Claude Code writes the same message.id multiple times during streaming.
The first write has partial tokens (often 1) and no tool_use blocks.
The last write has authoritative token counts and all tool_use/MCP blocks.
Old behavior kept the first occurrence (keep-first), silently dropping
real output tokens (+6.3% undercount) and all MCP tool calls.
New behavior keeps the last occurrence's content but preserves the first
occurrence's timestamp for correct date bucketing.
Validated against 21,390 real session files: 40.5% had duplicate IDs,
output tokens were understated by up to 78% per session.
Use strip-ansi (already in dep tree via Ink) in extractBashCommands
to prevent terminal escape codes from leaking into dashboard bash
breakdown keys. Route goose, gemini, qwen, and openclaw through
extractBashCommands instead of inline split, which also gives them
multi-command extraction (matching claude/codex/droid behavior).
Strip Ink v7 DEC mode 2026 synchronized output markers (BSU/ESU) on
Windows. ConPTY does not implement this protocol and buffers
indefinitely, causing the dashboard to hang with no output. The patch
intercepts standalone BSU/ESU writes on stdout while preserving full
interactivity (keyboard, live refresh, cursor management).
Fix ExperimentalWarning timing: the process.emit patch was restored
synchronously in the finally block, but Node defers the warning via
process.nextTick. Delay restore by one tick so the patch is still
active when the warning fires.
Closes#195
Goose: read token usage from ~/.local/share/goose/sessions/sessions.db.
Lazy-loaded, zero overhead for non-Goose users.
Codex: use sessionId instead of file path in dedup key so forked
sessions sharing the same session_id don't double-count tokens.
- Attach a no-op `stream.on('error', () => {})` so a late read-ahead
error that races with a successful first-line yield can never escape
as an unhandled 'error' event. Defense in depth: empirically the
destroy() in finally already swallows it on Node 18+, but the listener
removes any version-dependent surprise.
- Tighten the comment to say "up to FIRST_LINE_READ_CAP" instead of
"regardless of length"; the cap is real and worth being precise about.
- Stop tracking a separate streamError flag. createReadStream's default
64 KiB highWaterMark means the stream may already be reading chunk 2
when we break out of the loop after yielding the first line; if that
later chunk errors, the flag could reject an otherwise-valid line.
readline's async iterator already re-throws stream errors on Node 16+,
which the existing catch handles.
- Test: 120 KB session_meta line forces multi-chunk line assembly.
- Test: truncated mid-write first line is rejected, not parsed as half
an object.
- Cap createReadStream at 1 MiB so a malformed file with no newline
cannot make readline buffer indefinitely (real session_meta lines
are 22-27 KB).
- Capture stream errors explicitly; readline's async iterator does
not always re-throw underlying stream errors per Node docs.
- Test: assert project is extracted from the >16 KB session_meta to
prove the line was actually parsed, not just discovered.
- Test: session_meta line with no trailing newline is still accepted.
- Test: empty rollout file is silently skipped.
`readFirstLine` allocated a fixed 16 KB buffer, but Codex CLI 0.128+
embeds the entire base_instructions / system prompt in the
`session_meta` line, pushing it past 20 KB. When the buffer doesn't
catch a newline, `isValidCodexSession` rejects the session, so every
recent Codex session is silently excluded from totals.
Switch to a streaming readline read so the first line is captured
regardless of length, and add a regression test that creates a
40 KB session_meta payload.
Locally, this changes my 30-day Codex total from €267 (only ~half
of sessions parsed) to €878 (all sessions parsed).
