@geminixiang/mikan 1.0.0-beta.2 → 1.0.0-beta.21

package/CHANGELOG.md

@@ -9,6 +9,394 @@ any release.
 
 ## [Unreleased]
 
+## [1.0.0-beta.21]
+
+### Added
+
+- Fold each subagent's tokens and cost into the parent run's tally (`MikanAgentSession.recordExternalUsage`), so delegated spend counts against the parent run's budget instead of staying invisible to it.
+- Add a process-wide subagent fan-out ceiling shared across conversations.
+- Add `mikan --help` and a generated `mikan env` inventory from the daemon environment manifest.
+- Make the working-directory argument optional, defaulting to `<state-dir>/workspace`.
+- Add a public Gondolin runtime bootstrap seam for embedders.
+
+### Changed
+
+- Subagent runs never reject: request validation failures (unknown tools, invalid budgets, empty tasks, nested runs) now resolve to `failed` results, so one bad request in a `tasks`/`dag` batch can no longer orphan in-flight sibling subagents.
+- Cap parallel `tasks[]` batches at 4 concurrent subagents (the same limit as DAG mode) and run DAG waves through a slot pool instead of chunk barriers.
+- Report a subagent final response with no text as `failed` instead of `completed` with empty output.
+- Enforce parent budgets immediately when subagent usage is folded into the parent run.
+- Apply one state-directory precedence rule across boot, extensions, Sentry, and runtime readers.
+- Refuse model and sandbox settings updates while a conversation is busy, and invalidate affected cached runners consistently.
+- Drive PM2 environment configuration from `~/.mikan/mikan.env` instead of inline secrets.
+
+### Fixed
+
+- Harden Gondolin dial-home reconnects after transport failures and stale sessions.
+- Reject invalid one-shot event timestamps consistently across all event writers.
+- Apply global model settings to idle conversations and report busy conversations as stale.
+
+### Security
+
+- Keep PM2 secrets in an owner-only file outside repository trees and make the PM2 template supervision-only.
+
+### Tests
+
+- Add coverage for subagent accounting and concurrency, CLI and environment manifests, settings mutation, Gondolin reconnects and contracts, event formatting, and worker state layout.
+
+## [1.0.0-beta.20]
+
+### Fixed
+
+- Validate subagent `outputSchema` correctly when it arrives as plain JSON Schema (the only form tool calls can carry), instead of throwing `ValueCheckUnknownTypeError` because it lacks TypeBox's `Kind` metadata.
+
+### Tests
+
+- Add coverage for plain JSON Schema hydration, nested objects, arrays, unions, and validation failures.
+
+## [1.0.0-beta.19]
+
+### Added
+
+- Add fresh in-memory subagents for the main agent and extensions, with explicit tools, budgets, structured output, parallel batches, and bounded DAG orchestration.
+- Stream debounced subagent node progress through the shared Slack, Discord, and Telegram response lifecycle.
+
+### Changed
+
+- Let final responses at the LLM-call cap complete without tripping the run budget when no continuation is required.
+
+### Fixed
+
+- Install worker binaries from the newest GitHub release that contains a matching asset, including prereleases.
+- Restore generic Google Workspace CLI credential mounts in sandbox vaults.
+
+### Tests
+
+- Add coverage for subagent isolation, recursion guards, budgets, structured output, parallel execution, DAG validation and dependency flow, and platform-neutral progress rendering.
+
+## [1.0.0-beta.18]
+
+### Added
+
+- Add an idempotent Debian and Ubuntu worker-host initialization script.
+- Add persistent `mikan-worker` installation as a delegated systemd service.
+- Add NFS export detection with OS-specific setup guidance for `gondolin:remote` workspaces.
+- Ship host-side vault credential files securely to remote workers without placing them in the shared workspace.
+- Add bounded shared-workspace health probes and worker degradation reporting.
+
+### Changed
+
+- Require each Gondolin remote gateway and static worker to declare its shared `workspaceRoot`.
+- Exclude workers with unhealthy shared workspaces from new placements and restore them after a healthy heartbeat.
+
+### Fixed
+
+- Fail remote execution with actionable diagnostics instead of hanging on dead shared-workspace mounts.
+- Create runtime cgroups beneath the worker's delegated cgroup and report missing `Delegate=yes` configuration.
+- Verify downloaded worker binaries against the matching release checksum filename.
+- Validate `gondolin:remote` only after gateway and worker transports are configured.
+
+### Security
+
+- Materialize remote credential files as owner-only, read-only runtime files outside shared workspaces.
+
+### Tests
+
+- Add coverage for worker host services, cgroup delegation, workspace health, credential delivery, NFS advice, remote validation, and idle execution deadlines.
+
+## [1.0.0-beta.17]
+
+### Added
+
+- Add `gondolin:remote` for scheduling sandbox runtimes across a fleet of Linux/KVM workers.
+- Add a standalone `mikan-worker` daemon with mutual TLS, fenced leases, crash recovery, capacity-aware placement, draining, and sticky conversation assignment.
+- Add dial-home worker enrollment through one-time join tokens and a mikan-hosted gateway.
+- Add private workspace projection, vault injection, resource limits, lifecycle reconciliation, and drift recovery to Gondolin runtimes.
