Azimkin/multi-bot-tg
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: show AI progress and configure prompt directory

Browse Source
This commit is contained in:
Azimkin
2026-09-14 14:25:50 +02:00
parent b68e715267
commit 40e7930e60
9 changed files with 64 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
AGENTS.md
View File

@@ -30,7 +30,7 @@ The `.txt` transcription command uses `[elevenlabs]` settings or `ELEVENLABS_API
The `.ai` agent command uses `[ai.glm]` by default and `[ai.deepseek]` with the `.ds` flag. Provider environment variables are `GLM_API_URL`, `GLM_API_KEY`, `GLM_MODEL`, `DEEPSEEK_API_URL`, `DEEPSEEK_API_KEY`, and `DEEPSEEK_MODEL`. Z.AI GLM uses the Chat Completions protocol; DeepSeek uses the Responses protocol. `.th` enables reasoning. Brave Search is available in every AI session and requires `BRAVE_SEARCH_API_KEY` or `ai.brave_api_key`. Crawl4AI's `read_web_page` tool is also always available and uses headless Playwright Chromium to render public pages into Markdown before analysis. Configure it with `ai.web_page_timeout_seconds` / `AI_WEB_PAGE_TIMEOUT_SECONDS` and `ai.web_page_max_chars` / `AI_WEB_PAGE_MAX_CHARS`.
AI prompt templates are always loaded from `prompts/MASTER.txt` and `prompts/USER.txt` for every invocation. C-style `/* ... */` blocks and `//` comments (at line start or following whitespace) are removed before rendering. Both `{name}` and `{{name}}` placeholders are supported, including dotted values such as `caller_user.id`, `caller_user.name`, `owner.id`, `owner.name`, `is_owner`, `text`, `chat.*`, `message.*`, `reply.*`, `account.*`, `provider`, `thinking`, and `context_messages`. Unknown placeholders fail the command with 👎.
AI prompt templates are always loaded from `MASTER.txt` and `USER.txt` in `ai.prompt_dir` (or `AI_PROMPT_DIR`) for every invocation. The directory defaults to `prompts`; relative paths are resolved from the repository root. C-style `/* ... */` blocks and `//` comments (at line start or following whitespace) are removed before rendering. Both `{name}` and `{{name}}` placeholders are supported, including dotted values such as `caller_user.id`, `caller_user.name`, `owner.id`, `owner.name`, `is_owner`, `text`, `chat.*`, `message.*`, `reply.*`, `account.*`, `provider`, `thinking`, and `context_messages`. Unknown placeholders fail the command with 👎.
## Architecture
@@ -55,7 +55,9 @@ On supported platforms, `main.py` runs the application with `uvloop`; Windows au
`.ai [count] [.ds] [.th] <prompt>` runs `micro-agents` with GLM by default. `.ds` selects DeepSeek and `.th` enables reasoning. Every session exposes the `micro-agents-tools` Brave Search tool. Unknown leading dot-arguments are ignored. The optional count adds preceding Telegram messages; a replied message is always injected once. Media at or below 5 MiB is attached. Invalid syntax and runtime/API failures only react with 👎. Guests need an ACL grant for `ai` and invoke it as `..ai`.
The master and user prompt callbacks must render `prompts/MASTER.txt` and `prompts/USER.txt`; do not add a config or hard-coded fallback that bypasses those files.
While an `.ai` command is running, its Telegram message has a 🤔 reaction. The reaction is removed after a successful answer and replaced with 👎 on failure.
The master and user prompt callbacks must render `MASTER.txt` and `USER.txt` from the configured prompt directory; do not add a hard-coded fallback that bypasses those files.
Every historical or replied Telegram message is a `UserMessage` rendered through `USER.txt`; `message.id`, `message.text`, `message.date`, `message.user.*`, and `message.is_reply` describe that specific message. Filesystem and Python execution tools are registered through `AgentToolManager` but exposed and executable only when `is_owner` is true. Telegram `send_message`, `send_image`, and `send_file` tools target the current chat. Owner file sends are confined to the repository root; guest file sends are confined to the current session's temporary media directory to prevent repository data disclosure.