Changed startAutoRefillLoop to accept a config getter instead of a static
config object. The getter reads config from disk on every check cycle, so
CLI changes (nwc auto-refill on/off) take effect immediately.
- auto-refill.ts: config parameter replaced with getConfig() callback
- wallet/index.ts: always start loop when wallet exists, use getter
- daemon/index.ts: pass getAutoRefillConfig reading from disk sync
- config-store.ts: added loadDaemonConfigSync() for sync disk reads
- http/index.ts + cli.ts: removed 'Restart daemon to apply' messages
- Add step-by-step logging to fundFromNWC (initial/final balance, invoice,
payment status, fees) matching pay_invoice.mts pattern
- Remove invoice and preimage from POST /nwc/fund response
- Add final wallet balance to the response after funding completes
- auto-refill.ts: use WalletConnect instance directly instead of
NwcClient + RelayPool; check wallet.service for connection state
- wallet/index.ts: create single shared WalletConnect for auto-refill,
fundFromNWC, and getNwcStatus; remove NwcClient entirely
- daemon/index.ts: strip all NwcClient creation/connect/logging/cleanup;
auto-refill now gates on connectionString alone
- add applesauce-wallet-connect dependency
- Encryption auto-detection: reads wallet info event (kind 13194) on connect
to choose NIP-04 vs NIP-44 per NIP-47 spec
- Subscription readiness: wait for EOSE before resolving connect()
- Dual NIP-04 / NIP-44 encrypt/decrypt support
- Proper encryption tags on NIP-44 requests
- test_nwc.ts: standalone NWC test script for make_invoice + pay_invoice
Two bugs caused NWC responses to never arrive:
1. getPublicKey() in nostr-tools v2 already returns a hex string, but
the code wrapped it with Buffer.from().toString('hex'), producing a
double-encoded 128-char string. The relay rejected the REQ filter
with 'filter item too large' because the #p tag value was invalid.
2. The 'secret' from the NWC connection string (the pre-shared client
private key per NIP-47) was parsed but never used. Instead a new
random keypair was generated on every restart, so the wallet service
would see requests from an unexpected pubkey.
Also removed 'since' from the subscription filter (simpler, some relays
choke on it) and added debug logging for the REQ filter.
- Add Dockerfile, docker-compose.yml, and .dockerignore for Bun dev container
- Fix sdkLogger to use logger.warn instead of logger.log for warnings
- Add proper warn method to logger (writes to file instead of console)
- Use console.log for daemon startup messages to keep them visible
- Update cashu-ts getDecodedToken call with explicit well-known-pubkeys
- Use proof.amount.toNumber() for updated cashu-ts Amount type
- daemon/index.ts: add makeSdkLogger() factory, wire daemonSdkLogger into
createBunSqliteDriver, createProviderRegistryFromStore, ModelManager, ProviderManager
- daemon/http/index.ts: add makeSdkLogger() factory, generate per-request
reqId via randomBytes(4), pass reqLogger = sdkLogger.child("req:${reqId}")
to routeRequests so every log line from a request is prefixed [req:XXXXXXXX]
- start-daemon.ts: remove >> logfile 2>&1 redirect and getTodayLogFile();
all file logging now goes through the daemon's writeLog() with daily rotation
Result: Every log line from a request is prefixed [req:XXXXXXXX], all entries
have [ISO] [INFO/ERROR/DEBUG] timestamps, no duplicates, and the log file
rotates correctly at midnight.
- Add 'npubs' tab between Clients and Recent (key 7)
- Tab is hidden when no clients have ownerNpub set
- Groups usage entries by ownerNpub via client-id → npub mapping
- Shows truncated npub (first 10 + … + last 6) with full npub on detail line
- Displays requests, cost, tokens, avg cost per npub with bar charts
- Includes 'Top Models per Npub' sub-section
- Tab keys dynamically renumbered (1-7 without npubs, 1-8 with)
- Falls back to Clients tab if Npubs becomes unavailable on refresh
Adds a CLIENT column between TIME and MODEL in the Recent Requests tab,
color-coded using CLIENT_COLORS. Entries without a client show "unknown".
Closes#25
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
After bootstrapProviders runs, newly discovered URLs (e.g. privateprovider.xyz)
were only known to the ModelManager cache and never written into the store's
baseUrlsList. This caused `providers list` and `models -m <id>` to show
different sets of providers. Now the bootstrap step merges any new URLs into
the store so both commands draw from the same source of truth.
