ToothFairyAI_Public/tf_code
1
0
Fork 0
mirror of https://gitea.toothfairyai.com/ToothFairyAI/tf_code.git synced 2026-03-31 06:12:26 +00:00
Code Issues Packages Projects Releases Wiki Activity
9,137 Commits 3 Branches 2 Tags
006d673ed2e795ce41f30fc240189a54ff12c231
Commit Graph

624 Commits

Author SHA1 Message Date
Aiden Cline
006d673ed2 tweak: make read tool offset 1 indexed instead of 0 to avoid confusion that could be caused by line #s being 1 based (#13198) 2026-02-11 14:02:30 -06:00
Aiden Cline
0fd6f365be fix(core): ensure compaction is more reliable, add reserve token buffer to ensure that input window has enough room to compact (#12924) 
Co-authored-by: James Lal <james@littlebearlabs.io>
 2026-02-10 19:55:22 -06:00
Dax
8bdf6fa359 fix: show helpful message when free usage limit is exceeded (#13005) 2026-02-10 19:04:10 +00:00
Adam
659f15aa9b fix(app): no changes in review pane 2026-02-10 11:53:33 -06:00
Peter Dave Hello
87795384de chore: fix typos and GitHub capitalization (#12852) 2026-02-10 06:53:38 -06:00
Surma
832902c8e3 fix: publish session.error event for invalid model selection (#8451) 2026-02-09 16:27:48 -06:00
Aiden Cline
8ad4768ecd tweak: adjust agent variant logic to not require exact match on model, and instead check if the variant is available for model (#12838) 2026-02-09 11:00:06 -06:00
Aiden Cline
99ea1351ce tweak: add new ContextOverflowError type (#12777) 2026-02-08 23:54:01 -06:00
Aiden Cline
62f38087b8 fix: parse mid stream openai responses style errors to prevent infinite retries for errors that should STOP execution (#12768) 2026-02-08 20:55:41 -06:00
Shantur Rathore
a486b74b14 feat(core): Set variant in assistant messages too (#12531) 
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
 2026-02-06 16:33:47 -06:00
Khang Ha (Kelvin)
fde0b39b7c fix: properly encode file URLs with special characters (#12424) 2026-02-06 16:16:56 -06:00
opencode-agent[bot]
e767801db2 chore: generate 2026-02-06 22:14:34 +00:00
Goni Zahavy
def907ae4b fix(opencode): SessionPrompt.shell() now triggers loop if messages are queued (#10987) 2026-02-06 16:13:11 -06:00
Mariam Jabara
95ad6758af feat: add specific system prompt for Trinity model (#12144) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-06 11:43:10 -06:00
Dax
a45841396f core: fix unhandled errors when aborting with queued messages (#12369) 2026-02-05 22:27:27 +00:00
Zhiming Guo
72de9fe7a6 fix(opencode): Fixes image reading with OpenAI-compatible providers like Kimi K2.5. (#11323) 
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
 2026-02-05 01:54:07 -06:00
Adam
1721c6efdf fix(core): session errors when attachment file not found 2026-02-04 10:21:03 -06:00
Łukasz Gładysz
6daa962aaa fix: prioritize OPENCODE_CONFIG_DIR for AGENTS.md (#11536) 2026-02-04 01:35:22 +00:00
Aiden Cline
b5a4671c64 Revert "feat: add Trinity model system prompt support" (#12029) 2026-02-03 16:39:03 -06:00
Mariam Jabara
015cd404e4 feat: add Trinity model system prompt support (#12025) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-03 16:33:27 -06:00
Tyler Gannon
a30696f9bf feat(plugin): add shell.env hook for manipulating environment in tools and shell (#12012) 2026-02-03 15:18:41 -06:00
Aiden Cline
b7b734f51f fix: ensure mcp tools are sanitized (#11984) 2026-02-03 12:22:00 -06:00
Aiden Cline
aa6b552c39 Revert pr that was mistakenly merged (#11844) 2026-02-02 15:28:02 -06:00
Dax
c69474846f Simplify directory tree output for prompts (#11731) 2026-02-01 23:37:07 -05:00
Dax Raad