- Fix refresh loop: proper while loop with 30s sleep and force:true
instead of single-fire Task that never repeated
- Fix loading overlay: counter-based isLoading so concurrent fetches
don't flicker the overlay on/off
- Fix rapid tab switching: cancel previous switchTask, check
Task.isCancelled after CLI returns to discard stale results
- Fix tab strip vs hero desync: fetch provider-specific and all-provider
data in parallel so costs arrive from same data snapshot
- Fix stale menubar icon after wake: forceRefresh now fetches today/all
in parallel alongside the current selection
- Fix accent color: ThemeState is now @Observable so color changes
propagate via observation, removing .id() view hierarchy teardown
- Fix currency flash: defer store.currency and symbol update until a
rate is available so symbol and rate apply atomically
- Fix export: terminationHandler instead of waitUntilExit (no UI freeze),
HHmmss in filename to prevent overwrite on double-export
- Fix CurrencyState: @MainActor isolation with proper Sendable
conformance, nonisolated on pure static functions
- Fix streak count: iterate calendar days instead of sparse history
entries so gaps are counted as streak-breakers
- Fix TrendBar identity: stable date-based id instead of UUID
- Add GPT-5.3 and DeepSeek model display names
Three fixes for issue #184:
1. Menubar Swift code used UTC instead of local timezone in two places:
computeHistoryStats hardcoded TimeZone("UTC") and
effectiveTokensInLast7Days used ISO8601DateFormatter (UTC default).
Both now use .current to match CLI-produced local date keys.
2. Add --timezone flag and CODEBURN_TZ env var to override the system
timezone for all date grouping. Sets process.env.TZ before any Date
operations so all existing local-timezone code works unchanged.
3. Replace MS_PER_DAY arithmetic with Date constructor day-of-month
math for yesterday/backfill computations. Subtracting 86400000ms
from midnight skips a day on DST spring-forward (23-hour day).
Fixes#184
Fixes#183. Users with large Codex session directories (45 GB, 10K+
files) experienced CPU pegging because every 30-second refresh re-parsed
all session files from scratch.
Three optimizations:
1. readFirstLine now reads 16 KB via fs.open() instead of loading the
entire file through readSessionFile. Cuts discovery I/O from ~45 GB
to ~160 MB for 10K files.
2. Per-file result cache (codex-results.json) with mtime+size
fingerprinting. Parsed results are cached on first run; subsequent
runs return cached data instantly for unchanged files.
3. Cache-accelerated discovery skips header validation for cached files,
pulling the project name directly from the cache manifest.
Cache safety: fingerprint captured before read (no TOCTOU), atomic
write via temp+fsync+rename, 0o600 permissions, Object.hasOwn for
prototype pollution defense, eviction of deleted files on flush,
try/finally ensures flush even on parse errors.
- Wrap hydrateCache() in try/catch so disk errors don't crash commands
that previously never touched the cache
- Export MS_PER_DAY, BACKFILL_DAYS, toDateString from daily-cache.ts
and remove duplicates from cli.ts
- Remove double hydrateCache() call in report JSON path
- Persist migrated cache to disk so old-version files aren't
re-migrated on every run
- Export emptyCache() for use as fallback on hydration failure
- Extract ensureCacheHydrated() from menubar-json path into daily-cache.ts
- Call it from every command that parses sessions (report, status, today,
month, export, optimize, compare, yield) so CLI-only users also persist
historical data that survives source file deletion
- Replace strict version equality check with fill-defaults migration for
cache versions 2-4, preserving history across schema changes
- Back up old cache to .bak before discarding on unmigrateable versions
- Fix Copilot auto bucket display names in menubar (Copilot (Anthropic),
Copilot (OpenAI))
- Fix Roo Code / KiloCode provider key matching in menubar tab strip
- OpenClaw: JSONL parser with multi-path discovery, tool extraction
(toolCall + tool_use block types), model tracking via model_change
and custom model-snapshot events
- Roo Code + KiloCode: shared Cline-family parser extracts model from
<model> tags in api_conversation_history.json, strips provider
prefixes from model names
- Add cline-auto and openclaw-auto aliases and display names
- Add menubar provider filters and tab colors for all three
- Show cached data instantly instead of blocking on CLI refresh
Cursor emits dot-version tier-last names like claude-4.6-sonnet
that don't match our pricing keys. Map them so individual models
show costs instead of $0.
Gemini CLI 0.39 switched from single JSON to JSONL with one object
per line and $set metadata lines. Parser now handles both formats.
Also updated --provider help text to list all providers.
Parse ~/.gemini/tmp/<project>/chats/session-*.json files from Gemini
CLI 0.38+. Uses real token counts (input, output, cached, thoughts)
embedded in each message instead of character estimation. Correctly
separates cached tokens from fresh input to avoid double-charging.
