fieldrich-vscode-extension
VS Code extension for FieldRich AI OS chat, repository questions, expert consultation, and software development tasks.
Open the FieldRich sidebar and select Agent to ask it to investigate, implement, fix, or test code in the first open workspace folder. It reads actual files, searches source, makes focused edits, runs commands, and feeds the observed results back to the AI OS until it finishes or reports a blocker. Agent mode does not require an index. Normal chat, repository chat, and Consult keep their existing API contracts.
Select Commands → Automatic (terminal access) for unattended command execution. The default, Ask before running, prompts before each shell command. Automatic execution runs with your user permissions; commands are not sandboxed and can access more than the workspace. The setting is saved at User scope, and repository settings cannot enable it. Trusted VS Code workspaces are required. For multiple workspace folders, the first folder is the execution root; open the desired folder first.
The model selector also applies to Agent mode. The selected model must be available on the configured AI OS. The default is qwen3.6:35b. Use Stop to cancel the outstanding AI request and the active command. Completed edits remain in place for review; Stop does not roll them back. Use managed process tools for temporary servers and long-running checks; readiness, logs and cleanup are tracked. Interactive commands are not supported.
Agent and chat transcripts are separate views of the selected session. The last 30 agent runs are retained in workspace state; the latest three summaries provide follow-up context. Full run logs and original file contents are stored under the extension's global storage, in agent-runs/<run-id>/. Show log opens the FieldRich Agent output channel and shows each run's recovery directory. files.json contains original contents for files changed by file tools; original: null means the file was newly created. Review these records before manually restoring individual files. Terminal commands can change additional files and are not covered by these file-tool checkpoints; review Source Control too.
Deleting a session removes its agent transcript from workspace history. Recovery files remain in extension storage until manually removed.
File tools reject paths outside the workspace, symlinks, hard-link edits, protected credentials, binary/large files, and overwriting a file with unsaved editor changes. Existing files must be read before editing, and concurrent changes invalidate the edit. Root AGENTS.md is loaded automatically; reading a nested file supplies the applicable parent instructions, and new or changed instructions gate subsequent writes. Git ignore rules are used for discovery when available. Secrets and generated/dependency directories are excluded from discovery. Commands have separate terminal permissions and are not subject to file-tool restrictions.
Runs have a configurable implementation step limit (fieldrich.agent.maxSteps, default 80, maximum 200), a context window (fieldrich.agent.contextTokens, default 32768), a ten-minute inference timeout, and a maximum ten-minute timeout per command. Earlier observations are compacted while preserving the original request, plan, repository instructions, source changes and check results. A changed project cannot be marked complete without an observed successful verification after the last edit. A separate model review inspects final source, startup paths, requirements and check evidence before accepting completion; findings return to implementation for repair. Reviews are read-only, with at most three passes of eight decisions each, in addition to the implementation budget. The agent discovers actual runtimes and versions, works through the same tools for different languages, and can fetch known documentation URLs when needed. Hitting a budget produces an incomplete result with changes preserved. Model quality and available context determine how complex a task it can complete; this is an iterative development agent, not a guarantee that arbitrary software tasks will succeed.
Build and verify:
npm ci
npm run typecheck
npm run test:agent
npm run package
An optional live check creates a disposable calculator project and a temporary backend session, asks the actual model to fix the code and run its test, then deletes the temporary session. It permits only the fixture's test command and retains the disposable project for inspection:
npm run test:agent:live -- http://YOUR-AI-OS/fieldrich-api qwen3.6:35b
Create a VSIX using the existing VSCE workflow (install/deploy.bat on Windows), or package it with VSCE and --no-dependencies after building. The extension and React sidebar are bundled. Version 1.2.0 requires the updated AI OS backend route /api/ai/agent/decision; restart the backend before installing this extension. Ordinary chat and existing API routes remain compatible. Install the resulting VSIX in the VS Code instance where you work, then run Developer: Reload Window. Protocol v2 uses stateless inference and requires no additional web-chat deployment.
Additional real-model regressions exercise Python/C projects and the original React + Node.js JWT request from an empty folder:
npm run test:agent:languages -- API_URL qwen3.6:35b
npm run test:agent:fullstack -- API_URL qwen3.6:35b
Architecture and activation instructions are in docs/agent-implementation.md. Recorded results and limits are in docs/agent-v1.2-validation.md.
