@oar-sh/oar 0.9.15 → 0.9.17

package/.github/extensions/web-relay/polling/polling-loop.mjs

@@ -9,6 +9,14 @@ import { DEFAULT_QUESTION_TIMEOUT_MS } from "../../../../shared/question-timeout
 import { waitForRelayQuestion } from "../../../../shared/question-wait.mjs";
 import { EMPTY_TURN_COMPLETION_NOTE } from "../../../../shared/empty-turn-completion.mjs";
 import { stripPromptContextPrefix } from "../skills/prompt-context.mjs";
+import {
+  isOpenAIImageTerminalError,
+  runDirectOpenAIImageTurn,
+  shouldUseDirectOpenAIImageApi,
+} from "../../../../shared/worker-runtime/direct-openai-image.mjs";
+
+// Re-exported for the extension's tests, which import it from here.
+export { shouldUseDirectOpenAIImageApi };
 
 function isImageAttachment(att) {
   const type = String(att?.type || "").toLowerCase();
@@ -257,28 +265,6 @@ export function resolveEmptyFinalTextHandling({ lastStreamedSent = "", lastActiv
   };
 }
 
-export function shouldUseDirectOpenAIImageApi(message = {}) {
-  const providerType = String(message?.providerType || "").trim().toLowerCase();
-  if (providerType !== "openai") return false;
-  const model = String(message?.providerModel || message?.model || "").trim().toLowerCase();
-  return model.startsWith("gpt-image-") || model.startsWith("dall-e-");
-}
-
-function isDirectOpenAIImageTerminalStatus(status) {
-  const numeric = Number(status);
-  if (!Number.isFinite(numeric)) return false;
-  return (
-    numeric === 400
-    || numeric === 401
-    || numeric === 403
-    || numeric === 404
-    || numeric === 409
-    || numeric === 422
-    || numeric === 429
-    || numeric === 503
-  );
-}
-
 export async function publishRelayStreamEvent({
   api,
   message,
@@ -681,71 +667,12 @@ export function createPollingLoop({
     let sendAndWaitStartedAtMs = 0;
     const processDirectOpenAIImageRequest = async () => {
       if (!shouldUseDirectOpenAIImageApi(message)) return false;
-      if (message?.imageOperationId) {
-        const result = await api(
-          "POST",
-          `/api/image-operations/${encodeURIComponent(message.imageOperationId)}/execute`,
-          { messageId: message.id },
-        ).catch((error) => {
-          if (error?.status === 409 || error?.status === 503) {
-            return error?.payload || { outcome: error?.status === 503 ? "retryable" : "terminal" };
-          }
-          throw error;
-        });
-        const outcome = String(result?.outcome || "").trim().toLowerCase();
-        if (!["completed", "executing", "terminal", "uncertain", "retryable"].includes(outcome)) {
-          throw new Error("Image operation returned an invalid outcome");
-        }
-        await session.log(`Image operation ${outcome}`, {
-          ephemeral: true,
-        });
-        return true;
-      }
-      const directModel = String(message?.providerModel || requestedManualModelOrNull(message) || message?.model || "").trim();
-      const prompt = String(message?.text || "").trim();
-      if (!directModel) throw new Error("OpenAI image request is missing model");
-      if (!prompt) throw new Error("OpenAI image request is missing prompt");
-      await api("POST", "/api/activity", {
-        messageId: message.id,
-        conversationId: message.conversationId,
-        mode: message.relayMode || "agent",
-        text: `Calling OpenAI image API directly (${directModel})`,
-      }).catch(() => {});
-      let directResult;
-      try {
-        directResult = await api("POST", "/api/openai/images/generate", {
-          messageId: message.id,
-          conversationId: message.conversationId,
-          model: directModel,
-          prompt,
-          n: message?.n,
-          size: message?.size || message?.contextTier,
-          quality: message?.quality || message?.reasoningEffort,
-          attachments: Array.isArray(message?.attachments) ? message.attachments : [],
-        });
-      } catch (error) {
-        if (isDirectOpenAIImageTerminalStatus(error?.status)) {
-          const terminalError = new Error(
-            `OpenAI image request failed: ${error?.detail || `HTTP ${error?.status || "error"}`}`,
-          );
-          terminalError.code = "RELAY_OPENAI_IMAGE_TERMINAL";
-          throw terminalError;
-        }
-        throw error;
-      }
-      const generatedImages = Array.isArray(directResult?.generatedImages) ? directResult.generatedImages : [];
-      if (!generatedImages.length) {
-        throw new Error("OpenAI image API returned no images");
+      const result = await runDirectOpenAIImageTurn({ api, message });
+      if (result.via === "operation") {
+        await session.log(`Image operation ${result.outcome}`, { ephemeral: true });
+      } else {
+        await session.log(`✅ Sent generated image response (${result.imageCount} image${result.imageCount === 1 ? "" : "s"})`, { ephemeral: true });
       }
-      await api("POST", "/api/response", {
-        messageId: message.id,
-        conversationId: message.conversationId,
-        text: "",
-        generatedImages,
-        model: String(directResult?.model || directModel).trim() || directModel,
-        modelOrigin: isAutoRequestedModel(message?.model) ? "auto" : "manual",
-      });
-      await session.log(`✅ Sent generated image response (${generatedImages.length} image${generatedImages.length === 1 ? "" : "s"})`, { ephemeral: true });
       return true;
     };
 
@@ -988,7 +915,7 @@ export function createPollingLoop({
         }).catch(async () => {
           await api("POST", "/api/requeue", { messageId: message.id }).catch(() => {});
         });
-      } else if (String(e?.code || "").trim() === "RELAY_OPENAI_IMAGE_TERMINAL") {
+      } else if (isOpenAIImageTerminalError(e)) {
         await pushRelayStream(lastStreamedSent, true);
         await api("POST", "/api/response", {
           messageId: message.id,

package/CHANGELOG.md

@@ -3,6 +3,311 @@
 All notable changes to OAR are documented here. The format follows
 [Keep a Changelog](https://keepachangelog.com/en/1.1.0/); versions follow semver.
