neuron-technologies/neuron
2
0
Fork 0
Code Issues 44 Pull Requests Actions Packages Projects Releases Wiki Activity
10,298 Commits 60 Branches 1,094 Tags
c4ae100b70b5a0a98ebb6a9be2d9e18de709fe79
Commit Graph

445 Commits

Author SHA1 Message Date
Kit Langton c4ae100b70 refactor(instance): move scoped services to LayerMap (#17544) 2026-03-16 12:55:14 -04:00
Johannes Loher 3202268123 fix(core): consider code: context_length_exceeded as context overflow in API call errors (#17748) 2026-03-16 10:25:24 -05:00
Kit Langton 4df2577034 refactor(question): effectify QuestionService (#17432) 2026-03-14 11:58:00 -04:00
James Long 726caa9bd2 fix(core): increase default chunk timeout from 2 min to 5 min (#17490) 2026-03-14 14:27:06 +00:00
Tom Ryder 16edfe662d fix: filter empty content blocks for Bedrock provider (#14586) 2026-03-12 22:13:09 -05:00
Kit Langton 35f8e9ca55 refactor(provider): effectify ProviderAuthService (#17227) 2026-03-13 02:08:37 +00:00
Aiden Cline c7cc49da66 fix: non openai azure models that use completions endpoints (#17128) 2026-03-12 10:05:00 -05:00
opencode-agent[bot] a8a1b40406 chore: generate 2026-03-12 14:49:22 +00:00
Kit Langton 82307f8a45 refactor(provider): flow branded ProviderID/ModelID through internal signatures (#17182) 2026-03-12 14:48:17 +00:00
Kit Langton 36aee4908f feat(id): brand ProviderID and ModelID (#17110) 2026-03-12 09:27:52 -04:00
SOUMITRA-SAHA 3c48a076ce fix: add GOOGLE_VERTEX_LOCATION env var support for Vertex AI (#16922) 
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
 2026-03-10 22:32:39 -05:00
Aiden Cline 9e441a3ec3 chore: kill old copilot 403 message that was used for old plugin migration (#16904) 2026-03-10 16:20:41 -05:00
James Long 01233eab2e fix(core): a chunk timeout when processing llm stream (#16366) 2026-03-10 11:12:14 -04:00
Jérôme Benoit 565aefc073 fix(opencode): add thinking variants support for SAP AI provider (#14958) 
Co-authored-by: Test <test@test.com>
Co-authored-by: Stephen Collings <stevoland@gmail.com>
 2026-03-10 10:05:45 -05:00
Armin Pašalić 4204c932d0 feat(gitlab): send context-1m-2025-08-07 beta header to enable 1M context window (#16153) 
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
 2026-03-09 09:22:00 -05:00
Jack 5712554c4a add copilot gpt-5.4 xhigh support (#16294) 2026-03-09 22:07:12 +08:00
Dax Raad 8a26bc33cf disable fallback to free nano for small model 2026-03-08 19:27:15 -04:00
Dax Raad 25643cffc4 refactor: replace Bun.hash with Hash.fast using xxhash3-xxh64 2026-03-05 22:03:24 -05:00
opencode-agent[bot] a0be4ad767 chore: generate 2026-03-03 04:41:52 +00:00
Shoubhit Dash eeaf8b888e fix(opencode): avoid gemini combiner schema sibling injection (#15318) 2026-03-03 10:11:05 +05:30
opencode-agent[bot] 1409bd2df3 chore: generate 2026-03-03 03:53:50 +00:00
Ryan Skidmore 2bcf5e371c fix(provider): forward metadata options to cloudflare-ai-gateway provider (#15619) 2026-03-02 22:53:03 -05:00
bentrd 6ccc8b01f7 fix: recover from 413 Request Entity Too Large via auto-compaction (#14707) 
Co-authored-by: Noam Bressler <noamzbr@gmail.com>
 2026-03-02 13:10:55 +05:30
Rian van der Merwe e55c250aa5 fix(opencode): show human-readable message for HTML error responses (#15407) 2026-03-01 09:24:57 -06:00
