DEV Community

#agents

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
agent-message-window: a sliding context window that never breaks a tool pair

agent-message-window: a sliding context window that never breaks a tool pair

Comments
5 min read
Function Signatures to Multi-Provider Tool Schemas: One Source of Truth for All LLM Providers

Function Signatures to Multi-Provider Tool Schemas: One Source of Truth for All LLM Providers

Comments
4 min read
Composable Stop Conditions: Know When Your Agent Is Actually Done

Composable Stop Conditions: Know When Your Agent Is Actually Done

Comments
4 min read
llm-message-hash-py: Canonical Hashes for LLM Request Structures

llm-message-hash-py: Canonical Hashes for LLM Request Structures

Comments
5 min read
perfectcorp-tryon-concierge: Virtual Try-On via Chat

perfectcorp-tryon-concierge: Virtual Try-On via Chat

Comments
5 min read
How to Know When Your Agent Is Done (Before It Runs Forever)

How to Know When Your Agent Is Done (Before It Runs Forever)

Comments
6 min read
Rust: Stop Retries From Double-Submitting LLM Calls With Content-Derived Idempotency Keys

Rust: Stop Retries From Double-Submitting LLM Calls With Content-Derived Idempotency Keys

Comments
4 min read
Per-Tool Call-Count Caps: Prevent Any Single Tool From Running Away

Per-Tool Call-Count Caps: Prevent Any Single Tool From Running Away

Comments
4 min read
agenttap: Wire-Level Prompt Introspection for LLM Agents

agenttap: Wire-Level Prompt Introspection for LLM Agents

Comments
4 min read
prompt-replay: Record and Replay LLM Prompts Across Models

prompt-replay: Record and Replay LLM Prompts Across Models

Comments
5 min read
Stop Your Agent from Sneaking in 'I would recommend...' When You Said Only 'escalate', 'resolve', or 'defer'

Stop Your Agent from Sneaking in 'I would recommend...' When You Said Only 'escalate', 'resolve', or 'defer'

Comments
5 min read
agentvet-rs: Validate Tool Args Before Your Agent Executes Them (Rust)

agentvet-rs: Validate Tool Args Before Your Agent Executes Them (Rust)

Comments
5 min read
Run Your Agent in Shadow Mode Before You Trust It With Production

Run Your Agent in Shadow Mode Before You Trust It With Production

Comments
4 min read
prompt-replay: Record LLM Outputs Today, Replay Against a New Model Tomorrow

prompt-replay: Record LLM Outputs Today, Replay Against a New Model Tomorrow

Comments
5 min read
My agent cited a document that does not exist. Here is the library I wrote to catch that.

My agent cited a document that does not exist. Here is the library I wrote to catch that.

Comments
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.