ton/pi_harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
4,821 Commits 1 Branch 0 Tags
ca09b2b1a8317f1daa5ed3f339ebcc00add84f67
Commit Graph

763 Commits

Author SHA1 Message Date
Vegard Stikbakke e2ccdc8509 fix(ai): delay Copilot device-code token polling 
closes #6187
 2026-07-01 13:48:11 +02:00
Vegard Stikbakke 844d175eaf fix(ai): align Fireworks GLM 5.2 Fast with GLM 5.2 
Broaden the Fireworks GLM 5.2 special-case in generate-models.ts from
an exact id match to a glm-5p2 substring match, so the router variant
accounts/fireworks/routers/glm-5p2-fast also uses the OpenAI-compatible
endpoint and thinkingLevelMap instead of falling back to the default
Anthropic Messages config.

closes #6195
 2026-07-01 10:34:46 +02:00
Vegard Stikbakke 4206376410 feat(ai): add Copilot Claude Sonnet 5 
closes #6200
 2026-07-01 09:57:04 +02:00
Vegard Stikbakke 0ac3cfe09b feat(ai): use zstd compression for codex sse transport 2026-07-01 08:42:46 +02:00
Vegard Stikbakke a3cc169d97 fix(ai): avoid codex user-agent race 
The Codex provider previously loaded node:os asynchronously during module evaluation. A fresh process that imports the provider and immediately starts an SSE request can build headers before that promise callback runs, so the first request reports User-Agent: pi (browser) in Node/Bun.

Reproduced against parent fd6659dd with a stubbed-fetch harness: 50/50 immediate first requests reported pi (browser) in both Node and Bun. The same harness on this fix reports the OS-specific user agent 50/50 in both runtimes.

Use process.getBuiltinModule("node:os") behind the existing Node/Bun runtime guard so OS metadata is available synchronously while still avoiding top-level runtime Node builtin imports that break browser/Vite builds.
 2026-07-01 08:41:38 +02:00
Mario Zechner dd87c02cbf Add [Unreleased] section for next cycle 2026-06-30 22:29:44 +02:00
Mario Zechner a23abe4a69 Release v0.80.3 2026-06-30 22:29:41 +02:00
Mario Zechner f98a154d87 docs: audit changelog entries 2026-06-30 22:24:42 +02:00
Mario Zechner 5c1a2977bc fix(ai): update generated model catalogue 2026-06-30 22:12:48 +02:00
Vegard Stikbakke 3d6acb37b9 fix(ai): regenerate model catalog 
Includes updated Xiaomi MiMo pricing from models.dev. Closes #6138
 2026-06-30 08:33:18 +02:00
Vegard Stikbakke b91bdd5a3e fix(ai): preserve Z.AI thinking content 
closes #6083
 2026-06-29 08:40:20 +02:00
Armin Ronacher 54113731b2 fix(ai): use HTTP timeout for Codex SSE headers 
Refs #4945
 2026-06-28 19:57:47 +02:00
Mario Zechner 09f1059575 fix(ai): clamp streamSimple max tokens 
Clamps streamSimple max-token defaults against estimated context, addressing #5595.

closes #6061
 2026-06-25 14:10:28 +02:00
Mario Zechner f78b163713 fix(ai): revert minimax max token clamp 2026-06-25 13:36:04 +02:00
Mario Zechner b940c52e7e fix(ai): clamp MiniMax shared budget max tokens 
closes #6061
 2026-06-25 12:00:37 +02:00
Mario Zechner 8c9dbffa36 fix(ai): preserve responses reasoning for out-of-order items 
closes #6009
 2026-06-25 11:57:52 +02:00
Mario Zechner d7868b0998 feat(ai): add reasoning token counts to Usage 
Add optional reasoning?: number to Usage as a subset of output. Populate
for Anthropic (output_tokens_details.thinking_tokens), OpenAI
Responses/Codex/Azure (output_tokens_details.reasoning_tokens), OpenAI
Completions (completion_tokens_details.reasoning_tokens), and Google
Generative AI / Vertex (thoughtsTokenCount). Bedrock Converse and Mistral
do not return a reasoning breakdown, so they stay unset.

