@matterailab/orbcode 0.1.3 → 0.1.4

package/README.md

@@ -144,12 +144,13 @@ The two Axon models are built in; `/model` opens a scroll-and-select picker
 (`/model <id>` still selects directly). Additional models can be declared via
 `customModels` in settings.json. The choice persists across sessions.
 
-| id                  | context | max output | pricing                  |
-|---------------------|---------|------------|--------------------------|
-| `axon-code-2-5-pro` | 400k    | 64k        | $2/M in · $6/M out       |
-| `axon-code-2-5-mini`| 400k    | 64k        | free                     |
+| id                     | context | max output | pricing            |
+| ---------------------- | ------- | ---------- | ------------------ |
+| `axon-eido-3-code-pro` | 400k    | 64k        | $3/M in · $9/M out |
+| `axon-code-2-5-pro`    | 400k    | 64k        | $2/M in · $6/M out |
+| `axon-code-2-5-mini`   | 400k    | 64k        | free               |
 
-`axon-code-2-5-pro` is the default. Both support native JSON tool calls and
+`axon-code-2-5-pro` is the default. All three support native JSON tool calls and
 image input. Cost comes from the API's usage chunks (`is_byok`-aware) and is
 shown in the status bar.
 
@@ -196,35 +197,35 @@ shown in the status bar.
 
 ## Slash commands
 
-| command    | action |
-|------------|--------|
-| `/help`    | list commands |
-| `/model`   | scrollable model picker (`/model pro` / `/model mini` / full id selects directly) |
-| `/clear`   | clear the screen only, like the terminal's `clear` — the conversation and context continue |
-| `/new`     | start a fresh conversation/session with a clean slate |
-| `/resume`  | pick a previous session for this directory and continue it (screen is cleared, conversation replayed) |
-| `/analytics` | open the MatterAI analytics dashboard (app.matterai.so/orbital) in the browser |
-| `/compact` | summarize the conversation and replace history with the summary |
-| `/tasks`   | print the current task list |
-| `/status`  | version, model, account, gateway, context usage, cost, approval modes |
-| `/cost`    | show session cost and fetch account balance |
-| `/init`    | analyze the codebase and create/improve `AGENTS.md` |
-| `/login`   | start the browser sign-in flow |
-| `/logout`  | remove the saved token |
-| `/version` | print the CLI version |
-| `/exit`    | quit |
+| command      | action                                                                                                |
+| ------------ | ----------------------------------------------------------------------------------------------------- |
+| `/help`      | list commands                                                                                         |
+| `/model`     | scrollable model picker (`/model pro` / `/model mini` / full id selects directly)                     |
+| `/clear`     | clear the screen only, like the terminal's `clear` — the conversation and context continue            |
+| `/new`       | start a fresh conversation/session with a clean slate                                                 |
+| `/resume`    | pick a previous session for this directory and continue it (screen is cleared, conversation replayed) |
+| `/analytics` | open the MatterAI analytics dashboard (app.matterai.so/orbital) in the browser                        |
+| `/compact`   | summarize the conversation and replace history with the summary                                       |
+| `/tasks`     | print the current task list                                                                           |
+| `/status`    | version, model, account, gateway, context usage, cost, approval modes                                 |
+| `/cost`      | show session cost and fetch account balance                                                           |
+| `/init`      | analyze the codebase and create/improve `AGENTS.md`                                                   |
+| `/login`     | start the browser sign-in flow                                                                        |
+| `/logout`    | remove the saved token                                                                                |
+| `/version`   | print the CLI version                                                                                 |
+| `/exit`      | quit                                                                                                  |
 
