@plumbus/core 0.7.0 → 0.7.2

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 (20) hide show
  1. package/CHANGELOG.md +16 -1
  2. package/README.md +1 -4
  3. package/dist/.tsbuildinfo +1 -1
  4. package/dist/ai/ai/model-pricing.d.ts +3 -2
  5. package/dist/ai/ai-service.d.ts.map +1 -1
  6. package/dist/ai/ai-service.js +34 -5
  7. package/dist/ai/ai-service.js.map +1 -1
  8. package/dist/ai/model-pricing.d.ts +3 -2
  9. package/dist/ai/model-pricing.d.ts.map +1 -1
  10. package/dist/ai/model-pricing.js +23 -2
  11. package/dist/ai/model-pricing.js.map +1 -1
  12. package/dist/ai/provider.d.ts.map +1 -1
  13. package/dist/ai/provider.js +10 -0
  14. package/dist/ai/provider.js.map +1 -1
  15. package/dist/types/context.d.ts +1 -1
  16. package/dist/types/context.d.ts.map +1 -1
  17. package/instructions/framework.md +1 -1
  18. package/instructions/peer-dependencies.md +1 -1
  19. package/instructions/upgrading-security-release.md +20 -20
  20. package/package.json +6 -7
package/CHANGELOG.md CHANGED
@@ -1,10 +1,25 @@
1
1
  # @plumbus/core changelog
2
2
 
3
+ ## 0.7.2 — 2026-09-23
4
+
5
+ - Add `claude-opus-5-5` standard pricing: $4 input, $0.20 cached input, $5 five-minute cache writes, and $20 output per million tokens, with no long-context surcharge. Rechecked earlier Opus rates against Anthropic's pricing on 2026-09-23.
6
+
7
+ - Add standard pricing for `gpt-6-sol` ($2 input / $0.20 cached input / $10 output per MTok) and `gpt-6-luna` ($0.10 / $0.01 / $0.50), including cache writes and the full-request long-context premium above 272K input tokens. Verified against OpenAI documentation on 2026-09-23.
8
+
9
+ - Support explicit same-call final-answer schema validation with native tools and forward the schema on OpenAI Chat Completions/Responses; malformed output is not retried.
10
+ - Install alongside `@plumbus/chat@0.2.2` to use prompt-schema validation for structured custom-agent output. Existing core `0.7.x` peer ranges are unchanged.
11
+
12
+ ## 0.7.1 — 2026-09-10
13
+
14
+ ### Fixed
15
+
16
+ - Publish the corrected package README without the added “Release family” banner, using normal `latest` publication. Runtime behavior and peer dependencies are unchanged from 0.7.0.
17
+
3
18
  ## 0.7.0 — 2026-09-10 — security hardening and fixed pricing
4
19
 
5
20
  ### Upgrade boundary
6
21
 
7
- - This release is an explicit minor-line upgrade. Previous caret ranges exclude it; install the coordinated core 0.7.x family and follow the [migration checklist](../../docs/upgrading-security-release.md). Packages stage under the `next` dist-tag.
22
+ - This release is an explicit minor-line upgrade. Previous caret ranges exclude it; install the coordinated core 0.7.x family and follow the [migration checklist](../../docs/upgrading-security-release.md). Packages publish to npm’s default `latest` dist-tag.
8
23
 
9
24
  ### Agent instructions
10
25
 
package/README.md CHANGED
@@ -1,9 +1,6 @@
1
1
  # @plumbus/core
2
2
 
3
- ## Release family 0.7.0
4
-
5
- This package requires an explicit upgrade from its previous minor line. Current Plumbus peers: `@plumbus/api` `0.2.x`, `@plumbus/ai-bedrock` `0.2.x`, `@plumbus/mcp` `0.6.x`. Install the matching versions of all Plumbus packages the app uses; do not bypass peer checks with `--force` or `--legacy-peer-deps`. Historical feature floors below describe earlier releases, not compatibility with this new family. Packages stage under `next`; read the core `instructions/upgrading-security-release.md` checklist and refresh agent wiring with `plumbus init --patch` (v16).
6
-
3
+ Release notes: [changelog](./CHANGELOG.md) and [version/upgrade guide](../../docs/upgrading-voice-and-decision-release.md).
7
4
 
8
5
  **AI-native, contract-driven TypeScript application framework.**
9
6