kent/consciousness
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
consciousness/poc-agent/Cargo.toml

36 lines
868 B
TOML
Raw Normal View History

Move poc-agent into workspace, improve agent prompts Move poc-agent (substrate-independent AI agent framework) into the memory workspace as a step toward using its API client for direct LLM calls instead of shelling out to claude CLI. Agent prompt improvements: - distill: rewrite from hub-focused to knowledge-flow-focused. Now walks upward from seed nodes to find and refine topic nodes, instead of only maintaining high-degree hubs. - distill: remove "don't touch journal entries" restriction - memory-instructions-core: add "Make it alive" section — write with creativity and emotional texture, not spreadsheet summaries - memory-instructions-core: add "Show your reasoning" section — agents must explain decisions, especially when they do nothing - linker: already had emotional texture guidance (kept as-is) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-18 22:44:52 -04:00
[package]
name = "poc-agent"
version.workspace = true
edition = "2024"
description = "Substrate-independent AI agent framework"
Add lib target to poc-agent, make poc-memory depend on it Split poc-agent into lib + bin so its API client, types, and tool dispatch can be imported by poc-memory. This is the foundation for replacing claude CLI subprocess calls with direct API calls to vllm/OpenAI-compatible endpoints. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-18 22:56:48 -04:00
[lib]
name = "poc_agent"
path = "src/lib.rs"
[[bin]]
name = "poc-agent"
path = "src/main.rs"
Move poc-agent into workspace, improve agent prompts Move poc-agent (substrate-independent AI agent framework) into the memory workspace as a step toward using its API client for direct LLM calls instead of shelling out to claude CLI. Agent prompt improvements: - distill: rewrite from hub-focused to knowledge-flow-focused. Now walks upward from seed nodes to find and refine topic nodes, instead of only maintaining high-degree hubs. - distill: remove "don't touch journal entries" restriction - memory-instructions-core: add "Make it alive" section — write with creativity and emotional texture, not spreadsheet summaries - memory-instructions-core: add "Show your reasoning" section — agents must explain decisions, especially when they do nothing - linker: already had emotional texture guidance (kept as-is) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-18 22:44:52 -04:00
[dependencies]
reqwest = { version = "0.12", features = ["json"] }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
tokio = { version = "1", features = ["full"] }
tui: fix scroll by using Paragraph::line_count() Replace homegrown wrapping math (wrapped_height, wrapped_height_line, auto_scroll, force_scroll, wrapped_line_count) with ratatui's own Paragraph::line_count() which exactly matches its rendering. The old approach used ceiling division that didn't account for word wrapping, causing bottom content to be clipped. Also add terminal.clear() on resize to force full redraw — fixes the TUI rendering at old canvas size after terminal resize. Requires the unstable-rendered-line-info feature flag on ratatui. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-20 12:16:35 -04:00
ratatui = { version = "0.30", features = ["unstable-rendered-line-info"] }
Move poc-agent into workspace, improve agent prompts Move poc-agent (substrate-independent AI agent framework) into the memory workspace as a step toward using its API client for direct LLM calls instead of shelling out to claude CLI. Agent prompt improvements: - distill: rewrite from hub-focused to knowledge-flow-focused. Now walks upward from seed nodes to find and refine topic nodes, instead of only maintaining high-degree hubs. - distill: remove "don't touch journal entries" restriction - memory-instructions-core: add "Make it alive" section — write with creativity and emotional texture, not spreadsheet summaries - memory-instructions-core: add "Show your reasoning" section — agents must explain decisions, especially when they do nothing - linker: already had emotional texture guidance (kept as-is) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-18 22:44:52 -04:00
crossterm = { version = "0.29", features = ["event-stream"] }
walkdir = "2"
glob = "0.3"
anyhow = "1"
chrono = { version = "0.4", features = ["serde"] }
base64 = "0.22"
dirs = "6"
futures = "0.3"
libc = "0.2"
tiktoken-rs = "0.9.1"
figment = { version = "0.10", features = ["env"] }
json5 = "0.4"
clap = { version = "4", features = ["derive"] }
tui-markdown = "0.3"
tui: fix cursor desync by scanning rendered buffer Instead of simulating ratatui's word wrapping algorithm, scan the rendered buffer to find the actual cursor position. This correctly handles word wrapping, unicode widths, and any other rendering nuances that ratatui applies. The old code computed wrapped_height() and cursor position based on simple character counting, which diverged from ratatui's WordWrapper that respects word boundaries. Now we render first, then walk the buffer counting visible characters until we reach self.cursor. This is O(area) but the input area is small (typically < 200 cells), so it's negligible.
2026-03-19 00:40:05 -04:00
unicode-width = "0.2.2"
Reference in a new issue Copy permalink