Reading, decoding and line-parsing a Claude session JSONL is per-file work that
touches nothing shared, so it moves onto worker_threads for a large cold parse.
parseClaudeFileFull() is the extracted unit both sides run; a worker runs it
against an empty dedup set and returns the result as a JSON string, and the
parent installs results in the order the serial loop would. Everything with
cross-file state stays on the main thread, and a file whose message ids were
already claimed (or whose worker failed) re-parses in-process, so the output is
identical to the serial path.
Thread count is decided per parse: never with <=2 cores, under 2 GB free memory,
fewer than 200 pending whole-file re-parses or under 200 MB behind them, so warm
and incremental runs spawn nothing. CODEBURN_PARSE_WORKERS overrides it. The pool
is terminated when the parse ends, so the resident serve child accumulates no
threads.
Adversarial review of the serve design surfaced three weaknesses a
one-shot CLI never had, because it never lived long enough:
- Pricing-affecting config (model aliases, price overrides, local-model
savings) now participates in the parse memo key. Config reloads fresh
per request (the preAction hook), but a memoized or burst-reused parse
embedded costs priced under the OLD config; the widened key makes any
such change an automatic memo miss. New alias-hash helper + tests.
- Memory guard: past 3GB RSS the serve loop drops its in-memory memos
(session cache + parse entries) and the next request re-parses once.
The child never exits for this, so the client's death budget is
untouched.
- codeburn serve typed in an interactive terminal now explains itself on
stderr instead of hanging silently on stdin.
- vscode-cline-parser: entry.ts was truthy-checked but not validity-checked,
so a garbage timestamp made new Date(ts).toISOString() throw RangeError and
abort the whole session parse. Validate the date, fall back to empty.
- models: parseLiteLLMEntry read fields off its argument with no null/type
guard, so a null value in the remote LiteLLM pricing JSON threw and aborted
the entire live pricing load. Return null for a null/non-object entry.
Both mutation-checked: the tests raise RangeError / TypeError before the fix.
Several model ids price correctly but had no SHORT_NAMES entry, so the
By Model panel rendered the raw slug next to properly named siblings:
`gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `grok-4.5`,
`qwen3.7-max`, `minimax-m3` and `mimo-v2.5-pro`.
All display-only; no dollar amounts move.
Notes on the less obvious ones:
- The GPT-5.6 variants are listed individually rather than as a bare
`gpt-5.6`. A base entry would swallow every future `gpt-5.6-*` through
the prefix match and hide the variant behind a sibling's label, which
is exactly what getShortModelName's version-boundary rule prevents. An
unlisted variant still falls through to its raw id, and there is a test
pinning that.
- `grok-4.5` is the model the Grok Build harness runs and reports as
`current_model_id`, so it takes the model's own name. Ids that really
are `grok-build*` keep the "Grok Build" label, also covered by a test.
- ClinePass routes models as `cline-pass/<slug>`. No new prefix handling
was needed: getShortModelName's path fallback already strips the
prefix and re-resolves the bare slug, the same way it handles
`accounts/fireworks/models/<slug>`.
- MiniMax M3 is mapped under both the lowercase OpenRouter slug and the
capitalized spelling sessions report, since SHORT_NAMES matching is
case-sensitive (the case-insensitive index covers pricing only).
`mimo-v2.5-pro` remains unpriced upstream; this only gives it a name.
Codex driving a Kimi backend records the model as kimi/k3[1m] (provider prefix
plus a [1m] context tag). getCanonicalName stripped the prefix but not the tag,
so it matched no alias and priced to $0 - Kimi-via-codex spend was silently
reported as free, and the menubar showed no Codex segment. Strip a trailing
[...] context tag so kimi/k3[1m] -> k3 -> kimi-k3, repairing both cost and the
display name.
- Resolve k3/k3-agent/k2d6-agent model aliases to canonical Kimi names
- Discover sessions across all Kimi Code homes (CLI + desktop runtime)
- Accept conv-*/ctitle-* session directory naming, not just session_*
- Add Kimi Code provider tab with brand color to the menubar
- Show short model names (Kimi K3, Kimi K2.6) in the menubar payload
* Resolve Fireworks-hosted models to friendly display names
Fireworks fleet models arrive as `accounts/fireworks/models/<slug>` and
were leaking the raw path/slug in reports and the dashboard (e.g.
`fireworks/mode…`, `glm-5p2`). getShortModelName's path fallback now takes
the last path segment and re-resolves it, so a known slug earns a friendly
name (GLM-5.2, Qwen 3.7 Plus, Kimi K2.7 Code, DeepSeek v4 Pro/Flash) while
an unmapped slug still falls through to the raw segment.
Display-only: getModelCosts prices off the full id, so dollar amounts are
unchanged. The By Model dashboard panel now renders through getShortModelName
too, so already-cached raw keys normalize without a cache rebuild.
* Merge By Model rows that resolve to the same display name
Once path-style ids normalize, a mixed-vintage cache can hold more than one
raw key for the same model (the full accounts/fireworks/models/<slug> path
from an older build and the bare slug/friendly name from a newer one). The
dashboard By Model panel aggregated by raw id, so those rendered as duplicate
rows once both mapped to the same display name.
Extract the aggregation into a pure, tested aggregateModelTotals() keyed by the
resolved display name so the rows merge into one. This also aligns the panel
with modelEfficiency, which is already keyed by getShortModelName.
Five verified findings from the #756 review, each with a regression test:
Corrections now count only follow-up prompts. The session-opening prompt
cannot be correcting this assistant, however correction-shaped its task
text reads, and the revert pattern no longer matches ordinary 'revert
the <noun>' requests (undo was already guarded; the doc claimed both
were).
Time-to-first-edit returns null when the first edit's timestamp is
unparseable instead of silently measuring to the first parseable one.
File churn normalizes backslashed paths before keying, relativizing, and
basenaming. Previously the payload's basename-only privacy redaction was
a no-op on Windows and shipped the full absolute path, username
included; mixed separators also split one file across churn entries.