+- Add worker installation, enrollment, operations, and remote quickstart documentation with a one-command end-to-end smoke test.
+- Publish `mikan-worker` binaries and checksums with GitHub releases.
+
+### Changed
+
+- Rename the preview sandbox mode from `microvm:default` to `gondolin:default` and the image build command to `npm run gondolin:image:build`.
+
+### Fixed
+
+- Project mounted files correctly into Gondolin guests.
+- Refresh rotated credentials when Gondolin runtimes are recreated.
+
+### Security
+
+- Authenticate remote workers with mutual TLS and fence stale workers through expiring leases.
+- Keep enrollment tokens one-time and store worker credentials privately.
+
+### Tests
+
+- Add coverage for Gondolin lifecycle, workspace isolation, vaults, resource controls, fleet scheduling, gateways, enrollment, workers, leases, and remote execution.
+
+## [1.0.0-beta.16]
+
+### Added
+
+- Add a preview `gondolin:default` sandbox backed by Gondolin and QEMU.
+- Add a curated microVM guest image build with Node.js, Python, uv, Git, ripgrep, fd, jq, SSH, and build tools.
+- Manage one process-local microVM per conversation with idle shutdown and recreation on demand.
+
+### Changed
+
+- Broaden the coverage gate across all source modules.
+
+### Fixed
+
+- Keep top-level Slack file uploads out of threads.
+
+### Tests
+
+- Add coverage for microVM execution and lifecycle, events, logging, disabled vaults, channel storage, and core file and shell tools.
+
+## [1.0.0-beta.15]
+
+### Added
+
+- Add native image generation with automatic upload through the active model provider.
+- Add extension chat commands via `api.registerCommand`: deterministic `/name` dispatch with no model call; built-ins and first registrations win.
+- Add an extension disposal lifecycle (`api.onDispose` or an `activate` return value), run when a harness instance is discarded (`/pi-new`, idle eviction, session rotation).
+- Add `api.triggerRun(text)` to fire an immediate autonomous agent run, `api.uploadFile(path, title)` for proactive file uploads, and an explicit `conversationId` option on `api.notify` for cross-conversation posting.
+- Add `agent_error` and `budget_exceeded` extension hooks so monitoring extensions see failed turns and tripped run budgets.
+- Pass a `RunOrigin` (platform, triggering message id, user identity, attachments) to extension hook events, making `api.react` and per-user extension policy usable.
+- Let `before_agent_start` extensions rewrite the user prompt or block the turn before the model runs; blocked turns leave no trace in the transcript or session store.
+- Let `tool_result` extensions rewrite tool output (content and error flag) before the model and the session store see it, enabling secret redaction and output truncation.
+
+### Changed
+
+- Dispatch `before_agent_start` and `tool_result` hooks with chaining semantics (each handler sees earlier handlers' rewrites; any `block` wins) instead of first-result-wins.
+
+### Fixed
+
+- Dispose cached runners when models switch or environment credentials refresh.
+
+### Tests
+
+- Add coverage for image generation, extension lifecycle and hook rewrites, and runner disposal.
+
+## [1.0.0-beta.14]
+
+### Added
+
+- Add GitHub inline review-thread intake and a `github_review_reply` tool.
+- Add `github_sync`, `github_read`, and `github_issue` tools for repository refresh and issue or pull request operations.
+- Add host-side Cloud Build log retrieval using GCP ADC or Workload Identity Federation.
+- Add a minimal embedder example that runs without portal services.
+
+### Changed
+
+- Update eligible GitHub pull request head branches in place instead of opening duplicate pull requests.
+- Drive platform command registration and routing from a shared command manifest.
+- Use one cross-platform stop grammar, including `/stop` in GitHub conversations.
+- Route sandbox file reads and writes through executors with staged, shell-safe transport.
+- Keep sandbox settings nested through configuration resolution and updates.
+
+### Fixed
+
+- Preserve raw session keys when using Slack's Force Stop button.
+- Spill large bash output into the runtime workspace so sandboxed agents can read it.
+- Keep malformed event files visible in the admin portal for deletion.
+- Unify platform formatting guidance across adapter and conversation contexts.
+
+### Security
+
+- Keep Cloud Build credentials host-side and outside agent sandboxes.
+- Centralize runtime identity and sandbox path sanitization.
+
+### Tests
+
+- Add coverage for GitHub tool operations, review threads, Cloud Build logs, executor file transport, command manifests, runtime embedding, and session serialization.
+
+## [1.0.0-beta.13]
+
+### Added
+
+- Add the `max` thinking level to commands, configuration, and the admin portal.
+- Add quickstart and extension development guides across all supported locales.
+
+### Changed
+
+- Update pi agent dependencies to 0.80.6.
+- Load platform-specific tool packs only for their configured adapters.
+- Improve `github_checks` output and guidance for external CI providers.
+- Synchronize configuration, platform, sandbox, session, skill, event, portal, and deployment documentation across locales.
+
+### Fixed
+
