admin/Linux_post_install
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

feat: ai sessions + Telegram-friendly replies (--system, markdown strip)

Browse Source 
pos ai gemini: --session gives ask/chat persistent memory
(~/.local/share/linux_post_install/ai/<name>.json, capped 40 turns),
new 'sessions' subcommand to list/clear; --system injects a Gemini
systemInstruction on every turn without storing it in the session file.
Telegram listener keeps one session per chat (telegram-<chat_id>), clears
on 'ai /reset', passes a Telegram-voice system prompt (emojis welcome),
and strips markdown from replies before sendMessage since messages are
sent as plain text. Docs: howto/ai.md flags/sessions/bridge behavior.
This commit is contained in:
Your Name
2026-08-09 15:32:39 +00:00
parent 1832a88c71
commit 310367f3b2
6 changed files with 191 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
DOC/AGENT_Context_Project.md
+4 -4
View File
@@ -58,7 +58,7 @@ Linux_post_install/
├── bin/ # CLI tools — installed to /usr/local/bin/
│ ├── pos # Main dispatcher — smart arg matching to pos-* scripts
<!-- GEN:START tree -->
│ ├── pos-ai-gemini # Chat with Google Gemini (ask, chat, models)
│ ├── pos-ai-gemini # Chat with Google Gemini (ask, chat, models, sessions)
│ ├── pos-communication-telegram-listener # Telegram bot listener: map /command → bash, run them on chat messages
│ ├── pos-communication-telegram-sender # Send Telegram messages/files/links/stickers via Bot API (send, test)
│ ├── pos-config # Interactive editor for the tools' runtime config (reads # POS_CONFIG: registry)
@@ -253,7 +253,7 @@ All non-interactive `pos` commands log output to `~/.local/share/linux_post_inst
| Category | Command | Script | Description |
|----------|---------|--------|-------------|
<!-- GEN:START dispatch -->
| ai | gemini | `pos-ai-gemini` | Chat with Google Gemini (ask, chat, models) |
| ai | gemini | `pos-ai-gemini` | Chat with Google Gemini (ask, chat, models, sessions) |
| communication | telegram-listener | `pos-communication-telegram-listener` | Telegram bot listener: map /command → bash, run them on chat messages |
| communication | telegram-sender | `pos-communication-telegram-sender` | Send Telegram messages/files/links/stickers via Bot API (send, test) |
| | config | `pos-config` | Interactive editor for the tools' runtime config (reads # POS_CONFIG: registry) |
@@ -560,8 +560,8 @@ Use conventional prefixes: `feat:`, `fix:`, `docs:`, `refactor:`, `chore:`
| `features/autostart.sh` | 14 | Boot-time feature (moved from `bin/`, flag-gated service) |
<!-- GEN:START filetable -->
| `bin/pos` | 277 | CLI dispatcher with smart arg matching + logging + category help |
| `bin/pos-ai-gemini` | 198 | Chat with Google Gemini (ask, chat, models) |
| `bin/pos-communication-telegram-listener` | 526 | Telegram bot listener: map /command → bash, run them on chat messages |
| `bin/pos-ai-gemini` | 311 | Chat with Google Gemini (ask, chat, models, sessions) |
| `bin/pos-communication-telegram-listener` | 559 | Telegram bot listener: map /command → bash, run them on chat messages |
| `bin/pos-communication-telegram-sender` | 221 | Send Telegram messages/files/links/stickers via Bot API (send, test) |
| `bin/pos-config` | 80 | Interactive editor for the tools' runtime config (reads # POS_CONFIG: registry) |
| `bin/pos-docker-compose` | 366 | Docker Compose service manager (ls/up/down/restart/logs/update/config) |
DOC/howto/ai.md
+13
View File
@@ -6,8 +6,13 @@ Tools: `gemini` (`ask`, `chat`, `models`).
| Tool | What it does |
|------|--------------|
| `pos ai gemini ask "<prompt>"` | One-shot answer to stdout (scriptable) |
| `pos ai gemini ask --session <name> "…"` | Same, but remembers prior turns |
| `pos ai gemini chat` | Interactive multi-turn conversation |
| `pos ai gemini models` | List available model ids |
| `pos ai gemini sessions` | List/clear persistent sessions (`reset <name>`) |
Shared flags: `--model <id>` overrides the model; `--system "<text>"` adds a
system instruction to every turn (kept out of the session file).
---
@@ -50,6 +55,14 @@ Set a different model per message:
you: ai --model gemini-2.5-flash explain a Raft consensus log
```
### Telegram memory & formatting
Each chat has its own persistent session (`telegram-<chat id>`), so the model
remembers the conversation; `ai /reset` clears it. The listener passes a system
prompt telling the model it is answering in a Telegram chat — so it uses emojis
and stays lively — and strips markdown (`**x**`, backticks, `#`, links…) from
the reply before sending it, since messages go out as plain text.
## Recipes
- **Answer from a file:** `pos ai gemini ask "$(cat notes.txt)"`