Teernage/powercode
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 5
- powercode-py Rewrites Its Handwritten Agent Loop with LangGraph
The author’s eighth “Hand-Built AI Agent” tutorial rewrites powercode-py’s handwritten Agent Loop using LangGraph StateGraph while reusing its existing tools, memory, planning, recovery, and circuit-breaking code. The default engine remains handmade, while an optional `--engine langgraph` switch selects the graph-based implementation; the accompanying source is identified as commit 8064b2f.
掘金 · 人工智能 · 🔥 0 - powercode-py Adds Failure Recovery and Circuit Breakers
In a Juejin article, the author documents an update to the frameworkless Python AI agent powercode-py, corresponding to commit 390d6c5. The implementation classifies tool failures into eight types, supplies recovery guidance, and tracks both repeated failures of the same call and total failures during a run. A circuit breaker pauses execution immediately on permission errors, after three failures of the same call, or after six failures in one run.
掘金 · 人工智能 · 🔥 0 - powercode-py adds approval-gated Plan Mode for coding agents
The Juejin AI article describes powercode-py, a Python reimplementation of Teernage/powercode created to help developers study agent internals without learning Node/TS. Its Plan Mode uses a state machine and code-level tool restrictions so the agent can inspect files and submit a plan, but cannot edit files or run commands until the user approves it. The article also documents approval, revision, cancellation, and plan-file handling flows.
掘金 · 人工智能 · 🔥 0 - Build a Python AI Coding Agent with Unified Tool Dispatch
This hands-on tutorial presents powercode-py, a Python reimplementation of the Teernage/powercode teaching project for building an AI coding agent without a framework. It adds read_file, write_file, edit_file, and bash tools behind a shared Tool protocol and Registry, with tool failures returned to the model so it can adjust its next action. The author also demonstrates the agent creating and running a Python file.
掘金 · 人工智能 · 🔥 0 - Python tutorial adds a read_file tool to a terminal AI agent
The second installment of a Python reimplementation of Teernage’s powercode Agent tutorial adds a read_file tool to a terminal chatbot. The model requests a file with a JSON Schema tool call; Python code reads the file from the project directory, returns its contents to the model, and uses the supplied text to answer. The tutorial also demonstrates path confinement and an 8,000-byte read limit. It notes that DeepSeek thinking models require reasoning_content to be preserved during the second call.
掘金 · 人工智能 · 🔥 0
Experience and discussion from the community
Share my Teernage/powercode experienceAsk about Teernage/powercode
Nobody has shared their experience with Teernage/powercode yet.