 ## Keyboard shortcuts
 
-| key | action |
-|-----|--------|
-| `Esc` | interrupt the running turn (or cancel login polling / close a menu) |
-| `Ctrl+C` | quit |
-| `Ctrl+O` | toggle thinking display for the whole transcript (past turns included) |
-| `Shift+Tab` | cycle approval mode: ask → accept edits → auto-approve |
-| `↑` / `↓` | input history, or navigate any open menu |
-| `Ctrl+A` / `Ctrl+E` | start / end of line |
-| `Ctrl+U` | clear the input line |
+| key                 | action                                                                 |
+| ------------------- | ---------------------------------------------------------------------- |
+| `Esc`               | interrupt the running turn (or cancel login polling / close a menu)    |
+| `Ctrl+C`            | quit                                                                   |
+| `Ctrl+O`            | toggle thinking display for the whole transcript (past turns included) |
+| `Shift+Tab`         | cycle approval mode: ask → accept edits → auto-approve                 |
+| `↑` / `↓`           | input history, or navigate any open menu                               |
+| `Ctrl+A` / `Ctrl+E` | start / end of line                                                    |
+| `Ctrl+U`            | clear the input line                                                   |
 
 ## Approvals & safety
 
@@ -267,22 +268,22 @@ Two kinds of files under `~/.orbcode/`:
 
 ```json
 {
-	"apiKey": "<token used instead of logging in>",
-	"baseUrl": "https://my-gateway.example.com/v1",
-	"model": "my-custom-model",
-	"autoApproveEdits": false,
-	"autoApproveSafeCommands": false,
-	"customModels": [
-		{
-			"id": "my-custom-model",
-			"name": "My Custom Model",
-			"contextWindow": 128000,
-			"maxOutputTokens": 32000,
-			"inputPrice": 0.000001,
-			"outputPrice": 0.000002
-		}
-	],
-	"env": { "MY_VAR": "value" }
+  "apiKey": "<token used instead of logging in>",
+  "baseUrl": "https://my-gateway.example.com/v1",
+  "model": "my-custom-model",
+  "autoApproveEdits": false,
+  "autoApproveSafeCommands": false,
+  "customModels": [
+    {
+      "id": "my-custom-model",
+      "name": "My Custom Model",
+      "contextWindow": 128000,
+      "maxOutputTokens": 32000,
+      "inputPrice": 0.000001,
+      "outputPrice": 0.000002
+    }
+  ],
+  "env": { "MY_VAR": "value" }
 }
 ```
 
@@ -295,15 +296,15 @@ config.json.
 Sessions are stored in `~/.orbcode/sessions/<id>.json` and power `/resume`
 and `--resume <id>`.
 
-| env var | effect |
-|---------|--------|
-| `ORBCODE_TOKEN` | auth token (overrides everything) |
-| `ORBCODE_API_KEY` | same as `apiKey` in settings.json |
-| `ORBCODE_BASE_URL` | same as `baseUrl` in settings.json |
-| `ORBCODE_MODEL` | model override (what `--model` sets internally) |
-| `ORBCODE_CONFIG_DIR` | config directory (default `~/.orbcode`) |
-| `ORBCODE_BACKEND_URL` | device-auth backend (default `https://api.matterai.so`) |
-| `ORBCODE_APP_URL` | webapp for the authorize page (default `https://app.matterai.so`) |
+| env var               | effect                                                            |
+| --------------------- | ----------------------------------------------------------------- |
+| `ORBCODE_TOKEN`       | auth token (overrides everything)                                 |
+| `ORBCODE_API_KEY`     | same as `apiKey` in settings.json                                 |
+| `ORBCODE_BASE_URL`    | same as `baseUrl` in settings.json                                |
+| `ORBCODE_MODEL`       | model override (what `--model` sets internally)                   |
+| `ORBCODE_CONFIG_DIR`  | config directory (default `~/.orbcode`)                           |
+| `ORBCODE_BACKEND_URL` | device-auth backend (default `https://api.matterai.so`)           |
+| `ORBCODE_APP_URL`     | webapp for the authorize page (default `https://app.matterai.so`) |
 
 `autoApproveEdits` / `autoApproveSafeCommands` set the session defaults for the
 approval prompts (dangerous commands still always prompt); shift+tab cycles
@@ -365,19 +366,19 @@ reset date — the same data as the extension's profile view.
 