+- Fix broken CLI tables and dead documentation links across locales.
+
+### Security
+
+- Derive ambient shared-vault access from each platform's declared trust model and sandbox topology.
+
+### Tests
+
+- Add coverage for platform tool-pack isolation, external CI checks, and vault trust policy.
+
+## [1.0.0-beta.12]
+
+### Added
+
+- Let `github_checks` fetch the log tail for a failing GitHub Actions job by job ID.
+
+### Changed
+
+- Require GitHub App Actions read permission for job log inspection.
+
+### Fixed
+
+- Treat skipped and neutral GitHub checks separately from failures in check summaries.
+
+### Tests
+
+- Add coverage for job log retrieval and check conclusion classification.
+- Use collision-resistant temporary directories across parallel tests.
+
+## [1.0.0-beta.11]
+
+### Added
+
+- Add a read-only `github_checks` tool for inspecting branch and pull request check runs.
+
+### Changed
+
+- Make `github_pr` idempotent so pushing an existing branch updates its open pull request.
+- Teach the GitHub agent workflow to inspect CI, fix failures, and push updates.
+- Require GitHub App Checks read permission for CI inspection.
+
+### Tests
+
+- Add coverage for GitHub check summaries and existing pull request updates.
+
+## [1.0.0-beta.10]
+
+### Fixed
+
+- Retry cloning a GitHub repository on later triggers when the conversation clone is missing.
+
+### Security
+
+- Stop applying the ambient default shared vault to GitHub conversations while preserving explicit conversation vault grants.
+- Document the platform, shared machine, and personal credential trust boundaries.
+
+### Tests
+
+- Add coverage for GitHub clone retries and platform-gated default vault resolution.
+
+## [1.0.0-beta.9]
+
+### Added
+
+- Clone GitHub repositories into conversation workspaces and check out pull request heads.
+- Add a `github_pr` tool that pushes agent changes from `pi/*` branches and opens pull requests.
+
+### Changed
+
+- Require GitHub App Contents read and write permission for repository automation.
+- Post completed GitHub responses as single comments instead of streaming edits.
+
+### Fixed
+
+- Keep GitHub issue context inside the history recency window.
+
+### Security
+
+- Require commenters to have repository write permission or higher before triggering the agent.
+- Keep installation tokens out of sandboxes and restrict agent pushes to non-force `pi/*` branches.
+
+### Tests
+
+- Add coverage for GitHub repository checkout, permission gating, pull request creation, and branch restrictions.
+
+## [1.0.0-beta.8]
+
+### Added
+
+- Add a GitHub messaging adapter where each issue or pull request is an independent conversation.
+- Add GitHub App authentication, mention and participation triggers, persisted polling cursors, and downtime replay.
+- Add GitHub adapter deployment configuration and documentation.
+
+### Tests
+
+- Add coverage for GitHub polling, authentication, conversation context, triggers, and responses.
+
+## [1.0.0-beta.7]
+
+### Added
+
+- Add TypeScript and npm-package extensions with `package.json` entrypoints and runtime dependencies.
+- Add `mikan ext install`, `validate`, `list`, and `remove` commands.
+- Add extension installation from Git sources and repository subpaths.
+
+### Changed
+
+- Treat reinstalling an extension as an update while preserving its data directory.
+- Use `package.json` as the primary extension metadata source with `manifest.json` as a fallback.
+- Convert the agent project manager example to TypeScript with a typed extension API.
+- Add the Slack `reactions:write` scope and missing slash commands to the manifests and setup guides.
+
+### Tests
+
+- Add coverage for TypeScript loading, package metadata, extension CLI operations, and Git installation.
+
+## [1.0.0-beta.6]
+
+### Added
+
+- Add emoji reactions for agents and extensions across Slack, Discord, and Telegram.
+
+### Changed
+
+- Default the agent project manager example to conversation-scoped extension data.
+- Log when extensions rewrite the system prompt and report the resulting size change.
+
+### Fixed
+
+- Render Slack session links outside the triggered-by italic span.
+
+### Tests
+
+- Add coverage for the reaction tool and extension reaction API.
+
+## [1.0.0-beta.5]
+
+### Added
+
+- Add `api.paths.sharedDataDir` for extension state intentionally shared across conversations.
+- Add an idempotent, dry-run-first script for migrating extension code and data to the new layout.
+
+### Changed
+
+- Store conversation extension code and data under `conversations/<id>/` and global extension assets under `global/`.
+- Make `api.paths.dataDir` conversation-scoped by default to prevent accidental cross-conversation state sharing.
+
+### Tests
+
+- Update extension loader and command coverage for the conversation-scoped layout.
+
+## [1.0.0-beta.4]
+
+### Changed
+
+- Show an extension's slug in `/pi-extensions` when it differs from the manifest display name.
+
+### Fixed
+
+- Reject extensions installed directly at a scope root and show an actionable warning to use a named subdirectory.
+
+### Tests
+
+- Add coverage for scope-root extension mis-install detection and inventory warnings.
+
+## [1.0.0-beta.3]
+
+### Fixed
+
+- Route `/pi-extensions` through Slack and include it in the bundled app manifests.
+
 ## [1.0.0-beta.2]
 
