getThreadSession(channel.id)
+
+  if (!sessionId) {
+    await command.reply({
+      content: 'No active session in this thread',
+      flags: MessageFlags.Ephemeral,
+    })
+    return
+  }
+
+  await command.deferReply({ flags: MessageFlags.Ephemeral })
+
+  const getClient = await initializeOpencodeForDirectory(projectDirectory)
+  if (getClient instanceof Error) {
+    await command.editReply({
+      content: `Failed to fork session: ${getClient.message}`,
+    })
+    return
+  }
+
+  try {
+    // Fork the entire session (no messageID = fork at the latest point)
+    const forkResponse = await getClient().session.fork({
+      sessionID: sessionId,
+    })
+
+    if (!forkResponse.data) {
+      await command.editReply('Failed to fork session')
+      return
+    }
+
+    const forkedSession = forkResponse.data
+
+    const textChannel = await resolveTextChannel(channel as ThreadChannel)
+    if (!textChannel) {
+      await command.editReply('Could not resolve parent text channel')
+      return
+    }
+
+    const threadName = `btw: ${prompt}`.slice(0, 100)
+    const thread = await textChannel.threads.create({
+      name: threadName,
+      autoArchiveDuration: ThreadAutoArchiveDuration.OneDay,
+      reason: `btw fork from session ${sessionId}`,
+    })
+
+    // Claim the forked session immediately so external polling does not race
+    await setThreadSession(thread.id, forkedSession.id)
+
+    await thread.members.add(command.user.id)
+
+    logger.log(
+      `Created btw fork session ${forkedSession.id} in thread ${thread.id} from ${sessionId}`,
+    )
+
+    // Short status message with prompt instead of replaying past messages
+    const sourceThreadLink = `<#${channel.id}>`
+    await sendThreadMessage(
+      thread,
+      `Reusing context from ${sourceThreadLink} to answer prompt...\n${prompt}`,
+    )
+
+    // Create runtime and dispatch the prompt immediately
+    const runtime = getOrCreateRuntime({
+      threadId: thread.id,
+      thread,
+      projectDirectory,
+      sdkDirectory: projectDirectory,
+      channelId: textChannel.id,
+      appId,
+    })
+    await runtime.enqueueIncoming({
+      prompt,
+      userId: command.user.id,
+      username: command.user.displayName,
+      appId,
+      mode: 'opencode',
+    })
+
+    await command.editReply(
+      `Session forked! Continue in ${thread.toString()}`,
+    )
+  } catch (error) {
+    logger.error('Error in /btw:', error)
+    await command.editReply(
+      `Failed to fork session: ${error instanceof Error ? error.message : 'Unknown error'}`,
+    )
+  }
+}

package/src/discord-command-registration.ts

@@ -249,13 +249,7 @@ export async function registerCommands({
       })
       .setDMPermission(false)
       .toJSON(),
-    new SlashCommandBuilder()
-      .setName('toggle-mention-mode')
-      .setDescription(
-        truncateCommandDescription('Toggle mention-only mode (bot only responds when @mentioned)'),
-      )
-      .setDMPermission(false)
-      .toJSON(),
+
     new SlashCommandBuilder()
       .setName('add-project')
       .setDescription(
@@ -315,11 +309,7 @@ export async function registerCommands({
       )
       .setDMPermission(false)
       .toJSON(),
-    new SlashCommandBuilder()
-      .setName('stop')
-      .setDescription(truncateCommandDescription('Abort the current OpenCode request in this thread'))
-      .setDMPermission(false)
-      .toJSON(),
+
     new SlashCommandBuilder()
       .setName('share')
       .setDescription(truncateCommandDescription('Share the current session as a public URL'))
@@ -335,6 +325,18 @@ export async function registerCommands({
       .setDescription(truncateCommandDescription('Fork the session from a past user message'))
       .setDMPermission(false)
       .toJSON(),
+    new SlashCommandBuilder()
+      .setName('btw')
+      .setDescription(truncateCommandDescription('Ask something without polluting or blocking the current session'))
+      .addStringOption((option) => {
+        option
+          .setName('prompt')
+          .setDescription(truncateCommandDescription('The message to send in the forked session'))
+          .setRequired(true)
+        return option
+      })
+      .setDMPermission(false)
+      .toJSON(),
     new SlashCommandBuilder()
       .setName('model')
       .setDescription(truncateCommandDescription('Set the preferred model for this channel or session'))
@@ -456,13 +458,7 @@ export async function registerCommands({
       )
       .setDMPermission(false)
       .toJSON(),
-    new SlashCommandBuilder()
-      .setName('memory-snapshot')
-      .setDescription(
-        truncateCommandDescription('Write a V8 heap snapshot to disk for memory debugging'),
-      )
-      .setDMPermission(false)
-      .toJSON(),
+
     new SlashCommandBuilder()
       .setName('upgrade-and-restart')
       .setDescription(
@@ -494,10 +490,50 @@ export async function registerCommands({
       .toJSON(),
   ]
 
