feat: Microsoft Teams frontend via Power Automate - #2
Merged
Conversation
Bidirectional Teams channel integration without Azure AD or Bot Framework. Send direction POSTs Adaptive Cards to a Power Automate workflow webhook URL. Receive direction accepts POSTs from a Power Automate flow on a dedicated HTTP server. New files: - src/frontend/teams/ (index, actions, formatting) - prompts/teams.md Modified: config schema, index.ts, cli.ts, log.ts Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- formatting: buildAdaptiveCard (text, URL buttons, Submit buttons, empty) - formatting: splitTeamsMessage (paragraph split, line split, hard split) - formatting: stripHtml (tags, entities, nested, Teams mentions) - actions: send_message (success, empty no-op, webhook failure) - actions: get_chat_info, unsupported actions (graceful no-ops), unknown - proxy-fetch: exports verification - graph: exports verification 629 tests total. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Root cause: `--import tsx` resolves tsx from cwd, not the script directory. After moving workspace to ~/.talon/workspace/ (which has no node_modules), all MCP subprocesses failed to start silently. Tools appeared missing. Fix: resolve tsx to its absolute path from Talon's own node_modules: node_modules/tsx/dist/esm/index.mjs Affects: plugin MCP servers, telegram-tools, teams-tools — all fixed. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…elegram talon chat always uses terminal frontend, but config.frontend wasn't overridden — backend spawned teams-tools MCP server, and system prompt loaded teams.md instead of terminal.md. Claude saw send_message tool that doesn't work in terminal. Fix: override config.frontend to "terminal" and rebuild system prompt before backend initialization in talon chat. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
src/backend/claude-sdk/ is 3 levels deep from project root, not 2. ../../node_modules/ resolved to src/node_modules/ (doesn't exist). Teams MCP tools failed to spawn because of this. Terminal worked because plugin.ts (src/core/) is only 2 levels deep. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Root cause: Teams uses string chat IDs like "teams_chat_19:6d5c40..."
which get passed as TALON_CHAT_ID to MCP subprocesses. The gateway
tried Number("teams_chat_19:...") → NaN → context not found.
Fix: gateway.setContext() now stores an optional stringId alongside
the numeric key. handleAction() tries numeric parse first, then
falls back to string ID lookup across active contexts.
The dispatcher passes both numericChatId and string chatId to
context.acquire() so the mapping is established.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adaptive Card TextBlock doesn't support fenced code blocks (```). Messages with code blocks rendered as "Card unsupported" errors. Fix: parse fenced code blocks out of the message text and render them as CodeBlock elements (Adaptive Cards v1.6). Prose stays as TextBlock. Messages with mixed code and text get split into alternating elements. Schema version bumped from 1.4 to 1.6 (required for CodeBlock support). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
CodeBlock element requires schema v1.6 which Power Automate webhooks
don't support ("card couldn't be displayed" error).
Reverted to schema v1.4 with a workaround: fenced code blocks are
parsed out and rendered as monospace TextBlocks inside grey Containers
(style="emphasis"). Not as pretty as native code blocks but renders
correctly in all Teams clients.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Teams Adaptive Card TextBlock supports **bold**, _italic_, [links] but NOT backtick inline code. Inline backticks caused broken rendering. Now strips `code` → code in TextBlock prose. Fenced code blocks still render as monospace Containers (confirmed working in Test 3). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…d not headings Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replaced regex-based code block parsing with marked's AST tokenizer. Each markdown token type maps to the right Adaptive Card element: paragraph → TextBlock (bold/italic preserved, inline backticks stripped) heading → bold TextBlock with Medium size code block → monospace TextBlock in emphasis Container (grey box) list → TextBlock with bullet/number prefixes blockquote → emphasis Container with subtle text hr → subtle line No regex hacks — the marked lexer handles all markdown parsing. Inline backticks stripped via cleanInline() since Teams doesn't support them. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
TextBlock with wrap:true collapses newlines into spaces. Now each line of a code block is a separate TextBlock with spacing:None inside the emphasis Container, preserving the original formatting. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Teams TextBlock collapses consecutive spaces. Replace with non-breaking spaces (U+00A0) in code block lines to preserve column alignment in tables and formatted output. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
dylanneve1
added a commit
that referenced
this pull request
Apr 10, 2026
