opencode: declare the context these models actually serve

Every local model was declared at 32768 (16384 for the OMO local aliases)
regardless of what llama-swap is configured to serve. gpt-oss-20b runs with
`-c 65536`, so opencode was compacting at half the real window -- and
local/librarian and local/explore, which both route to gpt-oss-20b, at a
quarter of it.

Compaction is not free and it is not neutral. Measured on mainframe
2026-09-21, one agent session against a model told it had 32k when it had
131k: four cache-cold prefills, and 780 seconds spent after a working fix
re-reading the same forty lines, because each compaction discarded the memory
of having already verified it. Reasoning spend per step went from 2-5 tokens
to 1739. The model was not confused; it had been made to forget.

Values are llama-swap's own `-c`:

  gpt-oss-20b       65536    (was 32768)
  local/librarian   65536    (was 16384 / 32768)
  local/explore     65536    (was 16384 / 32768)
  qwen3-coder-30b   32768    unchanged, already correct
  gemma3-12b        32768    unchanged, already correct

The hosted entries were already right and are untouched.

⚠ These are hand-maintained and llama-swap's config is the source of truth.
If a `-c` changes there, change it here. llmbench now derives the same
numbers by parsing that file, and raises rather than guessing when an alias
is unknown -- a wrong context limit produces plausible numbers instead of an
error, which is how this went unnoticed.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01E9UH1zGZZtA9yhohmQrcT6

common/opencode/local.json

@@ -12,7 +12,7 @@
         "gpt-oss-20b": {
           "name": "gpt-oss-20b (local, resident)",
           "limit": {
-            "context": 32768,
+            "context": 65536,
             "output": 8192
           },
           "cost": {
@@ -51,7 +51,7 @@
         "local/librarian": {
           "name": "Librarian - local gpt-oss",
           "limit": {
-            "context": 16384,
+            "context": 65536,
             "output": 8192
           },
           "cost": {
@@ -64,7 +64,7 @@
         "local/explore": {
           "name": "Explore - local gpt-oss",
           "limit": {
-            "context": 16384,
+            "context": 65536,
             "output": 8192
           },
           "cost": {

common/opencode/personal.json

@@ -12,7 +12,7 @@
         "gpt-oss-20b": {
           "name": "gpt-oss-20b (local, resident)",
           "limit": {
-            "context": 32768,
+            "context": 65536,
             "output": 8192
           },
           "cost": {
@@ -51,7 +51,7 @@
         "local/librarian": {
           "name": "Librarian - local gpt-oss",
           "limit": {
-            "context": 32768,
+            "context": 65536,
             "output": 4096
           },
           "cost": {
@@ -64,7 +64,7 @@
         "local/explore": {
           "name": "Explore - local gpt-oss",
           "limit": {
-            "context": 32768,
+            "context": 65536,
             "output": 4096
           },
           "cost": {

common/opencode/work-strict.json

@@ -12,7 +12,7 @@
         "gpt-oss-20b": {
           "name": "gpt-oss-20b (local, resident)",
           "limit": {
-            "context": 32768,
+            "context": 65536,
             "output": 8192
           },
           "cost": {
@@ -51,7 +51,7 @@
         "local/librarian": {
           "name": "Librarian - local gpt-oss",
           "limit": {
-            "context": 32768,
+            "context": 65536,
             "output": 4096
           },
           "cost": {
@@ -64,7 +64,7 @@
         "local/explore": {
           "name": "Explore - local gpt-oss",
           "limit": {
-            "context": 32768,
+            "context": 65536,
             "output": 4096
           },
           "cost": {

common/opencode/work.json

@@ -12,7 +12,7 @@
         "gpt-oss-20b": {
           "name": "gpt-oss-20b (local, resident)",
           "limit": {
-            "context": 32768,
+            "context": 65536,
             "output": 8192
           },
           "cost": {
@@ -51,7 +51,7 @@
         "local/librarian": {
           "name": "Librarian - local gpt-oss",
           "limit": {
-            "context": 32768,
+            "context": 65536,
             "output": 4096
           },
           "cost": {
@@ -64,7 +64,7 @@
         "local/explore": {
           "name": "Explore - local gpt-oss",
           "limit": {
-            "context": 32768,
+            "context": 65536,
             "output": 4096
           },
           "cost": {