feat(kanban): validate dispatch capabilities before claim

.github/workflows/tests.yml

@@ -97,9 +97,18 @@ jobs:
         # fails if the lock is out of sync with pyproject.toml), giving a
         # reproducible env. It also creates .venv itself, so no separate
         # `uv venv` step is needed.
+        #
+        # The trailing extras beyond all/dev are the lazy-install features
+        # (tools/lazy_deps.py) that tests exercise for real: provider.anthropic,
+        # stt/tts.mistral, image.fal, terminal.modal, terminal.daytona,
+        # memory.hindsight, search.parallel. The hermetic test env forbids
+        # mid-run pip installs (HERMES_DISABLE_LAZY_INSTALLS=1 in
+        # tests/conftest.py), so the SDKs those tests need must be in the
+        # venv up front — resolved from uv.lock like everything else, which
+        # also honors the exact supply-chain pins these extras carry.
         uses: ./.github/actions/retry
         with:
-          command: uv sync --locked --python 3.11 --extra all --extra dev
+          command: uv sync --locked --python 3.11 --extra all --extra dev --extra anthropic --extra mistral --extra fal --extra modal --extra daytona --extra hindsight --extra parallel-web
 
       - name: Minimize uv cache
         # Optimized for CI: prunes pre-built wheels that are cheap to
@@ -216,9 +225,14 @@ jobs:
         # fails if the lock is out of sync with pyproject.toml), giving a
         # reproducible env. It also creates .venv itself, so no separate
         # `uv venv` step is needed.
+        #
+        # Same extras as the test job's sync above: the hermetic test env
+        # forbids mid-run pip installs (HERMES_DISABLE_LAZY_INSTALLS=1 in
+        # tests/conftest.py), so lazy-install SDKs exercised by tests must be
+        # in the venv up front.
         uses: ./.github/actions/retry
         with:
-          command: uv sync --locked --python 3.11 --extra all --extra dev
+          command: uv sync --locked --python 3.11 --extra all --extra dev --extra anthropic --extra mistral --extra fal --extra modal --extra daytona --extra hindsight --extra parallel-web
 
       - name: Minimize uv cache
         # Optimized for CI: prunes pre-built wheels that are cheap to

.gitignore

@@ -190,3 +190,7 @@ infographics/
 infograficos/
 infografico/
 native/fts5_cjk/*.so
+# Runtime marker written by hermes update when a lazy dependency refresh is
+# interrupted; consumed by launch-time recovery. Never commit it (was tracked
+# by accident via 3a69e34702, removed in the #72002 salvage).
+.lazy-refresh-incomplete