- Validate mcpServer.args elements are strings and reject empty command (#1) - Shell-quote interpolated paths in dream bash commands (#2, #11) - Replace CLI-based diary write with mempalace_diary_write MCP tool (#3) - Make validation error message platform-agnostic (#4) - Update mempalacePython comment for platform-dependent default (#5) - Wrap mp.init() in Promise.race with 30s timeout (#6) - Make init conditional on successful validation, pass actual config (#7) - Move import mempalace check into validateConfig (#8) - Replace execFileSync with async execFile in init() (#9) - Document that registerPlugin does NOT call init (#10) - Update dream prompt header from "4-stage" to "5-stage" (#12) - Update getPluginMcpServers JSDoc to document mcpServer path (#13, #17) - Add .min(1) to palacePath/pythonPath zod schemas (#14) - Distinguish ENOENT/EACCES/EPERM from import failures in validation (#15) - Fix test name from "logs warning" to match actual behavior (#16) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
dylanneve1
added a commit
that referenced
this pull request
Apr 10, 2026
* feat: integrate mempalace as built-in plugin for long-term memory Adds mempalace (Python MCP server) as a first-class memory system. When enabled, the agent gets semantic search, knowledge graph, and verbatim memory storage via ChromaDB — all local, zero API calls. Key changes: - Extend plugin system with `mcpServer` field for non-Node MCP servers - Add `registerPlugin()` for built-in plugin registration - Create mempalace plugin (factory pattern, validates python venv) - Wire mempalace into dream mode (Stage 5: mine logs into palace) - Add `mempalace` config schema (enabled, palacePath, pythonPath) - Add default paths for palace dir and python venv binary Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor(dream): mine daily notes instead of raw logs, add diary writing Dream Stage 5 now mines memory/daily/ (curated observations) instead of raw logs/ directory, eliminating junk chunks (tool JSON, df output, etc). Added personal diary writing instruction — agent reflects on feelings, state of mind, learnings, and loose threads after each dream run. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: address PR #27 review comments - plugin.ts: validate mcpServer.args entries are strings and reject empty command - dream.ts: quote interpolated paths in shell commands, replace mcp_server CLI diary with direct file write - mempalace/index.ts: platform-agnostic error message for missing python binary - paths.ts: update comment to reflect platform-dependent venv path - bootstrap.ts: wrap mempalace init in 30s timeout to match loadSinglePlugin behavior Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: restore mempalace CLI diary writer, keep path quoting Copilot suggested removing the mcp_server CLI invocation for diary writing but that's the intended mempalace interface. Restored it with quoted paths. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * test: add gating/validation tests for mempalace integration - plugin.ts: test rejection of empty mcpServer.command and non-string args elements - dream.ts: test mempalace section gating — verify mining/diary instructions only appear when mempalace is configured, skip message when not - 1306 tests passing (4 new) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: upgrade mempalace system prompt with comprehensive tool docs Adapted from mempalace SKILL.md (v3.1.0). Key improvements: - Session protocol (verify before responding, invalidate stale facts) - Full tool documentation including kg_timeline, traverse, find_tunnels, diary_read/write, delete_drawer, graph_stats, check_duplicate - Semantic search tips (meaning-based, not keyword) - Knowledge graph temporal validity guidance - Tests updated to verify all tool names appear in prompt Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor: extract mempalace prompt to prompts/mempalace.md Move system prompt instructions out of TypeScript into a .md file, matching the pattern used by dream.md and other prompts. Plugin loads and interpolates {{palacePath}} at runtime with graceful fallback. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: replace pixi.intel.com registry URLs in lockfile with npmjs.org Lockfile had resolved URLs pointing to pixi.intel.com (private/corporate registry) for @Anthropic-AI packages, causing CI to fail with ENOTFOUND. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: resolve all lint warnings and formatting issues Remove unused imports, variables, and catch bindings across 14 files. Add yield statements to generator function mocks. Fix prettier formatting. 0 lint warnings, 0 format issues, 1307 tests passing. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: address all 17 Copilot review comments on PR #27 - Validate mcpServer.args elements are strings and reject empty command (#1) - Shell-quote interpolated paths in dream bash commands (#2, #11) - Replace CLI-based diary write with mempalace_diary_write MCP tool (#3) - Make validation error message platform-agnostic (#4) - Update mempalacePython comment for platform-dependent default (#5) - Wrap mp.init() in Promise.race with 30s timeout (#6) - Make init conditional on successful validation, pass actual config (#7) - Move import mempalace check into validateConfig (#8) - Replace execFileSync with async execFile in init() (#9) - Document that registerPlugin does NOT call init (#10) - Update dream prompt header from "4-stage" to "5-stage" (#12) - Update getPluginMcpServers JSDoc to document mcpServer path (#13, #17) - Add .min(1) to palacePath/pythonPath zod schemas (#14) - Distinguish ENOENT/EACCES/EPERM from import failures in validation (#15) - Fix test name from "logs warning" to match actual behavior (#16) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: add 'mempalace' to LogComponent type TypeScript type check was failing because 'mempalace' wasn't in the LogComponent union type used by log/logError/logWarn functions. