mirror of
https://github.com/AgentSeal/codeburn.git
synced 2026-10-21 22:29:39 +00:00
|
Some checks are pending
CI / semgrep (push) Waiting to run
Tests / test (22) (push) Waiting to run
Tests / test (22.13.0) (push) Waiting to run
Tests / test (24) (push) Waiting to run
Tests / test (26) (push) Waiting to run
Tests / test-platforms (macos-latest) (push) Waiting to run
Tests / test-platforms (windows-latest) (push) Waiting to run
Tests / desktop (push) Waiting to run
Tests / vscode (push) Waiting to run
* Copilot: count every agent round and exact credits in VS Code chat sessions Copilot Chat 0.69 keeps only the last model call of an agent request in result.metadata. Read the request's modelTotals (input, cache reads, output over every call) first, then root completionTokens, then metadata. Carry copilotCredits as nanoAiu so plan credits are exact. Bump the copilot parse tag so cached chat sessions re-parse. modelKeyMatches no longer lets claude-sonnet-4 capture claude-sonnet-4-6. * Copilot: bill chat-session credits exactly and skip agent-host twins A chat-session request that records copilotCredits now costs credits x $0.01 through costFromBilling; requests without it stay priced from tokens. A chat session whose id matches a session-state dir is left to the agent-host path so it is counted once. * Copilot: drop agent-host twins at serve time, rate chat requests one by one, re-derive past days A chat-session journal request is left out when the same session has billed agent-host usage (session-state calls with tokens or nanoAiu, or session-store rows). Plan credits rate chat-session requests individually, so older requests in a mixed session keep their estimate. DAILY_CACHE_VERSION 75 with copilot pending re-derive so settled days pick up the new counts. |
||
|---|---|---|
| .. | ||
| design | ||
| providers | ||
| release-acceptance | ||
| sync | ||
| architecture.md | ||
| by-branch.md | ||
| cli.md | ||
| compare-cohorts.md | ||
| compare-periods.md | ||
| configuration.md | ||
| drill-through.md | ||
| guard.md | ||
| how-it-works.md | ||
| mcp.md | ||
| menubar.md | ||
| optimize.md | ||
| plans-and-quota.md | ||
| README.md | ||
| vscode.md | ||
| web.md | ||
| yield.md | ||
Docs index
One line per file in this directory, recursively.
docs/
- architecture.md — A map of the codebase.
- by-branch.md — The Spend view in CodeBurn Desktop has a By branch panel: pick a project and see where its AI spend went, per git branch, with the recorded worktrees and the individual sessions behind each branch.
- cli.md — Every CodeBurn command and keyboard shortcut, plus the report-focused flags for filtering, JSON output, and diagnosing detection.
- compare-cohorts.md — The classic Compare view answers "how do these two models differ across my whole history?" by aggregating everything each model ever did.
- compare-periods.md — Compare two date ranges side by side and see exactly what drove the change in usage and cost.
- configuration.md — Currency, model aliases, local/custom-priced/proxy models, and environment variables.
- drill-through.md — CodeBurn Desktop can open any aggregate as a session list that explains exactly what composes it, without losing your place.
- guard.md — Opt-in Claude Code hooks that watch session cost while you work: soft cap, hard cap, checkpoint nudge, session openers.
- how-it-works.md — Pricing, task categories, breakdowns, one-shot rate, per-tool data locations and parsing, and how to read the dashboard.
- mcp.md —
codeburn mcpruns a local MCP server over stdio so an AI agent can ask about your usage and savings mid-conversation. - menubar.md — The macOS menu bar app, Windows tray app (with WSL discovery), and Linux GNOME Shell extension.
- optimize.md —
codeburn optimizescans your Claude Code sessions and your~/.claude/setup, reports what is costing tokens without earning them, and grades the setup A to F. - plans-and-quota.md — Subscription plan tracking and live provider quota via
codeburn quota. - vscode.md — The VS Code extension: how it reuses the CLI client and the desktop renderer, which Node it runs on, workspace scope, and how to build and test it.
- web.md — The local browser dashboard and combining usage across your paired devices.
- yield.md —
codeburn yieldcorrelates AI sessions with git commits to show what actually shipped.
docs/design/
- design/capacity-dock.md — Status: implementation specification (Epic: Quota Intelligence #725).
- design/codeburn-desktop-plan.md — Goal: a standalone Electron desktop app that renders the approved v6 "indigo instrument" wireframes, fed entirely by spawning the
codeburnCLI for JSON. - design/codeburn-desktop.md — Build CodeBurn Desktop, a standalone, resizable native desktop application (Electron) that renders the approved v6 "indigo instrument" wireframes.
- design/codeburn-mcp-plan.md — Goal: add a
codeburn mcpstdio MCP server exposing CodeBurn's usage/cost data to AI agents via two tools (get_usage,get_savings). - design/codeburn-mcp.md — CodeBurn already aggregates rich AI-coding usage/cost data (by task, model, project, provider; retry tax; routing waste; optimize findings; 365-day history).
- design/desktop-data-lifecycle.md — Status: implementation contract for the quality/performance epic.
- design/perf-cache-fix.md —
codeburn status --format menubar-jsonwas measured taking 25-90+ seconds per call, with no speedup on a repeat call against an unchanged, freshly-warmed cache.
docs/providers/
- providers/README.md — One file per provider integration.
