We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Merge branch 'master' of https://github.com/Deep-CodeAI/Agents.KT.wiki
docs: reflect three model providers (Ollama / Anthropic / OpenAI) With the Anthropic (#1644) and OpenAI (#1656) adapters shipped, the wiki was still claiming Ollama-only. Updated: - Home: Installation and Model & Tool Calling links now mention all three providers. - Installation-and-Setup: prerequisites table, new "Model Provider Setup" overview section showing all three model {} forms side by side, Ollama section retitled and re-scoped to local development. - Model-and-Tool-Calling: the "model {}" intro now opens with all three providers and a one-line switching note; ModelConfig data class + DSL table extended with the new fields (apiKey, maxTokens, anthropicBaseUrl, openAiBaseUrl); ModelClient section enumerates OllamaClient / ClaudeClient / OpenAiClient with their wire-mapping one-liners. - Roadmap: Phase 1 lines for both new adapters; status table gains rows for Anthropic and OpenAI integration. Pre-existing local diffs in the same pages (typed-tools section, tool-authorization section) carried along untouched. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
docs: migrate examples to typed Tool<*, *> refs (#1015-#1017) Lead all skill-allowlist examples with the typed `tools(handle)` form. String-name `tools("...")` remains documented for built-in tools and runtime-discovered MCP tools, with inline comments calling out why. New "Typed tool refs" section in Skills-and-Knowledge.md (or new page, your call) cross-linked from Best-Practices.md and Cookbook.md. Tracks: agents-kt-11 #1017
Document typed tool DSL, provider schemas, validation routing (PR 2) Adds a "Typed Tools" section to Model-and-Tool-Calling that explains the tool<Args, Result>(...) builder shipped in #634, the real JSON-Schema provider envelopes from #635 (proper properties / required / @Guide descriptions, replacing the empty-properties fallback), and the invalidArgs routing from #636 (deserialization failures go through the same handler as JSON-parse failures, not through executionError). Includes a complete WriteFileArgs / WriteFileResult example. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Document tool authorization model (PR 1 security release) Model-and-Tool-Calling: new "Tool Authorization Model" section explaining the per-skill allowlist enforced at execution (skill.toolNames ∪ autoToolNames ∪ memory tools ∪ knowledge), the rejection error format, what's protected against (hallucination, cross-skill access, prompt injection), and practical guidance on declaring dangerous tools per-skill. MCP-Integration: cross-link from the Scope section so MCP-only readers see that MCP-discovered tools go through the same authorization boundary as local tools. References #630 (allowlist enforcement at execution), #631 (fail-fast on typos at agent construction), #632 (safer maxTurns default). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Initial wiki: 29 educational articles Getting Started, Core Concepts, Composition Operators, LLM Integration, Guided Generation, Agent Memory, and Reference articles with full code examples. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>