@hecer/yoke 1.7.0 → 1.9.0

package/.claude-plugin/plugin.json

@@ -2,7 +2,7 @@
   "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
   "name": "yoke",
   "displayName": "Yoke",
-  "version": "1.7.0",
+  "version": "1.9.0",
   "description": "Cross-agent coding harness: one curated skill canon (TDD, brainstorming, plans, reviews, shipping, design verification) plus mechanical safety gates and an autonomous loop via the yoke CLI.",
   "author": { "name": "HECer", "url": "https://github.com/HECer" },
   "homepage": "https://github.com/HECer/yoke#readme",

package/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "yoke",
-  "version": "1.7.0",
+  "version": "1.9.0",
   "description": "Cross-agent coding discipline, mechanical gates, and release workflows",
   "skills": "./canon/skills/",
   "hooks": "./hooks/hooks.json"

package/CHANGELOG.md

@@ -2,6 +2,41 @@
 
 ## Unreleased
 
+## 1.9.0 — 2026-09-06
+
+### Added
+- Add capability-based routing with persisted task assessments, explicit model/effort tiers, role eligibility and conservative use of independent task-class outcomes.
+- Keep planning on the start model; reuse assessments across attempts/worktrees and invalidate them when task requirements change.
+- Add bounded repair and tier escalation after mechanical gate failures, retaining the patch and forwarding failure evidence. Infrastructure failures do not trigger capability escalation.
+- Apply task-based profiles to reviews, quality critics/repairs and goal execution; display implementation selection reasons and next escalation in the dashboard.
+- Add setup options `--routing-strategy=capability` and `--routing-preset` for explicit migration. Preserve existing strategies and custom profiles by default.
+
+### Validation limits
+- Initial profile tiers are configurable hypotheses, not authenticated model benchmarks, price estimates or calibrated success probabilities. See [capability routing](docs/CAPABILITY-ROUTING.md) for defaults and bounds.
+
+## 1.8.0 — 2026-09-06
+
+### Added
+- Add persistent local measurement history and dashboard views for current work, usage/time and results, including UTC day/week/month filters, model history, project comparisons and consumption charts.
+- Display current tasks, worker phases, integration progress and status age, with automatic refresh of the current-work view.
+- Record explicit acceptances and show measured tokens and time per acceptance. Attribute available reviewer, critic and repair usage; distinguish actual reported models, unknown calls and partial costs.
+
+### Changed
+- Enable routing in new setups and automatically select up to three parallel workers when all pending tasks declare write scopes. Dependencies and overlapping scopes still constrain dispatch. Preserve explicit opt-outs and use isolated worktrees by default.
+- Share routing decisions between synchronous and asynchronous runners; support routed parallel workers, stable recovery history and explicit provider affinity.
+- Reserve execution capacity through integration and disable native delegation for loop providers; preserve Gemini system policy in a temporary bounded-execution configuration.
+- Require a dated changelog entry, synchronized version metadata and verified release checks for every new version in the project instructions.
+
+### Fixed
+- Avoid conflicting Codex sandbox arguments and prevent Codex-only options from leaking into Gemini workers.
+- Keep compact measurement history after recent activity expires, deduplicate archived events, and report incomplete history instead of treating missing usage as zero.
+- Preserve reviewer telemetry and worker/model attribution across parallel execution and recovery.
+
+### Migration and validation limits
+- Use `--parallel=N` to choose a worker limit, `--parallel=auto` for automatic selection, `--no-routing` to opt out of routing, and `--no-isolate` to opt out of default isolation. Explicit existing configuration remains authoritative. Unknown write scopes, tool actions and worktree recovery select serial execution in auto mode.
+- Automatic routing needs configured profiles; otherwise it keeps the selected parent provider. Explicit `--routing` without profiles reports a configuration error.
+- Missing historical usage cannot be reconstructed. Tokens per minute describe interval or summed call consumption, not measured generation speed. Live authenticated provider benchmarks, resource-adaptive concurrency and calibrated time/cost predictions are not established by this release.
+
 ## 1.7.0 — 2026-09-05
 
 ### Added

package/README.md

@@ -2,8 +2,8 @@
 
 # 🐂 Yoke
 
-<!-- yoke:version:start -->1.7.0<!-- yoke:version:end -->
-<!-- yoke:tests:start -->1100<!-- yoke:tests:end -->
+<!-- yoke:version:start -->1.9.0<!-- yoke:version:end -->
+<!-- yoke:tests:start -->1134<!-- yoke:tests:end -->
 <!-- yoke:skills:start -->34<!-- yoke:skills:end -->
 <!-- yoke:agents:start -->Claude | Codex | Gemini<!-- yoke:agents:end -->
 
@@ -17,7 +17,7 @@
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](#-license)
 ![Node](https://img.shields.io/badge/node-%E2%89%A520-339933?logo=node.js&logoColor=white)
 ![TypeScript](https://img.shields.io/badge/TypeScript-3178C6?logo=typescript&logoColor=white)
-![Tests](https://img.shields.io/badge/tests-1100%20defined-blue.svg)
+![Tests](https://img.shields.io/badge/tests-1134%20defined-blue.svg)
 ![Agents](https://img.shields.io/badge/agents-Claude%20%7C%20Codex%20%7C%20Gemini-8A2BE2)
 ![Built with TDD](https://img.shields.io/badge/built%20with-TDD%20%2B%20review-ff69b4.svg)
 
@@ -27,7 +27,7 @@
 
 > **TL;DR** — `yoke setup .` asks six questions and installs the native harness for your agent. `yoke new my-app --idea="..."` bootstraps a project and drafts its story backlog. `yoke loop run my-app --isolate --review` then implements it behind hard gates: **clean tree → acceptance criteria → your real tests green → an independent model approves → commit**. Add `--parallel=N` for dependency-aware workers, or declare a reference and add `--quality` for a bounded critic/repair gauntlet. If any blocking gate is red, nothing is committed. Proof lives in `.yoke/proof/<story>/`.
 
-**New in 1.7.0:** [verified project goals, recovery and one local dashboard for all your registered projects](docs/VERIFIED-PROJECTS.md). Check an existing project, continue a bounded goal with Codex, Claude or Gemini, and inspect tasks, acceptance evidence, recorded consumption and estimated timing in one place.
+**New in 1.9.0:** [routing by task requirements](docs/CAPABILITY-ROUTING.md). Keep planning on the start model, select execution models and effort from saved task assessments, and use bounded repair and escalation with independent checks. The dashboard explains model selection; existing routing settings remain authoritative.
 
 ### One dashboard, multiple projects
 
@@ -62,8 +62,8 @@ retain actionable failures and final summaries, while large complete stdout/stde
 in private, content-addressed local artifacts. Existing projects keep their serial behavior and use
 safe 2 KiB preview / 8 KiB artifact defaults unless configured otherwise.
 
