@bastani/atomic-ai 0.9.88 → 0.9.89-alpha.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (39) hide show
  1. package/CHANGELOG.md +7 -0
  2. package/dist/api/anthropic-messages.js +2 -2
  3. package/dist/api/anthropic-messages.js.map +1 -1
  4. package/dist/compat.js +2 -2
  5. package/dist/compat.js.map +1 -1
  6. package/dist/env-api-keys.d.ts +3 -0
  7. package/dist/env-api-keys.d.ts.map +1 -1
  8. package/dist/env-api-keys.js +97 -35
  9. package/dist/env-api-keys.js.map +1 -1
  10. package/dist/models.d.ts.map +1 -1
  11. package/dist/models.js +10 -3
  12. package/dist/models.js.map +1 -1
  13. package/dist/providers/data/.manifest.json +1 -1
  14. package/dist/providers/data/azure.json +1 -1
  15. package/dist/providers/data/baseten.json +1 -1
  16. package/dist/providers/data/huggingface.json +1 -1
  17. package/dist/providers/data/nvidia.json +1 -1
  18. package/dist/providers/data/openai-codex.json +1 -1
  19. package/dist/providers/data/openai.json +1 -1
  20. package/dist/providers/data/opencode.json +1 -1
  21. package/dist/providers/data/openrouter.json +1 -1
  22. package/dist/providers/data/vercel-ai-gateway.json +1 -1
  23. package/dist/providers/openai-mid-convo-effort.d.ts.map +1 -1
  24. package/dist/providers/openai-mid-convo-effort.js +2 -0
  25. package/dist/providers/openai-mid-convo-effort.js.map +1 -1
  26. package/dist/providers/openai-subscription-models.d.ts.map +1 -1
  27. package/dist/providers/openai-subscription-models.js +13 -2
  28. package/dist/providers/openai-subscription-models.js.map +1 -1
  29. package/dist/utils/models-dev-catalog.d.ts.map +1 -1
  30. package/dist/utils/models-dev-catalog.js +89 -7
  31. package/dist/utils/models-dev-catalog.js.map +1 -1
  32. package/dist/utils/provider-env.d.ts.map +1 -1
  33. package/dist/utils/provider-env.js +21 -18
  34. package/dist/utils/provider-env.js.map +1 -1
  35. package/dist/utils/version.d.ts +1 -1
  36. package/dist/utils/version.d.ts.map +1 -1
  37. package/dist/utils/version.js +1 -1
  38. package/dist/utils/version.js.map +1 -1
  39. package/package.json +3 -3
package/CHANGELOG.md CHANGED
@@ -4,6 +4,13 @@ This package is Atomic's fork of `@earendil-works/pi-ai`, published as `@bastani
4
4
 
5
5
  ## [Unreleased]
6
6
 
7
+ ## [0.9.89-alpha.1] - 2026-11-18
8
+
9
+ ### Added
10
+
11
+ - `getEnvApiKeyAsync()` checks environment-provided credentials without synchronous file access. `getEnvApiKey()` remains synchronous and recognizes a passed credentials file on its first call. The compatibility entry point also exports `getDirectEnvApiKey()` for environment-only lookups that never inspect a file
12
+ - Added GPT-6.2 Astra and GPT-6.2 Sol to the OpenAI (`openai`, `openai-api`), Azure OpenAI Responses and OpenAI Codex catalogs with OpenAI's published prices (Astra: $8 input, $0.40 cached input, $10 cache writes, $40 output per million tokens; Sol: $2, $0.10, $2.50, $10), the request-wide tier above 272K input tokens, Fast at 2x Standard, Ultrafast at 3x Standard (OpenAI's rate until March 1, 2027), tool search, additional tools, and mid-conversation effort changes. Both reject reasoning effort `none` and `minimal`, so `off` is unavailable. Azure serves them with a 1.05M context window; Codex and a ChatGPT sign-in on `openai` serve GPT-6.2 Sol with 500K and GPT-6.2 Astra with 272K (upstream [e56d35c](https://github.com/earendil-works/pi/commit/e56d35ce5eceedfa16eaf13a5f01a1f7b7271253), [cead615](https://github.com/earendil-works/pi/commit/cead615b48b80d1c61eecab2f0b576d16eeaf4c5))
13
+
7
14
  ## [0.9.88] - 2026-11-16
8
15
 
9
16
  ### Added
@@ -230,8 +230,8 @@ function shouldUseServerSideFallbackBeta(model) {
230
230
  * the affected thinking blocks and answers the turn instead of failing the session.
231
231
  *
232
232
  * This covers live prefix mismatches *between* compaction boundaries. It is not what handles
233
- * compaction itself: Atomic's client-side `preserve_recent` tail compaction serializes the
234
- * protected tail into a single boundary message, so no signed thinking block survives a
233
+ * compaction itself: Atomic's client-side compaction replaces the context with a single boundary
234
+ * message, so no signed thinking block survives a
235
235
  * boundary to be replayed behind it. That is Anthropic's documented keep-tail remedy applied
236
236
  * structurally rather than a case `drop_block` has to catch.
237
237
  * https://platform.claude.com/docs/en/build-with-claude/preserved-thinking