Files

T

asepharyana 25f084f9db feat(hive-mind): implement multi-agent orchestration with cognitive cycles

- Introduced a new hive-mind architecture that allows the Core Intelligence to issue directives to anonymous processing nodes.
- Each node executes its directive and merges output into a collective state, visible to all nodes in real-time.
- Added support for dynamic cognitive cycles, enabling flexible task management.
- Implemented documentation generation for hive-mind runs, ensuring a durable record of decisions and actions.
- Refactored existing company pipeline tools to align with the new hive-mind structure, replacing division-specific prompts with a more generalized approach.
- Updated workflow rendering to accommodate hive-mind nodes and their system-assigned designations.
- Enhanced error handling and validation for cognitive cycle plans.

2026-07-14 08:12:43 +07:00

3.4 KiB

Raw Blame History

Backend / Service Layer

AI Provider

src/service/provider.rs (310 lines)

LlmClient::new(api_key, model, base_url) — constructs blocking reqwest client
chat_with_tools() — non-streaming with tool definitions
chat_stream() — SSE streaming, returns SseParser yielding StreamEvent
Retry logic: up to 3 attempts on transient errors, exponential backoff

OAuth

src/service/oauth/manager.rs (113 lines) + loopback.rs + pkce.rs

PKCE flow: CodeVerifier → challenge → browser auth → loopback server → token exchange
Configurable via app_config.json provider definitions (auth URL, token URL, scopes)

IPC / Daemon

src/ipc/ (7 files, ~350 lines total)

Unix domain socket, length-prefixed JSON frames
Daemon sends DaemonFrame (state payload, stream tokens, system notes)
Clients send ClientRequest (key presses, resize, submit, scroll)
State sync uses full-state push from daemon to client after each action

Workflow Engine

src/app/workflow/engine.rs (648 lines) + script.rs

Inline JS-style DSL executed by a lightweight runtime
agent(), parallel(), pipeline(), phase(), log() — spawns sub-agents
Max concurrency configurable via workflow_max_concurrency setting
Hive-mind orchestrator in hive_mind.rs: Core Intelligence compiles a CognitiveCyclePlan per task — cycle count and nodes-per-cycle are decided fresh each time based on what the task actually needs

Sub-Agent System

src/app/subagent/ (6 files: spawn.rs, engine.rs, context.rs, event.rs, division.rs, auto.rs, ~450 lines total)

run_subagent() — spawns independent agent with its own tool set and context
Communicates via mpsc<SubagentEvent> channel (tool calls, results, completion)
Uses LlmClient (same as main agent) with tool-use API
Auto-healing: on build/test failure, spawns auto-fix sub-agent
Node access tiers (division.rs's tool_scope module): read, write, full — granted per node by the Core Intelligence based on what its directive needs

MCP Client

src/app/mcp/manager.rs (441+ lines)

Stdio transport: spawns child process, JSON-RPC via stdin/stdout
HTTP transport: streaming HTTP with JSON-RPC
Dynamic tool list refresh and error recovery
Persistent child handle for stdio (reuses connection across calls)

Self-Review

src/app/review/mod.rs (495 lines)

Post-tool execution quality check against learned lessons
Invokes run_subagent() with reviewer prompt
Staleness detection: skips review after N consecutive empty results
Three review types: code quality, architecture, security

Background Bash

src/app/bgbash/ (2 files: job.rs, control.rs)

spawn_bash_job() — runs sh -c in a thread, collects stdout line-by-line
Channels: output via mpsc<String>, PID via mpsc<u32>
Killable via PID (SIGTERM)
Output buffering capped at 10,000 lines to prevent memory issues

Gate Guard / Harness

src/app/harness.rs (495 lines)

Harness::gate_tool_call() — verdict-based tool gating (allow/block)
Path traversal, credential read, and destructive command detection
Pattern detection for stub code, denial language, and assumptions in write/edit content
Reason validation for mutating tools (minimum 8 characters, rejects generic non-answers)
Includes 8 unit tests for verdict parsing formats

3.4 KiB Raw Blame History