release: 0.1.1 with Gemini 3.6 support and two blog posts (#44)

Co-authored-by: Alice <alice@prismshadow.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

changelog/0.1.1/2026-07-22-skills.md

@@ -1,4 +1,4 @@
-# Skills: local serving and fine-tuning join AI App Development
+# Skills: local serving and fine-tuning join AI App Development, plus deck authoring
 
 Three new built-in skills extend the AI App Development group so agents can stand up and tune the models they build on:
 
@@ -10,4 +10,6 @@ Both serving skills share a guided workflow: ask the user which model to serve (
 
 The hard root-separation guardrail lives where configuration is taught — the `penguin-cli` skill (now v5) and the `penguin-sdk` skill: configuring Penguin's own model uses the default root, but models configured for an AI app under development must use the app's own project directory (`--root ./penguin_data`) unless the user chose otherwise — never the global `~/.penguin/data`. The serving skills point at that rule rather than restating it.
 
+**bento-slides** joins the Office Productivity group, so an agent asked for a presentation produces a real deck rather than a wall of bullets. A Bento deck is one self-contained `.bento.html` file whose document is plain JSON in a `#bento-doc` script block; the skill teaches the agent to edit that block in place, to fetch the app itself from bento.page when starting from nothing, and — the part that matters — to map source material onto the right feature (charts for numbers, tables for grids, morph transitions for a subject that changes across slides, state slides for drill-downs, ken-burns and count-ups for motion) instead of defaulting to text slides. It carries the gotchas that otherwise cost a round trip: chart series data must be plain numbers, morph needs stable shared element ids, assets are embedded as data URIs, and `docId` is never regenerated on an existing deck. Adapted from the Bento project's own skill (MIT, © 2026 The Bento/Suite authors) with attribution in the skill body; the authoritative schema stays at https://bento.page/agents.md.
+
 The `agenthub-models` skill tracks the AgentHub 0.4.1 upgrade: it documents the new supported-model registry, the config parameters a client may now reject outright, and the Gemini 3.6 / Kimi K3 / GLM-5.2 families with their reasoning-effort knobs, alongside a routing table rewritten from the release's actual client-matching order.

changelog/0.1.1/2026-07-22-tooling.md

@@ -0,0 +1,5 @@
+# Tooling and hardening: in-place upgrades, request validation and core test coverage
+
+- **`penguin update` upgrades an existing install in place.** `penguin update [--check] [--release <tag>] [-y|--yes]` resolves the newest version from the GitHub Releases API (the same source `install.sh` resolves `releases/latest/download` against) and upgrades using the mechanism the install actually came from, detected from the real path of the running CLI rather than guessed: a tarball install re-runs the official installer preserving its install dir and whether it bundles a Node runtime; a global npm/pnpm/yarn/bun install runs that manager's global install, and prints the command instead of guessing when the manager cannot be identified; a source checkout is refused with a pointer to `git pull` and a rebuild. Without `-y` it prints the mechanism, target version and install dir and asks for confirmation, and a non-TTY stdin requires `--yes` rather than blocking. The data root is never touched — only `bin`, `lib`, `web` and `node` are replaced. The target flag is `--release`, not `--version`, because the CLI's own `-v, --version` takes precedence over a subcommand option of the same name.
+- The server now validates `positiveIntParam` and `optionalDateParam` inputs instead of trusting query strings — malformed paging/date parameters return a clean 400 rather than leaking into SQL or arithmetic.
+- Core gained dedicated unit tests for `CappedTextBuffer` and `ToolCallIdAllocator`, two small pure modules that previously had no direct coverage.

changelog/0.1.1/README.md

@@ -1,15 +1,15 @@
-# Version 0.2.0
+# Version 0.1.1
 
-Unreleased.
+Released on 2026-07-22.
 
 - [2026-07-22] Models and core: empty tool lists are omitted from LLM requests (fixing 400s from strict OpenAI-compatible servers), the default system prompt gains service-protection and API-key retry guardrails with the default port as a core SDK constant, a per-model max output tokens cap lands on the Models page, the thinking level moves to a conversation-time picker (low and above) that writes through to Agent settings, subagents inherit the parent session's model and thinking level, sessions record their origin in `session_meta.source` as the single source of truth, the SDK moves to AgentHub 0.4.1 and its supported-model registry drives a catalog refresh across every provider group (with the READMEs trimmed to the newest generation per vendor), and session-title generation folds into core's internal module. ([details](2026-07-22-models-and-core.md))
 
 - [2026-07-22] Web App: the chat sidebar groups conversations by Workspace (with an Agent-mode toggle, group pinning, subagent/scheduled folders and paged loading), the collapsed sidebar becomes an eight-entry navigation rail with bilingual tooltips, the model picker lists key-configured models first, chat renders links in a new tab with clean CJK/URL wrapping and the subagent expansion below the tool's own output, mobile dropdowns stay inside the viewport, the Cost center's daily-token tooltip follows the pointer and shows the cache hit rate, the model and Agent settings forms were tightened, the copied task-stats line is localized, and custom model groups and Agents get initial-letter avatars. ([details](2026-07-22-web-app.md))
 
-- [2026-07-22] Skills: vLLM and Ollama deployment plus LlamaFactory fine-tuning join the AI App Development group with a guided serving workflow that follows the user's engine preference, and `agenthub-models` tracks the AgentHub 0.4.1 API. ([details](2026-07-22-skills.md))
+- [2026-07-22] Skills: vLLM and Ollama deployment plus LlamaFactory fine-tuning join the AI App Development group with a guided serving workflow that follows the user's engine preference, `bento-slides` joins Office Productivity for authoring single-file Bento decks, and `agenthub-models` tracks the AgentHub 0.4.1 API. ([details](2026-07-22-skills.md))
 
 - [2026-07-22] Sites: the docs and landing navbars are now identical, the blog gains Tech-practice and Perspectives categories, pinned posts, author/date/copy-link metadata, a second AMD practice post and three bilingual Perspectives posts (harness minimalism against the Databricks benchmark, a sourced comparison of five agent frameworks, and the AI development stack — vLLM, Ollama, LlamaFactory — as infrastructure now driven by agents rather than people), and the built-in Skills are listed in the READMEs and on the landing page. ([details](2026-07-22-sites-and-blog.md))
 
 - [2026-07-22] Docs and examples: two new README roadmap items, and the self-improvement example reworked to genuinely evolve itself. ([details](2026-07-22-docs-and-examples.md))
 
-- [2026-07-22] Tooling: server query-parameter validation hardening, and unit tests for two previously uncovered core modules. ([details](2026-07-22-tooling.md))
+- [2026-07-22] Tooling: `penguin update` upgrades an existing install in place via the mechanism it was installed with, plus server query-parameter validation hardening and unit tests for two previously uncovered core modules. ([details](2026-07-22-tooling.md))

changelog/0.2.0/2026-07-22-tooling.md

@@ -1,4 +0,0 @@
-# Tooling and hardening: request validation and core test coverage
-
-- The server now validates `positiveIntParam` and `optionalDateParam` inputs instead of trusting query strings — malformed paging/date parameters return a clean 400 rather than leaking into SQL or arithmetic.
-- Core gained dedicated unit tests for `CappedTextBuffer` and `ToolCallIdAllocator`, two small pure modules that previously had no direct coverage.