opencode-agent[bot] d398de6672 chore: generate 2026-02-19 22:19:09 +00:00
tctev 17fdd50b98 feat(opencode): support adaptive thinking for claude sonnet 4.6 (#14283) 
Co-authored-by: tctev <224793535+tctev@users.noreply.github.com>
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
 2026-02-19 16:17:57 -06:00
Aiden Cline aff1465aab core: bump ai sdk packages for google, google vertex, anthropic, bedrock, and provider utils (#14318) 2026-02-19 12:35:51 -06:00
Aiden Cline 5b59d06f0a tweak: add support for medium reasoning w/ gemini 3.1 (#14316) 2026-02-19 12:00:56 -06:00
Dax 019134be58 Remove use of Bun.file (#14215) 2026-02-19 11:32:32 -05:00
Aiden Cline 3359967745 tweak: bake in the aws and google auth pkgs (#14241) 2026-02-19 00:31:33 -06:00
Dax Raad 1567fa548c Revert: all refactor commits migrating from Bun.file() to Filesystem module 2026-02-18 19:41:14 -05:00
Dax 5a30e55da0 refactor: migrate src/provider/provider.ts from Bun.file() to Filesystem module (#14132) 2026-02-18 18:08:48 -05:00
Dax 80dc0b3d38 refactor: migrate src/provider/models.ts from Bun.file()/Bun.write() to Filesystem module (#14131) 2026-02-18 17:26:13 -05:00
Aiden Cline e31e36bfc0 fix: dont autoload kilo (#14052) 2026-02-17 18:42:18 -06:00
RAMA d82e1bf458 feat: add Kilo as a native provider (#13765) 2026-02-17 17:52:21 -06:00
Caleb Norton fe3cf3fb4e fix: don't fetch models.dev on completion (#13997) 2026-02-17 10:41:03 -06:00
Aiden Cline 31a30bea6b fix: google vertex var priority (#13816) 2026-02-16 02:41:52 -06:00
Jhin Lee b299880f49 feat: add openai-compatible endpoint support for google-vertex provider (#10303) 
Co-authored-by: BlueT - Matthew Lien - 練喆明 <BlueT@BlueT.org>
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
 2026-02-16 02:31:48 -06:00
dpuyosa 94e2af3c60 feat(opencode): Add Venice support in temperature, topP, topK and smallOption (#13553) 2026-02-15 22:24:24 -06:00
Aiden Cline b4bd78ce79 fix: ensure anthropic models on OR also have variant support (#13498) 2026-02-14 14:30:07 -06:00
Aiden Cline eb3e9c74c6 fix: ensure vercel variants pass amazon models under bedrock key (#13631) 2026-02-14 13:18:52 -06:00
Aiden Cline 442fc7c1c7 fix vercel gateway variants (#13541) 
Co-authored-by: Benjamin Woodruff <github@benjam.info>"
 2026-02-14 12:32:29 -06:00
Aiden Cline b4fe75a169 feat: update some ai sdk packages and uuse adaptive reasoning for opus 4.6 on vertex/bedrock/anthropic (#13439) 2026-02-13 00:56:11 -06:00
opencode-agent[bot] 51f3a5e7a3 chore: generate 2026-02-12 22:14:45 +00:00
Smit Chaudhary 939c63627e fix: look for recent model in fallback in cli (#12582) 2026-02-12 16:13:48 -06:00
Dax Raad 3c66ef216f core: allow model configurations without npm/api provider details 
Makes npm and api fields optional in the provider schema so model definitions

can be more flexible when provider package details aren't needed.
 2026-02-12 09:26:28 -05:00
Dax Raad 10f9176a93 support custom api url per model 2026-02-11 23:10:47 -05:00
dpuyosa 442d41191c feat(opencode): Venice Add automatic variant generation for Venice models (#12106) 2026-02-11 20:21:29 -06:00
Aiden Cline 525cf17315 fix: add additional context overflow cases, remove overcorrecting ones (#13077) 2026-02-10 23:30:29 -06:00
Aiden Cline 61c5e8ab80 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