 Active in the CLI (schemas byte-identical to the extension's `native-tools`):
 
-| tool | executor notes |
-|------|----------------|
-| `read_file` | line-numbered output (`LINE\|content`, 6-char pad), 1000-line cap, offset/limit |
-| `file_edit` | single replacement; unique-match enforcement; `replace_all`; empty `old_string` = whole file |
-| `multi_file_edit` | batched edits grouped per file, per-edit OK/FAILED results |
-| `file_write` | creates parent dirs, full-content writes |
-| `list_files` | optional recursive, ignores node_modules/.git/build dirs, 800-entry cap |
-| `search_files` | JS regex search with glob `file_pattern` (picomatch), 300-match cap, binary skip |
-| `execute_command` | user's shell, 120s timeout, 30k output cap, optional cwd |
-| `web_search` / `web_fetch` | proxied through the MatterAI backend with your token |
-| `update_todo_list` | drives the TUI todo panel |
-| `ask_followup_question` | interactive menu in the TUI |
-| `attempt_completion` | ends the turn with a completion card |
+| tool                       | executor notes                                                                               |
+| -------------------------- | -------------------------------------------------------------------------------------------- |
+| `read_file`                | line-numbered output (`LINE\|content`, 6-char pad), 1000-line cap, offset/limit              |
+| `file_edit`                | single replacement; unique-match enforcement; `replace_all`; empty `old_string` = whole file |
+| `multi_file_edit`          | batched edits grouped per file, per-edit OK/FAILED results                                   |
+| `file_write`               | creates parent dirs, full-content writes                                                     |
+| `list_files`               | optional recursive, ignores node_modules/.git/build dirs, 800-entry cap                      |
+| `search_files`             | JS regex search with glob `file_pattern` (picomatch), 300-match cap, binary skip             |
+| `execute_command`          | user's shell, 120s timeout, 30k output cap, optional cwd                                     |
+| `web_search` / `web_fetch` | proxied through the MatterAI backend with your token                                         |
+| `update_todo_list`         | drives the TUI todo panel                                                                    |
+| `ask_followup_question`    | interactive menu in the TUI                                                                  |
+| `attempt_completion`       | ends the turn with a completion card                                                         |
 
 Present in `tools/schemas/` but **inactive** (need IDE services): `codebase_search`,
 `lsp`, `list_code_definition_names`, `use_skill`, `check_past_chat_memories`,
@@ -417,6 +418,7 @@ Source-of-truth rule: behavior is **ported from the Orbital extension repo**
 schemas byte-identical rather than editing them here.
 
 Backend/web pieces of the device-auth flow live in:
+
 - `gravity-console-backend` → `src/controller/orbcodeAuthController.ts`
   (+ OAuth state in `router.ts`, callbacks in `authController.ts`)
 - `gravity-console-webapp` → authorize dialog in `src/App.js`, sign-in q-p

package/dist/api/models.js

@@ -21,6 +21,17 @@ export const AXON_MODELS = {
         outputPrice: 0.000006,
         free: false,
     },
+    "axon-eido-3-code-pro": {
+        id: "axon-eido-3-code-pro",
+        name: "Axon Eido 3 Pro",
+        description: "Axon Eido 3 Pro is the frontier Axon Code model for coding tasks, long running agents and general intelligence, fine-tuned on open source models.",
+        contextWindow: 400000,
+        maxOutputTokens: 64000,
+        supportsImages: true,
+        inputPrice: 0.000003,
+        outputPrice: 0.000009,
+        free: false,
+    },
 };
 export const DEFAULT_MODEL_ID = "axon-code-2-5-pro";
 /** Add user-defined models (from settings.json) to the registry. */

package/dist/auth/auth.js

@@ -78,7 +78,10 @@ export async function pollDeviceAuth(devicecode) {
 export async function fetchProfile(token) {
     const url = getUrlFromToken("https://api.matterai.so/axoncode/profile", token);
     const response = await fetch(url, {
-        headers: { Authorization: `Bearer ${token}`, "Content-Type": "application/json" },
+        headers: {
+            Authorization: `Bearer ${token}`,
+            "Content-Type": "application/json",
+        },
     });
     if (!response.ok) {
         throw new Error(`Profile request failed (${response.status}). Your token may be invalid or expired.`);
@@ -150,7 +153,9 @@ export async function fetchTaskTitle(taskId, token, maxRetries = 3, retryDelayMs
 export async function fetchBalance(token, organizationId) {
     try {
         const url = getUrlFromToken("https://api.matterai.so/api/profile/balance", token);
-        const headers = { Authorization: `Bearer ${token}` };
+        const headers = {
+            Authorization: `Bearer ${token}`,
+        };
         if (organizationId)
             headers["X-KiloCode-OrganizationId"] = organizationId;
         const response = await fetch(url, { headers });