Pricing coverage excludes deliberately-free models (local-looking,
local-savings mapped, zero-rate overrides) from the denominator via the
same exclusions findUnpricedModels applies, so a mostly-ollama user no
longer reads high coverage while every cost-bearing call is unpriced.
An absent coverage value now reaches the payload as null, never as a
fabricated 100%.
Also shares the one-shot minimum-edit-turns threshold between
worstOneShotCategory and the coaching gate so they cannot drift.
Adds an eager provider for Amazon Quick Desktop (aws.amazon.com/quick/desktop),
which stores local data under ~/.quickwork. Usage source of truth is the
per-day EMF metrics JSONL (Model, InputTokens, OutputTokens, CostUSD,
session_id); real CostUSD passes through the cache like kiro/devin/hermes.
sessions.db (SQLite, read-only) enriches calls with titles, first user
message, and tool names, and provides estimated usage (quickdesk-auto,
costIsEstimated) for sessions that predate metrics coverage. Multi-profile
layout via profiles.json entries plus the migrated legacy root; honors
QUICKWORK_HOME; schema-tolerant (sqlite_master and PRAGMA introspection,
per-line JSONL error isolation). The on-disk schema is reverse-engineered and
documented as such in docs/providers/quickdesk.md.
getModelCosts resolves exact overrides before any table hit, so an exact
zero-rate override provably priced the model and means free. Prefix and
case-insensitive overrides resolve after table hits: a zero-rate stub
shadowed by one still reports $0 from the stub, so it stays flagged.
Refs #638
Adversarial review found two false-negative paths and two polish items:
- Drop the reverse-display-name suppression. Droid prices the lowercased
display name and gets $0, so a $0 row keyed "Sonnet 4.6" is real
uncounted spend; suppressing it because claude-sonnet-4-6 prices today
hid exactly the failure this feature exists to expose.
- Treat zero-rate pricing hits as unpriced. LiteLLM ships [0,0] stubs
for models it lists without a price; a stub hit means unknown price,
not free. Explicit zero-rate user overrides still count as free.
- Make MenubarPayload.current.unpricedModels optional for source
compatibility with payload producers that predate the field.
- Replace localeCompare with a byte comparison so tied rows sort
identically on every host locale.
Refs #638
Models missing from the pricing tables silently contributed $0 to every
total with no indication anywhere (the warning was gated behind
CODEBURN_VERBOSE). Add render-time detection that flags aggregated model
rows with usage but $0 cost whose pricing lookup fails right now, and
surface it in overview, report/today/month JSON (unpricedModels), the
TUI By Model panel, and the MCP get_usage summary.
Render-time detection covers cached sessions (cost is computed at parse
time) and heals as soon as pricing data, an alias, or a price override
arrives. Rows with real cost are never flagged: aggregation keys rows by
display name, which the pricing lookup misses; $0 display-name rows are
reverse-resolved to their raw id before flagging so sessions cached
before their model's pricing landed don't get a misleading alias hint.
Local models and model-savings mappings stay excluded: $0 is correct
for them.
Fixes#638
* fix(cursor): use Cursor's real context tokens for input
Current Cursor builds leave the per-bubble tokenCount at {0,0}, so the provider
fell back to estimating input from visible text plus a second agentKv
content-char pass that double-counted the same conversation. Cursor records its
own tokenizer-accurate context size per conversation in
composerData.promptTokenBreakdown (the number behind the in-app context-window
bar); read that and credit it once per conversation for input instead.
Measured on a real local DB: today's Cursor input went 44,873 -> 168,486 tokens,
matching the sum of per-conversation context. The admin portal still counts
cumulative-per-turn plus cache, which are server-side only, so an opt-in Cursor
API stays the path to exact parity.
Output is a reply-text estimate; agentKv is retained for a tools/bash breakdown
in a follow-up.
* feat(cursor): add tools and bash-command breakdown from agentKv
Cursor logs the agent's tool calls (Read, Grep, Glob, Shell, ...) in agentKv
blobs. Join them to conversations via the turn requestId (carried on the bubble's
$.requestId and inherited positionally by the turn's agentKv rows) and attach each
conversation's tool list and Shell commands to the call that carries its input.
Measured on a real DB: Cursor now reports tools {Read, Grep, Glob, Shell,
SemanticSearch} and the executed shell commands, which were previously empty.
Removes the now-superseded parseAgentKv content-char estimate.
* fix(cursor): price composer-2.5 as Sonnet 4.6
composer-2.5 was missing from the built-in Cursor model aliases, so its usage
showed $0. Map it to claude-sonnet-4-6 like composer-2 (per cursor.com/blog).
* fix(cursor): cache version, model attribution, user message join, tool classification
- Bump CURSOR_CACHE_VERSION to 5: parser semantics changed (parseAgentKv
removed, real context tokens from composerData.promptTokenBreakdown),
stale v4 caches would show double-counted agentKv calls.
- Fix model attribution: real input tokens are credited on user bubbles
(type=1) which carry no modelInfo. Add a pre-pass building composerId ->
model from assistant bubbles so pricing/display uses the conversation's
actual model instead of the default cursor-auto/sonnet-4.5.
- Fix buildUserMessageMap: was keying by JSON conversationId (empty in
current Cursor builds). Now extracts composerId from the bubble key,
matching parseBubbles.
- Add 'Shell' to BASH_TOOLS in classifier: Cursor's agent uses 'Shell'
as the tool name, but it was missing from the bash tool set so Cursor
agent turns with shell commands wouldn't classify as bash/build/test.
- Fix null coalescing in loadComposerInputTokens: r.used ?? r.ctx would
fall through on a valid totalUsedTokens of 0. Use explicit null check.
- Decouple agentTools attachment from input credit: tools/bash were only
attached on the first credited turn (creditedHere), silently dropping
tool usage from subsequent turns in multi-turn conversations.
- Update stale comment about parseAgentKv being kept for a follow-up.
- Add tests for real token crediting, once-per-conversation, fallback,
contextTokensUsed, tool/bash attribution, and model attribution.