-Yoke 1.4 adds opt-in parallel workers and a bounded, reference-driven quality gauntlet without
-changing existing serial loop defaults. See [the 1.4 migration guide](docs/MIGRATING-TO-1.4.md)
+Yoke 1.4 introduced opt-in parallel workers and a bounded, reference-driven quality gauntlet.
+Yoke 1.8.0 uses automatic parallelism for tasks with declared write scopes. See [the 1.4 migration guide](docs/MIGRATING-TO-1.4.md)
 for the new flags, configuration, cleanup behavior, and review-verdict contract.
 
 Yoke 1.1 is safe-by-default: provider CLIs use autonomous sandbox profiles unless `--unsafe`
@@ -191,7 +191,7 @@ Yoke's CLI is deterministic and chainable by design: an agent (or a shell `&&`)
 | `yoke projects add\|list\|remove` | Register a project, list registrations or remove a reference by ID | `0` · `2` invalid/unavailable |
 | `yoke check [dir] [--json] [--requirement=] [--protect [--refresh]]` | Execute acceptance checks or explicitly pin their infrastructure | `0` passed/pinned · `1` failed · `2` unverified/unavailable |
 | `yoke goal set\|run\|resume\|pause\|status\|handoff\|budget [dir]` | Durable objectives, provider handoff, protected checks and checkpoint budgets | run/resume: `0` complete · `1` unfinished · `2` unavailable |
-| `yoke setup [dir] [--yes] [--host=] [--agent=] [--runner=] [--code-graph=] [--decision-policy=] [--loop\|--no-loop] [--routing\|--no-routing]` | Shared six-question setup for Claude, Codex, and Gemini; adaptive routing is always an explicit opt-in | `0` · `1` invalid setup |
+| `yoke setup [dir] [--yes] [--host=] [--agent=] [--runner=] [--code-graph=] [--decision-policy=] [--loop\|--no-loop] [--routing\|--no-routing]` | Shared six-question setup for Claude, Codex, and Gemini; routing defaults on for new setups and preserves explicit opt-outs | `0` · `1` invalid setup |
 | `yoke validate [canonDir]` | Validate the canon (schema, frontmatter, templates) | `0` valid · `1` errors |
 | `yoke new <dir> [--idea=] [--agent=] [--runner=] [--loop]` | Greenfield bootstrap: git init → scaffold → retrofit → context → PRD (drafted from `--idea`) → committed | `0` · `1` usage / non-empty dir / draft failed (scaffold survives) · `2` draft agent unavailable |
 | `yoke retrofit [dir] [--agent=claude,codex,gemini\|all] [--code-graph=graphify\|serena] [--loop]` | Install/update the harness, non-destructively | `0` |
@@ -563,14 +563,16 @@ use `yoke loop resume . --discard`; pending decisions are never deleted by that
 `loop.onAmbiguity: resolve|abort` and `--on-ambiguity=` remain supported as compatibility aliases;
 new projects should use `decisionPolicy: auto|critical`.
 
-### Adaptive model routing (explicit opt-in)
+### Adaptive model routing
 
-`yoke setup` asks before enabling routing; the default is **off**. When enabled, the selected
+`yoke setup` enables routing by default and preserves explicit opt-outs. Without configured
+worker profiles, automatic execution keeps the selected parent. When enabled, the selected
 parent remains the strong planner/controller. Before each bounded story it receives only the
 story, acceptance criteria, and at most three eligible worker profiles, then returns one
 machine-readable choice. The worker can be a cheaper/faster Claude, Codex, or Gemini profile;
-`SELF` keeps difficult work on the parent. Provider-native subagents are disabled for these
-runs so Yoke does not pay for two orchestration layers.
+`SELF` keeps difficult work on the parent. Explicit project rules skip the controller.
+Loop runners disable native delegation in Codex, Claude and Gemini so it cannot multiply
+the Yoke worker budget. Integration retains its execution slot until the candidate lands.
 
 **Provider support:** adaptive routing uses Yoke's shared provider adapter and works with Claude
 Code, Codex CLI, and Gemini CLI, including mixed-provider worker lists. Internal contract tests
@@ -584,7 +586,7 @@ runner:
   model: gpt-5.6-sol       # optional; provider model strings stay opaque to Yoke
   reasoningEffort: high
 routing:
-  enabled: true            # setup defaults false; setup --routing opts in
+  enabled: true            # new setup default; false preserves an explicit opt-out
   strategy: balanced       # balanced | cost | speed | quality
   maxCandidates: 3
   workers:
@@ -605,7 +607,7 @@ routing:
       capabilities: [large-context, implementation]
 ```
 
-Use `yoke loop run . --routing` for a one-run opt-in or `--no-routing` for a controlled
+Use `yoke loop run . --routing` to explicitly require configured routing or `--no-routing` for a controlled
 baseline. Routing control calls are read-only and deliberately tiny; malformed output or no
 eligible worker falls back to `SELF`. Yoke does not ship a universal, fast-aging
 "intelligence score". Candidate model IDs come from project configuration while setup defaults
@@ -615,9 +617,12 @@ after 30 days. It stores no prompts, source, or project paths—only a project h
 time/token/outcome evidence. Writes are immutable one-event files, so concurrent Yoke instances
 cannot overwrite a shared registry file.
 
-Routing is not free: it adds one controller call per story. It is most promising when a bounded
-worker saves more than that call costs; tiny stories may be slower. Keep it opt-in and measure it
-on your own backlog rather than assuming a win.
+Routing is not free: stories without a matching rule can add a controller call. Measure it
+on your own backlog rather than assuming a win. Routing now also runs within asynchronous
+parallel workers. Automatic parallelism starts at up to three workers when pending tasks declare
+write scopes; unknown scopes and configured tool actions keep execution serial. Isolation is
+on by default. Explicit `--parallel=N`, `--no-routing` and `--no-isolate` remain available.
+See [execution defaults and dashboard measurement details](docs/VERIFIED-PROJECTS.md#execution-defaults-in-180).
 
 ### Performance budgets: efficiency as a gate, not a style
 
@@ -841,7 +846,7 @@ the routed median used **33.8% less wall time, 11.0% less fresh input, 49.5% few
 and 78.2% fewer reasoning tokens**. All three pairs improved wall time and fresh input.
 
 The boundary matters: an earlier architecture/privacy task correctly stayed on `SELF` and paid
-controller overhead, so routing is an explicit opt-in rather than a universal win. Codex did not
+controller overhead, so the routing default is not evidence of universal savings. Codex did not
 emit dollar cost for these plan-backed runs; Yoke reports the measured token breakdown instead of
 inventing a price. Method, ranges, controller cost, caveats, analyzer, and six raw JSON rows are in
 [`bench/RESULTS.md`](bench/RESULTS.md#codex-only-full-repository-routing-study-2026-08-02).
@@ -890,7 +895,7 @@ release provenance.
 ## 🧪 Development
 