 
+## [0.9.17] — 2026-10-25
+
+Highlights: DeepSeek is a provider of its own. Paste a DeepSeek API key and
+New Chat offers DeepSeek's models, with all four modes, tools, question
+cards, sub-agents and reasoning effort, the 1M context window, a usage card
+with the balance and the estimated spend, and an import of earlier usage
+from DeepSeek's usage export. A new session in a group now shows
+at the top of the group. And the relay's own Anthropic credentials
+(`ANTHROPIC_API_KEY`, `ANTHROPIC_AUTH_TOKEN`) no longer reach the agents it
+starts.
+
+### Added
+
+- **DeepSeek is a provider of its own.** Paste a DeepSeek API key in
+  Settings → Providers → DeepSeek, and New Chat offers DeepSeek with the
+  models DeepSeek lists (`deepseek-flash` by default, `deepseek-v4-pro`).
+  - A DeepSeek chat runs Claude Code on the relay host against DeepSeek's
+    Anthropic-compatible API, so it has all four modes, tools, question
+    cards, sub-agents, steering, Stop and background tasks.
+  - Reasoning effort is low, high or max (high by default). The model can
+    change between turns; a switch to a model without image input is
+    refused once the chat holds images.
+  - The context panel shows the 1M window, and the chat compacts at 400K
+    unless you set another window there.
+  - Commits carry `Open Agent Relay (DeepSeek Flash)` or no attribution, as
+    set on the DeepSeek tab.
+  - The key is stored on the relay host, is never sent to browsers, and
+    reaches only DeepSeek's workers. Their Claude Code keeps its state in a
+    directory of its own, without your Claude login. The tab's Advanced
+    section takes another base URL (https, or http on the same machine).
+  - The chat folder's settings can't route the key elsewhere. A
+    `.claude/settings.json` or `.claude/settings.local.json` there that sets
+    `ANTHROPIC_BASE_URL`, a key of its own or an `apiKeyHelper` took the
+    DeepSeek key to that endpoint, or replaced it; the relay now pins
+    DeepSeek's endpoint and key over the folder's settings, and with them
+    the proxy, TLS trust, provider and credential settings, without putting
+    the key on the command line, and sends nothing when Claude Code doesn't
+    take them within a minute (`scripts/deepseek-cli-proof.mjs` shows it on
+    the bundled Claude Code). This covers settings, not commands: hooks and
+    a status line in those files still run as the relay's user, as in any
+    Claude Code chat, so use DeepSeek chats only in folders you trust.
+  - The agent's own commands can read the key from their environment, as
+    with any key a CLI holds. The relay replaces it with `[redacted]` in
+    everything a worker posts (replies, thoughts, tool activity, sub-agent
+    text, questions, task output), including the first part of a key cut
+    short at a text's end or before an ellipsis, the last part of one a
+    text starts with, and keys changed since the relay started, before it
+    stores or shows it; the DeepSeek worker does the same in its log. Task
+    output the relay reads from a task's file is scrubbed by shape only
+    (`sk-` keys and other long tokens), not by the saved key's exact text.
+    This keeps the key out of what the relay stores and shows; it is no
+    barrier against the agent, which can change the text, call the relay's
+    local API without the worker header or read the relay's database.
+  - The usage view has a DeepSeek card: the account balance, read with the
+    saved key, and the estimated spend of DeepSeek turns on this relay, by
+    model, from DeepSeek's published prices with peak and off-peak hours
+    (the card names the peak hours in your browser's time zone). On Chinese
+    public holidays DeepSeek charges off-peak prices all day; the estimate
+    doesn't know those dates, so turns at peak hours on a holiday are
+    counted at double the real price. Only WebSearch runs on DeepSeek's
+    servers: its searches are counted at $0.75 / ¥5 per 1,000 requests from
+    2026-10-31 16:00 UTC, on a "Search" row of their own, taken from Claude
+    Code's own totals, which count the request its WebSearch tool makes.
+    WebFetch reads the page on the relay host and costs only tokens, and
+    DeepSeek does not bill count_tokens requests.
