tanzhenxin 7251da0152 feat(channels): add dispatch modes and prompt lifecycle hooks ... Add three dispatch modes for handling concurrent messages: - steer (default): cancel current prompt and start new one - collect: buffer messages and coalesce into follow-up prompt - followup: queue messages for sequential processing Introduce onPromptStart/onPromptEnd lifecycle hooks for working indicators. These fire only when a prompt actually begins processing, not for buffered (collect mode) or gated/blocked messages. Refactor Telegram, WeChat, and DingTalk adapters to use the new hooks instead of overriding handleInbound, simplifying the working indicator pattern and ensuring correct behavior with dispatch modes. This enables better UX for async workflows and prevents indicator leaks when messages are buffered or cancelled.		2026-03-28 06:19:02 +00:00
..
development	refactor(telemetry): update session event fields to match current config	2026-03-15 12:06:01 +08:00
examples	refactor: unify sandbox configuration naming and improve telemetry config	2026-02-11 11:08:15 +08:00
tools	docs(tools): document file encoding and platform-specific behavior	2026-03-16 23:03:50 +08:00
_meta.ts	docs(channels): add plugin developer guide and rename mock to plugin-example	2026-03-27 03:19:34 +00:00
architecture.md	docs: enhance architecture documentation and add contribution guidelines	2025-12-11 18:31:24 +08:00
channel-plugins.md	feat(channels): add dispatch modes and prompt lifecycle hooks	2026-03-28 06:19:02 +00:00
contributing.md	docs: enhance architecture documentation and add contribution guidelines	2025-12-11 18:31:24 +08:00
roadmap.md	feat(cli): improve auth dialog UX with clearer three-option layout	2026-03-01 15:22:35 +08:00
sdk-java.md	feat: promote Agent Skills from experimental to stable	2026-02-06 13:04:08 +08:00
sdk-typescript.md	feat: add system prompt customization options for CLI and SDK	2026-03-16 03:06:35 +08:00