mirror of
https://github.com/AgentSeal/codeburn.git
synced 2026-07-09 17:19:15 +00:00
9b20dfd7dc
* feat(context): add experimental context command with per-session token tree Reconstructs context breakdown for a Claude Code session from its transcript: messages and tokens by role, block type, and tool, split into full-session history vs the live window since the last compaction (following preservedSegment.headUuid). Block tokens are chars/4 estimates, images estimated from sniffed PNG or JPEG dimensions, reasoning derived per message from output_tokens minus visible output since transcripts strip thinking text. The exact context size comes from the last assistant message's API usage, and the gap to the estimate is shown as derived system prompt and tool overhead. * feat(context): show session titles in context --list Reads the latest ai-title entry (summary entry as fallback for older sessions) from one tail and one head chunk of each transcript, so the list stays fast on 100MB files. * feat(dash): context explorer page with Claude Code and Codex session trees Adds a Context page to the web dashboard: a navbar toggle, a provider picker (Claude Code / Codex), the 15 most recent sessions with titles, and per-session expandable details showing the context token tree, the exact live context vs window, and a live/full-history scope toggle. Server side adds /api/context/sessions and /api/context/tree with an mtime-keyed tree cache, plus a Codex rollout builder: response items feed the tree, compacted entries (with replacement_history) split live window from full history, reasoning comes exact from cumulative token_count totals, and model_context_window gives the real window. * feat(context): interactive TUI for the context command codeburn context with no arguments now opens an ink TUI: arrow keys to move, enter to expand a session's token tree inline (with a spinner while the transcript reads), tab to switch between Claude Code and Codex, f to toggle live window vs full history, q to quit. Flag and id forms keep the plain output for scripts, and non-TTY runs fall back to the static list. Tree rows are shared with the static renderer via snapshotRows. * fix(context): review fixes across window detection, codex parsing, and surfaces Window sizes are no longer guessed from token counts alone: opus-4-8 and [1m] model ids map to the 1M window (a 190K opus-4-8 session used to render as 95% of a 200K window), and Codex omits the percentage instead of borrowing Anthropic constants when the rollout lacks model_context_window. Codex compaction accounting now reads the encrypted compaction item and developer messages from replacement_history, so post-compaction windows stop undercounting. Both builders stream with largeLineAsBuffer so one oversized line cannot silently truncate the walk. The tree API stops sending session.filePath, serves the flattened rows so the dash renders the same tree as the CLI and TUI, resolves ids directly instead of re-scanning every session file per request, and the tree cache evicts LRU. Session discovery honors CLAUDE_CONFIG_DIRS, CLAUDE_CONFIG_DIR, and CODEX_HOME, stats files in parallel, and id lookups stat only matching files. CLI gains --provider codex and machine-readable --list --json; --full now opens the TUI in full scope instead of bypassing it. The TUI shows build errors instead of a frozen spinner and drops the ref-plus-counter repaint for plain state. The dashboard scopes the usage error banner and device sidebar to the Usage page. |
||
|---|---|---|
| .. | ||
| public | ||
| src | ||
| index.html | ||
| package-lock.json | ||
| package.json | ||
| tsconfig.json | ||
| vite.config.ts | ||