.plans/message-reactions.md

@@ -0,0 +1,146 @@
+# Message reactions (desktop tapbacks)
+
+Two-way emoji reactions on individual messages in the desktop transcript: the
+user reacts to any message, the agent reacts to a user message, and both sides
+read the other's reactions as conversational signal.
+
+## What already exists
+
+Hermes already models reactions on the **platform** side — the desktop is the
+only surface without them.
+
+| Surface | Reaction support | Where |
+|---|---|---|
+| Agent → platform message | `send_message(action="react"/"unreact")` | `tools/send_message_tool.py:266` `_handle_react()` |
+| Photon / iMessage | tapbacks in + out, routed only for messages we sent | `plugins/platforms/photon/adapter.py:1240-1283` |
+| Telegram | `setMessageReaction`, config-gated | `plugins/platforms/telegram/adapter.py:9669+` |
+| Slack / Matrix / Feishu / Discord | inbound reaction events → hooks | `gateway/run.py:4688` `_handle_reaction_event()` → `HookRegistry.emit("reaction:added")` |
+| Adapter contract | `add_reaction()` / `remove_reaction()` coroutines, `set_reaction_handler()` | `gateway/platforms/base.py:3330` |
+| Core "affection" detector | regex on user text → `vibe`, drives CLI pet / TUI heart / desktop hearts | `agent/reactions.py`, `agent/turn_context.py:592-604` |
+
+Two things follow from that table:
+
+1. **The agent-facing verb already exists.** `send_message(action="react")` is
+   the established shape. A desktop reaction should extend that tool, not add a
+   new core tool — every new tool ships on every API call (AGENTS.md footprint
+   ladder).
+2. **The inbound convention already exists.** Photon turns a tapback into a
+   normal message event with `reply_to_message_id` + `reply_to_is_own_message`,
+   and the gateway prefixes `[Replying to your previous message: "…"]`
+   (`gateway/run.py:13125-13132`). Desktop reactions should read the same way to
+   the model.
+
+Nothing exists on the desktop side: `grep -ri reaction` across `apps/desktop`
+finds only the pet-overlay hearts.
+
+## Prior art
+
+**iOS Tapback** ([Apple](https://support.apple.com/guide/iphone/react-with-tapbacks-iph018d3c336/ios)):
+double-tap or touch-and-hold a message → floating pill above the bubble with
+heart / thumbs-up / thumbs-down / haha / ‼️ / ❓, swipe left for suggested emoji
+and stickers, or tap the emoji button for the full keyboard. **One tapback per
+message per person** — tapping the same one again removes it, tapping a
+different one replaces it. Multiple people's tapbacks stack on the badge.
+
+**Platform data models** converge on the same shape:
+
+| Platform | Model | Add / remove |
+|---|---|---|
+| Slack | `{name, count, users[]}` | [`reactions.add`](https://docs.slack.dev/reference/methods/reactions.add) / `reactions.remove`, emits `reaction_added` |
+| Discord | `{emoji, count, me}` on the message object | `PUT`/`DELETE .../reactions/{emoji}/@me` |
+| Telegram | `reaction: [{type:"emoji", emoji:"👍"}]` — replaces the whole set | `setMessageReaction`, `is_big` for the big animation |
+
+Telegram's "set the whole array" is the closest match to iOS semantics and the
+simplest thing to persist.
+
+**assistant-ui has no reaction primitive.** `@assistant-ui/react` 0.14.24 (MIT,
+vendored at `apps/desktop/node_modules`): zero hits for "reaction" in `core/src`,
+`react/src`, `dist/`, or the 2.2 MB `llms-full.txt` docs dump. What exists is a
+hard-coded binary `FeedbackAdapter` (`"positive" | "negative"`,
+`core/src/adapters/feedback.ts`) that throws when unconfigured and only writes
+back onto assistant messages. Not usable for emoji, not usable on user messages.
+
+**But `metadata.custom` is the supported extension channel** and this repo
+already uses it: `ThreadUserMessage`/`ThreadAssistantMessage`/`ThreadSystemMessage`
+all carry `metadata.custom: Record<string, unknown>` (`core/src/types/message.ts:319-366`),
+and `chat-runtime.ts:397` already ships `custom: { attachmentRefs }` through it.
+
+**Emoji picker survey** (npm week of 2026-07-22, sizes measured from the
+published ESM entry):
+
+| Library | License | Weekly DL | gzip | Headless | Latest |
+|---|---|---|---|---|---|
+| **frimousse** | MIT | 573k | **8.5 kB** | ✅ fully unstyled, composable parts | 0.3.0 · 2025-07-15 |
+| emoji-picker-react | MIT | 1.31M | 87 kB | ❌ own CSS-in-JS (flairup) | 4.19.1 · 2026-04-27 |
+| emoji-mart | MIT | 2.22M | ~120 kB w/ data | ❌ Preact + shadow styling | 5.6.0 · **2024-04-25**, 217 open issues |
+| emoji-picker-element | Apache-2.0 | 183k | — | ❌ Web Component / Shadow DOM | 1.29.1 · 2026-03-01 |
+
+No picker is currently a dependency (only `emoji-regex`, transitive). Already
+paid for and reusable: `radix-ui` (Popover), `motion`, `@tanstack/react-virtual`,
+Tailwind v4.
+
+## Recommendation
+
+**Hand-roll the tapback pill; add frimousse only behind the "+".** Six fixed
+emoji in a pill is ~40 lines of JSX against existing tokens — pulling 87 kB of
+`emoji-picker-react` to render six buttons, plus a CSS engine that fights
+`DESIGN.md`, is backwards. frimousse is headless, dependency-free, 10× smaller,
+and exposes `emojibaseUrl` so the data can be bundled as a Vite asset instead of
+hitting jsDelivr (Electron must work offline).
+
+### Data model
+
+One reaction per author per message, Telegram-style whole-set replacement:
+
+```ts
+type MessageReaction = { emoji: string; author: 'user' | 'agent'; at: number }
+```
+
+Persisted in the existing `messages.display_metadata` JSON column
+(`hermes_state_common.py:215`) — no new table. It already survives insert,
+compaction, and every read projection, and
+`set_latest_matching_message_display_kind()` (`hermes_state.py:5292`) is the
+precedent for stamping metadata onto an already-persisted row.
+
+### Model context
+
+Reactions must reach the model **without breaking prompt caching**. The
+`api_messages` build loop strips `display_metadata` from every outgoing copy
+(`agent/conversation_loop.py:1443-1446`) precisely so display state never
+becomes a provider field. Two candidate paths:
+
+| Path | Cache impact | Notes |
+|---|---|---|
+| Rewrite the reacted-to message's content to carry the annotation | **Breaks the cached prefix** — mutates past context | Rejected. AGENTS.md: prompt caching is sacred. |
+| Deliver the reaction as the *next* turn's leading annotation, mirroring photon | Prefix untouched; only the new turn carries it | Matches `[Replying to your previous message: "…"]` (`gateway/run.py:13125`), which the agent already understands |
+
+The second is the same trick the platform adapters already use, so the model
+sees a familiar shape and no existing conversation is rewritten.
+
+### Attach points
+
+| Concern | File | Lines |
+|---|---|---|
+| Assistant hover bar | `apps/desktop/src/components/assistant-ui/thread/assistant-message.tsx` | 134–175 |
+| User hover cluster | `apps/desktop/src/components/assistant-ui/thread/user-message.tsx` | 296–336 |
+| Callback threading (ref caveat 79–99) | `apps/desktop/src/components/assistant-ui/thread/index.tsx` | 109–133 |
+| `metadata.custom` → runtime | `apps/desktop/src/lib/chat-runtime.ts` | 384–432 |
+| RPC client ↔ server pattern | `sidebar/session-actions-menu.tsx:62-89` ↔ `tui_gateway/server.py:8322` | — |
+| Persistence | `hermes_state_common.py:192-216`, `hermes_state.py:5292-5324` | — |
+| Prompt injection / strip | `agent/conversation_loop.py` | 1430–1529 |
+
+### Known gaps to solve first
+
+- **No durable message id crosses the gateway RPC path.** `_history_to_messages()`
+  (`tui_gateway/server.py:6545`) builds `{"role", "text"}` and drops the id. The
+  REST path carries `messages.id` incidentally via `SELECT *` but TS
+  `SessionMessage` (`types/hermes.ts:513-533`) doesn't declare it. Renderer ids
+  are ephemeral and change shape between rehydrated (`<ts>-<i>-<role>`), live
+  (`assistant-<ms>`), and optimistic (`user-<ms>-<rand>`) messages. A reaction
+  needs a stable key — this is the first thing to fix.
+- **WeakMap identity cache** in `apps/desktop/src/app/chat/runtime-repository.ts:26-66`
+  keys normalized `ThreadMessage` by `ChatMessage` identity. A reaction change
+  must produce a **new** `ChatMessage` object or the UI renders stale.
+- **Rewind rewrites rows** (`replace_messages`), so anything keyed by row id
+  needs cascade handling — an argument for keeping reactions in
+  `display_metadata` on the row itself rather than a side table.