 ```bash
-npm test          # vitest (1100 tests)
+npm test          # vitest (1134 tests)
 npm run build     # tsc, no emit errors
 npm run yoke -- validate canon
 ```

package/canon/skills/authoring-prd/SKILL.md

@@ -22,6 +22,13 @@ new stories; they do not require a release object.
    placeholders; critical irreversible choices use the structured decision channel.
 8. Use `needs` only for hard prerequisites, `area` for collision domains, and `agent` only as
    a Claude/Codex/Gemini affinity hint.
+9. Keep planning on the start model. Add an `assessment` to each story: `taskClass`
+   (`mechanical`, `implementation`, `debugging`, `architecture`), `difficulty`, `uncertainty`,
+   `risk`, `scope`, `testability` (each `low`, `medium`, `high`), a concise `reason`, and
+   an actionable `approach` including checks. High testability means executable checks
+   reliably detect mistakes. Small security-sensitive changes can still be high-risk.
+   These are planning judgments, never invented success probabilities; Yoke selects the
+   execution model from configured profiles and independent outcomes.
 
 ## Format (`.yoke/prd.yaml`)
 

package/dist/agents/providers.js

@@ -1,4 +1,5 @@
 import { ModelSelectionSchema } from './contracts.js';
+import { fileURLToPath } from 'node:url';
 export { providerSpawnOptions, startProviderProcess, } from './process.js';
 const argsFor = (agent, permissions) => {
     if (agent === 'claude') {
@@ -13,7 +14,8 @@ const argsFor = (agent, permissions) => {
             return ['exec', '--dangerously-bypass-approvals-and-sandbox', '--json'];
         if (permissions === 'read-only')
             return ['exec', '--sandbox', 'read-only', '--json'];
-        return ['exec', '--sandbox', 'workspace-write', '--approve-for-me', '--json'];
+        // Automatic review already selects workspace-write and conflicts with --sandbox.
+        return ['exec', '--approve-for-me', '--json'];
     }
     if (permissions === 'unsafe')
         return ['--yolo', '--output-format', 'stream-json'];
@@ -26,8 +28,8 @@ export function buildProviderInvocation(agent, prompt, cwd, permissions = 'safe'
         throw new Error('Gemini does not support the bare startup selection');
     if (agent === 'gemini' && parsedSelection.reasoningEffort)
         throw new Error('Gemini does not support the reasoningEffort selection');
-    if (agent === 'gemini' && parsedSelection.nativeMultiAgent !== undefined)
-        throw new Error('Gemini does not support the nativeMultiAgent selection');
+    if (agent === 'gemini' && parsedSelection.nativeMultiAgent === true)
+        throw new Error('Gemini does not support enabling the nativeMultiAgent selection');
     const args = argsFor(agent, permissions);
     if (output.schemaFile !== undefined || output.jsonSchema !== undefined) {
         if (agent === 'codex' && output.schemaFile && output.jsonSchema === undefined) {
@@ -54,11 +56,16 @@ export function buildProviderInvocation(agent, prompt, cwd, permissions = 'safe'
     }
     if (agent === 'codex' && parsedSelection.nativeMultiAgent === false)
         args.push('--disable', 'multi_agent');
+    if (agent === 'claude' && parsedSelection.nativeMultiAgent === false)
+        args.push('--disallowedTools', 'Agent', 'Task', 'TeamCreate', 'SendMessage');
     if (parsedSelection.bare) {
         if (agent === 'codex')
             args.push('--ignore-user-config');
         else if (agent === 'claude')
             args.push('--bare');
     }
+    if (agent === 'gemini' && parsedSelection.nativeMultiAgent === false) {
+        return { command: process.execPath, args: [fileURLToPath(new URL('../../hooks/bounded-gemini.mjs', import.meta.url)), ...args], input: prompt, cwd };
+    }
     return { command: agent, args, input: prompt, cwd };
 }

package/dist/change/inbox.js

@@ -1,3 +1,4 @@
+import { assessmentInstructions } from "../routing/assessment.js";
 import { randomUUID } from 'node:crypto';
 import { execFileSync } from 'node:child_process';
 import { existsSync, mkdirSync, readFileSync, readdirSync, renameSync, rmSync, writeFileSync } from 'node:fs';
@@ -93,6 +94,7 @@ export function buildChangePrompt(request, proposalPath, stories) {
         `Change request ${request.id}: ${request.request}`,
         '',
         'Create an append-only proposal: add small new stories; never rewrite or delete existing stories.',
+        assessmentInstructions,
         `Existing story IDs: ${stories.map(story => story.id).join(', ') || '(none)'}`,
         'Every proposed story must have passes: false and 2-5 structured acceptance criteria.',
         'Every criterion must have a stable id, behavioral text, and one or more executable verify commands.',

package/dist/cli.js

@@ -134,10 +134,17 @@ export function main(argv) {
             }
             const loop = rest.includes('--loop') ? true : rest.includes('--no-loop') ? false : undefined;
             const routing = rest.includes('--routing') ? true : rest.includes('--no-routing') ? false : undefined;
+            const routingStrategy = rest.find(a => a.startsWith('--routing-strategy='))?.slice('--routing-strategy='.length);
+            if (routingStrategy && !['capability', 'balanced', 'cost', 'speed', 'quality'].includes(routingStrategy)) {
+                console.error('Invalid routing strategy');
+                return 1;
+            }
             return runSetup(targetDir, {
                 host: hostArg, agents, runner: runnerArg,
                 codeGraph: graphArg,
                 loop, routing, decisionPolicy: policyArg,
+                routingStrategy: routingStrategy,
+                routingPreset: rest.includes('--routing-preset'),
                 interactive: rest.includes('--yes') ? false : undefined,
             });
         }
@@ -466,7 +473,7 @@ export function main(argv) {
                     console.error(`Invalid --runner value: ${runnerArg} (expected claude|codex|gemini)`);
                     return 1;
                 }
-                const isolate = rest.includes('--isolate');
+                const isolate = rest.includes('--isolate') ? true : rest.includes('--no-isolate') ? false : undefined;
                 const reviewerArg = rest.find(a => a.startsWith('--reviewer='))?.slice('--reviewer='.length);
                 let reviewer;
                 if (reviewerArg) {
@@ -480,8 +487,8 @@ export function main(argv) {
                 const allowSelfReview = rest.includes('--allow-self-review');