* fix(cursor): avoid duplicating aggregated agent tools
* fix(cursor): price house composer models from Cursor's published rates
composer-1/1.5/2/2.5 were proxied to Claude Sonnet, overcounting cost
(~6x for composer-2/2.5). Use Cursor's published per-model rates instead,
and note in the parser why local reads undercount the admin console.
Co-authored-by: AgentSeal <hello@agentseal.org>
* fix(cursor): estimate non-Composer turn input from the agent stream
Non-Composer sessions (e.g. GPT) record no context-window meter and keep
the prompt in the agent stream, so the user bubble's own text is empty.
Those turns hit the 0/0-token fallback with text_length 0 and were dropped
entirely, so that model's traffic never appeared in the report.
loadAgentToolsByComposer now also sums the user-role stream text length per
conversation, and the meterless fallback estimates input from it (chars/4),
credited once per conversation, when the bubble text is empty. Turns with no
stream text are left untouched, so no phantom tokens are invented.
* fix(cursor): stable conversation crediting, restored stream coverage, and cache invalidation
Review fixes for the real-token accounting:
Conversation input now lands on one composer-anchored record
(cursor:composer-input:<id>) timestamped at composerData.createdAt, so
the credited day no longer depends on the parse window or cache floors,
daily-cache gap fills dedupe instead of multiplying, and each
conversation picks exactly one input source (real bubble tokenCounts,
the context meter, the agent stream, or visible text) so sources can
never stack or double count. A zero totalUsedTokens no longer shadows
contextTokensUsed.
The agent stream regained what the parseAgentKv removal dropped: tool
and system rows count as context, stream-only replies count as output,
and sessions with no bubble join are emitted again (DB mtime timestamp,
as before). Block-array content is measured by its text, not its JSON
envelope. Rows written before their requestId appears buffer forward
instead of inheriting the previous conversation, and a system row closes
the boundary. Tool names canonicalize to Bash and commands go through
extractBashCommands so cross-provider breakdowns merge; the classifier
no longer special-cases Shell (which also reclassified Copilot turns).
User bubbles consume their own queue entry so assistant replies pair
with the right question, and every cursor call is flagged
costIsEstimated.
The requestId and model joins ride the existing budgeted bubble scan
instead of two new unbounded full-table decodes, and the composerData
read seeks the key range. SQLITE_BUSY now propagates to the parser's
retry path instead of caching a silently degraded parse.
Upgrades actually take effect: the session cache gets a cursor parse
version, DAILY_CACHE_VERSION bumps to 10 so finalized days re-hydrate
under the new accounting, the cursor results cache bumps to v6, and the
builtin composer rates participate in the price config hash (rates now
cite cursor.com/docs/models).
Verified against a real Cursor store: all metered conversations match
the on-disk meter exactly, narrow and wide parse windows anchor
identically, repeat runs are byte-identical, and agentKv-only sessions
reappear.
---------
Co-authored-by: ozymandiashh <234437643+ozymandiashh@users.noreply.github.com>
Two post-0.9.12 cleanups.
Report model names: getShortModelName resolves a model's pricing alias before looking up its display name, so models priced via a sibling alias (ZCode/Hermes GLM-5.2 via glm-5p1, Grok Build via grok-build-0.1) leaked the internal pricing key as the model name in report --format json and the menubar model breakdown. Grok Composer was unmapped and showed raw. Add SHORT_NAMES entries so each resolves to its real name (GLM-5.2, Grok Build, Grok Composer 2.5 Fast). The models command was already correct because it uses each provider's own modelDisplayName.
Daily cache: providers added since the v8 rollup (Grok, Hermes, ZCode) parse usage that older binaries skipped, so days cached at v8 omit them and report 0 across history. Bump DAILY_CACHE_VERSION and MIN_SUPPORTED_VERSION to 9 to force a one-time full re-hydration so new providers backfill without a manual cache clear.
gpt-5.3-codex-spark is a distinct model variant, but the longest-first
startsWith(key+'-') matcher (intended for reasoning suffixes -high/-low)
swept it into the base 'GPT-5.3 Codex' label, making a distinct model look
like the retired base in today/models/status output. Add an explicit
display entry in SHORT_NAMES and the codex provider so the longer key wins;
-high/-low still fall through to the base. Pricing is unaffected (LiteLLM
has no spark entry; cost falls back to the base rate as before).
Fixes#461
Reads ZCode CLI usage from ~/.zcode/cli/db/db.sqlite. The model_usage
table has exact per-request tokens; cost is computed from the pricing
table since ZCode stores none (GLM-5.2 runs on the z.ai start-plan
subscription).
- Split cached tokens out of input_tokens (OpenAI-style) so fresh input
and cache reads price correctly
- Attach each turn's tool calls to one request to avoid double-counting
- Map GLM-5.2 to glm-5p1 (GLM-5.1 rate) until LiteLLM lists it
- Register as a lazy SQLite provider; add test and provider doc
Adds Grok Build (xAI coding CLI) as an eager provider with caching- and compaction-aware token estimation, real tool/shell extraction, Skills & Agents from spawn_subagent, grok-build pricing, and SuperGrok plan presets. Tested against real sessions; full suite green.
Mythos 5 ($10/$50) is not in LiteLLM or the models.dev/OpenRouter gap-fill
yet (Fable is), so dropping the manual patch left it priced at $0. Add it to
MANUAL_ENTRIES + the snapshot and map the "Mythos 5" display name.
Claude Code routed through a GitHub-Copilot-backed proxy (ANTHROPIC_BASE_URL
-> claude-code-over-github-copilot / claudegate) costs ~$0 marginal but was
priced at full Anthropic API rates, producing a misleading cost figure. The
JSONL records only the model name and no endpoint, so proxying cannot be
auto-detected; the user declares it.
Add a `proxyPaths` config (managed via a new `codeburn proxy-path` subcommand)
listing project directories served through a subscription proxy. Sessions whose
canonical path is under one keep their full API-rate totalCostUSD (the billable
would-be figure is never destroyed) and additionally report totalProxiedCostUSD,
so the JSON report overview exposes cost / proxiedCost / netCost
(netCost = cost - proxiedCost). With no proxyPaths configured the new fields are
0 and every existing consumer is unchanged.