- providers/NEW_PROVIDER.md — Guide for adding a new session-discovery provider to codeburn.
- providers/antigravity.md — Google Antigravity (CLI and IDE).
- providers/claude.md — Anthropic Claude Code CLI and Claude Desktop's local agent mode.
- providers/cline-cli.md — The Cline command-line agent (npm
cline, 3.x). - providers/cline.md — Cline VS Code extension and Cline home-data task storage.
- providers/codebuff.md — Codebuff (formerly Manicode) CLI coding agent.
- providers/codewhale.md — CodeWhale CLI saved sessions.
- providers/codex.md — OpenAI Codex CLI.
- providers/copilot.md — GitHub Copilot Chat (CLI, VS Code core chat sessions, VS Code extension transcripts, and JetBrains IDE sessions).
- providers/crush.md — Charmbracelet's Crush TUI coding agent.
- providers/cursor-agent.md — Cursor's background agent transcripts (separate from the regular chat).
- providers/cursor.md — Cursor IDE chat history.
- providers/devin.md — Cognition Devin CLI local usage tracking.
- providers/droid.md — Factory's Droid CLI.
- providers/dsh.md — DeepSeek's open-source agent harness (
dsh, npm@deepseek-ai/dsh). - providers/forge.md — Forge agent CLI.
- providers/gemini.md — Google Gemini CLI.
- providers/goose.md — Block's Goose CLI.
- providers/grok.md — Grok Build, xAI's coding CLI.
- providers/hermes.md — Hermes Agent CLI profiles.
- providers/ibm-bob.md — IBM Bob IDE task history.
- providers/kilo-code.md — KiloCode VS Code extension.
- providers/kimi.md — Kimi Code CLI session parser.
- providers/kimicode.md — MoonshotAI Kimi Code local session usage and tool activity.
- providers/kiro.md — Kiro IDE chat history.
- providers/lingtai-tui.md — LingTai TUI per-agent token ledger integration.
- providers/mistral-vibe.md — Mistral Vibe CLI.
- providers/mux.md — coder/mux, Coder's desktop/CLI app for parallel agentic development.
- providers/omp.md — OMP CLI.
- providers/open-design.md — Open Design coding agent.
- providers/openclaude.md — OpenClaude (npm
@gitlawb/openclaude) is a Claude Code fork that runs the same agent loop against any LLM backend. - providers/openclaw.md — OpenClaw, plus the older Clawdbot / Moltbot / Moldbot lineage.
- providers/opencode.md — OpenCode (sst/opencode).
- providers/pi.md — Pi agent CLI.
- providers/quickdesk.md — Amazon Quick Desktop local usage and session history.
- providers/qwen.md — Qwen Code CLI.
- providers/vercel-gateway.md — Cloud usage for Vercel AI Gateway via the reporting API.
- providers/vscode-cline-parser.md — Shared discovery and parsing for Cline and VS Code extensions descended from Cline.
- providers/warp.md — Warp Oz agent sessions from Warp's local SQLite database.
- providers/zcode.md — ZCode CLI coding agent (z.ai), running GLM-5.2 over the z.ai start-plan.
- providers/zed.md — Zed's built-in AI agent.
- providers/zerostack.md — Zerostack (gi-dellav/zerostack), a minimal Rust coding agent.
docs/release-acceptance/
- release-acceptance/README.md — This directory turns the August 2026 dogfood audit into a repeatable release gate.
- release-acceptance/AGENT-RUNBOOK.md — Use this contract when assigning a CodeBurn candidate to an audit agent.
- release-acceptance/cases.csv — CSV, columns: id, phase, persona, surface, test, method, automation, evidence, threshold, blocking, owner.
- release-acceptance/ledger.schema.json — JSON Schema titled "CodeBurn release acceptance run".
- release-acceptance/ledger/history.jsonl — JSON Lines log; each line is one release-acceptance run record (run_id, verdict, surfaces, findings, evidence).
- release-acceptance/templates/accuracy.csv — CSV template, columns: run_id, case_id, persona, surface, filter, provider, session_id, expected/actual token and cost fields, status, evidence, notes.
- release-acceptance/templates/click-through.csv — CSV template, columns: run_id, case_id, persona, surface, destination_or_control, prerequisites, action, resulting_state, status, feedback_ms, settled_ms, screenshot, accessibility_notes, notes.
- release-acceptance/templates/findings.csv — CSV template, columns: run_id, id, severity, status, confidence, frequency, persona, surface, candidate_sha, version, prerequisites, repro, expected, actual, evidence, privacy_impact, owner, size, execution_lane, acceptance_condition.
- release-acceptance/templates/residue.csv — CSV template, columns: run_id, kind, path, active, version, bundle_id, sha256, size_bytes, process_pid, package_manager, disposition, backup_path, notes.
- release-acceptance/templates/timings.csv — CSV template, columns: run_id, case_id, surface, persona, operation, trial, cache_state, start_monotonic_ms, first_feedback_ms, first_useful_ms, complete_ms, cpu_peak_pct, rss_peak_bytes, calls, tokens, cost_usd, identical_totals, notes.
docs/sync/
- sync/README.md — Push your AI usage telemetry to a shared backend so teams can track adoption, budgets, and ROI across developers.
- sync/DEVELOPER.md — Architecture, protocol, server contract, and testing for
codeburn sync.