chore: one changeset for the release, and no new em-dashes

Consolidates the four contributor changesets, and rewords the em-dashes this release
added in comments and docs. The five in test/settings-save-failure-ui.test.ts stay:
they assert existing toast text.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Codeman maintainer committed 2026-11-04 17:31:48 +01:00
1 parent eb3b08d58b
commit 4960bee779
36 files changed
+117 -106

No files matched your search

+7 -7
View File
@@ -71,7 +71,7 @@ hosts — these are machine-level infra, not per-user settings.
servers state no context-window field in the plain `GET /v1/models`
response at all; current llama-swap states one per model (both
`context_length` and `context_window`) and gateways like Bifrost pass
`context_window` through — that listed figure is the *lowest*-precedence
`context_window` through: that listed figure is the *lowest*-precedence
source, used only when neither probe below answers, and because llama-swap
documents it as the PER-SLOT window, a model whose figure comes from the
listing is recorded with a slot count of 1 so the slot check never divides a
@@ -82,7 +82,7 @@ llama-swap treats `?model=` as a routing hint and asking about a model that
isn't loaded risks triggering an actual (slow, GPU-swapping) load as a side
effect of what should be read-only discovery. A server with no `status` field
on any entry at all (not llama-swap) gets no launch-command/`/props`
enrichment, only whatever its listings state — rather than guessing. A
enrichment, only whatever its listings state, rather than guessing. A
model's previously-learned context length survives a
later cycle where it wasn't the loaded one; it's dropped only once the model
disappears from the endpoint's list entirely. Stored per model in
@@ -344,9 +344,9 @@ agent, so the selection would report success and change nothing.
**Claude gets two more env vars when known/applicable, both declared on its
registry entry (`contextLengthVar`/`configDirVar`), not hardcoded here:**
- `CLAUDE_CODE_MAX_CONTEXT_TOKENS` is set to `modelId`'s context length —
- `CLAUDE_CODE_MAX_CONTEXT_TOKENS` is set to `modelId`'s context length:
the discovered figure (see the discovery section above), falling back to
the endpoint's user-set `defaultContextLength` — whenever one is known.
the endpoint's user-set `defaultContextLength`, whenever one is known.
Without
it, Claude Code assumes a large (200k) window for any unrecognized custom
model id and never compacts, which reliably overflows a much smaller real
@@ -602,7 +602,7 @@ for '<id>' not found. Defaulting to fallback metadata...` on launch —
`POST <baseUrl>/v1/chat/completions` succeeds; the harness's own error
template (`DeepSeek API error (HTTP ${status})`) matches the originally
reported symptom exactly. The fix is no longer the original env redirect:
deepseek's `customModelInjection` is a `configDir` recipe — a per-session
deepseek's `customModelInjection` is a `configDir` recipe: a per-session
`DSH_HOME` holding only a generated `cordis.patch.yml` that declares a
`codeman-custom` `openai-completions` provider (the base URL gets the `/v1`
suffix from the shared `renderConfigFile` step every file template goes
@@ -610,7 +610,7 @@ for '<id>' not found. Defaulting to fallback metadata...` on launch —
recipe's `linkFromRealHome` field symlinks `profiles`, `sessions` and
`settings.yaml` back out of the real dsh home so installed bundles,
transcripts and user settings all survive the redirect (missing
directory entries are created first — a home that has never run a
directory entries are created first: a home that has never run a
turn would otherwise get a dangling link whose every write through
it failed with ENOENT). **Verified end-to-end against a real dsh
install by the maintainer** (dsh 0.1.1-rc.2, dsh-TUI 0.10.0-beta.1):
@@ -619,7 +619,7 @@ for '<id>' not found. Defaulting to fallback metadata...` on launch —
`POST /v1/chat/completions` with the right model, the bearer key and
`max_tokens: 8192`; the reply renders and the context window shows in
the footer. What such a session SHARES with the real home is
exactly the linked entries — `profiles/`, `sessions/`,
exactly the linked entries: `profiles/`, `sessions/`,
`settings.yaml`. The last is shared only until the session writes
it: dsh saves settings with a temp file and a rename
(`writeFileAtomic` in `@deepseek-ai/dsh-atomic-write`), which replaces