+  - The card draws the money: a balance bar per currency, measured against
+    the balance after its last top-up (kept on the relay; migration 0029
+    notes when it rose), or against a starting balance set on the DeepSeek
+    tab, such as the first top-up, until the next top-up replaces it (typed
+    in again, the same amount too, it counts from then on); the
+    daily spend of the last 30 days as columns stacked by model, with the
+    day's total on hover or tap; where the money goes per model (cache hits, misses,
+    output, searches) with what the cache saved; and a monthly
+    budget bar when a budget is set on the DeepSeek tab, in the currency
+    chosen with it (USD or CNY, named on the bar; a budget saved without one
+    follows the balance's currency), amber near it and red over it, starting
+    over on the 1st (UTC). No chart library; every bar has a text equivalent
+    and every chart a table, in both themes. The card shows everything at
+    once, figures first (the balance and the spend as label-and-value rows,
+    the tables by model open, the note on the estimate last), and fits a
+    phone's width.
+  - A DeepSeek chat's cold start reads "Starting Claude Code for DeepSeek",
+    and the `preview` tool tells the agent to bind its dev server to
+    127.0.0.1 (every provider).
+  - Sub-agents stay on the chat's model. Claude Code's model aliases are
+    pinned to it, so a sub-agent the agent asks for as "opus" or "sonnet",
+    or one without a model, runs on the chat's model, and one asked for as
+    "haiku" on DeepSeek Flash; before, an alias went to DeepSeek as a Claude
+    model id, which DeepSeek serves by its own mapping (a Flash chat got a
+    V4 Pro sub-agent). A model switch between turns now restarts the chat's
+    Claude Code, like an effort change. A sub-agent's badge names the
+    DeepSeek model, and usage a Claude Code still reports under a Claude
+    name is booked and priced under the DeepSeek model that served it;
+    rows booked under a Claude name earlier are folded in at start-up
+    (migration 0026). The folded rows are priced at one time each, the
+    row's last turn, so a row that spans peak and off-peak turns is
+    approximated (the token part by up to 2×).
+  - **Import usage export** on the DeepSeek tab takes the two CSV files
+    DeepSeek's usage page exports (amount and cost) and shows what was
+    imported. The usage card then shows DeepSeek's own figures for the saved
+    key on the days the export covers, by the export's days, and the
+    estimate on the other days; the card says through when. Only rows in
+    the card's currency are used, and the import says when they won't be.
+    A re-import replaces the key's days it covers, a day with a period that
+    has not ended is left out, and so are export days up to and including
+    the first day of the relay's daily history.
+    `npm run deepseek:import -- amount.csv cost.csv [db-path]` does the same
+    from the shell. The relay's own usage logging is unchanged (migration
+    0030 adds a table of its own).
+
+### Changed
+
+- **A new session in a group shows at the top of the group.** In a group
+  you ordered by hand, a session an agent creates there, one started with
+  the group chosen, or one moved in by its menu used to join at the end;
+  it now comes first, right under the group's first session. The order you
+  set stays, and the next drag numbers the members again from there.
+- **A host's `ANTHROPIC_API_KEY` and `ANTHROPIC_AUTH_TOKEN` no longer reach
+  any worker.** A relay started with either in its environment handed it to
+  every worker it started (Copilot, OpenAI, Cursor, Grok, Claude, Claude
+  Cloud, DeepSeek), on every platform, and Claude Code prefers either to the
+  Claude login. Now no worker gets them, and under tmux the worker's shell
+  also unsets them, so they cannot come back from a tmux server that was
+  already running or from your login profile. Claude chats that ran on such
+  a key now run on the host's Claude login.
+
+### Fixed
+
+- **The Inbox opens at the top, or where you left it.** It used to open at
+  the scroll height of the transcript it replaced, somewhere in the middle of
+  the list. It now opens at the top the first time and afterwards where it
+  was scrolled when you last left it.
+- **The session header on a phone comes in two rows.** ☰, the title and the
+  buttons share the first row, so the title gets the width left after the
+  buttons. The "via agent" line, the watching, watched and scheduled chips
+  and the folder sit side by side on a second row across the header, and a
+  chip no longer breaks inside its text. The desktop header is unchanged.
+- **A DeepSeek chat's failures carry DeepSeek's codes, and their buttons
+  show.** A refused DeepSeek request printed as `relay.claude-api-error`,
+  and a used-up balance or a refused key as `relay.claude-deepseek-balance`
+  or `relay.claude-deepseek-api-key`, which the **Top up DeepSeek** and
+  **DeepSeek settings** buttons never matched. They now print as
+  `relay.deepseek-balance`, `relay.deepseek-api-key`,
+  `relay.deepseek-api-error` and so on, without the Claude account advice.
+- **A relay's Claude login token no longer reaches workers that are not
+  Claude's.** On a relay started with `CLAUDE_CODE_OAUTH_TOKEN` in its
+  environment, the Copilot, OpenAI, Cursor and Grok workers got the token too:
+  on Windows and without tmux through the environment they inherit, and under
+  tmux whenever the launch started the tmux server, which then kept it for
+  every later session. Now only Claude Cloud and Claude workers get it, under
+  tmux through the owner-only file. Local Claude chats on a host that runs on
+  the token alone now get it under tmux as well.
