hodtienandCursor 54e3245ace feat(usage): track cached tokens + correct input/output/cache cost (#2209) ...

Normalize every provider to one cache-inclusive convention via
canonicalizeUsage() before persist, and price cached + cache_creation as
subsets of prompt_tokens in calculateCostFromTokens() to stop
double-counting. usageRepo now delegates cost math to a single source.
Surface Cached tokens/cost across dashboard (overview, tokens, cost,
details). Merge Claude message_start cache with message_delta output so
cache counts survive. Compatible LLM nodes now allow multiple API-key
connections (key pool).

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-07-03 15:18:27 +07:00

..

claude-to-openai.js

feat(usage): track cached tokens + correct input/output/cache cost (#2209)

2026-07-03 15:18:27 +07:00

commandcode-to-openai.js

refactor(open-sse): translator DRY + schema enums, bug fixes, dead code cleanup

2026-06-14 18:49:38 +07:00

cursor-to-openai.js

refactor(open-sse): translator DRY + schema enums, bug fixes, dead code cleanup

2026-06-14 18:49:38 +07:00

gemini-to-openai.js

fix(antigravity): preserve Claude tool delta index (#2223)

2026-07-01 09:36:43 +07:00

kiro-to-claude.js

feat(kiro): headless API-key auth + direct Claude/Kiro route

2026-06-17 10:01:30 +07:00

kiro-to-openai.js

refactor(open-sse): translator DRY + schema enums, bug fixes, dead code cleanup

2026-06-14 18:49:38 +07:00

ollama-to-openai.js

refactor(open-sse): translator DRY + schema enums, bug fixes, dead code cleanup

2026-06-14 18:49:38 +07:00

openai-responses.js

Refactor

2026-06-15 18:18:04 +07:00

openai-to-antigravity.js

refactor(open-sse): translator DRY + schema enums, bug fixes, dead code cleanup

2026-06-14 18:49:38 +07:00

openai-to-claude.js

Fix OpenCode Go GLM

2026-06-29 15:00:03 +07:00