                 const permissions = rest.includes('--unsafe') ? 'unsafe' : undefined;
                 const parallelArg = rest.find(a => a.startsWith('--parallel='));
-                const parallel = parallelArg ? Number(parallelArg.slice('--parallel='.length)) : 1;
-                if (!Number.isInteger(parallel) || parallel < 1) {
+                const parallel = parallelArg && parallelArg !== '--parallel=auto' ? Number(parallelArg.slice('--parallel='.length)) : undefined;
+                if (parallel !== undefined && (!Number.isInteger(parallel) || parallel < 1)) {
                     console.error(`Invalid --parallel value: ${parallelArg}`);
                     return 1;
                 }
@@ -512,9 +519,9 @@ export function main(argv) {
                     console.error(qualityFlags.error);
                     return 1;
                 }
-                return runLoopCommand(targetDir, { maxIterations: rawMax, agent, isolate, resumeWorktree: rest.includes('--resume-worktree'), parallel, reviewer, review, allowSelfReview, timeoutMinutes, json, routing, onAmbiguity: oaArg, decisionPolicy: dpArg, permissions, ...qualityFlags.options });
+                return runLoopCommand(targetDir, { maxIterations: rawMax, agent, isolate, resumeWorktree: rest.includes('--resume-worktree'), parallel, parallelAuto: parallelArg === '--parallel=auto', reviewer, review, allowSelfReview, timeoutMinutes, json, routing, onAmbiguity: oaArg, decisionPolicy: dpArg, permissions, ...qualityFlags.options });
             }
-            console.log('usage: yoke loop <on|off|status|decision|answer|resume [--discard] [--quality|--no-quality] [--quality-rounds=N] [--quality-minutes=N] [--quality-policy=<blocking|advisory>] [--quality-unbounded] [--candidates=N]|cleanup [--remove-worktrees] [--discard-stale-recovery]|run [--max=N] [--parallel=N] [--runner=<claude|codex|gemini>] [--reviewer=<claude|codex|gemini>] [--review] [--allow-self-review] [--routing|--no-routing] [--isolate] [--unsafe] [--timeout=<minutes>] [--decision-policy=<auto|critical>] [--quality|--no-quality] [--quality-rounds=N] [--quality-minutes=N] [--quality-policy=<blocking|advisory>] [--quality-unbounded] [--candidates=N] [--json]> [targetDir]');
+            console.log('usage: yoke loop <on|off|status|decision|answer|resume [--discard] [--quality|--no-quality] [--quality-rounds=N] [--quality-minutes=N] [--quality-policy=<blocking|advisory>] [--quality-unbounded] [--candidates=N]|cleanup [--remove-worktrees] [--discard-stale-recovery]|run [--max=N] [--parallel=<auto|N>] [--runner=<claude|codex|gemini>] [--reviewer=<claude|codex|gemini>] [--review] [--allow-self-review] [--routing|--no-routing] [--isolate|--no-isolate] [--unsafe] [--timeout=<minutes>] [--decision-policy=<auto|critical>] [--quality|--no-quality] [--quality-rounds=N] [--quality-minutes=N] [--quality-policy=<blocking|advisory>] [--quality-unbounded] [--candidates=N] [--json]> [targetDir]');
             return 1;
         }
         case 'new': {

package/dist/dashboard/analytics.js

@@ -0,0 +1,123 @@
+import { readMeasurements } from '../observability/history.js';
+import { readEvents } from '../observability/events.js';
+export function parsePeriod(params, now = Date.now()) {
+    const to = params.has('to') ? Date.parse(params.get('to')) : now;
+    const from = params.has('from') ? Date.parse(params.get('from')) : to - 30 * 86400000;
+    const bucket = params.get('bucket') ?? 'day';
+    if (!Number.isFinite(from) || !Number.isFinite(to) || from >= to || to - from > 366 * 86400000 || !['day', 'week', 'month'].includes(bucket))
+        throw Error('Choose a valid period of at most 366 days and day, week or month grouping');
+    return { from, to, bucket: bucket };
+}
+const finite = (value) => typeof value === 'number' && Number.isFinite(value) && value >= 0;
+const numeric = (value) => finite(value) ? value : 0;
+const name = (value) => typeof value === 'string' ? value.slice(0, 200) : 'unknown';
+function bucketOf(timestamp, bucket) {
+    const date = new Date(timestamp);
+    if (bucket === 'month')
+        return date.toISOString().slice(0, 7);
+    if (bucket === 'week')
+        date.setUTCDate(date.getUTCDate() - (date.getUTCDay() + 6) % 7);
+    return date.toISOString().slice(0, 10);
+}
+function empty() {
+    return { inputTokens: 0, outputTokens: 0, cachedInputTokens: 0, cacheWriteInputTokens: 0, reportedCostUsd: 0,
+        measuredCalls: 0, unknownCalls: 0, costReportedCalls: 0, incompleteCosts: 0, callDurationMs: 0, attemptDurationMs: 0,
+        attempts: 0, successfulAttempts: 0, accepted: 0, repairs: 0, escalations: 0, unmeasuredAttempts: 0 };
+}
+export function aggregateMeasurements(events, period) {
+    const total = empty(), buckets = new Map(), models = new Map(), modelBuckets = new Map(), tasks = new Map(), phases = new Map();
+    const modelDetails = new Map();
+    const seen = new Set(), accepted = new Set();
+    let earliest, latest;
+    const get = (map, key) => { if (!map.has(key))
+        map.set(key, empty()); return map.get(key); };
+    for (const event of events) {
+        const time = Date.parse(event.timestamp);
+        if (seen.has(event.id) || !Number.isFinite(time) || time < period.from || time >= period.to || event.type === 'status')
+            continue;
+        seen.add(event.id);
+        if (!earliest || event.timestamp < earliest)
+            earliest = event.timestamp;
+        if (!latest || event.timestamp > latest)
+            latest = event.timestamp;
+        const data = event.data ?? {}, bucket = get(buckets, bucketOf(event.timestamp, period.bucket)), task = get(tasks, event.storyId ?? 'unattributed');
+        const targets = [total, bucket, task];
+        if (event.type === 'tokens') {
+            const calls = Array.isArray(data.calls) && data.calls.length ? data.calls : [{ ...data, actualModel: data.model, durationMs: event.durationMs }];
+            for (const item of calls) {
+                if (!item || typeof item !== 'object')
+                    continue;
+                const call = item;
+                const provider = name(call.provider), model = name(call.actualModel), role = name(call.role);
+                const key = JSON.stringify([provider, model, role]);
+                modelDetails.set(key, { provider, model, role });
+                for (const target of [...targets, get(models, key), get(modelBuckets, JSON.stringify([bucketOf(event.timestamp, period.bucket), provider, model, role]))]) {
+                    target.inputTokens += numeric(call.inputTokens);