package/dist/ui/App.js

@@ -41,6 +41,28 @@ function setTerminalTitle(title) {
         process.stdout.write(`\x1b]0;${title}\x07`);
     }
 }
+function formatRelativeTime(isoStr) {
+    if (!isoStr)
+        return "???";
+    const now = Date.now();
+    const target = new Date(isoStr).getTime();
+    if (Number.isNaN(target))
+        return "???";
+    const diff = target - now;
+    if (diff <= 0)
+        return "now";
+    const sec = Math.floor(diff / 1000);
+    const min = Math.floor(sec / 60);
+    const hrs = Math.floor(min / 60);
+    const days = Math.floor(hrs / 24);
+    if (days >= 1)
+        return `in ${days} day${days > 1 ? "s" : ""}`;
+    if (hrs >= 1)
+        return `in ${hrs}h ${min % 60}m`;
+    if (min >= 1)
+        return `in ${min}m`;
+    return "soon";
+}
 /** Human lines for the /status and /cost usage block (extension profile data). */
 function usageLines(profile) {
     const lines = [];
@@ -52,8 +74,22 @@ function usageLines(profile) {
     if (typeof profile.remainingReviews === "number") {
         lines.push(`Reviews     ${profile.remainingReviews} remaining`);
     }
-    if (profile.creditsResetDate)
+    if (profile.tieredUsage) {
+        const ws = [
+            ["5hr", "5-Hour", profile.tieredUsage.fiveHour],
+            ["wk", "Weekly", profile.tieredUsage.weekly],
+            ["mo", "Monthly", profile.tieredUsage.monthly],
+        ];
+        for (const [short, label, w] of ws) {
+            const remaining = Math.max(0, w.remaining || 0);
+            const pct = Math.max(0, Math.min(100, w.percentage || 0));
+            const reset = formatRelativeTime(w.resetsAt);
+            lines.push(`${label.padEnd(12)} ${remaining.toFixed(1)}/${w.limit.toFixed(1)} left (${pct}% used) · Resets ${reset}`);
+        }
+    }
+    else if (profile.creditsResetDate) {
         lines.push(`Resets      ${profile.creditsResetDate}`);
+    }
     return lines;
 }
 const INIT_PROMPT = `Analyze this codebase and create an AGENTS.md file containing:
@@ -139,7 +175,7 @@ export function App({ initialView, initialPrompt, initialSession, }) {
         if (!token)
             return;
         fetchProfile(token)
-            .then((profile) => setUsage({ plan: profile.plan, usagePercentage: profile.usagePercentage }))
+            .then((profile) => setUsage({ plan: profile.plan, usagePercentage: profile.usagePercentage, tieredUsage: profile.tieredUsage }))
             .catch(() => { });
     }, []);
     const agentRef = useRef(null);
@@ -227,6 +263,10 @@ export function App({ initialView, initialPrompt, initialSession, }) {
             case "usage":
                 setContextTokens(event.inputTokens + event.outputTokens);
                 setTotalCost(event.totalCost);
+                // A usage chunk arrives once per LLM response, so the plan/usage
+                // shown below the chat box stays current mid-turn, not only
+                // after the turn finishes.
+                refreshUsage();
                 break;
             case "completion":
                 pushRow({ kind: "completion", text: event.result });
@@ -324,11 +364,20 @@ export function App({ initialView, initialPrompt, initialSession, }) {
                 if (arg && isValidAxonModel(arg)) {
                     switchModel(arg);
