c135ee811d
✨ Identity onboarding + Verbatim dialogue memory
...
- Added [identity] config section (agent_name, agent_role, user_name,
user_role, setup_complete) to GyandootConfig and AgentConfig
- Agent loop now injects identity into system prompt on startup
- Agent loop injects past verbatim dialogue memory into system prompt
- Added dialogue_append() / dialogue_read() to MemPalace
- Word-by-word, line-by-line verbatim record in dialogue.md
- No compression, no truncation — every message preserved
- Agent loop writes to BOTH daily transcript AND verbatim dialogue
on every turn
- All config paths pass identity through (flat converter, subagents)
2026-06-11 22:31:20 +05:30
54d8ca3774
P0 deep-dive: core, providers, agent, memory, TUI, setup wizard
...
DEEP DIVE — Agent Loop (gyandoot-agent):
- Real conversation loop with interactive (run()) and non-interactive
(run_conversation()) modes
- Retry logic with exponential backoff and error classification
(RateLimit, Auth, Timeout, ServerError, ContextOverflow)
- Context window management — token estimation, 75% threshold compression
- 7 built-in tools: Read, Write, Edit, Bash, Grep, Find, Ls
- BashTool with destructive-command security blocks
- ContextCompressor — prune tool results, summarize middle messages
DEEP DIVE — Memory (gyandoot-memory):
- Real MemPalace with ~/.gyandoot/palace/wings/<wing>/ directory tree
- Daily transcript files (YYYY-MM-DD_transcript.md) with append-only format
- L0/L1 identity persistence (< 157 tokens for L0)
- Session digest to drawer.md
- File persistence support for transcripts and identity store
DEEP DIVE — Core (gyandoot-core):
- GyandootConfig with TOML deserialization for all sections
- ConfigLoader with env > profile > file > default chain
- Rich types: Message, ToolCall, ToolResult, SessionId
- Comprehensive error types with thiserror derive
DEEP DIVE — Providers (gyandoot-providers):
- Provider trait with chat/chat_stream/models
- OpenAI provider with streaming SSE and function calling
- Anthropic provider with Messages API + tool use
- Ollama provider with merge_system/no_tools auto-detect
- SseParser, StreamEvent, TokenStream for SSE parsing
- ProviderFactory for creation from config
NEW — TUI crate (gyandoot-tui):
- Banner: Kapil-approved robot head ASCII art with ANSI colors
- Setup wizard: 7 providers, interactive config, connection test
- Terminal helpers: spinner, confirm, text input, selection menu
- Ratatui TUI: keyboard input, commands, status display
All 12 crates + CLI binary compile with 0 errors.
2026-06-11 20:53:38 +05:30
851c838ca5
Initial scaffold: GyanDoot v2.0 in Rust
...
Full Cargo workspace with 11 crates:
- gyandoot-core: Shared types, config, error types
- gyandoot-agent: Agent loop, tool execution, context compression
- gyandoot-providers: LLM provider abstraction (OpenAI, Anthropic, Ollama)
- gyandoot-memory: MemPalace persistent memory system
- gyandoot-platform: Platform adapters (Telegram, Discord, Webhook, CLI)
- gyandoot-security: Credential vault, sanitizer, threat detector
- gyandoot-kanban: Task decomposition, swarm orchestration, diagnostics
- gyandoot-subagents: Sub-agent spawning and orchestration
- gyandoot-skills: Skills discovery, loading, preprocessing, bundles
- gyandoot-profile: Multi-agent profile manager
- gyandoot-gateway: Gateway sessions, routing, access control
Plus: CLI entry point with clap, cross-platform installer script,
KANBAN.md, .gnpl/AGENTS.md
Workspace compiles clean: cargo check passes with 0 errors.
2026-06-11 20:04:12 +05:30