+- **A relay started from inside a Claude Code session no longer hands that
+  session to its workers.** Its variables (`CLAUDECODE`, the session id, the
+  messaging socket and token, entrypoint, `CLAUDE_PID`, `CLAUDE_EFFORT`)
+  reached every worker, with and without tmux, and a DeepSeek chat's Claude
+  Code took itself for a child of the host's session. The launcher now drops
+  them for every provider, and the DeepSeek backend drops them again. The
+  values of one launch (worker kind, model, folder) go into that session's
+  command only, no longer into the environment a tmux server started by the
+  relay kept for every later session. Under tmux that was not enough: a new
+  tmux session starts from the tmux server's own environment, which a
+  server started from inside a Claude Code session, or by an older relay,
+  carried on to every worker. Every worker's command now begins by unsetting
+  the host session's variables and the launch variables it sets no value
+  for, so a stale model or worker kind from an earlier launch is gone too.
+  The host session's variables are matched by family as well as by name
+  (every `CLAUDE_CODE_SESSION_*`, `CLAUDE_CODE_*_SESSION_ID` and
+  `CLAUDE_CODE_MESSAGING_*`, with the SDK host's version and app markers
+  and the Bash cap a relay's Claude worker gives its CLI), so a name a
+  newer Claude Code adds is dropped too; your own `CLAUDE_CODE_*` and
+  `CLAUDE_AGENT_SDK_*` settings stay. A DeepSeek chat's Claude Code also no
+  longer gets the relay's settings for its worker (worker kind, the relay's
+  folders and tools file, `COPILOT_ALLOW_ALL`, `SESSION_ID`);
+  with them the worker log file a relay started from inside a worker
+  session inherited, and, by name, every secret the launch carries no value
+  for (other kinds' and its own alike) that a shell may have exported into
+  the tmux server's environment; the worker's own keys come from its secret
+  file, read after that.
+- **The DeepSeek spend no longer undercounts a Claude Code that started
+  counting over, and no longer double-counts a report that fell behind.**
+  The relay books what a worker's report adds to the session's last totals;
+  totals below them were booked as nothing. Now the worker names its Claude
+  Code process in each report (`runId`; migration 0027 keeps it with the
+  checkpoint): totals below the checkpoint from the same process are a
+  stale report (a retried post, or one delivered after a later one) and
+  book nothing, while from another process they are a CLI counting from
+  zero again on the same session id, booked in full. The web searches and
+  fetches are reported as the process's running counts and booked the same
+  way, so a retried post no longer counts them twice.
+- **The DeepSeek spend no longer books a session's history again after a
+  Claude Code died hard.** Claude Code writes its cost state at exit, so a
+  resumed CLI that was killed left an older snapshot, and the next resume
+  restored totals below what the relay had booked: read as a process
+  counting from zero, the whole restored history was booked once more. The
+  worker no longer reports what the CLI restored: it reports each process's
+  own totals, counted from zero (what the session totals grow by per
+  result; for the first result of a resumed process the turn's own usage,
+  which leaves out what sub-agents spent in that one turn), and the relay
+  books a new process in full and the increase within one. The search and
+  fetch counts keep a run id of their own in the checkpoint (migration
+  0028), so a report with counts only no longer moves the token totals' run
+  id, and a `/clear` in the CLI, which starts a new session id, starts the
+  worker's counts over with it instead of booking the old session's under
+  the new one. A turn that finishes after its Claude Code died (a background
+  task's continuation whose row was still registering) reports under that
+  process, not under the one running by then or as a report from no
+  process, and a result that arrives behind a newer one never lowers the
+  worker's baseline. A late report of an earlier process after a later one
+  started is booked in full, and the later process's next report is booked
+  in full too: the relay cannot tell either from a new process.
+- **OpenAI image models work on the SDK engine again.** A turn on
+  `gpt-image-*` or `dall-e-*` went to the Copilot runtime as a chat turn
+  and failed ("No available capacity was found for the model", or a request
+  rejected as invalid). It now goes to the OpenAI Images API, as on the
+  Extension engine, and an attached image is edited. A refused image request
+  now fails its turn with `relay.image-provider-rejected` instead of staying
+  in progress until the relay ran it again, and an OpenAI chat turn that
+  fails on the SDK engine says OpenAI rather than Copilot.
+
+## [0.9.16] — 2026-10-24
+
+Highlights: agents can file the sessions they start into your session
+groups, change another session's model, mode or other settings, watch other
+sessions with fewer wake-ups (digests, quiet hours, exclusions), and
+schedule prompts that survive a relay restart. Agents can ask you a question
+without stopping their work, and the new Inbox lists every open question
+from this relay and its paired relays in one place. A new switch lets the
+agents of a conversation start sessions themselves.