                 }
-                else if (arg && isValidAxonModel(`axon-code-2-5-${arg}`)) {
-                    switchModel(`axon-code-2-5-${arg}`);
-                }
                 else if (arg) {
-                    pushRow({ kind: "error", text: `Unknown model "${arg}". Available: ${ids.join(", ")}` });
+                    // Allow short suffixes like "pro" or "mini" to resolve to the
+                    // latest matching registered id, so /model pro keeps working
+                    // as new model generations are added.
+                    const matches = ids
+                        .filter((id) => id.endsWith(`-${arg}`))
+                        .sort()
+                        .reverse();
+                    if (matches.length > 0) {
+                        switchModel(matches[0]);
+                    }
+                    else {
+                        pushRow({ kind: "error", text: `Unknown model "${arg}". Available: ${ids.join(", ")}` });
+                    }
                 }
                 else {
                     setModelPickerOpen(true);
@@ -539,7 +588,7 @@ export function App({ initialView, initialPrompt, initialSession, }) {
         saveSettings(updated);
         agentRef.current = null;
         setView("chat");
-        setUsage({ plan: profile.plan, usagePercentage: profile.usagePercentage });
+        setUsage({ plan: profile.plan, usagePercentage: profile.usagePercentage, tieredUsage: profile.tieredUsage });
         const who = profile.user?.name || profile.user?.email;
         pushRow({ kind: "info", text: `Signed in${who ? ` as ${who}` : ""}. Ready when you are.` });
     }, [pushRow]);
@@ -558,7 +607,7 @@ export function App({ initialView, initialPrompt, initialSession, }) {
                                 pushRow({ kind: "user", text: answer });
                                 pendingFollowup.resolve(answer);
                                 setPendingFollowup(null);
-                            } }) })), busy && !pendingApproval && !pendingFollowup && !streamingText && (_jsx(Box, { marginTop: 1, children: _jsx(Spinner, { label: busyLabel }) })), _jsxs(Box, { marginTop: 1, flexDirection: "column", children: [_jsx(InputBox, { active: inputActive, slashCommands: SLASH_COMMANDS, onSubmit: handleSubmit }), _jsx(StatusBar, { modelId: settings.model, contextTokens: contextTokens, totalCost: totalCost, state: busy ? busyLabel : "", approvalMode: approvalMode, busy: busy, title: sessionTitle, plan: usage?.plan, usagePercentage: usage?.usagePercentage })] })] }))] }));
+                            } }) })), busy && !pendingApproval && !pendingFollowup && !streamingText && (_jsx(Box, { marginTop: 1, children: _jsx(Spinner, { label: busyLabel }) })), _jsxs(Box, { marginTop: 1, flexDirection: "column", children: [_jsx(InputBox, { active: inputActive, slashCommands: SLASH_COMMANDS, onSubmit: handleSubmit }), _jsx(StatusBar, { modelId: settings.model, contextTokens: contextTokens, totalCost: totalCost, state: busy ? busyLabel : "", approvalMode: approvalMode, busy: busy, title: sessionTitle, plan: usage?.plan, usagePercentage: usage?.usagePercentage, tieredUsage: usage?.tieredUsage })] })] }))] }));
 }
 function tail(text, lines) {
     const all = text.split("\n").filter((l) => l.trim());