-  // Add user-defined commands with source-based suffixes (-cmd / -skill)
+  // Dynamic commands are registered in priority order: agents → user commands → skills → MCP prompts.
+  // This ordering matters because we slice to MAX_DISCORD_COMMANDS (100) at the end,
+  // so lower-priority dynamic commands get trimmed first if the total exceeds the limit.
+
+  // 1. Agent-specific quick commands like /plan-agent, /build-agent
+  // Filter to primary/all mode agents (same as /agent command shows), excluding hidden agents
+  const primaryAgents = agents.filter(
+    (a) => (a.mode === 'primary' || a.mode === 'all') && !a.hidden,
+  )
+  for (const agent of primaryAgents) {
+    const sanitizedName = sanitizeAgentName(agent.name)
+    // Skip if sanitized name is empty or would create invalid command name
+    // Discord command names must start with a lowercase letter or number
+    if (!sanitizedName || !/^[a-z0-9]/.test(sanitizedName)) {
+      continue
+    }
+    // Truncate base name before appending suffix so the -agent suffix is never
+    // lost to Discord's 32-char command name limit.
+    const agentSuffix = '-agent'
+    const agentBaseName = sanitizedName.slice(0, 32 - agentSuffix.length)
+    const commandName = `${agentBaseName}${agentSuffix}`
+    const description = buildQuickAgentCommandDescription({
+      agentName: agent.name,
+      description: agent.description,
+    })
+
+    commands.push(
+      new SlashCommandBuilder()
+        .setName(commandName)
+        .setDescription(truncateCommandDescription(description))
+        .setDMPermission(false)
+        .toJSON(),
+    )
+  }
+
+  // 2. User-defined commands, skills, and MCP prompts (ordered by priority)
   // Also populate registeredUserCommands in the store for /queue-command autocomplete
   const newRegisteredCommands: RegisteredUserCommand[] = []
-  for (const cmd of userCommands) {
+  // Sort: regular commands first, then skills, then MCP prompts
+  const sourceOrder: Record<string, number> = { config: 0, skill: 1, mcp: 2 }
+  const sortedUserCommands = [...userCommands].sort((a, b) => {
+    return (sourceOrder[a.source || ''] ?? 0) - (sourceOrder[b.source || ''] ?? 0)
+  })
+  for (const cmd of sortedUserCommands) {
     if (SKIP_USER_COMMANDS.includes(cmd.name)) {
       continue
     }
@@ -549,35 +585,14 @@ export async function registerCommands({
   }
   store.setState({ registeredUserCommands: newRegisteredCommands })
 
-  // Add agent-specific quick commands like /plan-agent, /build-agent
-  // Filter to primary/all mode agents (same as /agent command shows), excluding hidden agents
-  const primaryAgents = agents.filter(
-    (a) => (a.mode === 'primary' || a.mode === 'all') && !a.hidden,
-  )
-  for (const agent of primaryAgents) {
-    const sanitizedName = sanitizeAgentName(agent.name)
-    // Skip if sanitized name is empty or would create invalid command name
-    // Discord command names must start with a lowercase letter or number
-    if (!sanitizedName || !/^[a-z0-9]/.test(sanitizedName)) {
-      continue
-    }
-    // Truncate base name before appending suffix so the -agent suffix is never
-    // lost to Discord's 32-char command name limit.
-    const agentSuffix = '-agent'
-    const agentBaseName = sanitizedName.slice(0, 32 - agentSuffix.length)
-    const commandName = `${agentBaseName}${agentSuffix}`
-    const description = buildQuickAgentCommandDescription({
-      agentName: agent.name,
-      description: agent.description,
-    })
-
-    commands.push(
-      new SlashCommandBuilder()
-        .setName(commandName)
-        .setDescription(truncateCommandDescription(description))
-        .setDMPermission(false)
-        .toJSON(),
+  // Discord allows max 100 guild commands. Slice to stay within the limit,
+  // trimming lowest-priority dynamic commands (MCP prompts, then skills) first.
+  const MAX_DISCORD_COMMANDS = 100
+  if (commands.length > MAX_DISCORD_COMMANDS) {
+    cliLogger.warn(
+      `COMMANDS: ${commands.length} commands exceed Discord limit of ${MAX_DISCORD_COMMANDS}, truncating to ${MAX_DISCORD_COMMANDS}`,
     )
+    commands.length = MAX_DISCORD_COMMANDS
   }
 