Design: "full cost, flagged" was chosen over zeroing cost so a misconfigured or
since-changed path can never silently erase real Anthropic spend. Attribution is
project-level (one canonical path per project), computed in a single helper
(summarizeProject) that all ProjectSummary builders route through, including the
cross-provider merge in parseAllSessions (re-derived from the merged total so a
repo used with both Claude and Codex stays correct). The in-memory session-cache
key folds in a proxy-config hash so toggling proxyPaths in a long-lived process
cannot serve stale attribution. Path matching is segment-boundary anchored
(/foo does not match /foobar), trailing-slash and backslash tolerant, leading-
slash agnostic (so a non-Claude provider's slash-stripped path matches the same
way Claude's absolute path does), and case-folded only on case-insensitive
filesystems (macOS/Windows, not Linux). The proxy-path CLI sanitizes a
hand-edited config.json (non-array / non-string entries) rather than crashing.
Tested: isProxiedPath matching matrix (boundary, case, Windows, empty, root,
multi-path, leading-slash form); config-hash distinctness/order-independence;
end-to-end attribution through parseAllSessions incl. the critical negative
cases (real spend must not be zeroed); cross-provider Claude+Codex merge;
Codex-only project under a proxy path; date-range-filtered attribution;
cache-staleness after a config change; and the proxy-path CLI add/list/remove,
malformed-config robustness, and the report --format json overview.
Scope note: proxiedCost/netCost currently surface in `report --format json`
only; wiring them into the TUI dashboard and menubar payload is a follow-up.
Keep model pricing automatic instead of hand-coding new models. The bundler
now layers three sources in priority order: LiteLLM (broad list prices),
hand-curated MANUAL_ENTRIES overrides, then a separate last-resort fallback
file gap-filled from models.dev first-party makers (official direct prices)
and OpenRouter (resale backstop). New models such as MiniMax-M3 ($0.6/$2.4)
now price correctly with no per-model code.
The fallback is written to its own pricing-fallback.json and consulted only
case-insensitively as the final step in getModelCosts, so a reseller variant
name can never shadow a canonical or aliased match.
Fixes surfaced while building and verifying this:
- Alias precedence: LiteLLM ships snowflake/claude-4-opus ($5), which the
bundler strips to a bare claude-4-opus key that shadowed the curated alias
to claude-opus-4 ($15 official). An explicit alias for a bare name now wins
over a coincidental stripped reseller key; the prefixed gateway price is
still returned for the fully-qualified id.
- Zero-stub guard: LiteLLM [0,0] price stubs (e.g. GigaChat-2-Max) are
excluded from the case-insensitive index so a case-mismatched query stays
null and keeps firing the unknown-model warning instead of silently
reporting $0.
- Negative-sentinel guard: OpenRouter returns -1 for variable/BYOK-priced
models. The bundler now rejects any non-positive rate pair (and strips the
sentinel from cache fields) so a negative per-token cost can never ship and
subtract from spend totals.
Bundler hardening: bareKey strips @pin and date suffixes to match the runtime
canonical form, seen-set dedupes on both full and bare key shapes, and it logs
MANUAL_ENTRIES now covered upstream plus models.dev allowlist drift. Extracted
buildCosts so the cache-cost heuristics live in one place. Added a data-hygiene
test that fails CI if a rebundle reintroduces negative, free, or unreachable
fallback entries.
Resolves conflicts from the post-PR refactor that moved buildPeriodData,
hydrateCache, and the menubar payload builder out of main.ts into
usage-aggregator.ts. The PR's savings additions to those functions are
re-homed there; config.ts keeps both new fields; parser.ts keeps both imports;
redact.ts session details carry savingsUSD.
The pricing fetch (loadPricing -> fetchAndCachePricing) runs on every CLI
invocation, and the macOS menubar shells out to the CLI and blocks on its
exit. fetch() had no timeout, so a half-open network after wake-from-sleep
made it hang forever once the 24h pricing cache expired — wedging the
menubar on its loading spinner until relaunch.
Add a shared fetchWithTimeout helper (8s default, AbortSignal.timeout) and
apply it to the two daily-critical-path fetches: pricing (models.ts) and
the currency rate (currency.ts). On timeout the existing catch falls back
to the bundled price snapshot / cached or USD rate.
Reproduced on main (stale cache + black-holed host -> hangs indefinitely);
with the timeout the same scenario aborts in 8s and renders via fallback.
Add a new `localModelSavings` config and `codeburn model-savings` CLI
that maps a local-model name (e.g. llama3.1:8b) to a paid baseline
(e.g. gpt-4o). The local call still costs $0; the new `savingsUSD`
field tracks the counterfactual spend avoided by running locally and
is reported separately from `costUSD` everywhere a number is shown.
* Parser normalization (`applyLocalModelSavings`) runs on Claude
parse, direct provider calls, and the cached-call path. It forces
`costUSD` to 0 and attaches `savingsUSD` + `savingsBaselineModel`
+ `isLocalSavings` on the `ParsedApiCall`. Local-savings wins for
actual cost even when the same model is also in `modelAliases`.
* Session, project, day, model, category, activity, skill, and
subagent rollups all carry `savingsUSD` alongside `costUSD`.
* `status --format json` adds `today.savings` and `month.savings`.
* `status --format menubar-json` adds a `current.localModelSavings`
block (totalUSD, calls, byModel, byProvider) plus savings on
topModels, topProjects, topSessions, topActivities, and history
daily entries. Schema fields default-decode for backward compat.
* `report --format json` adds savings across overview/daily/
projects/models/activities/skills/subagents/topSessions, with
the active paid baseline name on each model row.
* `models` command gains a `Saved` column on table/markdown/CSV
and a `savingsUSD`/`savingsBaselineModel` pair in JSON. Default
`--min-cost 0.01` filter now ORs in `savingsUSD >= minCost` so
local models with $0 actual cost but >0 savings still surface.
* CSV/JSON exports add a `Saved (CODE)` column on summary/daily/
models/projects/sessions.