+                    target.outputTokens += numeric(call.outputTokens);
+                    target.cachedInputTokens += numeric(call.cachedInputTokens);
+                    target.cacheWriteInputTokens += numeric(call.cacheWriteInputTokens);
+                    target.reportedCostUsd += numeric(call.totalCostUsd);
+                    target.callDurationMs += numeric(call.durationMs);
+                    const measured = finite(call.inputTokens) && finite(call.outputTokens) && call.usageAvailable !== false && call.measurementComplete !== false;
+                    if (measured)
+                        target.measuredCalls++;
+                    else
+                        target.unknownCalls++;
+                    if (finite(call.totalCostUsd))
+                        target.costReportedCalls++;
+                    if (call.costMeasurementComplete === false || data.costMeasurementComplete === false)
+                        target.incompleteCosts++;
+                }
+            }
+            if (data.escalated === true)
+                for (const target of targets)
+                    target.escalations++;
+        }
+        else if (event.type === 'phase-ended') {
+            const phase = name(event.phase);
+            phases.set(phase, (phases.get(phase) ?? 0) + numeric(event.durationMs));
+            if (phase === 'repairing')
+                for (const target of targets)
+                    target.repairs++;
+        }
+        else if (event.type === 'attempt-ended') {
+            for (const target of targets) {
+                target.attempts++;
+                target.attemptDurationMs += numeric(event.durationMs);
+                if (['completed', 'passed'].includes(event.outcome ?? ''))
+                    target.successfulAttempts++;
+                if (data.usageAvailable !== true)
+                    target.unmeasuredAttempts++;
+            }
+        }
+        else if (event.type === 'accepted') {
+            const key = event.runId + ':' + (event.storyId ?? event.attemptId ?? event.id);
+            if (!accepted.has(key)) {
+                accepted.add(key);
+                for (const target of targets)
+                    target.accepted++;
+            }
+        }
+    }
+    const decorate = (value) => ({ ...value,
+        tokensPerCallMinute: value.callDurationMs > 0 ? (value.inputTokens + value.outputTokens) / (value.callDurationMs / 60000) : null,
+        tokensPerAccepted: value.accepted ? (value.inputTokens + value.outputTokens) / value.accepted : null,
+        timePerAcceptedMs: value.accepted ? value.attemptDurationMs / value.accepted : null,
+        costState: value.costReportedCalls === 0 ? 'unknown' : value.costReportedCalls === value.measuredCalls && value.unknownCalls === 0 && value.unmeasuredAttempts === 0 && value.incompleteCosts === 0 ? 'measured' : 'partial',
+    });
+    return { total: { ...decorate(total), tokensPerElapsedMinute: (total.inputTokens + total.outputTokens) / ((period.to - period.from) / 60000) },
+        buckets: [...buckets].sort(([a], [b]) => a.localeCompare(b)).map(([label, value]) => ({ label, ...decorate(value) })),
+        models: [...models].map(([key, value]) => ({ ...modelDetails.get(key), ...decorate(value) })),
+        modelBuckets: [...modelBuckets].sort(([a], [b]) => a.localeCompare(b)).map(([key, value]) => { const [label, provider, model, role] = JSON.parse(key); return { label, provider, model, role, ...decorate(value) }; }),
+        tasks: [...tasks].map(([storyId, value]) => ({ storyId, ...decorate(value) })),
+        phases: [...phases].map(([phase, durationMs]) => ({ phase, durationMs })), earliest, latest, };
+}
+export function projectAnalytics(root, period) {
+    const history = readMeasurements(root, period.from, period.to);
+    const recent = readEvents(root, 1000);
+    return { ...aggregateMeasurements([...history.events, ...recent], period),
+        from: new Date(period.from).toISOString(), to: new Date(period.to).toISOString(), bucket: period.bucket, timezone: 'UTC',
+        errors: history.errors,
+        coverage: 'Recorded measurements only. Earlier unrecorded or expired activity cannot be reconstructed. Usage is assigned to its reporting time; durations to their end time.',
+    };
+}

package/dist/dashboard/page.js

@@ -1,3 +1,4 @@
+import { dashboardPanels } from './panels.js';
 export function dashboardPage(token, nonce) {
     if (!/^[a-f0-9]{64}$/u.test(token) || !/^[A-Za-z0-9+/=]+$/u.test(nonce))
         throw new Error('Invalid dashboard session');
@@ -5,7 +6,7 @@ export function dashboardPage(token, nonce) {
 <html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1"><title>Yoke · Project workspace</title>
 <style nonce="${nonce}">
 :root{color-scheme:light;--ink:#15242d;--muted:#647077;--line:#dce1df;--paper:#f4f5f0;--accent:#c34c27;--green:#167452}*{box-sizing:border-box}body{margin:0;background:var(--paper);color:var(--ink);font:15px/1.5 system-ui,sans-serif}button{font:inherit;cursor:pointer}button:focus-visible,a:focus-visible{outline:3px solid #dc734a;outline-offset:3px}.layout{display:grid;grid-template-columns:250px minmax(0,1fr);min-height:100vh}aside{background:#142b32;color:#eef5f1;padding:34px 22px;display:flex;flex-direction:column;gap:30px}.brand{font-size:31px;font-weight:780;letter-spacing:-1.5px}.brand span{color:#ffb185}aside p{color:#afc3c6;font-size:13px}.label{text-transform:uppercase;font-size:11px;letter-spacing:1.7px;font-weight:750;color:var(--muted)}aside .label{color:#91a9ad}nav{display:grid;gap:7px}.nav-button{border:0;background:transparent;color:#cad8d9;text-align:left;padding:11px 12px;border-radius:8px;overflow-wrap:anywhere}.nav-button[aria-current=true]{background:#29444b;color:#fff}.aside-foot{margin-top:auto;border-top:1px solid #355057;padding-top:20px}main{max-width:1500px;width:100%;padding:40px 5vw 70px}.top{display:flex;justify-content:space-between;align-items:center;gap:20px}.local{font-size:12px;color:var(--green);background:#e2ece1;border-radius:30px;padding:6px 12px}.button{border:1px solid #bcc7c5;background:#fff;border-radius:7px;padding:9px 15px;color:var(--ink)}.button.primary{background:var(--ink);color:#fff;border-color:var(--ink)}h1{font-size:clamp(27px,3vw,40px);line-height:1.2;margin:17px 0 8px;letter-spacing:-1.4px}h2{font-size:18px;margin:0 0 18px}h3{font-size:16px;margin:0 0 8px}p{margin:6px 0}.muted{color:var(--muted)}.summary{max-width:850px;overflow-wrap:anywhere}.metrics{display:grid;grid-template-columns:repeat(3,minmax(0,1fr));gap:16px;margin:28px 