usage.reasoningTokens is the AI SDK v6 normalized field across all
provider families, so the providerMetadata.openai fallback never fired.
Removed it and the now-unused openai extraction.
* feat(providers): add coder/mux as a datasource
Reads coder/mux session data from ~/.mux/sessions/<workspaceId>/chat.jsonl and normalizes per-assistant-message token usage into ParsedProviderCall. Discovery resolves project names from config.json; the token decomposition matches mux's own inclusive input/output accounting, and cost is recomputed via LiteLLM. Includes unit tests and a provider doc.
Change-Id: Ie6ce9d41254d8bf05ff0965b443328dfa7b598de
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Signed-off-by: Thomas Kosiewski <tk@coder.com>
* fix(providers): discover mux sub-agent transcripts
discoverSessions only globbed sessions/<id>/chat.jsonl and skipped each
spawned sub-agent's transcript at
sessions/<id>/subagent-transcripts/<childTaskId>/chat.jsonl. Against a real
~/.mux (629 workspaces) those nested files are 5,889 sessions and ~51% of all
assistant messages, so sub-agent spend was silently dropped: total mux usage
went from $17,113 to $21,564 (+26%) once counted.
Walk the subagent-transcripts dir per workspace and attribute each child
session to the parent's project. Dedup is unaffected: the parser keys off the
<childTaskId> dir name, which is disjoint from every workspace id, so each call
is still counted once. Cross-checked parsed per-model token totals against
mux's sibling session-usage.json.
Also corrects the provider doc, which wrongly claimed sub-agents get their own
top-level sessions/<id>/chat.jsonl, and documents the Google reasoning>output
decomposition edge case.
Change-Id: I1d43f26eec7c9c6c523e5ea541e2ff8d0c3aa07e
Signed-off-by: Thomas Kosiewski <tk@coder.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Signed-off-by: Thomas Kosiewski <tk@coder.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds a "Config Directories" section under the Claude settings tab so users
can aggregate usage across multiple Claude config directories (work /
personal accounts) from the GUI. The menubar is an accessory app that
doesn't inherit the user's shell environment, so CLAUDE_CONFIG_DIRS was
previously unreachable from the app.
Rather than injecting the value as an env var into every spawned subprocess
(which would force arbitrary user paths through the shell/AppleScript
allowlist that deliberately excludes shell metacharacters), the list is
persisted to the shared ~/.config/codeburn/config.json. The CLI reads it
regardless of how it's launched, so both the menubar's data refresh and
terminal-launched `report`/`optimize` honor it consistently.
CLI: getClaudeConfigDirs() now reads a claudeConfigDirs array from config
as a fallback below the CLAUDE_CONFIG_DIRS / CLAUDE_CONFIG_DIR env vars
(env still wins for per-shell overrides), above the ~/.claude default.
Menubar: CLIClaudeConfig mirrors CLICurrencyConfig's flock-guarded write;
the Settings UI offers an add/remove list with a folder picker and forces
a refresh on edit.
The currency picker hardcoded 8 currencies while the SupportedCurrency
enum defines 18. New currencies added to the enum (like CNY in #430)
required a separate SettingsView edit to appear in the picker.
discoverSessions always checks the SQLite path at ~/.local/share/kilo
regardless of overrideDir, so the test found real sessions on the host.
Filter to override-dir sessions and avoid hardcoded /tmp paths.
- Add per-install random salt to pseudonym hash to prevent rainbow table
reversal of common project names
- Redact session details (dates, models) when project names are hashed
to prevent re-identification via cost fingerprinting
- Return structuredContent in error responses to satisfy strict MCP
clients that validate against declared outputSchema
- Remove pre-warm fire-and-forget that raced with the inflight map
- Fix empty markdown table producing malformed cells
- Add tests for session detail redaction and cross-field consistency
The menubar wedged on "Loading Today…" for hours after an idle period.
Root cause: DataClient.runCLI called the blocking process.waitUntilExit()
from an async function on Swift's cooperative thread pool. On a 16-core
machine, 16 concurrent slow `codeburn` subprocesses pinned all 16
cooperative threads inside waitUntilExit; the 45s timeout — itself a Task
on that same pool — could then never be scheduled to kill them, so the
deadlock was permanent. Confirmed via sample: 16/16 cooperative threads
parked in waitUntilExit. PR #412 (AppStore inFlightKeys bookkeeping) was a
layer above the OS-thread deadlock and could not fix it.