 ### Added

package/README.md

@@ -9,6 +9,9 @@
 
 A multi-platform AI coding agent for Slack, Telegram, and Discord.
 
+> [!WARNING]
+> **Pre-1.0 status** — the overall framework stabilizes at 1.0.0. Until then, releases may change settings and on-disk data formats without migrations: upgrading between pre-1.0 versions can require resetting or manually adjusting existing state and workspace data.
+
 ## Architecture
 
 mikan keeps the chat record, agent session, and execution runtime separate:
@@ -51,21 +54,51 @@ npm install && npm run build
 
 ## Quick Start
 
-All platforms share the same CLI:
+Run mikan under [PM2](https://pm2.keymetrics.io/) so it stays up, restarts after failures, and starts on boot:
+
+```bash
+npm i -g @geminixiang/mikan pm2
+
+# One-time setup: create the state directory and settings
+mikan --onboard --state-dir=~/.mikan
+
+# Secrets live in ~/.mikan/mikan.env (0600), outside any repo tree
+curl -o ~/.mikan/mikan.env https://raw.githubusercontent.com/geminixiang/mikan/main/deploy/pm2/mikan.env.example
+chmod 600 ~/.mikan/mikan.env   # then fill in your tokens
+
+# Grab the maintained ecosystem file (supervision only), edit `args`
+curl -O https://raw.githubusercontent.com/geminixiang/mikan/main/deploy/pm2/ecosystem.config.cjs
+
+pm2 start ecosystem.config.cjs
+pm2 save
+pm2 startup   # run the printed command to enable boot autostart
+```
+
+Each file has one job: `settings.json` holds behavior (model, sandbox limits, reply modes — the Admin surface), `~/.mikan/mikan.env` holds secrets and platform tokens, and `ecosystem.config.cjs` holds process supervision only. In `ecosystem.config.cjs`, point `args` at your state dir, sandbox mode, and working directory (`mikan --help` documents the flags):
+
+```js
+args: "--state-dir=/srv/mikan/state --sandbox=host /srv/mikan/workspace",
+```
+
+Set the platform tokens you need in `~/.mikan/mikan.env`; you can run multiple platforms at once. `mikan env` prints the full inventory and what is currently set:
 
 ```bash
-mikan [--state-dir=~/.mikan] [--sandbox=<mode>] <working-directory>
+SLACK_APP_TOKEN=xapp-...
+SLACK_BOT_TOKEN=xoxb-...
+TELEGRAM_BOT_TOKEN=123456:ABC-...
+DISCORD_BOT_TOKEN=MTI...
 ```
 