0}.metric,.panel,.project-card{background:#fff;border:1px solid var(--line);border-radius:12px;padding:22px}.metric strong{display:block;font-size:28px;letter-spacing:-.8px;margin:8px 0 4px}.metric p{font-size:12px;color:var(--muted)}.cards{display:grid;grid-template-columns:repeat(auto-fit,minmax(260px,1fr));gap:18px;margin:28px 0}.project-card{display:flex;flex-direction:column;align-items:flex-start;gap:12px}.project-card p{color:var(--muted);overflow-wrap:anywhere}.project-card button{margin-top:auto}.columns{display:grid;grid-template-columns:1.2fr 1fr;gap:22px}.panel{margin-bottom:22px}.row{display:flex;justify-content:space-between;align-items:flex-start;gap:18px;padding:13px 0;border-top:1px solid #edf0eb}.row:first-child{border-top:0}.row-main{min-width:0;overflow-wrap:anywhere}.row small{display:block;color:var(--muted);margin-top:4px}.badge{font-size:11px;font-weight:650;background:#edf0ed;padding:4px 9px;border-radius:20px;white-space:nowrap}.badge.good{color:#166343;background:#e4f0e7}.badge.attention{color:#a43e22;background:#fff0e7}.notice{padding:13px 16px;margin:18px 0;border-left:3px solid var(--accent);background:#fff2e9;overflow-wrap:anywhere}.actions{display:flex;align-items:center;gap:12px;margin:22px 0}.path{font:12px/1.5 ui-monospace,monospace;word-break:break-all}.empty{padding:26px 0;color:var(--muted)}details{font-size:12px;margin-top:8px}details p{white-space:pre-wrap;max-height:220px;overflow:auto}.timeline .row{font-size:13px}.loading{padding:50px;color:var(--muted)}@media(max-width:900px){.layout{grid-template-columns:1fr}aside{padding:16px 24px;gap:12px}.brand{font-size:25px}aside>p,.aside-foot,aside>.label{display:none}nav{display:flex;overflow:auto}.nav-button{white-space:nowrap}.metrics{gap:9px}.metric{padding:15px}.columns{grid-template-columns:1fr}main{padding:25px 22px}.metric strong{font-size:23px}}@media(max-width:520px){.metrics{grid-template-columns:1fr}.top{align-items:flex-start}.local{white-space:nowrap}.metric strong{font-size:26px}.metric p{font-size:13px}}
-</style></head><body><div class="layout"><aside><div class="brand">yoke<span>.</span></div><p>Work you can verify.<br>Projects you can pick up again.</p><div class="label">Your workspace</div><nav id="navigation" aria-label="Projects"></nav><div class="aside-foot"><div class="label">Local workspace</div><p>Project data stays on this machine.</p></div></aside><main><div class="top"><div class="label">Project workspace</div><div><span class="local">● Local session</span> <button id="refresh" class="button">Refresh</button></div></div><div id="content" aria-live="polite"><p class="loading">Loading your projects…</p></div></main></div>
+main,aside,.panel{min-width:0}.actions{flex-wrap:wrap}.table-scroll{overflow-x:auto;max-width:100%}table{width:100%;border-collapse:collapse;font-size:13px}th,td{text-align:left;padding:10px;border-bottom:1px solid var(--line)}select,input{font:inherit;padding:8px;margin:4px;border:1px solid var(--line);border-radius:6px;max-width:100%}</style></head><body><div class="layout"><aside><div class="brand">yoke<span>.</span></div><p>Work you can verify.<br>Projects you can pick up again.</p><div class="label">Your workspace</div><nav id="navigation" aria-label="Projects"></nav><div class="aside-foot"><div class="label">Local workspace</div><p>Project data stays on this machine.</p></div></aside><main><div class="top"><div class="label">Project workspace</div><div><span class="local">● Local session</span> <button id="refresh" class="button">Refresh</button></div></div><div id="content" aria-live="polite"><p class="loading">Loading your projects…</p></div></main></div>
 <script nonce="${nonce}">
 const sessionToken = ${JSON.stringify(token)};
 const content=document.getElementById('content'), navigation=document.getElementById('navigation');
@@ -13,7 +14,7 @@ let selected=null, projects=[];
 function el(tag,text,cls){const node=document.createElement(tag);if(text!==undefined)node.textContent=String(text);if(cls)node.className=cls;return node}
 function append(parent,...children){for(const child of children)parent.append(child);return parent}
 function badge(state){return el('span',state||'unknown','badge '+(['complete','passed'].includes(state)?'good':['blocked','failed','paused','unverified'].includes(state)?'attention':''))}
-function button(label,action,primary=false){const node=el('button',label,'button'+(primary?' primary':''));node.addEventListener('click',action);return node}
+function button(label,action,primary=false){const node=el('button',label,'button'+(primary?' primary':''));node.addEventListener('click',()=>Promise.resolve().then(action).catch(error=>content.append(el('p',error.message,'notice'))));return node}
 function duration(ms){if(!Number.isFinite(ms))return 'Unknown';if(ms<60000)return Math.round(ms/1000)+'s';if(ms<3600000)return Math.round(ms/60000)+'m';return (ms/3600000).toFixed(1)+'h'}
 function tokenText(value){return Number.isFinite(value)?value.toLocaleString('en-US'):'Unknown'}
 function taskTiming(task,estimate){const planned=estimate?.available?estimate.tasks.find(item=>item.storyId===task.id):undefined;return planned?'Predicted '+duration(planned.endMs-planned.startMs)+' · planned start +'+duration(planned.startMs):task.passes?'Completed · timing unknown':'Duration and planned start unknown'}
@@ -23,9 +24,10 @@ function metric(title,value,note){return append(el('div',undefined,'metric'),el(
 async function api(path,options){const response=await fetch(path,options);const data=await response.json();if(!response.ok)throw Error(data.error||'Request failed');return data}
 function nav(){navigation.replaceChildren();const all=el('button','All projects','nav-button');all.setAttribute('aria-current',String(selected===null));all.onclick=()=>{selected=null;renderOverview()};navigation.append(all);for(const project of projects){const item=el('button',project.name,'nav-button');item.setAttribute('aria-current',String(selected===project.id));item.onclick=()=>showProject(project.id);navigation.append(item)}}
 function heading(title,subtitle){content.replaceChildren(el('h1',title),el('p',subtitle,'summary muted'))}