closes #6057
 2026-06-25 10:35:02 +02:00
Armin Ronacher 371adcf371 fix(coding-agent): retry explicit provider retry errors 
closes #6019
 2026-06-24 18:14:06 +02:00
Armin Ronacher 8277bd6896 Add [Unreleased] section for next cycle 2026-06-23 23:45:39 +02:00
Armin Ronacher 0201806adf Release v0.80.2 2026-06-23 23:45:36 +02:00
Armin Ronacher 9096d5f9a6 docs: update changelog entries 2026-06-23 23:42:02 +02:00
Mario Zechner e1a2dc04f4 fix(ai): restore detectCompat runtime fallback in openai-completions 
refs #6020
 2026-06-23 23:29:44 +02:00
Mario Zechner ef231c4910 fix(ai): resolve request-scoped auth before provider calls 
closes #6021
 2026-06-23 23:27:00 +02:00
Mario Zechner 04fce8099f Merge remote-tracking branch 'origin/main' 2026-06-23 22:30:15 +02:00
Mario Zechner 49fbe6834f fix(ai): align api key credentials with auth json 2026-06-23 22:29:46 +02:00
Armin Ronacher 386d079afa fix(ai): restore legacy compat stream aliases 
closes #6016
 2026-06-23 22:20:20 +02:00
Armin Ronacher e00074358d Add [Unreleased] section for next cycle 2026-06-23 20:04:12 +02:00
Armin Ronacher 1c4a9ba7c8 Release v0.80.1 2026-06-23 20:04:09 +02:00
Armin Ronacher 828493b37c fix(ai): unblock release provider tests 2026-06-23 19:57:29 +02:00
Armin Ronacher 86528dd9ee Add [Unreleased] section for next cycle 2026-06-23 19:30:35 +02:00
Armin Ronacher f08e968c83 Release v0.80.0 2026-06-23 19:30:32 +02:00
Armin Ronacher 526351d99a docs: audit unreleased changelogs 2026-06-23 19:25:26 +02:00
Mario Zechner cd95c2749f fix(ai): require OpenAI Responses terminal events 2026-06-23 16:35:45 +02:00
Mario Zechner 2285f87964 fix(ai): remove legacy raw API subpaths 2026-06-23 15:58:50 +02:00
Mario Zechner 12ace0ba46 docs(ai): reference README in migration guide 2026-06-23 15:33:37 +02:00
Mario Zechner 15f92260d7 docs(ai): expand models migration guide 2026-06-23 15:32:42 +02:00
Mario Zechner 129eb460cd feat(ai): complete models runtime migration 2026-06-23 15:29:46 +02:00
Mario Zechner 6a4813a7ca Merge remote-tracking branch 'origin/main' 
# Conflicts:
#	packages/ai/CHANGELOG.md
 2026-06-23 13:52:09 +02:00
Mario Zechner 2cbce395fb feat(ai): pass provider-resolved env to APIs 2026-06-23 13:42:25 +02:00
Armin Ronacher d0e0b84cb9 fix(ai): reconnect Codex websocket on connection limit 
closes #5973
 2026-06-23 00:17:37 +02:00
Mario Zechner 732bb1617b Merge model-registry into main 2026-06-22 14:53:24 +02:00
Mario Zechner abbd911693 Merge main into model-registry 2026-06-22 14:00:18 +02:00
Armin Ronacher 71ca9b2b92 fix(ai): expose OpenCode Go GLM-5.2 xhigh effort 
closes #5967
 2026-06-22 13:45:44 +02:00
Armin Ronacher 329dceb5f3 Add [Unreleased] section for next cycle 2026-06-22 11:14:46 +02:00
Armin Ronacher 8e1900666f Release v0.79.10 2026-06-22 11:14:43 +02:00
Vegard Stikbakke 7d0497fdb7 fix(ai): preserve early reasoning details 
closes #5114
 2026-06-22 10:14:59 +02:00
Armin Ronacher b4f31408b6 Add [Unreleased] section for next cycle 2026-06-20 22:15:40 +02:00
Armin Ronacher 615bf2f874 Release v0.79.9 2026-06-20 22:15:37 +02:00
Armin Ronacher 500b568b04 fix(ai): use OpenAI endpoint for Fireworks GLM-5.2 
closes #5923
 2026-06-20 21:32:02 +02:00
Armin Ronacher 8597ebafd9 fix(ai): expose OpenRouter GLM-5.2 xhigh effort 
closes #5770
 2026-06-20 18:47:42 +02:00