-Set the platform tokens you need; you can run multiple platforms at once:
+Tail logs with `pm2 logs mikan`; upgrade with `npm i -g @geminixiang/mikan && pm2 reload mikan`. See [the deployment guide](src/content/docs/deployment.mdx) for sandbox images, graceful shutdown, and the health endpoint.
+
+For a one-off foreground run, the same CLI works directly:
 
 ```bash
-export SLACK_APP_TOKEN=xapp-...
-export SLACK_BOT_TOKEN=xoxb-...
-export TELEGRAM_BOT_TOKEN=123456:ABC-...
-export DISCORD_BOT_TOKEN=MTI...
+mikan [--state-dir=~/.mikan] [--sandbox=<mode>] [<working-directory>]
 ```
 
+The working directory is optional: it defaults to `<state-dir>/workspace` (so `~/.mikan/workspace` with the default state dir) and is created on first run.
+
 ## Platforms
 
 - **Slack** — create a Socket Mode app using [src/content/docs/slack-bot-minimal-guide.md](src/content/docs/slack-bot-minimal-guide.md). The bot responds when `@mentioned` in channels and to all DMs.
@@ -88,16 +121,16 @@ For routing, mounts, vault behavior, managed container details, and Firecracker/
 
 ## Chat commands
 
-| Command                                                    | Purpose                                          |
-| ---------------------------------------------------------- | ------------------------------------------------ |
-| `/login` / `/pi-login`                                     | Store API keys or run built-in OAuth flows       |
-| `session` / `/session`                                     | Open a read-only web view of the current session |
-| `new` / `/new`                                             | Reset the current session                        |
-| `model` / `/model` / `/pi-model provider/model[:thinking]` | Switch the LLM for the current conversation      |
-| `auto-reply` / `/pi-auto-reply on\|off\|status`            | Control group/channel auto-reply                 |
-| `stop` / `/stop`                                           | Stop the current run                             |
+| Command                                          | Purpose                                          |
+| ------------------------------------------------ | ------------------------------------------------ |
+| `/login` / `/pi-login`                           | Store API keys or run built-in OAuth flows       |
+| `session` / `/session`                           | Open a read-only web view of the current session |
+| `/new` / `/pi-new`                               | Reset the current session                        |
+| `/model` / `/pi-model provider/model[:thinking]` | Switch the LLM for the current conversation      |
+| `/auto-reply` / `/pi-auto-reply on\|off\|status` | Control group/channel auto-reply                 |
+| `stop` / `/stop`                                 | Stop the current run (works on every platform)   |
 
-See [src/content/docs/commands.md](src/content/docs/commands.md) for command details and web session viewer setup.
+`session` is the only command accepted without a leading slash. See [src/content/docs/commands.mdx](src/content/docs/commands.mdx) for the full command reference and web session viewer setup.
 
 ## Configuration
 

package/dist/adapter.d.ts

@@ -1,2 +1,2 @@
-export type { MessagingBot, ConversationContext, ConversationEvent, MessagingEventHandler, ChatAdapter, ConversationMessage, ConversationResponder, ChatToolResult, ConversationKind, MessagingInfo, PlatformName, PlatformNotifier, RunningSession, } from "./types.js";
+export type { MessagingBot, ConversationContext, ConversationEvent, MessagingEventHandler, ChatAdapter, ConversationMessage, ConversationResponder, ChatToolResult, ConversationKind, MessagingInfo, PlatformName, PlatformNotifier, PlatformReactor, PlatformUploader, RunningSession, } from "./types.js";
 //# sourceMappingURL=adapter.d.ts.map