-function renderOverview(){nav();heading('A clear view of the work.','Goals, independent checks and the next thing that needs your attention.');const blocked=projects.filter(p=>p.errors.length||['blocked','paused'].includes(p.goal?.status||p.status?.state)).length;const active=projects.filter(p=>['active','running'].includes(p.goal?.status||p.status?.state)).length;content.append(append(el('div',undefined,'metrics'),metric('Projects',projects.length,'Registered on this machine'),metric('In progress',active,'Active goals and story loops'),metric('Needs attention',blocked,'Blocked, paused or unavailable')));const cards=el('div',undefined,'cards');for(const p of projects){const card=append(el('article',undefined,'project-card'),badge(p.goal?.status||p.status?.state||(p.errors.length?'unavailable':'ready')),el('h2',p.name),el('p',p.goal?.objective||'No active objective yet.'),el('p',p.root,'path'));if(p.errors.length)card.append(el('p',p.errors.join('; '),'notice'));card.append(button('Open project →',()=>showProject(p.id)));cards.append(card)}if(!projects.length)cards.append(el('p','No registered projects. Run yoke dashboard from a project directory.','empty'));content.append(cards)}
+function renderOverview(){nav();heading('A clear view of the work.','Goals, independent checks and the next thing that needs your attention.');const blocked=projects.filter(p=>p.errors.length||['blocked','paused'].includes(p.goal?.status||p.status?.state)).length;const active=projects.filter(p=>['active','running'].includes(p.goal?.status||p.status?.state)).length;content.append(append(el('div',undefined,'metrics'),metric('Projects',projects.length,'Registered on this machine'),metric('In progress',active,'Active goals and story loops'),metric('Needs attention',blocked,'Blocked, paused or unavailable')));content.append(button('Compare consumption',showWorkspaceUsage));const cards=el('div',undefined,'cards');for(const p of projects){const card=append(el('article',undefined,'project-card'),badge(p.goal?.status||p.status?.state||(p.errors.length?'unavailable':'ready')),el('h2',p.name),el('p',p.goal?.objective||'No active objective yet.'),el('p',p.root,'path'));if(p.errors.length)card.append(el('p',p.errors.join('; '),'notice'));card.append(button('Open project →',()=>showProject(p.id)));cards.append(card)}if(!projects.length)cards.append(el('p','No registered projects. Run yoke dashboard from a project directory.','empty'));content.append(cards)}
 function row(title,note,state){return append(el('div',undefined,'row'),append(el('div',undefined,'row-main'),el('div',title),el('small',note)),badge(state))}
-async function showProject(id){selected=id;nav();heading('Loading project…','');try{const p=await api('/api/projects/'+id);if(selected!==id)return;heading(p.name,p.goal?.objective||'No active goal. Explore the saved work and acceptance evidence below.');content.append(el('p',p.root,'path'));for(const error of p.errors)content.append(el('div',error,'notice'));if(p.goal?.reason||p.status?.reason)content.append(el('div',p.goal?.reason||p.status?.reason,'notice'));const tasks=p.stories||[],passed=tasks.filter(t=>t.passes).length, estimate=p.estimate;const tokens=p.status?.tokens,cost=tokens?.totalCostUsd;const costState=p.status?.measurement?.costAvailable||'unknown';const measuredCost=costState==='measured'&&Number.isFinite(cost);const costLabel=Number.isFinite(cost)&&costState==='partial'?'$'+cost.toFixed(3)+' known':measuredCost?'$'+cost.toFixed(3):'Unknown';const range=estimate?.available?duration(estimate.lowerMs)+' – '+duration(estimate.upperMs):'Unknown';content.append(append(el('div',undefined,'metrics'),metric('Accepted tasks',passed+' / '+tasks.length,'Saved task acceptance state'),metric('Remaining time',range,estimate?.available?'Empirical range · '+estimate.sampleCount+' samples · '+estimate.confidence+' confidence':estimate?.reason||'No duration evidence yet'),metric('Reported cost',costLabel,costState==='partial'?'Partial measurement; total cost unknown':measuredCost?'For measured calls; other work may be unreported':'Provider cost is not fully reported')));renderUsage(p);const actions=el('div',undefined,'actions');actions.append(badge(p.goal?.status||p.status?.state||'ready'));if(p.goal&&!['complete','paused'].includes(p.goal.status)){const pause=button('Request pause',async()=>{pause.disabled=true;try{await api('/api/projects/'+id+'/pause',{method:'POST',headers:{'x-yoke-token':sessionToken}});pause.textContent='Pause requested';actions.append(el('small','Takes effect at a safe boundary.','muted'))}catch(error){pause.disabled=false;actions.append(el('span',error.message,'notice'))}});actions.append(pause)}content.append(actions);const columns=el('div',undefined,'columns'),left=el('div'),right=el('div');const taskPanel=append(el('section',undefined,'panel'),el('h2','Tasks'));for(const task of tasks)taskPanel.append(row(task.title,task.id+(task.area?' · '+task.area:'')+(task.needs?.length?' · after '+task.needs.join(', '):'')+' · '+taskTiming(task,estimate),task.passes?'passed':'open'));if(!tasks.length)taskPanel.append(el('p','No story plan saved yet.','empty'));left.append(taskPanel);const checks=append(el('section',undefined,'panel'),el('h2','Acceptance evidence'));if(p.check){checks.append(el('p',p.check.summary,'muted'));for(const criterion of p.check.criteria){const item=row(criterion.text,criterion.id,criterion.status);if(criterion.summary){const detail=append(el('details'),el('summary','View evidence'),el('p',criterion.summary));item.firstChild.append(detail)}checks.append(item)}checks.append(el('p','Checked '+p.check.generatedAt+' · historical evidence, not a fresh verification.','muted'))}else checks.append(el('p','No saved independent check. Run yoke check to create evidence.','empty'));left.append(checks);const attempts=append(el('section',undefined,'panel'),el('h2','Goal attempts'));for(const attempt of p.goal?.attempts||[])attempts.append(row(attempt.provider||'Agent',(attempt.summary||duration(attempt.durationMs))+' · input '+tokenText(attempt.inputTokens)+' / output '+tokenText(attempt.outputTokens)+' tokens',attempt.success?'finished':'failed'));if(!p.goal?.attempts?.length)attempts.append(el('p','No goal attempts recorded.','empty'));right.append(attempts);const timeline=append(el('section',undefined,'panel timeline'),el('h2','Recent activity'));for(const event of (p.events||[]).slice(-16).reverse())timeline.append(row(event.storyId||event.type,event.phase?event.phase+' · '+duration(event.durationMs):event.timestamp,event.outcome||event.type));if(!p.events?.length)timeline.append(el('p','Activity will appear as Yoke records transitions.','empty'));right.append(timeline);append(columns,left,right);content.append(columns)}catch(error){heading('Project unavailable',error.message)}}
+
+${dashboardPanels()}
