|
1 | 1 | # Release Notes |
2 | 2 |
|
| 3 | +# Copilot for Obsidian - Release v3.2.5 🛠️ |
| 4 | + |
| 5 | +A packed patch release with **Composer V2 editing**, **Azure provider unification**, **drag-to-insert wikilinks**, **Obsidian Bases support**, **LM Studio Responses API**, and a wave of agent, search, and UI improvements! |
| 6 | + |
| 7 | +- ✏️ **Composer V2: smarter file editing** — The new `editFile` tool replaces `replaceInFile` as the primary targeted-edit tool, bringing more reliable and precise in-file edits when Copilot modifies your notes. (@wenzhengjiang) |
| 8 | +- 🔗 **Drag relevant notes into your editor** — You can now drag notes and sources from the Copilot chat panel directly into any editor to insert wikilinks instantly. Great for building connections while researching! (@logancyang) |
| 9 | +- ☁️ **Azure OpenAI and Azure Foundry unified** — Both Azure providers are now merged into a single, cleaner Azure provider. No more confusion about which Azure to use! (@logancyang) |
| 10 | +- 🗂️ **Obsidian Bases support** — Copilot's agent now has a `base:create` command and can read `.base` active notes, with a new read-only `obsidianBases` CLI tool for querying your Bases. (@logancyang) |
| 11 | +- ⚡ **LM Studio: Responses API with KV cache reuse** — LM Studio models now use the Responses API for stateful KV cache reuse, giving you faster, more efficient conversations with local models. (@logancyang) |
| 12 | +- 💡 **Gemini Embedding 2 preview support** — Gemini Embedding 2 preview is now available as an embedding model option. (@logancyang) |
| 13 | +- 🤖 **GitHub Copilot Chat supports tool calling** — The GitHub Copilot Chat model now supports native tool calling, unlocking agent mode with it! (@Emt-lin) |
| 14 | +- 🗺️ **Automatic file renaming to match topic titles** — When Copilot generates a topic title for a chat, the file is now automatically renamed to match. (@somethingSTRANGE) |
| 15 | +- 💾 **OpenRouter prompt caching** — OpenRouter models now support `cache_control` for prompt caching, saving tokens on repeated context. (@logancyang) |
| 16 | +- 🧠 **Miyo improvements** — Customizable vault name setting, remote backend mobile re-indexing support, and license auth header for Miyo requests. (@wenzhengjiang) |
| 17 | +- 📅 **CLI tool upgrades** — Daily/random read tools, reasoning summaries, enhanced instructions from obsidian-skills reference, and daily note template workflow fixes for past/future dates. (@logancyang) |
| 18 | +- 🛠️ **Agent & search fixes** — Improved inline citations, query deduplication, answer source priority, expanded search limits for time-range/tag queries, and removed `returnAll` to prevent token spikes. (@logancyang) |
| 19 | +- 🎨 **UI & UX polish** — Quick Ask panel positioning overhaul, LaTeX rendering fix, Ollama numCtx config, "None" system prompt option, clickable citations, and more. (@Emt-lin, @logancyang) |
| 20 | +- 🔧 **Local model fixes** — Stripped leaked special tokens from local model responses; agent tool paths now use `vault.read` instead of `cachedRead` for reliability. (@logancyang, @yu-zou) |
| 21 | +- 🎬 **YouTube transcript fix** — Both classic and modern YouTube transcript panel DOM structures are now supported. (@Emt-lin) |
| 22 | +- 🔒 **Tiktoken CDN timeout fix** — Defense-in-depth overrides prevent tiktoken CDN timeouts in Plus mode. (@logancyang) |
| 23 | + |
| 24 | +More details in the changelog: |
| 25 | + |
| 26 | +### Improvements |
| 27 | + |
| 28 | +- #2305 Composer V2: Replace replaceInFile with editFile as the primary targeted-edit tool @wenzhengjiang |
| 29 | +- #2311 feat(miyo): add customizable vault name setting @wenzhengjiang |
| 30 | +- #2306 feat(lm-studio): use Responses API for stateful KV cache reuse @logancyang |
| 31 | +- #2303 feat(tools): add base:create command and .base active note support @logancyang |
| 32 | +- #2265 feat: add obsidianBases CLI tool (read-only) @logancyang |
| 33 | +- #2299 feat: add Gemini Embedding 2 preview model support @logancyang |
| 34 | +- #2291 feat: unify Azure OpenAI and Azure Foundry into single Azure provider @logancyang |
| 35 | +- #2288 feat: drag relevant notes and sources into editor to insert wikilinks @logancyang |
| 36 | +- #2279 feat(openrouter): enable prompt caching via cache_control @logancyang |
| 37 | +- #2242 feat: refactor GitHubCopilotChatModel to support tool calling @Emt-lin |
| 38 | +- #2301 feat: enhance CLI tool instructions from obsidian-skills reference @logancyang |
| 39 | +- #2181 Add Obsidian CLI daily/random read tools and reasoning summaries @logancyang |
| 40 | +- #2312 feat: add PR pricing agent @logancyang |
| 41 | +- #2260 Add license auth header to Miyo requests @wenzhengjiang |
| 42 | + |
| 43 | +### Bug Fixes |
| 44 | + |
| 45 | +- #2313 fix(ui): show enabled models without API keys as disabled in dropdown @logancyang |
| 46 | +- #2308 fix(search): allow remote backends to re-index on mobile when disableIndexOnMobile is enabled @wenzhengjiang |
| 47 | +- #2307 refactor(tools): remove daily note append/prepend CLI commands @logancyang |
| 48 | +- #2304 fix(tools): daily note template workflow for past/future dates @logancyang |
| 49 | +- #2300 fix(agent): improve inline citations, query dedup, and answer source priority @logancyang |
| 50 | +- #2295 fix: restore expanded search limits for time-range and tag queries @logancyang |
| 51 | +- #2293 fix: add "None" option to system prompt dropdown in chat settings @logancyang |
| 52 | +- #2287 fix: agent loop improvements, clickable citations, and UI fixes @logancyang |
| 53 | +- #2286 fix: support both classic and modern YouTube transcript panel DOM structures @Emt-lin |
| 54 | +- #2285 fix: strip leaked special tokens from local model responses @logancyang |
| 55 | +- #2283 fix: defense-in-depth overrides to prevent tiktoken CDN timeout in Plus mode @logancyang |
| 56 | +- #2278 fix: Quick Ask/Command panel positioning overhaul @Emt-lin |
| 57 | +- #2276 fix: command UI improvements, LaTeX rendering, and Ollama numCtx config @Emt-lin |
| 58 | +- #2274 fix(tools): replace cachedRead with vault.read in agent/tool paths @yu-zou |
| 59 | +- #2273 fix: remove returnAll from agent-facing search tools to prevent token spikes @logancyang |
| 60 | +- #2269 fix: pass timeRange to Miyo search path @logancyang |
| 61 | +- #2240 fix(rename): Add automatic file renaming to match generated topic titles @somethingSTRANGE |
| 62 | + |
| 63 | +## Troubleshoot |
| 64 | + |
| 65 | +- If models are missing, navigate to Copilot settings -> Models tab and click "Refresh Built-in Models". |
| 66 | +- Please report any issue you see in the member channel! |
| 67 | + |
| 68 | +--- |
| 69 | + |
3 | 70 | # Copilot for Obsidian - Release v3.2.4 |
4 | 71 |
|
5 | 72 | A patch release with **Gemini stability fixes**, **Miyo improvements**, and **mobile/UI polish**. |
|
0 commit comments