+
+### Added
+
+- **Agents can put a new session into an existing session group.**
+  `remote_relay` create_session takes `group` (a group id, or its name in
+  any case) on this relay or a paired one, and `relay_info` lists the groups
+  there. An unknown group is refused with the groups listed, and nothing is
+  created. The approval card names the group, and the result carries it. A
+  relay too old for this is refused before anything is created. Renaming
+  and rearranging groups stays the owner's. An argument an action does not
+  take is no longer dropped without a word: create_session refuses it, and
+  the other actions list it in `ignored`.
+- **Agents can change another session's settings.** `remote_relay`
+  update_session sets a session's model, reasoning effort, relay mode,
+  auto-compact window, title, group, thinking or working folder for its next
+  turns, on this relay or a paired one, and answers the settings and what
+  changed. An unknown model is refused with the close matches; a group name
+  that does not exist makes a new group, and `none` takes the session out (a
+  group you made is never removed this way: it stays, shown empty in the
+  sidebar for you to rename or dissolve); a new folder
+  restarts the session's CLI there and is refused while it works. Only a
+  session the agent's own conversation started may be changed freely; any
+  other, yours or another agent's, needs your Allow once per conversation and
+  relay. A failed change still lists what it wrote. An open page shows the
+  change at once.
+- **"Agents in this conversation may start sessions."** A switch in the 🧠
+  settings of a session an agent started lets its agents start sessions
+  themselves, past the one-level rule; the limit of four at work and your
+  first Allow still apply. Only you can set it: agents and paired relays are
+  refused.
+- **Fewer wake-ups for watching agents.** A `remote_relay` subscription takes
+  `digest_minutes` (its events come as one message every N minutes),
+  `quiet_hours` (a daily window in a time zone, crossing midnight and the
+  clock changes included, whose events come as one message when it ends) and
+  `exclude` (sessions a subscription to all leaves out). Questions and errors
+  still come at once, held events survive a restart, and the hourly limit
+  stays on top. A turn the watcher prompted itself and whose finished reply it
+  waited for no longer wakes it a second time with turn_end.
+  `list_subscriptions` shows how many events each subscription holds and when
+  they are due, and the watching chip shows a small digest or quiet-hours hint.
+- **Scheduled prompts that survive a restart.** `remote_relay` schedule
+  queues a prompt at a time (`at`) or every N minutes (`every_minutes`, 5 to
+  10080), into the agent's own conversation or, with the user's approval in
+  ask and plan mode, another session on this relay. The relay keeps it in its
+  database, so a nightly review or a sweep no longer has to be set up again
+  after a deploy. A time missed while the relay was down fires once when it is
+  back, and a repeat waits while the one before is still queued. The message
+  says it is automated and approves nothing. `list_schedules` and `unschedule`
+  manage them, archiving a session ends its schedules, and a conversation
+  holds at most 20. The sidebar marks a scheduled session, and its header
+  lists the schedules with a Cancel button each.
+- **Questions that don't block, and the Inbox.** `remote_relay` ask puts a
+  question for you into the agent's session (up to eight options, a
+  recommendation, a folded detail, and urgency `now` for a push) and returns
+  at once, so the agent goes on with what does not depend on it. Your answer
+  or dismissal reaches it as a relay event, question_answered, without a
+  subscription, and does not count as your message for the agents' loop
+  guard. A lead can ask on behalf of another session, on this relay or a
+  paired one (kept where that session lives); `list_questions` and `withdraw`
+  manage them, and `read_session` lists them with their kind. The new
+  **Inbox** in the sidebar, with its count, lists every pending question
+  across this relay and the paired relays that answer, grouped by relay,
+  with a filter for your sessions or the agents', and what you answered in
+  the last day under a divider. An ask is answered there or in its session,
+  also one on a paired relay; a paired relay's cards open there, and the
+  pairing never carries an answer to a card. Agent text shows as plain text,
+  and on a phone the Inbox is one column with full-width buttons.
+
+### Fixed
+
+- **The agents' loop guard no longer counts the relay's own messages as the
+  user's.** A relay event, the usage-limit follow-up or the note after a
+  restart reset the count of prompts an agent may send to other agents
+  before the user is asked, so two agents that watched each other could go
+  on without the user. Only a message the user wrote resets it now.
+
 ## [0.9.15] — 2026-10-22
 
 Highlights: `oar setup` asks how the relay starts on Windows, at sign-in or

package/README.md

@@ -17,7 +17,7 @@ On Windows, run `irm oar.sh/install.ps1 | iex` in PowerShell. Other ways to inst
 
 ## What OAR does
 
-Coding agents such as GitHub Copilot, Claude Code, Cursor and Grok usually live in a terminal. OAR puts them into a chat you can open anywhere: start a task at your desk, follow it from the sofa, answer the agent's question from your phone. The agents keep running on your own computer, with your files and your logins; OAR passes the conversation back and forth.
+Coding agents such as GitHub Copilot, Claude Code, Cursor, Grok and DeepSeek usually live in a terminal. OAR puts them into a chat you can open anywhere: start a task at your desk, follow it from the sofa, answer the agent's question from your phone. The agents keep running on your own computer, with your files and your logins; OAR passes the conversation back and forth.