README.md

@@ -26,7 +26,7 @@ Use any model you want — [Nous Portal](https://portal.nousresearch.com), OpenR
 <tr><td><b>A closed learning loop</b></td><td>Agent-curated memory with periodic nudges. Autonomous skill creation after complex tasks. Skills self-improve during use. FTS5 session search with LLM summarization for cross-session recall. <a href="https://github.com/plastic-labs/honcho">Honcho</a> dialectic user modeling. Compatible with the <a href="https://agentskills.io">agentskills.io</a> open standard.</td></tr>
 <tr><td><b>Scheduled automations</b></td><td>Built-in cron scheduler with delivery to any platform. Daily reports, nightly backups, weekly audits — all in natural language, running unattended.</td></tr>
 <tr><td><b>Delegates and parallelizes</b></td><td>Spawn isolated subagents for parallel workstreams. Write Python scripts that call tools via RPC, collapsing multi-step pipelines into zero-context-cost turns.</td></tr>
-<tr><td><b>Runs anywhere, not just your laptop</b></td><td>Six terminal backends — local, Docker, SSH, Singularity, Modal, and Daytona. Daytona and Modal offer serverless persistence — your agent's environment hibernates when idle and wakes on demand, costing nearly nothing between sessions. Run it on a $5 VPS or a GPU cluster.</td></tr>
+<tr><td><b>Runs anywhere, not just your laptop</b></td><td>Seven terminal backends — local, Docker, SSH, Singularity, Modal, Daytona, and Vercel Sandbox. Daytona and Modal offer serverless persistence — your agent's environment hibernates when idle and wakes on demand, costing nearly nothing between sessions. Run it on a $5 VPS or a GPU cluster.</td></tr>
 <tr><td><b>Research-ready</b></td><td>Batch trajectory generation, trajectory compression for training the next generation of tool-calling models.</td></tr>
 </table>
 