- Pricing for gemini-3.1-pro-preview, gemini-3-flash-preview,
gemini-2.5-pro, gemini-2.5-flash from official Google API rates
- Tool name normalization (ReadFile->Read, SearchText->Grep, etc.)
- Menubar tab with Google Blue color (#4485F4)
Closes#166
* Add Kiro provider and transparent auto-model naming
- Add Kiro IDE provider: parses .chat JSON files, estimates tokens,
normalizes dot-versioned model IDs for cost lookup
- Show "Cursor (auto)", "Copilot (auto)", "Kiro (auto)" in CLI
dashboard instead of pretending to know which model was used
- Route auto model names through BUILTIN_ALIASES for cost estimation
* Fix menubar tabs: add missing providers, show period-scoped costs
- Add Kiro, OMP to ProviderFilter enum so installed providers appear as tabs
- Merge Cursor + Cursor Agent into single Cursor tab
- Tab costs now reflect the selected period (7d/30d/month/all) instead
of always showing today
- Tab visibility still uses today's provider list so tabs don't
disappear when switching to periods with no data
* Add accent color picker to menubar with Apple system presets
- 9 presets using Apple's exact macOS dark-mode accent colors
(Ember, Blue, Purple, Pink, Red, Orange, Yellow, Green, Graphite)
- Color picker in header, persisted via UserDefaults
- "Burn" text stays fixed ember regardless of accent
- ThemeState is MainActor-isolated for thread safety
- Picker state lifted to AppStore so it survives .id() tree rebuild
- Accessibility labels on all color swatches
- Renamed brandAccentDark/brandEmberDeep/brandEmberGlow to match
their actual light/deep/glow semantics
* Fix review findings: case-sensitive cost lookup, Kiro timestamp guard, cache versioning
- Normalize provider dictionary keys to lowercase in tab cost lookup
so "Cursor Agent" (title-case from CLI) matches providerKeys
- Guard against missing/invalid/epoch startTime in Kiro parser to
prevent RangeError crash or 1970-01-01 ghost entries
- Bump DAILY_CACHE_VERSION to 4 so upgraded users get a clean
recompute with the new auto-model naming (cursor-auto vs default)
- Add version field to cursor-results.json cache to invalidate stale
entries that still use the old 'default' model name
The Copilot provider only looked in ~/.copilot/session-state/ which is
from an older CLI tool. VS Code Copilot agent stores transcripts in
~/Library/Application Support/Code/User/workspaceStorage/*/GitHub.copilot-chat/transcripts/.
The new transcript format has no outputTokens or model_change events,
so tokens are estimated from content length and the model is inferred
from tool call ID prefixes. Both legacy and VS Code paths are now
scanned in parallel.
Fixes#161
Cursor v3 stores zero token counts in bubbles, causing parseBubbles to
return empty results. The query also dropped rows with NULL createdAt
via the SQL comparison, hiding data from older Cursor versions too.
Changes:
- Remove inputTokens > 0 SQL filter, estimate tokens from text length
when token counts are zero (same 4 chars/token ratio as agentKv)
- Include NULL createdAt rows with OR IS NULL, fall back to current
timestamp when createdAt is missing
- Parse agentKv entries with plain string content instead of skipping
them (not all content is a JSON array)
- Always parse both bubbles and agentKv instead of agentKv-only fallback
- Discover subagent transcripts in subagents/ subdirectories
- Fix timezone-dependent test in day-aggregator
Fixes#159, #163
New command: codeburn yield --period <period>
Correlates AI sessions with git commits to categorize spend:
- Productive: sessions with nearby commits that made it to main
- Reverted: sessions with commits that were reverted
- Abandoned: sessions with no commits or not in main
Uses timestamp proximity heuristic (session time + 1 hour window).
Works across branches, squash merges, and rebases by checking
if commits are in main branch ancestry.
Closes#152
PR #136 (2e5e449) changed parseAllSessions to use periodInfo.range
(full period) instead of just today's range. When combined with
cached historical data, this caused days to be counted twice:
- Once from getDaysInRange(cache, ...)
- Again from parseAllSessions(periodInfo.range, ...)
Result: 7-day cost showed ~$402 instead of correct ~$209.
Fix: Parse only today's sessions when using cache path. Historical
data comes exclusively from cache, today's data from fresh parse.
