* model pricing routing: extend prefix-match families (gpt-/o1-o5/
gemini-/deepseek-/qwen-/glm-/kimi-/minimax-) with per-family dash
thresholds so short base IDs like gpt-5 no longer mis-match
gpt-5-mini; strip ISO and 8-digit date suffixes via UTF-8-safe
byte matching so claude-haiku-4-5-20251001 falls back to
claude-haiku-4-5 pricing
* SSE collector: SseUsageFinishGuard (RAII) guarantees finish() on
early return or panic; AtomicBool fast path lets push() skip the
Mutex once first-event time is recorded
* validation: shared validate_cost_multiplier / validate_pricing_source
helpers across DAO and service layers; PRICING_SOURCE_RESPONSE /
PRICING_SOURCE_REQUEST constants replace string literals; price
fields in update_model_pricing now reject empty / non-decimal /
negative input before INSERT
* backfill: add backfill_missing_usage_costs_for_model so a single
price edit only scans matching rows instead of the full log table;
startup backfill remains full-scan
* session_usage{,_codex,_gemini}: share find_model_pricing helper from
usage_stats; metadata_modified_nanos centralizes mtime precision
* frontend: NON_NEGATIVE_DECIMAL_REGEX + isNonNegativeDecimalString
replace three copies of the same multiplier regex; isUnpricedUsage
surfaces zero-cost rows that have usage tokens (cached per row to
avoid double evaluation); invalidate usageKeys.all on pricing mutate
so backfilled rows refresh
- Split CostCalculator into per-app cache semantics: Anthropic's
input_tokens is already fresh input, while Codex/Gemini include
cached tokens in their prompt count. The old shared formula
double-subtracted cache_read for Claude, under-billing input cost.
- Backfill now reads cost_multiplier from the per-log snapshot column
instead of re-querying providers.meta, so historical rows are no
longer rewritten with the current multiplier.
- Move the "pricing not found" warn out of find_model_pricing_row;
emit it only when a brand new log is written, and skip placeholder
models (unknown / empty / null / none) entirely.
- Broaden model id normalization: strip namespace prefixes
(anthropic./openai./global./bedrock.), bedrock-style -vN suffixes,
reasoning effort suffixes (-low/-medium/-high/-xhigh/-minimal),
Claude Desktop's claude-<non-anthropic> wrapper, dot-to-dash for
Claude, and try a LIKE prefix match for Claude short route ids
(e.g. claude-haiku-4-5 -> claude-haiku-4-5-20251001).
- Fall back to request_model when the stored model is missing, so
early Codex session rows with model=unknown can still be priced.
Hermes:
- Parse ~/.hermes/state.db sessions (incl. profiles/*/state.db) into
proxy_request_logs with data_source='hermes_session', WAL-aware
incremental sync, Hermes-reported cost preferred over model_pricing
fallback
Zero-cost bug (dashboard showed \$0 totals):
- GPT-5.5 family default pricing (~83% of affected rows used GPT-5.5)
- find_model_pricing_row: ASCII-lowercase normalization so
"OpenAI/GPT-5.5@HIGH" matches seeded "gpt-5.5"
- Startup cost backfill in async task: scan rows where total_cost <= 0
but tokens > 0, recompute via model_pricing in a single transaction
Performance:
- Add (app_type, created_at DESC) covering index for dashboard range
queries
- Add expression index on COALESCE(data_source, 'proxy') so dedup EXISTS
subqueries use index lookup instead of full scan; drop superseded
idx_request_logs_dedup_lookup
Refactor:
- row_to_request_log_detail helper (3-way de-dup; fixes cost_multiplier
\"1\" vs \"1.0\" drift between callers)
- Promote get_sync_state/update_sync_state to shared session_usage
module (4 copies -> 1)
- run_step helper in lib.rs replaces 9 if-let-Err blocks
- maybe_backfill_log_costs returns bool to skip duplicate total_cost
parsing in caller
Proxy writes and session-log sync wrote to proxy_request_logs with
mismatched request_ids: only Claude on a native Anthropic backend used the
shared `session:{message_id}` key. Codex/Gemini and Claude-through-OpenAI
providers always produced distinct ids, so primary-key dedup never fired
and every real request was recorded twice.
Adds a 7-dim fingerprint dedup (app_type, 4 token counts, 2xx status,
model with case-insensitive match, ±10min window) wired into three layers:
- Write path: should_skip_session_insert() blocks duplicate session rows
before INSERT, unifying the previously-divergent Claude/Codex/Gemini
paths through a single DedupKey-based helper.
- Read path: effective_usage_log_filter() excludes already-covered session
rows from every aggregation query.
- Rollup path: same filter applied so usage_daily_rollups never absorbs
duplicates.
Also adds a covering index (idx_request_logs_dedup_lookup) so the EXISTS
subquery stays index-only, and a transform.rs regression test that pins
openai_to_anthropic id preservation - the missing piece that lets
Claude+OpenAI-compatible providers reuse the session: id scheme.
Extract message_id from Claude API responses (msg_xxx) and use it to
generate a shared request_id format (session:{msg_xxx}) between the
proxy logger and session log sync. When session sync encounters the
same request_id via INSERT OR IGNORE, it skips the duplicate.
- Add message_id field to TokenUsage, extracted from Claude responses
- Add TokenUsage::dedup_request_id() to generate shared request IDs
- Define SESSION_REQUEST_ID_PREFIX constant to eliminate magic strings
- Change proxy logger to INSERT OR REPLACE for richer-data-wins semantics
- Use UPSERT with WHERE guard instead of INSERT OR IGNORE, so updated
token values on existing messages are properly synced without
unnecessary rewrites of unchanged rows
- Include cached tokens in the skip-zero filter to stop silently
discarding pure cache-hit records
- Restrict file collection to session-*.json to match documented scope
and prevent ingesting non-session JSON files
Parse ~/.gemini/tmp/*/chats/session-*.json for precise per-message
token data (input/output/cached/thoughts). Integrates with existing
background sync and manual sync button alongside Claude and Codex.
Jason