   const rest = createDiscordRest(token)

package/src/interaction-handler.ts

@@ -23,7 +23,7 @@ import {
 import { handleToggleWorktreesCommand } from './commands/worktree-settings.js'
 import { handleWorktreesCommand } from './commands/worktrees.js'
 import { handleTasksCommand } from './commands/tasks.js'
-import { handleToggleMentionModeCommand } from './commands/mention-mode.js'
+
 import {
   handleResumeCommand,
   handleResumeAutocomplete,
@@ -43,6 +43,7 @@ import { handleCompactCommand } from './commands/compact.js'
 import { handleShareCommand } from './commands/share.js'
 import { handleDiffCommand } from './commands/diff.js'
 import { handleForkCommand, handleForkSelectMenu } from './commands/fork.js'
+import { handleBtwCommand } from './commands/btw.js'
 import {
   handleModelCommand,
   handleProviderSelectMenu,
@@ -93,7 +94,7 @@ import { handleRestartOpencodeServerCommand } from './commands/restart-opencode-
 import { handleRunCommand } from './commands/run-command.js'
 import { handleContextUsageCommand } from './commands/context-usage.js'
 import { handleSessionIdCommand } from './commands/session-id.js'
-import { handleMemorySnapshotCommand } from './commands/memory-snapshot.js'
+
 import { handleUpgradeAndRestartCommand } from './commands/upgrade.js'
 import { handleMcpCommand, handleMcpSelectMenu } from './commands/mcp.js'
 import {
@@ -218,12 +219,6 @@ export function registerInteractionHandler({
               })
               return
 
-            case 'toggle-mention-mode':
-              await handleToggleMentionModeCommand({
-                command: interaction,
-                appId,
-              })
-              return
 
             case 'resume':
               await handleResumeCommand({ command: interaction, appId })
@@ -245,7 +240,6 @@ export function registerInteractionHandler({
               return
 
             case 'abort':
-            case 'stop':
               await handleAbortCommand({ command: interaction, appId })
               return
 
@@ -265,6 +259,10 @@ export function registerInteractionHandler({
               await handleForkCommand(interaction)
               return
 
+            case 'btw':
+              await handleBtwCommand({ command: interaction, appId })
+              return
+
             case 'model':
               await handleModelCommand({ interaction, appId })
               return
@@ -328,12 +326,7 @@ export function registerInteractionHandler({
               await handleSessionIdCommand({ command: interaction, appId })
               return
 
-            case 'memory-snapshot':
-              await handleMemorySnapshotCommand({
-                command: interaction,
-                appId,
-              })
-              return
+
 
             case 'upgrade-and-restart':
               await handleUpgradeAndRestartCommand({

package/src/markdown.test.ts

@@ -222,6 +222,22 @@ test('generate markdown with system info', async () => {
 
 
     *Completed in Xs*
+
+    ### 🤖 Assistant (deterministic-v2)
+
+    **Started using deterministic-provider/deterministic-v2**
+
+    Hello! This is a deterministic markdown test response.
+
+
+    *Completed in Xs*
+
+    ### 🤖 Assistant (deterministic-v2)
+
+    **Started using deterministic-provider/deterministic-v2**
+
+    Hello! This is a deterministic markdown test response.
+
     "
   `)
 })
@@ -261,6 +277,22 @@ test('generate markdown without system info', async () => {
 
 
     *Completed in Xs*
+
+    ### 🤖 Assistant (deterministic-v2)
+
+    **Started using deterministic-provider/deterministic-v2**
+
+    Hello! This is a deterministic markdown test response.
+
+
+    *Completed in Xs*
+
+    ### 🤖 Assistant (deterministic-v2)
+
+    **Started using deterministic-provider/deterministic-v2**
+
+    Hello! This is a deterministic markdown test response.
+
     "
   `)
 })