Bars now always show their assigned colors (blue for model A, green
for model B) instead of graying out the non-winner. Only the winner's
percentage value is highlighted in green.
Codex records file modifications as event_msg entries with type
patch_apply_end rather than function_call tool invocations. This fix
tracks those events and adds Edit to the tools list, enabling proper
calculation of edit turns, one-shot rates, and retry rates.
Fixes edit detection showing 0 edit turns despite actual file changes.
Newer Cursor versions store conversation data in agentKv entries
instead of populating tokenCount in bubbleId entries. This adds
a fallback parser that reads agentKv blobs and estimates tokens
from content length.
Closes#114Closes#102
The menubar showed stale prices because provider all used end:now while provider specific queries used end:endOfDay. Sessions with timestamps after now was captured were excluded from all providers but included in specific provider queries.
Use periodInfo.range consistently across all parseAllSessions calls in menubar json status.
readViaStream (used for files ≥8 MB) reconstructs the full file as a
single string via chunks.join('\n'), giving the same peak allocation as
readFile. Callers then call content.split('\n'), creating a second copy.
With FILE_READ_CONCURRENCY=16 and files up to 128 MB this can exhaust
the V8 heap (~6 GB theoretical peak).
readSessionLines already exists as a proper async generator that yields
one line at a time. Switch both hot-path callers to iterate it directly
so the full file string is never held in memory.
Adds two tests: a spy test confirming readSessionLines is called (not
readSessionFile), and a 500-entry correctness test.
Fixes#131
Second merge of main since the PR was opened. Main moved 30+ commits
(0.8.5 bump, plan tracking feature, MiniMax pricing, menubar
prefetchAll walk-back, aicrowd cache rewrite revert) so the branch
needed another reconciliation before merging to main.
Two new conflicts resolved. Took main's text in both cases per the
policy of favoring main when the feature work is neutral:
README.md Kept main's Node 20+ / better-sqlite3
Requirements wording and main's shorter src/
tree listing. Added OMP to the Requirements
line.
src/providers/pi.ts Main dropped the discovery-cache snapshot and
the rich source-metadata fields as part of the
aicrowd revert. Took main's simpler structure
and only kept the providerName parameter so
OMP sources still report the correct provider
in the session source and dedup key.
Earlier fixups carried forward from the prior merge commit:
- Object.hasOwn guards in resolveAlias against prototype-pollution
via a model literally named '__proto__'.
- source.provider in the dedup key prefix so OMP rows no longer
stamp 'pi:'.
- Combined pi.js imports in providers/index.ts.
- Trailing newline on pi.ts.
- Unknown-model fallback in cursor-agent.ts from yesterday's PR #117
fixup (preserved via main).
353 tests pass (count dropped from 378 because main deleted the
parse-progress / parser-cache / provider-colors / source-cache test
files alongside the cache-rewrite revert).
Feature work by @cgrossde.
Adds FALLBACK_PRICING entries plus display names so MiniMax sessions
show up with the right cost and readable labels when users route MiniMax
through providers like OpenCode. Pricing verified against the live
MiniMax paygo page:
MiniMax-M2.7 input $0.3/M output $1.2/M cache-read $0.06/M cache-write $0.375/M
MiniMax-M2.7-highspeed input $0.6/M output $2.4/M cache-read $0.06/M cache-write $0.375/M
A turn that straddles midnight (user typed at 23:58, assistant responded
at 00:30) was bucketed and filtered inconsistently across call sites.
parseSessionFile filtered entries by timestamp, producing orphan assistant
calls that groupIntoTurns pushed as turns with empty timestamp. Some
downstream code counted those (buildPeriodData summing project totals)
and other code dropped them (renderStatusBar's empty-timestamp skip).
The menubar showed today = $32 while the terminal status showed today = $27
for the same dataset; each was internally consistent but used a different
turn-bucket rule.
Fix both: parseSessionFile now builds all turns first, then filters each
turn by its first assistant call timestamp (the moment cost was incurred).
renderStatusBar buckets the same way. day-aggregator.ts already bucketed
on assistant time, so it is now consistent too.
Net effect: a turn is counted in the day the API call actually ran in.