package/dist/adapter.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../src/adapter.ts"],"names":[],"mappings":"AAAA,YAAY,EACV,YAAY,EACZ,mBAAmB,EACnB,iBAAiB,EACjB,qBAAqB,EACrB,WAAW,EACX,mBAAmB,EACnB,qBAAqB,EACrB,cAAc,EACd,gBAAgB,EAChB,aAAa,EACb,YAAY,EACZ,gBAAgB,EAChB,cAAc,GACf,MAAM,YAAY,CAAC"}
+{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../src/adapter.ts"],"names":[],"mappings":"AAAA,YAAY,EACV,YAAY,EACZ,mBAAmB,EACnB,iBAAiB,EACjB,qBAAqB,EACrB,WAAW,EACX,mBAAmB,EACnB,qBAAqB,EACrB,cAAc,EACd,gBAAgB,EAChB,aAAa,EACb,YAAY,EACZ,gBAAgB,EAChB,eAAe,EACf,gBAAgB,EAChB,cAAc,GACf,MAAM,YAAY,CAAC"}

package/dist/adapter.js.map

@@ -1 +1 @@
-{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../src/adapter.ts"],"names":[],"mappings":"","sourcesContent":["export type {\n  MessagingBot,\n  ConversationContext,\n  ConversationEvent,\n  MessagingEventHandler,\n  ChatAdapter,\n  ConversationMessage,\n  ConversationResponder,\n  ChatToolResult,\n  ConversationKind,\n  MessagingInfo,\n  PlatformName,\n  PlatformNotifier,\n  RunningSession,\n} from \"./types.js\";\n"]}
+{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../src/adapter.ts"],"names":[],"mappings":"","sourcesContent":["export type {\n  MessagingBot,\n  ConversationContext,\n  ConversationEvent,\n  MessagingEventHandler,\n  ChatAdapter,\n  ConversationMessage,\n  ConversationResponder,\n  ChatToolResult,\n  ConversationKind,\n  MessagingInfo,\n  PlatformName,\n  PlatformNotifier,\n  PlatformReactor,\n  PlatformUploader,\n  RunningSession,\n} from \"./types.js\";\n"]}

package/dist/adapters/buffered-responder.d.ts

@@ -0,0 +1,60 @@
+import type { ChatToolResult, ConversationResponder } from "../adapter.js";
+import { type ChatResponseErrorOperation } from "./shared.js";
+/**
+ * The per-platform verbs and policy behind one buffered responder. Everything
+ * else — the accumulated-text state machine, split-first-then-continuations
+ * posting, response-id capture, ordered-queue error choreography, typing
+ * interval, working indicator, delete semantics — is owned by
+ * {@link createBufferedResponder} and identical on every buffered platform.
+ * (Slack keeps its own streaming lifecycle; this covers the platforms that
+ * edit one response message in place.)
+ */
+export interface BufferedResponderPlatform {
+    /** Log label, e.g. "Discord". */
+    label: string;
+    /** Hard message length; longer responses continue in extra messages. */
+    maxLength: number;
+    formatContinuation: (partNum: number) => string;
+    /** Prefix for respondDiagnostic({style:"error"}). */
+    errorPrefix: string;
+    /** Platform text normalization applied before accumulation (e.g. HTML). */
+    sanitize?: (text: string) => string;
+    /**
+     * Suffix rendered while the run is working (and re-rendered away by
+     * setWorking(false)). Platforms without one leave setWorking to typing.
+     */
+    workingIndicator?: string;
+    /** Enable appendResponseDelta/finishResponse over a buffered stream. */
+    streaming: boolean;
+    typing?: {
+        send: () => Promise<unknown>;
+        intervalMs: number;
+        /** Also stop the indicator when a message is actually sent. */
+        stopOnSend?: boolean;
+    };
+    formatToolResult: (result: ChatToolResult) => string;
+    reportError: (err: unknown, operation: ChatResponseErrorOperation, extra: Record<string, unknown>) => void;
+    /** Posted into the conversation after a send fails (e.g. Telegram's ⚠️). */
+    notifySendFailure?: (errorMessage: string) => Promise<void>;
+    /** Post the first response message; returns its platform id. */
+    post: (text: string) => Promise<string>;
+    /** Edit the existing response message. */
+    update: (id: string, text: string) => Promise<void>;
+    /** Post an out-of-band message (continuations, diagnostics). */
+    postExtra: (text: string, responseId: string | null) => Promise<unknown>;
+    /** Delete the response message. */
+    delete?: (id: string) => Promise<void>;
+    /** Record a bot response chunk against the response message id. */
+    logBotResponse?: (text: string, id: string) => void;
+    /** Direct upload; absent platforms fall back to uploadFallbackNote. */
+    uploadFile?: (filePath: string, title?: string) => Promise<void>;
+    /** Posted (queued) instead of uploading when uploadFile is absent. */
+    uploadFallbackNote?: (name: string) => string;
+    react?: (emoji: string) => Promise<void>;
+}
+/** The tool-result rendering shared by the Markdown platforms (Discord, GitHub). */
+export declare function formatMarkdownToolResult(result: ChatToolResult): string;
+export declare function createBufferedResponder(platform: BufferedResponderPlatform): {
+    responder: ConversationResponder;
+};
+//# sourceMappingURL=buffered-responder.d.ts.map

