pi-bob 0.2.2 → 0.2.3
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.
- package/README.md +1 -1
- package/extensions/bob.ts +5 -3
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -13,7 +13,7 @@ Updated for the installed `bobshell@2.0.1` package (upgraded from 1.0.6; finding
|
|
|
13
13
|
|
|
14
14
|
- Bob Shell 2.x moved stored SSO tokens to `~/.bob/settings/auth-secrets.json` (key `bob.auth.tokens-<gateway>`); `~/.bob/settings.json` keeps only non-secret settings. This extension still reads only `ibm.instanceId`/`ibm.teamId` from there and still ignores Bob's secrets.
|
|
15
15
|
- Token endpoints are unchanged in practice: 2.x builds `${gateway}/authn` + `v1/auth/token|refresh`, which resolves to the same `/authn/v1/auth/token` and `/authn/v1/auth/refresh` routes used here. The web login URL is now assembled as `https://bob.ibm.com` + `/login`; the final URL is the same as the 1.x constant.
|
|
16
|
-
- **Breaking:** 2.x `model/info` entries dropped `litellm_params` (the backend identifier) and now carry `max_output_tokens` and `supports_prompt_caching` alongside `max_tokens`. The parser accepts both shapes and falls back to the route name when the backend is missing.
|
|
16
|
+
- **Breaking:** 2.x `model/info` entries dropped `litellm_params` (the backend identifier) and now carry `max_output_tokens` and `supports_prompt_caching` alongside `max_tokens`. The parser accepts both shapes and falls back to the route name when the backend is missing. `max_output_tokens` is the enforced output cap under 2.x (verified 2026-08-31: `premium` accepted `max_tokens=50000` despite a catalog `max_tokens` of 12000) and is advertised when present.
|
|
17
17
|
- **Breaking:** 2.x `model/info` requires `x-instance-id` (HTTP 400 without it); `x-team-id` stays optional. The extension already sends both from Bob settings or the JWT `instances` claim.
|
|
18
18
|
- Model tiers were renamed: 1.x `premium`/`pro`/`flash`/`flash-lite` became 2.x tiers `fast`/`premium`/`ultra` (`explorer` exists but is hidden). Live catalog also exposes `premium-ide`, `premium-shell`, `sonnet-4.5`, `wxO-model` (1M ctx / 64k out), `gpt-oss-20b`, and granite/rnj code models. The `premium` alias still exists, so the fallback catalog stays valid.
|
|
19
19
|
- **Breaking (entitlement):** under 2.0, the `anthropic-messages` and `openai-responses` routes return `403 Access denied` with a valid token (routes exist; access is denied for this instance). Only the default `openai-completions` adapter works; treat the alternates as unavailable until IBM grants access.
|
package/extensions/bob.ts
CHANGED
|
@@ -365,10 +365,12 @@ export function parseBobModelCatalog(payload: unknown): BobDiscoveredModel[] {
|
|
|
365
365
|
entry.model_info.supports_thinking === true,
|
|
366
366
|
supportsVision: entry.model_info.supports_vision === true,
|
|
367
367
|
contextWindow: positiveNumber(entry.model_info.max_input_tokens),
|
|
368
|
-
// bobshell 2.x
|
|
369
|
-
//
|
|
368
|
+
// bobshell 2.x: max_tokens is no longer the enforced output cap
|
|
369
|
+
// (verified 2026-08-31: premium accepts max_tokens=50000; its
|
|
370
|
+
// max_output_tokens=64000 is the real limit). 1.x payloads have no
|
|
371
|
+
// max_output_tokens and keep the old max_tokens behavior.
|
|
370
372
|
maxTokens:
|
|
371
|
-
positiveNumber(entry.model_info.
|
|
373
|
+
positiveNumber(entry.model_info.max_output_tokens) ?? positiveNumber(entry.model_info.max_tokens),
|
|
372
374
|
cost: {
|
|
373
375
|
input: perMillionCost(entry.model_info.input_cost_per_token),
|
|
374
376
|
output: perMillionCost(entry.model_info.output_cost_per_token),
|