Commit Graph
12 Commits
Author SHA1 Message Date
KunN-21andCursor 97a6708651 feat(caveman): add targeted upstream-aligned style rules (#2424)
Add four shared Caveman prompt fragments (no invented abbreviations,
preserve user language, no self-reference, no decoration) across all six
levels, and remove ULTRA contradictions around abbreviations/arrow
shorthand. Adds regression tests for the prompt rules.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-07 11:55:45 +07:00
Sutarto Jordan ChrisfivoandCursor 373850ee36 fix(headroom): skip unsafe responses tool history (#2132)
Guard openai-responses compression: skip Headroom when body.input
contains non-message items (function_call, function_call_output,
reasoning) to preserve the Responses contract instead of collapsing
them into chat messages.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-29 15:59:21 +07:00
AnkitandCursor d4d11357ab fix(headroom): translate openai-responses input through OpenAI for compression
Codex (openai-responses) body.input holds Responses items, not OpenAI
messages. Translate input -> OpenAI -> compress -> back to input so the
Responses contract is preserved. Fixes #1998

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-26 11:12:10 +07:00
Sutarto Jordan ChrisfivoandCursor fb543a1f39 fix(headroom): clarify token diagnostics vs provider billing
Distinguish Headroom-reported token deltas from outbound payload size,
scrub credentials in logs, and warn on phantom savings when compressed
JSON barely shrinks. Refs #1998

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-26 11:12:07 +07:00
decoluaandCursor b55cf36d2e feat(headroom): add proxy lifecycle management + dashboard UI
Build on the optional Headroom Token Saver from Carmelo Campos
(PR: feat: add optional Headroom token saver). Add managed start/stop
of the local headroom proxy from the dashboard, install detection,
status probing, and a simplified Token Saver UI.

- detect headroom CLI + python>=3.10, probe proxy /health
- spawn/stop proxy as a detached, pid-tracked process
- /api/headroom/{status,start,stop} routes, gated local-only in dashboardGuard
- one-click Start/Stop Headroom modal, no manual config needed
- claude<->openai shape conversion for /v1/compress via 9router translators

Thanks to Carmelo Campos (@carmelogunsroses) for the original Headroom integration.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-20 10:09:50 +07:00
decolua b282f05549 Refactor 2026-06-15 18:18:04 +07:00
arden1601andCursor 047792205f feat(caveman): add wenyan classical Chinese levels and sync upstream prompts
Add wenyan-lite/wenyan/wenyan-ultra levels for max token compression,
sync SHARED_EXAMPLES/AUTO_CLARITY/PERSISTENCE across all levels, and
expose 3 wenyan buttons in endpoint settings UI.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-06 12:35:08 +07:00
Zanuar Tri Romadon e03b28138a feat(rtk): add Kiro format support for tool result compression (#1194)
- Add compressKiroFormat() to handle conversationState.history and currentMessage
- Compress toolResults[].content[].text in Kiro's AWS CodeWhisperer format
- Preserve error tool results (status === 'error')
- Add 7 comprehensive tests covering all edge cases
- Verified with real usage: 13.6% savings on npm install output
2026-05-17 15:13:37 +07:00
decolua 3cca2252a6 chore: add buildOutput RTK filter, drop legacy cloud sync, internal cleanup
- feat(rtk): buildOutput filter + autodetect for npm/yarn/cargo logs
- chore: remove unused cloud sync module and related routes
- ui: hide deprecated providers (qwen, iflow, antigravity)
- chore: minor tray/cli/internal adjustments
2026-05-16 10:54:41 +07:00
decolua 936d65ae1c Enhance chat handling and introduce Caveman feature
- Refactored handleChatCore to include Caveman functionality, allowing for terse-style system prompts to reduce output token usage.
- Updated APIPageClient to manage Caveman settings, including enabling/disabling and selecting compression levels.
- Adjusted AntigravityExecutor to consolidate function declarations for compatibility with Gemini.
- Removed unnecessary console logs during translator initialization across multiple routes.
2026-04-30 18:00:38 +07:00
decolua cca615eaff - Cap maximum cooldown for rate limit handling in account unavailability and single-model chat flows
- Dynamic custom model fetching for model selection
2026-04-24 16:14:18 +07:00
decolua 8de9aae90c Feature : RTK compress 2026-04-22 15:36:51 +07:00