@leanandmean/coding-agent 0.74.1-scramjet.55 → 0.74.1-scramjet.56

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 (2) hide show
  1. package/docs/models.md +3 -1
  2. package/package.json +4 -4
package/docs/models.md CHANGED
@@ -225,7 +225,9 @@ Built-in metadata is not proof of endpoint acceptance. The provider audit in [is
225
225
 
226
226
  GPT-6 Astra through the public OpenAI API stores the standard scalar rates of $10 input, $50 output, $1 cache read, and $12.50 cache write per million tokens. Requests above 272,000 input tokens use higher rates for the whole request, which the current scalar estimator cannot represent, so its monetary estimate may be too low while its token counts remain valid. The `openai-codex` and `github-copilot` Astra records carry the same scalar values only as usage estimates; those subscription providers do not imply marginal per-request API charges.
227
227
 
228
- GitHub Copilot catalog visibility requires configured Copilot authentication, but a listed model is not proof that the current account is entitled to use it or that the endpoint will accept a request. Copilot prices are scalar usage estimates for a subscription route, not guaranteed marginal charges. Grok's separate long-context rates cannot be represented by the scalar estimator, so estimates for long requests may be too low while token counts remain valid.
228
+ The GitHub Copilot records for `gpt-6-sol`, `gpt-6-luna`, and `claude-opus-5.5` use models.dev and an authenticated individual-account Copilot `GET /models` response observed on 2026-09-23. Where those sources conflicted, the account-scoped Copilot route governed: each record uses 1,000,000 total context, an independent 872,000 input limit, and a 128,000 output limit. These are metadata observations, not paid invocation or maximum-boundary acceptance tests.
229
+
230
+ GitHub Copilot catalog visibility requires configured Copilot authentication, but a listed model is not proof that the current account is entitled to use it or that the endpoint will accept a request. Copilot prices are scalar default/low-context usage estimates for a subscription route, not guaranteed marginal charges, and cannot encode separately reported long-context tiers. Grok's separate long-context rates likewise cannot be represented by the scalar estimator, so estimates for long requests may be too low while token counts remain valid.
229
231
 
230
232
  Current behavior:
231
233
  - `/model` and `--list-models` list entries by model `id`.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@leanandmean/coding-agent",
3
- "version": "0.74.1-scramjet.55",
3
+ "version": "0.74.1-scramjet.56",
4
4
  "publishConfig": {
5
5
  "access": "public"
6
6
  },
@@ -37,9 +37,9 @@
37
37
  "test": "vitest --run --passWithNoTests"
38
38
  },
39
39
  "dependencies": {
40
- "@leanandmean/agent": "0.74.1-scramjet.34",
41
- "@leanandmean/ai": "0.74.1-scramjet.30",
42
- "@leanandmean/tui": "0.74.1-scramjet.27",
40
+ "@leanandmean/agent": "0.74.1-scramjet.35",
41
+ "@leanandmean/ai": "0.74.1-scramjet.31",
42
+ "@leanandmean/tui": "0.74.1-scramjet.28",
43
43
  "@silvia-odwyer/photon-node": "^0.3.4",
44
44
  "chalk": "^5.5.0",
45
45
  "dictionary-en": "^4.0.0",