fix(server): default max_tokens 2048 -> 8192, which was starving the lesson

On a reasoning model the reasoning is spent from the same completion budget
and it goes first, so a small ceiling truncates the actual reply away. It
fails silently and looks exactly like a model that cannot follow the system
prompt, which is the expensive way to debug it.

Measured on gpt-oss-20b against the real ~3.5k-token system prompt, same
prompt and same model, only the ceiling changing:

  1400  an empty string, 0 bytes, after 27s
  2048  a truncated half-Korean fragment, none of the required blocks
  8000  99% English prose, no romanization, 0 batchim violations in the
        task lines, all three blocks, 11s

The old comment justified 2048 by worrying about 4k-context local models.
That reasoning was wrong: the system prompt alone is ~3.5k tokens, so such
a model cannot run this app at all and there was nothing to protect.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

server/.env.example

@@ -28,9 +28,11 @@ HANKAN_OPENAI_BASE_URL=http://host.docker.internal:1234/v1
 HANKAN_OPENAI_MODEL=local-model
 # Local servers ignore this; hosted ones require it. Leave blank for local.
 HANKAN_OPENAI_API_KEY=
-# Completion ceiling. Kept modest because a small-context local model errors
-# outright if asked for more than its context holds.
-HANKAN_OPENAI_MAX_TOKENS=2048
+# Completion ceiling. Do not lower this much: on a reasoning model the
+# reasoning comes out of the same budget and goes first, so a small value
+# truncates the actual lesson away. gpt-oss-20b returns an empty string at
+# 1400 and a broken half-Korean fragment at 2048.
+HANKAN_OPENAI_MAX_TOKENS=8192
 
 # The docker network your existing Postgres and Caddy are on.
 #   docker network ls

server/README.md

@@ -184,6 +184,15 @@ Measured on a 6,948-character prompt against gpt-oss-20b: **first token
 1,563ms cold, 324ms with the prefix already warm.** Which is why the system
 prompt goes first and stays put in this backend too.
 
+**Give a reasoning model room.** Its reasoning is spent from the same
+`max_tokens` budget and goes first, so too small a value truncates the
+lesson away entirely — and it fails silently, looking exactly like a model
+that cannot follow instructions. Measured on gpt-oss-20b with the real
+~3.5k-token system prompt: an empty string at 1,400, a broken half-Korean
+fragment with none of the required blocks at 2,048, and a correct English
+lesson with all three at 8,000. `HANKAN_OPENAI_MAX_TOKENS` defaults to
+8192 for that reason.
+
 A reasoning model served locally often emits chain-of-thought inline in
 `content` rather than in a separate field. `<think>` blocks are stripped
 from the stream, including when the tags arrive split across chunks —

server/src/backends/openai.ts

@@ -38,10 +38,20 @@ const DEFAULT_BASE_URL = "http://localhost:1234/v1";
 const DEFAULT_MODEL = "local-model";
 
 /* A tutor turn is a lesson intro at most — the prompt caps it at 250-450
-   words. Deliberately far below the Anthropic backend's 16k: this one may
-   be pointed at a 4k-context local model, where asking for more completion
-   tokens than the context holds is an outright error rather than a ceiling. */
-const DEFAULT_MAX_TOKENS = 2048;
+   words, so roughly 1,200 tokens of visible text.
+
+   This is 8k anyway, because on a reasoning model the reasoning is spent
+   from the SAME budget and it goes first. Measured on gpt-oss-20b with the
+   real ~3.5k-token system prompt: at 1,400 it returned an empty string, at
+   2,048 a truncated fragment of Korean with none of the required blocks,
+   and at 8,000 a correct English lesson with all three. The failure is
+   silent and looks exactly like a model that cannot follow instructions,
+   which is the expensive way to debug it.
+
+   An earlier note here worried about 4k-context models. That was wrong:
+   the system prompt alone is ~3.5k tokens, so such a model cannot run this
+   app at all and there is nothing to protect. */
+const DEFAULT_MAX_TOKENS = 8192;
 
 /**
  * Strip <think> blocks from a token stream.