package/dist/ui/components/StatusBar.js

@@ -7,12 +7,51 @@ const MODE_LABELS = {
     edits: "⏵⏵ accept edits on",
     auto: "⏵⏵⏵ auto-approve on",
 };
+function formatRelativeTime(isoStr) {
+    if (!isoStr)
+        return "???";
+    const now = Date.now();
+    const target = new Date(isoStr).getTime();
+    if (Number.isNaN(target))
+        return "???";
+    const diff = target - now;
+    if (diff <= 0)
+        return "now";
+    const sec = Math.floor(diff / 1000);
+    const min = Math.floor(sec / 60);
+    const hrs = Math.floor(min / 60);
+    const days = Math.floor(hrs / 24);
+    if (days >= 1)
+        return `${days}d`;
+    if (hrs >= 1)
+        return `${hrs}h${min % 60 > 0 ? ` ${min % 60}m` : ""}`;
+    if (min >= 1)
+        return `${min}m`;
+    return "soon";
+}
 function truncate(text, max) {
     return text.length > max ? text.slice(0, max - 1) + "…" : text;
 }
-export function StatusBar({ modelId, contextTokens, totalCost, state, approvalMode, busy, title, plan, usagePercentage, }) {
+/**
+ * Picks the most constrained window (highest percentage used) and returns a
+ * compact string like "5hr 12% · resets in 3h 15m".
+ */
+function mostConstrainedSummary(tu) {
+    const windows = [
+        ["5hr", tu.fiveHour.percentage, tu.fiveHour.resetsAt],
+        ["wk", tu.weekly.percentage, tu.weekly.resetsAt],
+        ["mo", tu.monthly.percentage, tu.monthly.resetsAt],
+    ];
+    const [label, pct, resetsAt] = windows.reduce((best, cur) => cur[1] >= best[1] ? cur : best);
+    return `${label} ${Math.round(pct)}% · resets ${formatRelativeTime(resetsAt)}`;
+}
+export function StatusBar({ modelId, contextTokens, totalCost, state, approvalMode, busy, title, plan, usagePercentage, tieredUsage, }) {
     const model = getModel(modelId);
     const contextPct = Math.min(100, Math.round((contextTokens / model.contextWindow) * 100));
-    const remaining = typeof usagePercentage === "number" ? Math.max(0, Math.round(100 - usagePercentage)) : undefined;
-    return (_jsxs(Box, { flexDirection: "column", children: [_jsxs(Box, { justifyContent: "space-between", children: [_jsxs(Text, { dimColor: true, children: [_jsx(Text, { color: approvalMode === "ask" ? undefined : COLORS.warning, children: MODE_LABELS[approvalMode] }), " (shift+tab to cycle)", busy && " · esc to interrupt", state ? _jsxs(Text, { color: COLORS.thinking, children: [" \u00B7 ", state] }) : null] }), _jsxs(Text, { dimColor: true, children: [title ? `${truncate(title, 32)} · ` : "", model.name, " \u00B7 ctx ", contextTokens.toLocaleString(), " (", contextPct, "%)", model.free ? " · free" : ` · $${totalCost.toFixed(4)}`] })] }), (plan || remaining !== undefined) && (_jsx(Box, { justifyContent: "flex-end", children: _jsxs(Text, { dimColor: true, children: [plan ? `${plan} plan` : "", plan && remaining !== undefined ? " · " : "", remaining !== undefined ? (_jsxs(Text, { color: remaining <= 10 ? COLORS.error : undefined, children: [remaining, "% usage remaining"] })) : null] }) }))] }));
+    const constrainedLine = tieredUsage
+        ? mostConstrainedSummary(tieredUsage)
+        : typeof usagePercentage === "number"
+            ? `${Math.round(usagePercentage)}% used`
+            : null;
+    return (_jsxs(Box, { flexDirection: "column", children: [_jsxs(Box, { justifyContent: "space-between", children: [_jsxs(Text, { dimColor: true, children: [_jsx(Text, { color: approvalMode === "ask" ? undefined : COLORS.warning, children: MODE_LABELS[approvalMode] }), " (shift+tab to cycle)", busy && " · esc to interrupt", state ? _jsxs(Text, { color: COLORS.thinking, children: [" \u00B7 ", state] }) : null] }), _jsxs(Text, { dimColor: true, children: [title ? `${truncate(title, 32)} · ` : "", model.name, " \u00B7 ctx ", contextTokens.toLocaleString(), " (", contextPct, "%)", model.free ? " · free" : ` · $${totalCost.toFixed(4)}`] })] }), (plan || constrainedLine) && (_jsx(Box, { justifyContent: "flex-end", children: _jsxs(Text, { dimColor: true, children: [plan && constrainedLine ? " · " : "", constrainedLine] }) }))] }));
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@matterailab/orbcode",
-  "version": "0.1.3",
+  "version": "0.1.4",
   "description": "OrbCode CLI — agentic coding in your terminal, powered by Axon models by MatterAI",
   "type": "module",
   "bin": {