* Dashboard TUI shows a green 'saved $X by local models' footer
line in the overview when any savings are present.
* macOS Swift payload gains a `LocalModelSavings` Codable block
and savings fields on every model/activity/session/daily
struct. Hero shows a green leaf 'Saved $X' caption, models
section gets a green `Saved` column. `swift build` clean.
* GNOME indicator adds 'saved $X' to the hero meta line and a
`codeburn-model-saved` column to the model row.
* Daily cache schema bumped to v8 (`savingsUSD` on day/model/
category/provider). `savingsConfigHash` invalidates the cache
when the user changes their baseline mapping so historical
saved-spend numbers never lie about a stale baseline.
* Defensive `Object.hasOwn` lookup in `getLocalSavingsBaseline`
blocks the prototype-pollution test that previously surfaced via
the savings path with a hostile `__proto__` model name.
* New tests (5 files, 25 tests, 549 lines) cover pricing helpers,
end-to-end parser normalization, day aggregator savings,
menubar payload savings, CLI set/list/remove, and
daily-cache hash invalidation. Existing tests for daily-cache
/ day-aggregator / models-report updated for the new fields.
Full vitest suite: 1028/1028 passing across 73 test files.
`tsc --noEmit` clean. `npm run build` clean.
(Note: `mac/Tests` has a pre-existing `no such module 'Testing'`
environment error on the installed Swift toolchain, confirmed
on `main` before this PR; not caused by these changes.)
A bare startsWith let an unlisted future minor collapse into the base entry
(gpt-5.6 -> "GPT-5"), the same mis-bucketing class as #420 but for non-Claude
families. Require an exact match or a key-plus-dash boundary in both
getShortModelName and the Codex provider so new versions fall through to their
raw id instead of a wrong name and pricing tier.
New Claude releases no longer need a hand-maintained SHORT_NAMES entry or
FAST_MULTIPLIERS row. Display names are derived from the claude-<family>-<major>-<minor>
id, and the fast-mode multiplier rides along as a 5th element in the LiteLLM
snapshot tuple (provider_specific_entry.fast). Fixes#420: claude-opus-4-8 gets
its own line and correct pricing instead of falling into the Opus 4 bucket.
* Add IBM Bob provider
* Add workspace extraction for Cline-family providers
Extract project name from workspace directory in api_conversation_history.json
so sessions show actual folder names instead of the provider display name.
Thread projectPath through ParsedProviderCall to avoid unsanitizePath mangling
hyphenated folder names.
---------
Co-authored-by: ozymandiashh <234437643+ozymandiashh@users.noreply.github.com>
Co-authored-by: iamtoruk <hello@agentseal.org>
Cursor emits model names in a `claude-<dot-version>-<tier>` shape
(`claude-4.6-sonnet`, `claude-4.5-opus`, `claude-4.5-opus-high-thinking`,
etc.) plus its own `composer-1` house model. None of these match
the canonical LiteLLM pricing keys (`claude-sonnet-4-6`,
`claude-opus-4-5`).
The alias map in `src/models.ts` filled some of these in v0.9.4
but missed:
- plain no-suffix forms: `claude-4.5-opus`, `claude-4.5-sonnet`,
`claude-4.6-opus`
- haiku tier: `claude-4.5-haiku`, `claude-4.6-haiku`
- forward-looking: `claude-4.7-opus`
- Cursor's house model: `composer-1`
The dashboard rendered $0 for sessions that used any unaliased
model — visible in the screenshots posted in #159 even after the
v0.9.4 fix that added the `-thinking` variants.
This PR fills the gaps and adds 16 regression tests under
`Cursor model variants resolve to pricing` that assert every
model name in `src/providers/cursor.ts:modelDisplayNames` plus
the additional plain forms resolves to a non-null pricing entry
with `inputCostPerToken > 0` and `outputCostPerToken > 0`. So a
future LiteLLM snapshot bump or a typo in the alias map will fail
the test before users see $0.
Direct hits in the snapshot (no alias needed): `gpt-5`, `gpt-5.2`,
`grok-code-fast-1`, `gemini-3-pro` (already aliased). These are
covered in the test suite as well so a snapshot that drops them
would also be caught.
Tests: 45 files, 617 passing locally (16 new). Closes#159.
* Quiet routine pricing warnings + menubar recovery from stuck-loading
CLI:
- Default `codeburn` invocation no longer prints "no pricing data for model"
warnings on every run. Greeting a fresh user with three lines of stderr
before the dashboard even draws looked like the tool was broken on first
launch. The warning now requires --verbose, and the suppressed pricing
miss still results in $0 cost (correct for unmapped models).
- Local-model heuristic skips the warning entirely for Ollama tags
(`qwen3.6:35b-a3b-bf16`), GGUF/quantized fingerprints, and similar names
that will never have public pricing. The "update codeburn" hint was
actively misleading there.
- When the warning does fire (with --verbose), it points users at
`codeburn model-alias <model> <known-model>` as the actual escape hatch
alongside the package update suggestion.
Menubar:
- Replace perpetual "Loading…" spinner with a FetchErrorOverlay when the
per-key fetch fails and the cache is empty. User sees the error and a
Retry button instead of an infinite hang.
- Add diagnostic breadcrumbs (NSLog, invisible to normal users — Console.app
/ `log stream --process CodeBurnMenubar` only) for the four states that
produce a stuck loading overlay:
- subprocess timeout after 45s
- fetch result dropped due to Task cancellation (rapid tab switch)
- fetch result dropped due to mid-fetch calendar rollover
- retry attempt where the last successful fetch is >2 min stale
- Track lastSuccessByKey separately from cache freshness so the staleness
diagnostic survives day-rollover cache wipes.
* Stop flashing the compare-view loading screen on background refresh
When the 30s CLI tick updated `projects` while the user was reading the
model comparison results, the projects-watching effect always fired
setLoadTrigger, which flipped phase to 'loading' and re-ran the slow
scanSelfCorrections walk over every provider's session directory. The
user lost their scroll position and saw a loading flash mid-read.