Move both blocking points off the cooperative pool: bridge waitUntilExit
through a global (overcommit) queue via a continuation, and drive the
timeout from a DispatchSource on a global queue so it fires even when the
pool is saturated. Extract runProcess for testability; add a concurrency +
timeout smoke test and an output/exit-code test.
Extract the duplicated codeburn-binary lookup (PATH building, npx-shim skipping,
default lookup dirs, resolver) from menubar-installer and the Antigravity
statusline installer into src/persistent-codeburn.ts. Both now import it and
keep their own user-facing "install globally" message.
Match the Antigravity statusLine hook on the trailing agy-statusline-hook token
instead of a bare substring, so a custom command that merely mentions the token
is treated as custom (protected, backed up) rather than silently overwritten.
Fix Antigravity hook stale CLI paths: install the statusLine hook through a
persistent codeburn binary resolved from PATH and repair stale CodeBurn-owned
hooks on re-install.
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.
The Claude provider kept its own shortNames map with no claude-opus-4-8
entry, so the models table and menubar bucketed it into "Opus 4" — the
actual #420 path (the earlier models.ts map is unused here). Delegating to
getShortModelName removes the duplicate and picks up new versions for free.
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.
The menubar kept its own copy of each provider's OAuth grant and refreshed
it on a timer, racing the CLI. Both Claude and Codex use single-use refresh
tokens that rotate on every refresh, so the menubar's self-rotation could
invalidate the user's own CLI login and surfaced as "disconnected" after a
long idle period.
Codex: read ~/.codex/auth.json fresh each cycle; only self-refresh when
last_refresh is older than 8 days; on 401 re-read the source before spending
our token; write rotated tokens back to auth.json (atomic, preserving other
keys); recover from reuse/invalid_grant by re-reading instead of going
terminal.
Claude: never HTTP-refresh the CLI-owned token. On expiry/401 re-read the
keychain with a no-UI query (LAContext.interactionNotAllowed) to adopt a
token the CLI already rotated; when none is available yet, report a transient
sourceTokenStale rather than a terminal disconnect.
A launchd-spawned process gets separate TCC attribution from the LaunchServices
app, so the out-of-process refresher prompted for "access data from other apps"
on every run regardless of the GUI's grant. Remove it entirely: the in-app loop
(timer survives sleep, popover-open recovery) is the source of truth and now
writes menubar-status.json on each successful refresh. On upgrade, any leftover
com.codeburn.refresh LaunchAgent is unloaded and deleted.
Run CodeBurn's own signed binary in --refresh-once mode under the LaunchAgent
so the spawned CLI inherits CodeBurn's TCC grant. The bare-node shell script
prompted "node would like to access data from other apps" because launchd-
spawned children lose the signed app's TCC attribution. Drops the generated
shell script, scriptEnvironment, and per-period regeneration; the plist is now
static and period is read from UserDefaults at refresh time.
refreshStatusButton now uses the fresher of the in-memory payload and
the file written by the LaunchAgent, so the menubar number advances
within ~30s even if the in-app loop is dead.
Migrate off the osascript distributed-notification form (dropped by
napped apps) to a static /bin/sh runner. The plist no longer encodes
period, so it migrates once; period changes rewrite only the script.
Opening the popover now unconditionally restarts a dead timer and
clears stuck loading bookkeeping before force-fetching, so a user
looking at a stuck tab always recovers within one CLI round-trip.
The sleep handler tore down the DispatchSource timer; a missed wake
notification then left it nil forever, stranding the refresh loop.
Cancel only in-flight tasks and let the kernel-paused timer resume.
A quiet refresh torn down across sleep/wake (or a generation reset) can
leave an orphaned inFlightKeys entry for the current key. The stuck-loading
recovery guard bailed whenever any in-flight entry existed, so the popover's
retry loop no-oped forever and the spinner ("Loading Today...") never
cleared — observed on a long-lived instance that crossed the midnight day
rollover.
Clear stale loading/in-flight state via the existing watchdog before the
in-flight guard, so an orphaned entry can no longer trap recovery. A healthy
in-flight fetch (younger than the watchdog) is still respected.
