pi-bob 0.2.2 → 0.2.4

package/README.md

@@ -13,7 +13,7 @@ Updated for the installed `bobshell@2.0.1` package (upgraded from 1.0.6; finding
 
 - 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.
 - 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.
-- **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.
+- **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.
 - **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.
 - 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.
 - **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.
@@ -63,6 +63,16 @@ Model discovery is enabled by default:
 
 Discovered context limits, output limits, vision support, reasoning support, backend identifiers, and token prices are mapped into Pi model definitions. Bob reports prices per token; Pi displays prices per million tokens, so the extension performs that conversion.
 
+### How context/output limits are determined
+
+Every advertised number comes from Bob's own `/model/info` catalog — the extension never hardcodes per-model values:
+
+- **Context window** ← `model_info.max_input_tokens`.
+- **Max output tokens** ← `model_info.max_output_tokens` when present (2.x), else `model_info.max_tokens` (the 1.x output cap).
+- Models that report no limits (e.g. `granite-8b-code-instruct`, `rnj-1-*`) use the defaults: 200,000 context / 8,192 output, overridable via `IBM_BOB_CONTEXT_WINDOW` / `IBM_BOB_MAX_TOKENS`.
+
+The 2.x precedence was determined empirically, not from documentation. The 2.x catalog reports *two* output fields for the same route (e.g. `premium`: `max_tokens: 12000`, `max_output_tokens: 64000`), so on 2026-08-31 the extension author probed the live endpoint: a `chat/completions` request for `premium` with `max_tokens=50000` — four times the catalog's `max_tokens` — returned HTTP `200` and completed normally. That proves `max_tokens` is no longer the enforced cap and `max_output_tokens` is the real limit, so the larger, newer field is advertised when present. 1.x payloads have no `max_output_tokens`, where `max_tokens` was verified to be the output cap, keeping that behavior unchanged.
+
 ## Quick start for the discovered Bob endpoint
 
 Use Bob SSO through Pi:

package/extensions/bob.ts

@@ -365,10 +365,12 @@ export function parseBobModelCatalog(payload: unknown): BobDiscoveredModel[] {
 				entry.model_info.supports_thinking === true,
 			supportsVision: entry.model_info.supports_vision === true,
 			contextWindow: positiveNumber(entry.model_info.max_input_tokens),
-			// bobshell 2.x adds max_output_tokens; keep the conservative 1.x
-			// max_tokens precedence and only use it as a fallback.
+			// bobshell 2.x: max_tokens is no longer the enforced output cap
+			// (verified 2026-08-31: premium accepts max_tokens=50000; its
+			// max_output_tokens=64000 is the real limit). 1.x payloads have no
+			// max_output_tokens and keep the old max_tokens behavior.
 			maxTokens:
-				positiveNumber(entry.model_info.max_tokens) ?? positiveNumber(entry.model_info.max_output_tokens),
+				positiveNumber(entry.model_info.max_output_tokens) ?? positiveNumber(entry.model_info.max_tokens),
 			cost: {
 				input: perMillionCost(entry.model_info.input_cost_per_token),
 				output: perMillionCost(entry.model_info.output_cost_per_token),

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-bob",
-  "version": "0.2.2",
+  "version": "0.2.4",
   "type": "module",
   "description": "Pi provider extension for IBM Bob / IBM-approved compatible model endpoints.",
   "keywords": [