@blockrun/franklin 3.35.2 → 3.35.4
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/dist/agent/optimize.js +7 -2
- package/dist/gateway-models.d.ts +15 -5
- package/dist/gateway-models.js +15 -5
- package/package.json +1 -1
package/dist/agent/optimize.js
CHANGED
|
@@ -32,9 +32,14 @@ const MODEL_MAX_OUTPUT = {
|
|
|
32
32
|
'anthropic/claude-opus-4.6': 32_000,
|
|
33
33
|
'anthropic/claude-opus-4.5': 32_000,
|
|
34
34
|
'anthropic/claude-sonnet-5': 128_000,
|
|
35
|
-
'anthropic/claude-sonnet-4.6':
|
|
35
|
+
'anthropic/claude-sonnet-4.6': 128_000, // Anthropic-documented; gateway corrected 2026-07-21
|
|
36
36
|
'anthropic/claude-sonnet-4.5': 64_000,
|
|
37
|
-
|
|
37
|
+
// Anthropic documents 64000 for Haiku 4.5. Held at 16384 until 2026-07-21
|
|
38
|
+
// because the gateway clamped to 8192 — asking for more only inflated the
|
|
39
|
+
// price quote (quotedOutputTokens scales with the ceiling) while the reply
|
|
40
|
+
// stayed capped. blockrun#266 corrected the gateway and it is live, so the
|
|
41
|
+
// real ceiling is now reachable.
|
|
42
|
+
'anthropic/claude-haiku-4.5': 64_000,
|
|
38
43
|
'openai/gpt-5.6-sol': 128_000,
|
|
39
44
|
'openai/gpt-5.6-terra': 128_000,
|
|
40
45
|
'openai/gpt-5.6-luna': 128_000,
|
package/dist/gateway-models.d.ts
CHANGED
|
@@ -64,11 +64,21 @@ export declare function clearGatewayModelsCache(): void;
|
|
|
64
64
|
* Deliberately ignores the TTL: a stale gateway record still beats no record
|
|
65
65
|
* at all, and the only callers are fallbacks for models we have no static
|
|
66
66
|
* entry for. Callers must treat the static tables as authoritative — the
|
|
67
|
-
* gateway's own metadata
|
|
68
|
-
* max_output 8192 for claude-haiku-4.5
|
|
69
|
-
* and 64000 for claude-sonnet-4.6
|
|
70
|
-
*
|
|
71
|
-
*
|
|
67
|
+
* gateway's own metadata has been wrong for models we already know. As of
|
|
68
|
+
* 2026-07-20 it reported max_output 8192 for claude-haiku-4.5 (Anthropic
|
|
69
|
+
* documents 64000) and 64000 for claude-sonnet-4.6 (documented 128000).
|
|
70
|
+
* Those two specific numbers are being corrected upstream, so do not treat
|
|
71
|
+
* them as current — the point that outlives them is that the catalog can be
|
|
72
|
+
* wrong, and a wrong value here is not cosmetic.
|
|
73
|
+
*
|
|
74
|
+
* Correction to an earlier note here: these values are NOT inert metadata.
|
|
75
|
+
* The gateway clamps with them — Math.min(request.max_tokens, model.maxOutput)
|
|
76
|
+
* in both the messages and chat/completions handlers — and derives its price
|
|
77
|
+
* quote from the clamped ceiling. An over-cap request is accepted rather than
|
|
78
|
+
* rejected: the handler logs "capping to <limit>" server-side and continues,
|
|
79
|
+
* so from here the clamp is invisible until a reply is long enough to hit it.
|
|
80
|
+
* That is why a short smoke test against a wrongly-capped model looks healthy.
|
|
81
|
+
* Treat this as "better than a blind default", nothing more.
|
|
72
82
|
*/
|
|
73
83
|
export declare function peekGatewayModel(id: string): GatewayModel | null;
|
|
74
84
|
/** Test helper — seed the cache without a network call. */
|
package/dist/gateway-models.js
CHANGED
|
@@ -32,11 +32,21 @@ export function clearGatewayModelsCache() {
|
|
|
32
32
|
* Deliberately ignores the TTL: a stale gateway record still beats no record
|
|
33
33
|
* at all, and the only callers are fallbacks for models we have no static
|
|
34
34
|
* entry for. Callers must treat the static tables as authoritative — the
|
|
35
|
-
* gateway's own metadata
|
|
36
|
-
* max_output 8192 for claude-haiku-4.5
|
|
37
|
-
* and 64000 for claude-sonnet-4.6
|
|
38
|
-
*
|
|
39
|
-
*
|
|
35
|
+
* gateway's own metadata has been wrong for models we already know. As of
|
|
36
|
+
* 2026-07-20 it reported max_output 8192 for claude-haiku-4.5 (Anthropic
|
|
37
|
+
* documents 64000) and 64000 for claude-sonnet-4.6 (documented 128000).
|
|
38
|
+
* Those two specific numbers are being corrected upstream, so do not treat
|
|
39
|
+
* them as current — the point that outlives them is that the catalog can be
|
|
40
|
+
* wrong, and a wrong value here is not cosmetic.
|
|
41
|
+
*
|
|
42
|
+
* Correction to an earlier note here: these values are NOT inert metadata.
|
|
43
|
+
* The gateway clamps with them — Math.min(request.max_tokens, model.maxOutput)
|
|
44
|
+
* in both the messages and chat/completions handlers — and derives its price
|
|
45
|
+
* quote from the clamped ceiling. An over-cap request is accepted rather than
|
|
46
|
+
* rejected: the handler logs "capping to <limit>" server-side and continues,
|
|
47
|
+
* so from here the clamp is invisible until a reply is long enough to hit it.
|
|
48
|
+
* That is why a short smoke test against a wrongly-capped model looks healthy.
|
|
49
|
+
* Treat this as "better than a blind default", nothing more.
|
|
40
50
|
*/
|
|
41
51
|
export function peekGatewayModel(id) {
|
|
42
52
|
if (!cache)
|
package/package.json
CHANGED