Recompute the comparison rows in place when:
- the user is already on the results phase, AND
- both picked models still exist in the new aggregate.
Skip the corrections rescan on these in-place refreshes — corrections
drift slowly enough that holding the previous value until the user
re-enters compare is acceptable, and the rescan is the slow part of the
load. Initial selection and post-selection load still run the full
pipeline.
Two passes of validators across CLI accuracy, dashboard UX, menubar Swift,
performance, security, and end-to-end smoke tests on real session data.
Data-correctness fixes:
- parseLocalDate rejects month/day overflow. JS Date silently rolled
Feb 31 to Mar 3, so --from 2026-02-31 --to 2026-03-15 quietly dropped
sessions on Feb 28 - Mar 2. Now throws "Invalid date" with a clear
reason. Leap-day case covered (2024-02-29 valid, 2025-02-29 rejected).
- CSV/JSON exports use the active currency's natural decimal places. The
previous round2 helper produced ¥412.37 in CSV while the dashboard
rendered ¥412 — finance teams comparing the two surfaces saw a
discrepancy. New roundForActiveCurrency consults Intl.NumberFormat for
the right precision (0 for JPY/KRW/CLP, 2 for USD/EUR, etc).
- Copilot toolRequests is Array.isArray-guarded in both modern and legacy
event branches. Previously a corrupt session with toolRequests=null or
a string aborted the whole file's parse loop and silently dropped every
legitimate call after it.
- Codex token_count dedup uses a null sentinel for prevCumulativeTotal so
the first event is never confused with a duplicate. Sessions that emit
only last_token_usage (no total_token_usage) report cumulativeTotal=0
on every event; with the previous 0-initialized prev, the first event
matched the dedup guard and was dropped.
- LiteLLM pricing values are clamped to [0, 1] per token via safePerTokenRate.
Defense in depth against a tampered upstream JSON shipping negative or
absurdly large per-token costs that would otherwise propagate into all
cost totals.
Performance:
- Cursor SQLite parse no longer pegs at minutes on multi-GB DBs. Two
changes: per-conversation user-message buffer uses an index pointer
instead of Array.shift() (which was O(n) per call); and a real ROWID
cutoff via subquery limits the scan to the most recent 250k bubbles
with a stderr warning so power users get a partial report rather than
a stalled CLI.
- Spawned codeburn CLI subprocesses are terminated when the calling Task
is cancelled. Without this, rapid period/provider tab clicks in the
menubar cancelled the Task but left the subprocess running to
completion, piling up zombie processes.
UX:
- Dashboard period switch flips to loading and clears projects
synchronously before reloadData runs, eliminating the frame where the
new period label rendered over the old period's projects.
- Optimize findings tab paginates 3-at-a-time with j/k scroll. With 4
new detectors plus 7 originals, 8-10 findings * 6 lines was scrolling
the StatusBar off the alt buffer top.
- Custom --from/--to ranges hide the period tab strip and disable the
1-5 / arrow keys so a stray period press no longer abandons the user's
explicit range. A "Custom range: X to Y" banner replaces the tab strip.
- OpenCode storage-format warning is per-table-set, rate-limited to once
per process, and points the user at OpenCode's migration step or the
issue tracker. The previous all-or-nothing check fired the generic
"format not recognized" string for any schema mismatch.
Menubar / OAuth:
- Both Claude and Codex bootstrap (Reconnect button) now honour the
usageBlockedUntil 429 backoff that refreshIfBootstrapped respects.
Spamming Reconnect during sustained rate-limit windows previously
hammered the upstream endpoint on every click.
- Codex Retry-After HTTP header is parsed (delta-seconds plus IMF-fixdate
fallback) so we don't over-back-off when ChatGPT tells us a shorter
window than our 5-minute floor.
- Both credential cache files are written via SafeFile.write
(O_CREAT | O_EXCL | O_NOFOLLOW with explicit 0600) so there is no race
window where the temp file briefly exists at default umask, and a
symlink at the destination cannot redirect the write. Reads now route
through SafeFile.read with a 64 KiB cap, closing the symlink-follow gap
on Data(contentsOf:).
CI signal:
- TypeScript strict typecheck (tsc --noEmit) is now zero errors. The
six errors in src/providers/copilot.ts came from a discriminated-union
catch-all branch whose `data: Record<string, unknown>` shape TS picked
over the specific event branches when narrowing on `type`. Removed the
catch-all; runtime falls through unknown event types via the existing
if/else chain.
Tests added: 16 new (now 555 total)
- date-range-filter: month/day/year overflow rejection, leap-day correctness
- currency-rounding: convertCost no-rounding contract, roundForActiveCurrency
for USD/JPY/KRW/EUR
- providers/copilot: malformed toolRequests does not abort the parse
- providers/cursor-bubble-dedup: re-parse after token mutation does not
double-count, single parse yields one call per bubble
- providers/codex: first event with cumulativeTotal=0 not dropped,
consecutive zero-cumulative duplicates still deduped
* Five correctness fixes from multi-agent bug hunt
A multi-agent audit of the codeburn correctness surface found five
real bugs each producing visibly wrong numbers or risking data loss.
All five fixes were validated by parallel review agents and exercised
end-to-end against real session data on this machine.
- src/cli.ts: --refresh <seconds> was using bare parseInt as the
commander callback. Commander invokes the callback as
parseInt(value, previous), so previous becomes the radix:
--refresh 30 was being parsed as parseInt('30', 30) = 90, and
--refresh 60 became NaN. Replaced with parseInteger (already
defined at line 48 with radix locked to 10) at all three sites.
- src/providers/cursor.ts: parseAgentKv was timestamping every
agentKv call as new Date().toISOString() because the Cursor
SQLite schema has no per-message timestamp. Result: every
Cursor agent call regardless of when it happened landed in
today's date bucket. Now uses statSync(dbPath).mtimeMs as a
bounded ceiling so calls land at the actual last-write time of
the Cursor database, not today. Verified locally: a 1904-call
Cursor history with March 22 mtime now correctly bucket into
all-time only and shows 0 calls for today/week/30days.