 
 ```mermaid
 flowchart LR
@@ -27,7 +27,7 @@ flowchart LR
   end
   subgraph host["Your computer"]
     relay["OAR relay<br/>chats, queue, history, files"]
-    agents["Copilot · OpenAI · Claude<br/>Cursor · Grok"]
+    agents["Copilot · OpenAI · Claude<br/>Cursor · Grok · DeepSeek"]
   end
   cloud["☁️ Claude Cloud<br/>sandbox at Anthropic"]
   phone <--> relay
@@ -45,29 +45,29 @@ flowchart LR
 <table>
 <tr>
 <td width="42%" rowspan="4" valign="top">
-<a href="https://oar.sh/assets/shots/cfmail-mobile.png?v=0.9.15"><picture><source media="(prefers-color-scheme: light)" srcset="https://oar.sh/assets/shots/cfmail-mobile.light.png?v=0.9.15"><img src="https://oar.sh/assets/shots/cfmail-mobile.png?v=0.9.15" alt="OAR on a phone: a finished agent turn in a conversation, with the composer below"></picture></a>
+<a href="https://oar.sh/assets/shots/cfmail-mobile.png?v=0.9.17"><picture><source media="(prefers-color-scheme: light)" srcset="https://oar.sh/assets/shots/cfmail-mobile.light.png?v=0.9.17"><img src="https://oar.sh/assets/shots/cfmail-mobile.png?v=0.9.17" alt="OAR on a phone: a finished agent turn in a conversation, with the composer below"></picture></a>
 <br><sub>On a phone: the same conversations, installable as an app.</sub>
 </td>
 <td width="58%" valign="top">
-<a href="https://oar.sh/assets/shots/cfmail-agents.png?v=0.9.15"><picture><source media="(prefers-color-scheme: light)" srcset="https://oar.sh/assets/shots/cfmail-agents.light.png?v=0.9.15"><img src="https://oar.sh/assets/shots/cfmail-agents.png?v=0.9.15" alt="Background subagents running in parallel in the task panel, each with live token counts, elapsed time, and its own Stop button"></picture></a>
+<a href="https://oar.sh/assets/shots/cfmail-agents.png?v=0.9.17"><picture><source media="(prefers-color-scheme: light)" srcset="https://oar.sh/assets/shots/cfmail-agents.light.png?v=0.9.17"><img src="https://oar.sh/assets/shots/cfmail-agents.png?v=0.9.17" alt="Background subagents running in parallel in the task panel, each with live token counts, elapsed time, and its own Stop button"></picture></a>
 <br><sub>Agents working in parallel, each with live token counts and its own Stop.</sub>
 </td>
 </tr>
 <tr>
 <td valign="top">
-<a href="https://oar.sh/assets/shots/cfmail-question.png?v=0.9.15"><picture><source media="(prefers-color-scheme: light)" srcset="https://oar.sh/assets/shots/cfmail-question.light.png?v=0.9.15"><img src="https://oar.sh/assets/shots/cfmail-question.png?v=0.9.15" alt="A question card in the middle of a turn: the agent offers several choices and a free-text reply"></picture></a>
+<a href="https://oar.sh/assets/shots/cfmail-question.png?v=0.9.17"><picture><source media="(prefers-color-scheme: light)" srcset="https://oar.sh/assets/shots/cfmail-question.light.png?v=0.9.17"><img src="https://oar.sh/assets/shots/cfmail-question.png?v=0.9.17" alt="A question card in the middle of a turn: the agent offers several choices and a free-text reply"></picture></a>
 <br><sub>When the agent needs a decision, it asks, and waits for your answer.</sub>
 </td>
 </tr>
 <tr>
 <td valign="top">
-<a href="https://oar.sh/assets/shots/pingcf-thoughts.png?v=0.9.15"><picture><source media="(prefers-color-scheme: light)" srcset="https://oar.sh/assets/shots/pingcf-thoughts.light.png?v=0.9.15"><img src="https://oar.sh/assets/shots/pingcf-thoughts.png?v=0.9.15" alt="An expanded Thoughts block showing the agent's reasoning above its reply"></picture></a>
+<a href="https://oar.sh/assets/shots/pingcf-thoughts.png?v=0.9.17"><picture><source media="(prefers-color-scheme: light)" srcset="https://oar.sh/assets/shots/pingcf-thoughts.light.png?v=0.9.17"><img src="https://oar.sh/assets/shots/pingcf-thoughts.png?v=0.9.17" alt="An expanded Thoughts block showing the agent's reasoning above its reply"></picture></a>
 <br><sub>Read the reasoning, not just the answer.</sub>
 </td>
 </tr>
 <tr>
 <td valign="top">
-<a href="https://oar.sh/assets/shots/pagewright-watching.png?v=0.9.15"><picture><source media="(prefers-color-scheme: light)" srcset="https://oar.sh/assets/shots/pagewright-watching.light.png?v=0.9.15"><img src="https://oar.sh/assets/shots/pagewright-watching.png?v=0.9.15" alt="A session watching two other sessions: a finished reply arrives as a compact relay-event row, the watching 2 sessions list is open with Unsubscribe, and a request to also watch a session on a paired relay waits on an Allow / Deny card"></picture></a>