agent/agent_init.py

@@ -1161,8 +1161,8 @@ def init_agent(
                 client_kwargs["default_headers"] = hermes_xai_default_headers()
             elif "default_headers" not in client_kwargs:
                 # Fall back to profile.default_headers for providers that
-                # declare custom headers (e.g. Kimi User-Agent on non-kimi.com
-                # endpoints).
+                # declare custom headers (e.g. Vercel AI Gateway attribution,
+                # Kimi User-Agent on non-kimi.com endpoints).
                 try:
                     from providers import get_provider_profile as _gpf
                     _ph = _gpf(agent.provider)

agent/auxiliary_client.py

@@ -543,6 +543,7 @@ def _get_aux_model_for_provider(provider_id: str) -> str:
     "kimi-coding-cn": "kimi-k2-turbo-preview",
     "gmi": "google/gemini-3.1-flash-lite-preview",
     "anthropic": "claude-haiku-4-5-20251001",
+    "ai-gateway": "google/gemini-3-flash",
     "opencode-zen": "gemini-3-flash",
     "opencode-go": "glm-5",
     "kilocode": "google/gemini-3.6-flash",
@@ -729,6 +730,15 @@ def build_nvidia_nim_headers(base_url: str | None) -> dict:
     return {}
 
 
+# Vercel AI Gateway app attribution headers. HTTP-Referer maps to
+# referrerUrl and X-Title maps to appName in the gateway's analytics.
+from hermes_cli import __version__ as _HERMES_VERSION
+
+_AI_GATEWAY_HEADERS = {
+    "HTTP-Referer": "https://hermes-agent.nousresearch.com",
+    "X-Title": "Hermes Agent",
+    "User-Agent": f"HermesAgent/{_HERMES_VERSION}",
+}
 
 # Nous Portal extra_body for product attribution.
 # Callers should pass this as extra_body in chat.completions.create()
@@ -5725,7 +5735,8 @@ def _wrap_if_needed(client_obj, final_model_str: str, base_url_str: str = "",
         else:
             # Fall back to profile.default_headers for providers that declare
             # client-level attribution headers on their profile (e.g. GMI
-            # User-Agent for traffic identification).
+            # User-Agent for traffic identification, Vercel AI Gateway
+            # Referer/Title for analytics).
             try:
                 from providers import get_provider_profile as _gpf_main
                 _ph_main = _gpf_main(provider)

agent/conversation_loop.py

@@ -1445,6 +1445,12 @@ def run_conversation(
             api_msg.pop("display_kind", None)
             api_msg.pop("display_metadata", None)
 
+            # Durable row identity stamped by _rows_to_conversation so the
+            # desktop can address a specific persisted message (reactions).
+            # Bookkeeping, never a provider field — only the chat-completions
+            # transport strips underscore keys, so drop it centrally here.
+            api_msg.pop("_row_id", None)
+
             # Inject ephemeral context into the current turn's user message.
             # Sources: memory manager prefetch + plugin pre_llm_call hooks
             # with target="user_message" (the default).  Both are

