Skip to content

Commit ee00e2a

Browse files
author
1bcMax
committed
release: 3.35.5 — the last three OpenAI ceilings, measured
1 parent bab8245 commit ee00e2a

3 files changed

Lines changed: 38 additions & 3 deletions

File tree

CHANGELOG.md

Lines changed: 35 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,40 @@
11
# Changelog
22

3+
## Franklin Agent 3.35.5 — the last three OpenAI ceilings, measured
4+
5+
| model | was | now |
6+
|---|---|---|
7+
| `openai/gpt-5.5` | 32,768 | 128,000 |
8+
| `openai/gpt-5.4` | 32,768 | 128,000 |
9+
| `openai/gpt-5-mini` | 16,384 | 65,536 |
10+
11+
These took three attempts to get right, and the story is worth keeping because
12+
the table is where a wrong belief gets frozen.
13+
14+
The first attempt set gpt-5.5 and gpt-5.4 to 100,000, citing "upstream's stated
15+
maximum". There was no upstream response: both BlockRun SDKs rejected
16+
`max_tokens > 100000` client-side, so 19 probes at 128,000 never reached a
17+
provider. The uniform limit across three unrelated vendors should have been the
18+
tell. That PR was closed. The second attempt put them back at 32,768 and
19+
recorded the catalog's 128,000 as unrefuted but unverified — honest, but still
20+
not measured.
21+
22+
Re-probed with the SDK guard bypassed: every model advertising a ceiling above
23+
100,000 accepts it, including `zai/glm-5.2` at 262,144. The catalog was right
24+
the whole time; the measurement was broken. Fixed at the root in
25+
blockrun-llm 1.8.1 and @blockrun/llm 3.8.1, which raise that guard to a
26+
1,000,000 typo bound and reword the message so it no longer reads like a
27+
provider response.
28+
29+
Franklin never ran that guard — both request paths use raw fetch and import
30+
only payment helpers from the SDK — so these values do not depend on the SDK
31+
release.
32+
33+
Effect is on the escalation path. A normal turn still sends
34+
`min(16384, ceiling)`; after a `max_tokens` stop the ceiling for gpt-5.5 and
35+
gpt-5.4 goes from 32,768 to 65,536 (`ESCALATED_MAX_TOKENS`), so recovery
36+
doubles instead of clamping back below where it started.
37+
338
## Franklin Agent 3.35.4 — Haiku and Sonnet 4.6 get their real output ceilings
439

540
**Haiku 4.5 goes from 16,384 to 64,000 max output. Sonnet 4.6 from 64,000 to

package-lock.json

Lines changed: 2 additions & 2 deletions
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

package.json

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
{
22
"name": "@blockrun/franklin",
3-
"version": "3.35.4",
3+
"version": "3.35.5",
44
"description": "Franklin Agent — The AI agent with a wallet. Spends USDC autonomously to get real work done. Pay per action, no subscriptions.",
55
"type": "module",
66
"exports": {

0 commit comments

Comments
 (0)