6c9b2c37a5 core: allow starting new sessions after errors by fixing stuck session status 2026-02-01 20:39:58 -05:00
Aiden Cline
612b656d36 fix: adjust resolve parts so that when messages with multiple @ references occur, the tool calls are properly ordered 2026-02-01 19:26:23 -05:00
Filip
91f2ac3cb2 test(app): workspace tests (#11659) 2026-02-01 15:39:50 -06:00
Aiden Cline
ec720145fa fix: when using codex sub, send the custom agent prompts as a separate developer message (previously sent as user message but api allows for instructions AND developer messages) (#11667) 
Co-authored-by: Carlos <carloscanas942@gmail.com>
 2026-02-01 14:57:47 -06:00
neavo
f15755684f fix(opencode): scope agent variant to model (#11410) 2026-02-01 14:12:30 -06:00
YeonGyu-Kim
16145af480 fix: prevent duplicate AGENTS.md injection when reading instruction files (#11581) 
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
 2026-02-01 13:46:08 -06:00
Aiden Cline
da7c874808 tweak: show actual retry error message instead of generic error msg (#11520) 2026-01-31 13:15:42 -06:00
Steffen Deusch
d9f18e4006 feat(opencode): add copilot specific provider to properly handle copilot reasoning tokens (#8900) 
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
 2026-01-30 19:53:22 -06:00
Aiden Cline
11d486707c fix: rm ai sdk middleware that was preventing <think> blocks from being sent back as assistant message content (#11270) 
Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>
 2026-01-30 09:36:57 -05:00
Ravi Kumar
03ba49af4e fix(telemetry): restore userId and sessionId metadata in experimental_telemetry (#8195) 2026-01-29 10:14:28 -06:00
Ariane Emory
e84d92da28 feat: Sequential numbering for forked session titles (Issue #10105) (#10321) 2026-01-28 23:08:35 -06:00
Aiden Cline
29ea9fcf25 fix: ensure variants for copilot models work w/ maxTokens being set 2026-01-28 21:55:50 -06:00
ideallove
870c38a6aa fix: maxOutputTokens was accidentally hardcoded to undefined (#10995) 2026-01-28 21:28:15 -06:00
RenegadeE
26e14ce628 fix: add SubtaskPart with metadata reference (#10990) 
Co-authored-by: yangtianzhe <yangtianzhe@corp.netease.com>
 2026-01-28 11:11:43 -05:00
Aiden Cline
558590712d fix: ensure parallel tool calls dont double load AGENTS.md 2026-01-28 01:38:10 -05:00
Aiden Cline
f12f7e7718 tweak: adjust retry check to be more defensive 2026-01-27 11:31:02 -05:00
GitHub Action
dbc8d7edca chore: generate 2026-01-27 15:59:54 +00:00
dpuyosa
d8e7e915e2 feat(opencode): Handle Venice cache creation tokens (#10735) 
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
 2026-01-27 10:59:12 -05:00
Aiden Cline
8b5dde5536 tweak: retry logic to catch certain provider problems 2026-01-26 16:12:41 -05:00
Tim
837037cd04 fix: ensure openai 404 errors are retried (#10590) 2026-01-26 13:50:04 -05:00
Aiden Cline
ac53a372b0 feat: use anthropic compat messages api for anthropic models through copilot 2026-01-26 13:18:08 -05:00
Aiden Cline
39a73d4894 feat: dynamically resolve AGENTS.md files from subdirectories as agent explores them (#10678) 2026-01-26 10:49:41 -05:00
adamelmore
7c34319b19 fix(app): query selector with non-latin chars 2026-01-26 09:33:42 -06:00
Noam Bressler
6b83b172ae fix: await SessionRevert.cleanup for shell (#10669) 2026-01-26 07:36:17 -05:00
Aiden Cline
94dd0a8dbe ignore: rm spoof and bump plugin version 2026-01-25 17:27:24 -05:00
Aiden Cline
88bcd04659 tweak: tell the model what model it is in environment section of prompt 2026-01-24 12:10:15 -05:00