agent/model_metadata.py

@@ -72,7 +72,7 @@ def _resolve_requests_verify() -> bool | str:
 _PROVIDER_PREFIXES: frozenset[str] = frozenset({
     "openrouter", "nous", "openai-codex", "copilot", "copilot-acp",
     "gemini", "ollama-cloud", "zai", "kimi-coding", "kimi-coding-cn", "stepfun", "minimax", "minimax-oauth", "minimax-cn", "anthropic", "deepseek", "deepinfra",
-    "opencode-zen", "opencode-go", "kilocode", "alibaba", "novita",
+    "opencode-zen", "opencode-go", "ai-gateway", "kilocode", "alibaba", "novita",
     "qwen-oauth",
     "xiaomi",
     "arcee",
@@ -84,7 +84,7 @@ def _resolve_requests_verify() -> bool | str:
     "glm", "z-ai", "z.ai", "zhipu", "github", "github-copilot",
     "github-models", "kimi", "moonshot", "kimi-cn", "moonshot-cn", "claude", "deep-seek", "deep-infra",
     "ollama",
-    "stepfun", "opencode", "zen", "go", "kilo", "dashscope", "aliyun", "qwen",
+    "stepfun", "opencode", "zen", "go", "vercel", "kilo", "dashscope", "aliyun", "qwen",
     "mimo", "xiaomi-mimo",
     "tencent", "tokenhub", "tencent-cloud", "tencentmaas",
     "arcee-ai", "arceeai",

agent/models_dev.py

@@ -168,6 +168,7 @@ class ProviderInfo:
     "alibaba": "alibaba",
     "qwen-oauth": "alibaba",
     "copilot": "github-copilot",
+    "ai-gateway": "vercel",
     "opencode-zen": "opencode",
     "opencode-go": "opencode-go",
     "kilocode": "kilo",

agent/prompt_builder.py

@@ -981,7 +981,7 @@ def format_steer_marker(steer_text: str) -> str:
 # misleading — the agent should only see the machine it can actually touch.
 _REMOTE_TERMINAL_BACKENDS = frozenset({
     "docker", "singularity", "modal", "daytona", "ssh",
-    "managed_modal",
+    "vercel_sandbox", "managed_modal",
 })
 
 
@@ -995,6 +995,7 @@ def format_steer_marker(steer_text: str) -> str:
     "modal": "a Modal sandbox (Linux)",
     "managed_modal": "a managed Modal sandbox (Linux)",
     "daytona": "a Daytona workspace (Linux)",
+    "vercel_sandbox": "a Vercel sandbox (Linux)",
     "ssh": "a remote host reached over SSH (likely Linux)",
 }
 
@@ -1069,7 +1070,7 @@ def _probe_remote_backend(env_type: str) -> str | None:
             }
 
         container_config = None
-        if env_type in {"docker", "singularity", "modal", "daytona"}:
+        if env_type in {"docker", "singularity", "modal", "daytona", "vercel_sandbox"}:
             container_config = {
                 "container_cpu": config.get("container_cpu", 1),
                 "container_memory": config.get("container_memory", 5120),
@@ -1159,7 +1160,7 @@ def build_environment_hints() -> str:
       and a Windows-only note that `terminal` shells out to bash, not
       PowerShell).
     - For **remote / sandbox** terminal backends (docker, singularity,
-      modal, daytona, ssh): host info is **suppressed**
+      modal, daytona, ssh, vercel_sandbox): host info is **suppressed**
       because the agent's tools can't touch the host — only the backend
       matters. A live probe inside the backend reports its OS, user, $HOME,
       and cwd. Falls back to a static summary if the probe fails.

agent/usage_pricing.py

@@ -1244,8 +1244,8 @@ def normalize_usage(
         output_tokens = _to_int(getattr(response_usage, "completion_tokens", 0))
         details = getattr(response_usage, "prompt_tokens_details", None)
         # Primary: OpenAI-style prompt_tokens_details. Fallback: Anthropic-style
-        # top-level fields that some OpenAI-compatible proxies (OpenRouter, Cline)
-        # expose when routing Claude models — without this
+        # top-level fields that some OpenAI-compatible proxies (OpenRouter, Vercel
+        # AI Gateway, Cline) expose when routing Claude models — without this
         # fallback, cache writes are undercounted as 0 and cache reads can be
         # missed when the proxy only surfaces them at the top level.
         # Port of cline/cline#10266.

apps/bootstrap-installer/src-tauri/Cargo.toml

@@ -66,6 +66,10 @@ windows-sys = { version = "0.59", features = [
     "Win32_UI_WindowsAndMessaging",
 ] }
 
+# Signal-0 liveness probe for the update-lock marker owner (update.rs).
+[target.'cfg(unix)'.dependencies]
+libc = "0.2"
+
 [profile.release]
 # A 5-10MB signed installer is the goal. LTO + size-opt + single codegen unit.
 panic = "abort"