- src/providers/codex.ts: prev token counters were only updated
inside the cumulative-fallback branch, so a session emitting N
events with last_token_usage followed by one cumulative-only
event computed the next delta against prev=0 and double-counted
the entire cumulative window. Cost could be inflated 10-100x
for any mixed-format Codex session. Now prev advances to the
current cumulative state regardless of which branch ran.
- src/providers/gemini.ts: totalOutput accumulated output+thoughts
while totalThoughts was tracked separately. The result was
outputTokens = output+thoughts AND reasoningTokens = thoughts;
any consumer summing the two double-counted thoughts. Now
totalOutput holds just output, reasoningTokens holds thoughts,
and the cost calc folds thoughts into the output count to keep
pricing correct (Google bills thoughts at the output rate;
calculateCost has no reasoning parameter).
- src/export.ts: exportJson had no safety check before writeFile,
so codeburn export -f json -o ~/important.json would silently
clobber the user's file. CSV path had a marker-file guard; JSON
did not. Now refuses to overwrite a file unless its first 4KB
contain the codeburn schema marker. Uses a streaming partial
read so a large existing file does not OOM Node's ~512MB
string limit. Refuses directories outright.
Skipped intentionally: cursor-auto/copilot-auto/cline-auto/
qwen-auto are aliased to claude-sonnet-4-5. The audit flagged
this as wrong pricing for non-Anthropic auto-routed turns, but
Cursor's "auto" mode does not expose the actual model and any
alternative estimate is equally arbitrary. README already
documents this as a Sonnet-based estimate.
vitest run: 38 files, 529 tests pass.
* Five more correctness fixes from the bug-hunt round
This commit closes out the remaining critical-tier findings from the
multi-agent audit, with one item documented as a known limitation.
- src/providers/cursor.ts: bubble dedup key included mutable
inputTokens/outputTokens. Cursor mutates token counts on the row in
place when streaming completes, so re-parsing the same DB produced
a fresh dedup key per bubble and silently double-counted. Switched
to the SQLite row key (`bubbleId:<unique>`) which is stable per
bubble. Adjusted BubbleRow type and BUBBLE_QUERY_BASE to expose
`key as bubble_key`.
- src/providers/pi.ts: usage fields were destructured non-optionally,
but real Pi/OMP session files sometimes omit individual fields.
`calculateCost(model, undefined, ...)` returned NaN, and that NaN
propagated into every aggregate cost total. Coerce each field to
0 with `?? 0`.
- src/models.ts: getShortModelName and the getModelCosts startsWith
fallback both walked the dictionary in insertion order. A model id
like `gpt-5-mini` could resolve to the entry for `gpt-5` (matched
by startsWith first) and silently get GPT-5's display name and
pricing tier. Iterate longest keys first so more-specific prefixes
win. Tightened the cost fallback's match condition from
`startsWith(key) || startsWith(key + '-')` to require either an
exact match or a `key + '-'` continuation, removing accidental
matches like `gpt-50` against `gpt-5`.
- src/models.ts: calculateCost returned 0 silently for any model
missing from the pricing snapshot. New Anthropic / OpenAI models
shipped between snapshot refreshes look free until the user
notices. Now warns once per unknown model name per process to
stderr. Skips the warning for the `<synthetic>` placeholder so
the noise floor stays low.
- src/yield.ts: revert detection was broken on the canonical case.
Two problems: (1) `subject.toLowerCase().includes('revert')`
matched any commit whose subject mentioned the word ("Add revert
button" was misclassified). (2) The window logic only counted
reverts within the original session's 1-hour boundary, but real
`git revert` commits land in later sessions, so original sessions
always looked productive. Now: getRevertedShas runs once with
`--grep=^This reverts commit` and parses bodies to build a Set of
SHAs that were the target of a revert anywhere in history.
CommitInfo.wasReverted is set when this commit's SHA appears in
that set. categorizeSession then flags a session as reverted when
its in-main commits were later reverted, regardless of when the
revert itself happened.
- src/providers/droid.ts: SKIPPED with comment. Droid records token
usage only at session level. The current behavior splits evenly
across emitted assistant calls and prices all of them at
settings.model (the latest model). For sessions where the user
switched models mid-stream, costs are approximate. Added an
inline comment documenting this; a real fix requires per-message
model data that isn't in the Droid JSONL schema.
Verified end-to-end on this machine:
- vitest run: 38 files, 529 tests pass
- `codeburn report --format json` produces valid JSON
- `codeburn yield -p week` runs without crashing, finds 0 reverts
in the user's recent git history (plausible — fix changed the
detection from "subject contains revert" to "this commit's SHA
appears in a later 'This reverts commit ...' body")
- Stderr now warns for unknown model ids: `openai/gpt-5.3`,
`qwen3.6:35b-a3b-bf16`, `big-pickle`. These previously priced
silently at $0.
* Four high-severity fixes from the bug-hunt round
- src/currency.ts: getExchangeRate wrapped fetchRate and cacheRate in
one try/catch. If fetchRate succeeded but cacheRate threw (disk
full, ENOSPC, no permissions on the cache dir), the catch block
swallowed the error and returned 1. Every cost rendered after that
point became USD-equivalent silently. Now the fetch and the cache
write live in separate paths: a successful fetch returns the rate
even if the persist fails, and the cache-write error is dropped to
a fire-and-forget so transient disk problems do not corrupt the
user's currency display.
- src/cursor-cache.ts: writeFile was non-atomic. Two concurrent
codeburn invocations writing to cursor-results.json could
interleave bytes mid-write, leaving a truncated file that
parsed-error on next read and forced a full SQLite re-scan every
run. Switched to the temp-file + rename pattern with a randomized
temp name so each writer gets its own staging file and the rename
is atomic on POSIX. Crash mid-write also leaves only a leftover
temp file, which gets unlinked in the catch path; the destination
is never half-written.
- mac/.../CodeBurnApp.swift refresh loop on sleep: the loop's
Task.sleep keeps a wakeup pending across system sleep, so on wake
the natural tick fires the same instant the wake observers do.