+<a href="https://oar.sh/assets/shots/pagewright-watching.png?v=0.9.17"><picture><source media="(prefers-color-scheme: light)" srcset="https://oar.sh/assets/shots/pagewright-watching.light.png?v=0.9.17"><img src="https://oar.sh/assets/shots/pagewright-watching.png?v=0.9.17" alt="A session watching two other sessions: a finished reply arrives as a compact relay-event row, the watching 2 sessions list is open with Unsubscribe, and a request to also watch a session on a paired relay waits on an Allow / Deny card"></picture></a>
 <br><sub>Agents that watch agents: woken by events, approving nothing.</sub>
 </td>
 </tr>
@@ -105,6 +105,7 @@ The runtime (the *provider* in the UI) is chosen in **New Chat** and stays fixed
 | [**Claude Cloud**](docs/providers.md#claude-cloud) (experimental) | Claude Code in a sandbox at Anthropic, on a GitHub repository | A claude.ai account with GitHub connected |
 | [**Cursor**](docs/providers.md#cursor-agent-sdk) | Cursor's agent | A Cursor API key |
 | [**Grok**](docs/providers.md#grok-cli-acp) | xAI's Grok CLI | A Grok sign-in, made from **⚙️ Settings** |
+| [**DeepSeek**](docs/providers.md#deepseek) | Claude Code on your machine, thinking with DeepSeek's models | A DeepSeek API key |
 
 API keys are entered in **⚙️ Settings** and stay on the relay host. The Claude and Grok CLIs can be [installed and signed in to from the browser](docs/providers.md#installing-a-provider-cli-from-the-relay), so no shell on the host is needed. Each runtime discovers its own [models](docs/providers.md#models). The full picture of each runtime is in [Providers](docs/providers.md).
 
@@ -116,11 +117,11 @@ API keys are entered in **⚙️ Settings** and stay on the relay host. The Clau
 <table>
 <tr>
 <td width="62%" valign="top">
-<a href="https://oar.sh/assets/shots/cfmail-steering.png?v=0.9.15"><picture><source media="(prefers-color-scheme: light)" srcset="https://oar.sh/assets/shots/cfmail-steering.light.png?v=0.9.15"><img src="https://oar.sh/assets/shots/cfmail-steering.png?v=0.9.15" alt="A running Claude turn with a message steered into it mid-turn, the reply streaming with its tool calls, and the Steer button in the composer"></picture></a>
+<a href="https://oar.sh/assets/shots/cfmail-steering.png?v=0.9.17"><picture><source media="(prefers-color-scheme: light)" srcset="https://oar.sh/assets/shots/cfmail-steering.light.png?v=0.9.17"><img src="https://oar.sh/assets/shots/cfmail-steering.png?v=0.9.17" alt="A running Claude turn with a message steered into it mid-turn, the reply streaming with its tool calls, and the Steer button in the composer"></picture></a>
 <br><sub>Send a message while the agent works, and it steers the running turn.</sub>
 </td>
 <td width="38%" valign="top">
-<a href="https://oar.sh/assets/shots/usage-copilot-compact.png?v=0.9.15"><picture><source media="(prefers-color-scheme: light)" srcset="https://oar.sh/assets/shots/usage-copilot-compact.light.png?v=0.9.15"><img src="https://oar.sh/assets/shots/usage-copilot-compact.png?v=0.9.15" alt="The GitHub Copilot card in Check Usage: premium requests and plan quota with reset dates, and the cost of the last turn"></picture></a>
+<a href="https://oar.sh/assets/shots/usage-copilot-compact.png?v=0.9.17"><picture><source media="(prefers-color-scheme: light)" srcset="https://oar.sh/assets/shots/usage-copilot-compact.light.png?v=0.9.17"><img src="https://oar.sh/assets/shots/usage-copilot-compact.png?v=0.9.17" alt="The GitHub Copilot card in Check Usage: premium requests and plan quota with reset dates, and the cost of the last turn"></picture></a>
 <br><sub>What each plan has left, in one place.</sub>
 </td>
 </tr>
@@ -137,7 +138,7 @@ API keys are entered in **⚙️ Settings** and stay on the relay host. The Clau
 - **Share** a conversation as a read-only link, hide single messages and the host's paths from it, and see when it was opened ([Sharing](docs/web-ui.md#sharing)).
 - **On your phone**: install OAR as an app and get push notifications ([Notifications and the app](docs/web-ui.md#notifications-and-the-app)).
 
-The full tour is in [Using the web UI](docs/web-ui.md); every setting and config key is in [Settings and configuration](docs/configuration.md). What changed in each release is in the [changelog](CHANGELOG.md), with [0.9.15](CHANGELOG.md#0915--2026-10-22) as the latest.