Co-Authored-By: Claude Sonnet 4 <noreply@anthropic.com>
When cocod cannot assemble enough proofs to send (e.g. due to
denomination fragmentation or stale proof state), it returns
"Send failed: Not enough proofs to send". This was propagating
as a generic Error, causing the HTTP handler to return 500 instead
of the structured 402 insufficient_balance response.
Map that cocod error to InsufficientBalanceError in walletAdapter.sendToken
so the existing handler path returns the correct 402.
Co-Authored-By: Claude Sonnet 4 <noreply@anthropic.com>
- Updated npubs list to display role (admin/user) for each npub
- Changed header from 'Admin npubs' to 'Npubs' to reflect all roles
- Updated command descriptions to reflect broader scope
- Also fixed 'admin npub' message in add command output
The auth proxy intercepts GET /usage and returns only entries belonging to
the authenticated npub's clients, with owner suffixes stripped. The TUI no
longer needs to filter entries client-side.
- Remove getNpubSuffix and loadConfig from tui/usage/data.ts imports
- Remove old suffix-based filtering logic from fetchUsage()
- Remove unused getNpubSuffix from cli.ts imports
- Add ownerNpub?: string to ClientEntry and DaemonClient interfaces
- Update getClientsFromStore() to preserve ownerNpub field
- GET /clients: include ownerNpub in daemon response
- POST /clients/add: accept and store ownerNpub from auth proxy
- Remove getNpubSuffix/addSuffixToId/removeSuffixFromId from clients.ts (moved to auth proxy)
- Remove CLI-side suffixing in addDaemonClient and deleteClientAction
- Remove config loading from getClientsList (no longer needed for filtering)
- CLI output now shows raw client IDs without suffix stripping
- Add new installHermesIntegration to write ~/.hermes/config.yaml
- Prepend model block with base_url/api_key/default model at top
- Append custom_providers block at the bottom
- Use 3rd model in daemon list as default
- Add Hermes to setup menu and registry
When multiple routstrd processes (or CLI auto-starts) bootstrap simultaneously,
each process found cocod/routstrd unreachable, spawned its own copy, and
contended for the same database socket. The paired ~200ms burst timestamps
in the logs were the symptom.
Fixes applied:
- Add cross-process startup lock (process-lock.ts)
- Uses atomic mkdir as the lock primitive.
- Stores PID + UUID token; verifies ownership on release to avoid
removing a lock taken by a new process after the original crashed.
- Removes stale locks (unreachable PID or lock older than staleAfterMs).
- Exports withCrossProcessLock() for simple RAII-style usage.
- Fix cocod startup race (cocod-client.ts)
- Wrap ensureDaemonRunning() in a socket-derived lock path.
- Re-ping inside the lock before spawning; if another process just started
cocod, the current process detects it and connects instead of spawning.
- Switch from 'cocod daemon' to 'cocod init' for cleaner daemonization.
- Allow exit code 0 from 'cocod init' (normal daemon exit without error).
- Consolidate routstrd daemon startup (daemon-client.ts)
- startDaemonProcess() now delegates to startDaemon() from start-daemon.ts,
sharing the same lock and health-check logic.
- Add cross-process lock to routstrd daemon startup (start-daemon.ts)
- Performs pre-lock isDaemonHealthy() check to skip lock entirely when
already running.
- Performs re-check inside the lock before spawning to avoid duplicate
daemon processes.
- Added 'routstrd refresh' command that:
- Calls /v1/models?refresh=true to refresh routstr21 models
- Calls runIntegrationsForClients() for all registered clients
- Fixed type signature in refreshModelsAndIntegrations (returns any[] not void)
- Imports getClientsList and runIntegrationsForClients in cli.ts
- Created reusable refreshModelsAndIntegrations() function that combines
model refresh with client integration refresh
- Updated src/daemon/index.ts to use the new function in both the scheduled
refresh job and the initial bootstrap refresh
- Merged two chained .then() calls into one in the initial bootstrap flow
- Removed redundant imports (runIntegrationsForClients, getClientsList) from
daemon/index.ts since they're now encapsulated in the function
- Add addSuffixToId() and removeSuffixFromId() helper functions
- Only suffix client IDs, never names
- Update getClientsList, deleteClientAction, and addClientAction to use helpers
Replace ensureDaemonClient (try-create → catch 'already exists' → fetch list) with
a single addDaemonClient that fetches the list first, checks if client exists,
then creates only if needed. Returns { client, created } in all cases.
redshift
redshiftandGitHub
