@adia-ai/llm 0.8.39 → 0.8.41

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/CHANGELOG.md CHANGED
@@ -1,5 +1,15 @@
1
1
  # Changelog
2
2
 
3
+ ## [0.8.41] — 2026-08-17
4
+
5
+ ### Docs
6
+ - **`README.md` — dead pointer to the retired session-journal record removed** (the `.claude/docs/journal/` tree was deleted in the harness reset; history lives in git). No code change.
7
+
8
+ ## [0.8.40] — 2026-08-15
9
+
10
+ ### Maintenance
11
+ - **Lockstep version bump only.** No source changes in this package; bumped to maintain the lockstep version coherence enforced by `scripts/release/check-lockstep.mjs`. Substantive v0.8.40 work shipped in the ADR-0052/0053/0054/0056 attribute-grammar and token-convention breaking wave. See `packages/web-components/CHANGELOG.md#0840--2026-08-15` for details.
12
+
3
13
  ## [0.8.39] — 2026-08-15
4
14
 
5
15
  ### Maintenance
package/README.md CHANGED
@@ -148,8 +148,7 @@ holds a drop-in Caddyfile fragment for exe.dev VMs. The §188 (v0.5.5)
148
148
  arc deleted ~155 LOC of hand-rolled passthrough from `server.js` in
149
149
  favor of this approach. See `.claude/docs/specs/exe-dev-platform-reference.md`
150
150
  + `.claude/docs/guides/production-llm-proxy-deployment.md` for the full
151
- recipe and `.claude/docs/journal/2026/05/2026-05-14.md §185-§188` for the
152
- architectural migration arc.
151
+ recipe (the architectural migration arc lives in git history around v0.5.5).
153
152
 
154
153
  **Stage 0b recon checklist**: before hand-rolling a proxy, check whether
155
154
  your platform provides one natively. Look for `LLM Gateway` / `AI` /
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@adia-ai/llm",
3
- "version": "0.8.39",
3
+ "version": "0.8.41",
4
4
  "description": "Provider-agnostic LLM client — anthropic / openai / gemini adapters with a unified chat() + streamChat() facade. Used by AdiaUI's chat-shell and the A2UI generation pipeline; works in browser (with proxyUrl) and Node.",
5
5
  "type": "module",
6
6
  "exports": {