package/dist/adapters/buffered-responder.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"buffered-responder.d.ts","sourceRoot":"","sources":["../../src/adapters/buffered-responder.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,qBAAqB,EAAE,MAAM,eAAe,CAAC;AAE3E,OAAO,EAA6B,KAAK,0BAA0B,EAAE,MAAM,aAAa,CAAC;AAGzF;;;;;;;;GAQG;AACH,MAAM,WAAW,yBAAyB;IACxC,iCAAiC;IACjC,KAAK,EAAE,MAAM,CAAC;IACd,wEAAwE;IACxE,SAAS,EAAE,MAAM,CAAC;IAClB,kBAAkB,EAAE,CAAC,OAAO,EAAE,MAAM,KAAK,MAAM,CAAC;IAChD,qDAAqD;IACrD,WAAW,EAAE,MAAM,CAAC;IACpB,2EAA2E;IAC3E,QAAQ,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,MAAM,CAAC;IACpC;;;OAGG;IACH,gBAAgB,CAAC,EAAE,MAAM,CAAC;IAC1B,wEAAwE;IACxE,SAAS,EAAE,OAAO,CAAC;IACnB,MAAM,CAAC,EAAE;QACP,IAAI,EAAE,MAAM,OAAO,CAAC,OAAO,CAAC,CAAC;QAC7B,UAAU,EAAE,MAAM,CAAC;QACnB,+DAA+D;QAC/D,UAAU,CAAC,EAAE,OAAO,CAAC;KACtB,CAAC;IACF,gBAAgB,EAAE,CAAC,MAAM,EAAE,cAAc,KAAK,MAAM,CAAC;IACrD,WAAW,EAAE,CACX,GAAG,EAAE,OAAO,EACZ,SAAS,EAAE,0BAA0B,EACrC,KAAK,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,KAC3B,IAAI,CAAC;IACV,4EAA4E;IAC5E,iBAAiB,CAAC,EAAE,CAAC,YAAY,EAAE,MAAM,KAAK,OAAO,CAAC,IAAI,CAAC,CAAC;IAC5D,gEAAgE;IAChE,IAAI,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,OAAO,CAAC,MAAM,CAAC,CAAC;IACxC,0CAA0C;IAC1C,MAAM,EAAE,CAAC,EAAE,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,KAAK,OAAO,CAAC,IAAI,CAAC,CAAC;IACpD,gEAAgE;IAChE,SAAS,EAAE,CAAC,IAAI,EAAE,MAAM,EAAE,UAAU,EAAE,MAAM,GAAG,IAAI,KAAK,OAAO,CAAC,OAAO,CAAC,CAAC;IACzE,mCAAmC;IACnC,MAAM,CAAC,EAAE,CAAC,EAAE,EAAE,MAAM,KAAK,OAAO,CAAC,IAAI,CAAC,CAAC;IACvC,mEAAmE;IACnE,cAAc,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,EAAE,EAAE,EAAE,MAAM,KAAK,IAAI,CAAC;IACpD,uEAAuE;IACvE,UAAU,CAAC,EAAE,CAAC,QAAQ,EAAE,MAAM,EAAE,KAAK,CAAC,EAAE,MAAM,KAAK,OAAO,CAAC,IAAI,CAAC,CAAC;IACjE,sEAAsE;IACtE,kBAAkB,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,MAAM,CAAC;IAC9C,KAAK,CAAC,EAAE,CAAC,KAAK,EAAE,MAAM,KAAK,OAAO,CAAC,IAAI,CAAC,CAAC;CAC1C;AAED,oFAAoF;AACpF,wBAAgB,wBAAwB,CAAC,MAAM,EAAE,cAAc,GAAG,MAAM,CASvE;AAED,wBAAgB,uBAAuB,CAAC,QAAQ,EAAE,yBAAyB,GAAG;IAC5E,SAAS,EAAE,qBAAqB,CAAC;CAClC,CAoPA"}