+The full tour is in [Using the web UI](docs/web-ui.md); every setting and config key is in [Settings and configuration](docs/configuration.md). What changed in each release is in the [changelog](CHANGELOG.md), with [0.9.17](CHANGELOG.md#0917--2026-10-25) as the latest.
 
 ## Remote access
 
@@ -188,7 +189,7 @@ flowchart LR
 
 You stay in charge: per paired relay you decide whether agents may only read, also prompt, or do everything, and in the `ask` and `plan` modes every write asks you first. A subscription only notifies; it approves nothing.
 
-<p><a href="https://oar.sh/assets/shots/pagewright-cross-relay.png?v=0.9.15"><picture><source media="(prefers-color-scheme: light)" srcset="https://oar.sh/assets/shots/pagewright-cross-relay.light.png?v=0.9.15"><img src="https://oar.sh/assets/shots/pagewright-cross-relay.png?v=0.9.15" alt="A session watching two sessions on a paired relay: a reply arrives as a relay-event row, and after a short outage the events the other relay kept arrive as one replayed row" width="720"></picture></a></p>
+<p><a href="https://oar.sh/assets/shots/pagewright-cross-relay.png?v=0.9.17"><picture><source media="(prefers-color-scheme: light)" srcset="https://oar.sh/assets/shots/pagewright-cross-relay.light.png?v=0.9.17"><img src="https://oar.sh/assets/shots/pagewright-cross-relay.png?v=0.9.17" alt="A session watching two sessions on a paired relay: a reply arrives as a relay-event row, and after a short outage the events the other relay kept arrive as one replayed row" width="720"></picture></a></p>
 
 How pairing, permissions and limits work is in [Agents working together](docs/agents-together.md).
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@oar-sh/oar",
-  "version": "0.9.15",
+  "version": "0.9.17",
   "type": "module",
   "description": "OAR — Open Agent Relay: drive your local coding agents from any browser",
   "license": "MIT",
@@ -49,6 +49,7 @@
     "setup:git": "node scripts/setup-git.mjs",
     "land": "node scripts/land.mjs",
     "prune:local": "node scripts/prune-local.mjs",
+    "deepseek:import": "node server/services/deepseek-usage-import.mjs",
     "test:e2e:raw": "node ./node_modules/@playwright/test/cli.js test --config tests/playwright.config.mjs"
   },
   "dependencies": {

package/server/claude-worker/claude-attachments.mjs

@@ -52,6 +52,9 @@ function imageBlockFromDataUrl(att, maxInlineImageBytes) {
 export function buildClaudeAttachmentContent(rawAttachments, {
   fsImpl = fs,
   maxInlineImageBytes = MAX_INLINE_IMAGE_BYTES,
+  // False for a model that takes no image input: an image block would fail
+  // the whole request, so every image goes by its path instead.
+  embedImages = true,
 } = {}) {
   const input = Array.isArray(rawAttachments) ? rawAttachments : [];
   const imageBlocks = [];
@@ -67,7 +70,7 @@ export function buildClaudeAttachmentContent(rawAttachments, {
       // Only media types the Anthropic image block accepts are embedded;
       // everything else (svg, bmp, heic, …) would 400 the whole turn and
       // falls back to a path reference instead.
-      if (filePath && isEmbeddableImageMediaType(mime) && fsImpl.existsSync(filePath)) {
+      if (embedImages && filePath && isEmbeddableImageMediaType(mime) && fsImpl.existsSync(filePath)) {
         try {
           const bytes = fsImpl.readFileSync(filePath);
           if (Buffer.isBuffer(bytes) && bytes.length && bytes.length <= maxInlineImageBytes) {
@@ -85,7 +88,7 @@ export function buildClaudeAttachmentContent(rawAttachments, {
           embedded = false;
         }
       }
-      if (!embedded) {
+      if (!embedded && embedImages) {
         const blockFromDataUrl = imageBlockFromDataUrl(att, maxInlineImageBytes);
         if (blockFromDataUrl) {
           imageBlocks.push(blockFromDataUrl);
@@ -118,9 +121,9 @@ export function buildClaudeAttachmentContent(rawAttachments, {
  * Text first (user text + attachment notes + server-provided attachment
  * context), then inline image blocks.
  */
-export function buildClaudeUserContent(message, { fsImpl = fs, maxInlineImageBytes = MAX_INLINE_IMAGE_BYTES } = {}) {
+export function buildClaudeUserContent(message, { fsImpl = fs, maxInlineImageBytes = MAX_INLINE_IMAGE_BYTES, embedImages = true } = {}) {
   const text = String(message?.text || '').trim();
-  const { imageBlocks, noteLines } = buildClaudeAttachmentContent(message?.attachments, { fsImpl, maxInlineImageBytes });
+  const { imageBlocks, noteLines } = buildClaudeAttachmentContent(message?.attachments, { fsImpl, maxInlineImageBytes, embedImages });
   const attachmentPromptContext = String(message?.attachmentPromptContext || '').trim();
   const textParts = [text];
   if (noteLines.length) textParts.push(noteLines.join('\n'));