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: allow MCP tools in dream prompt when required by Stage 5 Update tool access statement to permit MCP tools for mempalace mining stage instead of blanket-blocking all MCP tools. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: duplicate guard in registerPlugin, pass MCP servers to dream - registerPlugin now checks for duplicates before setting env vars or logging success, preventing misleading logs and env clobbering - Dream agent now receives mempalace MCP servers when configured, so Stage 5 diary/mining tools actually work Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: add selective MCP server loading via 'only' filter getPluginMcpServers now accepts an optional plugin name filter: - omitted = all plugins (backwards compatible for chat sessions) - [] = none - ["mempalace"] = only mempalace Dream mode uses ["mempalace"] to load only what it needs. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: load mempalace prompt from dirs.prompts, fix dream systemPrompt - Mempalace prompt now loads from ~/.talon/prompts/mempalace.md (user-customisable, seeded on first run) instead of relative to source file. Consistent with heartbeat/dream prompt loading. - Dream systemPrompt now permits MemPalace MCP tools when configured, preventing conflict with the markdown prompt's Stage 5 instructions. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: move duplicate check before validation, gate dream on plugin registration - registerPlugin checks for duplicates before running validateConfig, avoiding expensive re-validation on accidental double registration - Dream mempalace integration now gated on getPlugin("mempalace") instead of just config.mempalace.enabled, so failed validation or registration doesn't cause dream-time MCP tool failures Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(mempalace): correct CLI arg order for status check The --palace flag is a global option that must come before the subcommand. Wrong order caused the init health check to always fail with exit 2, logging a misleading "not yet initialized" warning. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: address Copilot review round 8 — validation, error handling, unused param - Validate `import mempalace.mcp_server` (actual spawned module) instead of just `import mempalace` in validateConfig - Add timeout/killed error branching in validateConfig catch block (ETIMEDOUT, signal, killed) with specific messages instead of generic "not installed" - Include stderr details in import failure messages for debugging - Remove unused `config` from ProcessAndReplyParams and all processAndReply call sites (flushQueue, retry, callback handler) - Replace `mempalace status` CLI smoke test in init() with a simple import check — fixes false "Palace not yet initialized" warning when palace IS initialized but CLI subcommand doesn't exist Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: remove config from message queue chain, fix pythonPath comment - Remove config from queue entry type, enqueueMessage signature, and all 3 call sites — completes the cleanup started in round 8 - Eliminates unnecessary TalonConfig reference (including botToken) from queue state - Update mempalace plugin header comment to document platform-dependent pythonPath default (bin/python on Unix, Scripts/python.exe on Windows) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
dylanneve1
pushed a commit
that referenced
this pull request
May 7, 2026
* chore(deps): bump hono in lockfile to close CVE alert Closes Dependabot alert #2 (hono <4.12.14, HTML injection in JSX SSR). The lockfile was pinning hono@4.12.12 even though node_modules already had 4.12.16 installed (verified via `npm ls hono`). GitHub reads the lockfile, so the alert kept firing despite the actually-installed version being unaffected. `npm update hono @hono/node-server --include=optional` resolves both to the latest version satisfying the existing transitive constraints (`^4.11.4`, `^4`). Followed by clean install to ensure node_modules matches. - hono: 4.12.12 -> 4.12.16 - @hono/node-server: 1.19.13 -> 1.19.14 - emnapi optional-dep placement reshuffle (npm dedupe, no behavior change) Tests: 1635/1635 passed. tsc clean. lint 0 errors. Note: leaves @anthropic-ai/sdk Dependabot alert #3 untouched -- that one needs an `overrides` block or upstream SDK bump and was flagged for live review with Dylan. * fix(deps): surgical lockfile bump (only hono entries) to fix CI The previous npm install --include=optional regenerated the entire optional-dep tree, removing @emnapi/core@1.10.0 entries that CI's plain 'npm ci' (no --include=optional) needs. Reverting to main's lockfile and only patching the hono and @hono/node-server entries keeps the diff surgical and cross-platform. Verified: 'npm ci' (no flags), 1635/1635 tests, tsc clean, 0 lint errors.
This was referenced May 12, 2026
3 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
markedlexerKey changes
src/frontend/teams/— 6 files: index, actions, tools, graph, formatting, proxy-fetchprompts/teams.md— Teams-specific formatting rules for Claudetalon chatoverrides config.frontend to prevent wrong tools leakingFixes included
Test plan
🤖 Generated with Claude Code