Combined with didWakeNotification, screensDidWakeNotification, and
the launchd com.codeburn.refresh distributed notification, that
produced 2-3 concurrent CLI spawns within ms of every wake. Now:
willSleepNotification cancels the loop task; didWakeNotification
restarts it. The loop also reads lastRefreshTime and skips its
natural tick if a wake/manual/distributed-notification refresh ran
within the last 5 seconds, coalescing the two sources of refresh
into one CLI spawn per wake event.
- mac/.../CodeBurnApp.swift observeStore: the read closure had an
implicit strong self capture (it accessed store.* without a
capture annotation), pinning self for the lifetime of any
unfired observation. Added [weak self] and a guard to make the
capture explicit. withObservationTracking is one-shot per call,
so there is at most one active subscription at a time; the
earlier audit's claim of an unbounded leak overstated the issue,
but tightening the capture pattern is still cleaner.
Verified:
- vitest run: 38 files, 529 tests pass
- swift build -c release --arch arm64 --arch x86_64: clean, no
diagnostics, no MainActor warnings
- mac/Scripts/package-app.sh dev produces a valid universal bundle
- Menubar launches and runs without crash
* Eleven medium-severity fixes from the bug-hunt round
- src/format.ts formatTokens: guard against Infinity, NaN, and
negative input. Previously a corrupt aggregate could leak into
the UI as the literal strings "NaN" or "Infinity". Negatives now
render as "0" rather than "-500" with no scaling.
- src/cli-date.ts parseDateRangeFlags: the missing-from default
was new Date(0), which opened a 55-year scan from 1970 epoch
whenever the user passed only --to. Default now anchors at 6
months back from now, matching the dashboard's all-time period.
Test updated to assert the new bounded window.
- src/cli-date.ts toPeriod: previously fell back silently to "week"
for any unknown input, so a typo like `-p mounth` produced a
quiet 7-day report while the user thought they were viewing the
month. Now exits with a clear stderr error and exit code 1.
Test updated to assert the loud-failure behavior.
- src/optimize.ts urgencyScore: rebalanced weights so a high-impact
finding with zero observed tokens cannot outrank a medium-impact
finding with millions of tokens. Old 0.7/0.3 split made high+0
(0.70) beat medium+1B (0.65). New 0.5/0.5 split makes medium+1B
(0.75) beat high+0 (0.50). Token normalization lifted to 5M so
the ramp covers a realistic spend range.
- src/models.ts calculateCost: clamp negative or non-finite token
inputs to 0 before pricing. A corrupt JSONL emitting a negative
count would otherwise produce a negative cost that silently
subtracted from real spend in aggregates.
- src/currency.ts convertCost: stop rounding during aggregation.
For zero-fraction currencies (JPY, KRW, CLP) this clamped every
per-session cost to a whole unit before sum, so a project of
1000 sessions averaging ¥0.4 each aggregated to ¥0 instead of
¥400. formatCost still rounds at the display boundary.
- src/config.ts saveConfig: the temp file path was a fixed
`${configPath}.tmp` suffix. Two simultaneous saveConfig calls
(overlapping menubar and CLI runs) raced on the same staging
file and could leave one writer reading partial bytes from the
other. Randomized the temp suffix per call.
- src/providers/antigravity.ts flushCache: the early return on
`!cacheDirty` short-circuited eviction when liveCascadeIds was
supplied but no cascade had been added or updated this run. As
a result, deleted .pb files persisted in the cache forever once
the user stopped writing to it. Eviction now runs whenever
liveCascadeIds is provided, marks the cache dirty if anything
was removed, and only then short-circuits if there is nothing
to write.
- src/daily-cache.ts addNewDays: cap retention at 2 years. The
days array previously merged forever, growing the cache file by
hundreds of bytes per day until JSON parse on every CLI
invocation became measurable. The 6-month UI period plus the
365-day BACKFILL_DAYS bootstrap both fit comfortably inside the
cap, with headroom for a future longer window.
- src/dashboard.tsx useInput: period number keys (1-5) and arrow
keys triggered a reload while the compare view was mounted. The
parent's data state changed underneath the user with no visual
affordance back to the dashboard. Now those keys are gated on
view !== 'compare', and `b` / Esc inside compare returns to the
dashboard.
- mac/.../HeatmapSection.swift formatters: prettyDate, buildTrend
Bars, computeTrendStats, computeForecast, and computeAllStats
each allocated a fresh DateFormatter (and Calendar) on every
call. SwiftUI re-evaluates these views many times per second
during hover scrubbing on the trend chart, so the allocations
were a measurable hot spot. Lifted the yyyy-MM-dd / "EEE MMM d"
/ "MMM d" formatters and the gregorian Calendar to fileprivate
cached singletons.
Two findings from the same bucket were not addressed here:
- UpdateChecker SHA-256 / codesign verification is already
performed by src/menubar-installer.ts (verifyChecksum at line
85). The Swift side just kicks off `codeburn menubar --force`
which runs that path. The audit's claim of missing verification
was a misread.
- NSDistributedNotificationCenter sender validation: the
`com.codeburn.refresh` listener accepts from any sender, but
forceRefresh has a 5-second rate-limit gate so the abuse
ceiling is one CLI spawn per 5 seconds. Mitigations (Mach IPC,
per-launch shared secret) are disproportionate to the impact.
vitest run: 38 files, 529 tests pass.
swift build -c release: clean, no warnings.
* Validator hardenings on the bug-hunt batch
Hoist the per-call sort in getModelCosts and getShortModelName to module
scope so model lookups on the hot path stop reallocating sorted key arrays.
Sanitize the unknown-model stderr warning by stripping C0/C1 controls
and capping length, so a hostile or corrupt JSONL cannot inject terminal
escape sequences via the model field.
Skip the daily-cache prune when newestDate fails to parse. The previous
code produced a NaN cutoff and silently dropped every cached day on the
next merge.
Adds tests locking down the stable resolution of common model names
(gpt-5-mini vs gpt-5, claude-haiku-4-5 vs claude-3-5-haiku, etc.) and
the prune NaN guard.