 async function refresh(){try{projects=await api('/api/projects');if(selected)await showProject(selected);else renderOverview()}catch(error){heading('Workspace unavailable',error.message)}}
 document.getElementById('refresh').onclick=refresh;refresh();
 </script></body></html>`;

package/dist/dashboard/panels.js

@@ -0,0 +1,19 @@
+/** Static script; all project-controlled values are inserted through textContent. */
+export function dashboardPanels() {
+    return String.raw `
+let projectView='now', periodDays=30, bucket='day', customFrom='', customTo='', requestVersion=0;
+function panel(title){return append(el('section',undefined,'panel'),el('h2',title))}
+function table(headers,rows){const wrap=el('div',undefined,'table-scroll'),t=el('table'),head=el('thead'),hr=el('tr');for(const title of headers)hr.append(el('th',title));head.append(hr);t.append(head);const body=el('tbody');for(const values of rows){const r=el('tr');for(const value of values)r.append(el('td',String(value)));body.append(r)}t.append(body);wrap.append(t);return wrap}
+function costText(t){return t.costState==='unknown'?'Unknown':'$'+t.reportedCostUsd.toFixed(3)+(t.costState==='partial'?' reported (partial)':' reported')}
+function rate(value){return Number.isFinite(value)?value.toLocaleString('en-US',{maximumFractionDigits:1}):'Unknown'}
+function usageChart(buckets){const data=buckets.slice(-31);const svg=document.createElementNS('http://www.w3.org/2000/svg','svg');svg.setAttribute('viewBox','0 0 800 220');svg.setAttribute('role','img');svg.setAttribute('aria-label','Recorded input and output tokens over the latest '+data.length+' periods; exact values in the following table');const max=Math.max(1,...data.map(d=>d.inputTokens+d.outputTokens));const step=760/Math.max(1,data.length);data.forEach((d,i)=>{let y=180;for(const [value,color] of [[d.inputTokens,'#29444b'],[d.outputTokens,'#c34c27']]){const h=value/max*160;y-=h;const r=document.createElementNS(svg.namespaceURI,'rect');for(const [k,v] of Object.entries({x:20+i*step,y,width:Math.max(1,step-4),height:h,fill:color}))r.setAttribute(k,String(v));const title=document.createElementNS(svg.namespaceURI,'title');title.textContent=d.label+': input '+d.inputTokens+', output '+d.outputTokens;r.append(title);svg.append(r)}if(i===0||i===data.length-1){const label=document.createElementNS(svg.namespaceURI,'text');label.setAttribute('x',String(i===0?20:780));label.setAttribute('y','205');label.setAttribute('text-anchor',i===0?'start':'end');label.setAttribute('font-size','12');label.textContent=d.label;svg.append(label)}});return svg}
+async function showWorkspaceUsage(){selected=null;const version=++requestVersion;nav();heading('Compare project consumption','Recorded usage in the selected period; missing measurements remain unknown.');periodControls(null);const p=panel('Projects');p.append(el('p','Loading…','muted'));content.append(p);const rows=[];const query=queryPeriod();for(const project of projects){try{const a=await api('/api/projects/'+project.id+'/analytics?'+query);rows.push([project.name,tokenText(a.total.inputTokens),tokenText(a.total.outputTokens),costText(a.total),a.total.accepted,a.total.unknownCalls,a.errors.length?'Partial history':'Recorded portion'])}catch(error){rows.push([project.name,'Unknown','Unknown','Unknown','Unknown','Unknown',error.message])}if(version!==requestVersion||selected!==null)return}p.replaceChildren(el('h2','Projects'),table(['Project','Input','Output','Cost','Accepted','Unknown calls','Coverage'],rows))}
+function queryPeriod(){const end=customTo?new Date(customTo+'T00:00:00Z').getTime()+86400000:Date.now();const start=customFrom?Date.parse(customFrom+'T00:00:00Z'):end-periodDays*86400000;return new URLSearchParams({from:new Date(start).toISOString(),to:new Date(end).toISOString(),bucket}).toString()}
+function periodControls(id){const p=panel('Period · UTC');const select=el('select');select.setAttribute('aria-label','Period');for(const [value,label] of [[1,'Last 24 hours'],[7,'Last 7 days'],[30,'Last 30 days'],[90,'Last 90 days'],[365,'Last 365 days']]){const o=el('option',label);o.value=String(value);o.selected=value===periodDays;select.append(o)}select.onchange=()=>{periodDays=Number(select.value);customFrom='';customTo='';(id?showProject(id):showWorkspaceUsage())};p.append(select);const grouping=el('select');grouping.setAttribute('aria-label','Group by');for(const value of ['day','week','month']){const o=el('option',value);o.value=value;o.selected=value===bucket;grouping.append(o)}grouping.onchange=()=>{bucket=grouping.value;(id?showProject(id):showWorkspaceUsage())};p.append(grouping);const from=el('input'),to=el('input');from.type=to.type='date';from.value=customFrom;to.value=customTo;from.setAttribute('aria-label','From date UTC');to.setAttribute('aria-label','Through date UTC');p.append(from,to,button('Apply dates',()=>{if(!from.value||!to.value||from.value>to.value){p.append(el('p','Choose both dates in chronological order.','notice'));return}customFrom=from.value;customTo=to.value;(id?showProject(id):showWorkspaceUsage())}));p.append(el('p','Calendar dates include the entire end date. Maximum range: 366 days.','muted'));content.append(p)}
+function renderNow(p){const status=p.status||{},goal=p.goal||{},workers=status.parallel?.workers||[];const age=status.updatedAt?Date.now()-Date.parse(status.updatedAt):undefined;const stale=Number.isFinite(age)&&age>20*60000;const summary=panel('Now');summary.append(badge(goal.status||status.state||'unknown'));summary.append(el('p',goal.reason||status.reason||'No reported blocker.'));summary.append(el('p','Last status: '+(status.updatedAt||'Unknown')+(stale?' · stale; activity is not confirmed':''),'muted'));summary.append(el('p','Reported workers: '+workers.length+' / '+(status.parallel?.maxConcurrency||1)+' · queue: '+tokenText(status.parallel?.queuedCandidates),'muted'));if(goal.pendingAttempt)summary.append(row('Goal attempt',goal.pendingAttempt.provider+' · requested model '+(goal.pendingAttempt.model||'provider default')+' · started '+goal.pendingAttempt.startedAt,'running'));if(status.execution&&status.state==='running')summary.append(el('p',status.execution.provider+' · requested model '+(status.execution.requestedModel||'provider default')+' · elapsed '+duration(Date.now()-Date.parse(status.execution.startedAt))));if(status.story&&!workers.length)summary.append(row(status.storyTitle||status.story,status.phase||'Phase unknown',status.state));for(const w of workers)summary.append(row(w.storyTitle||w.story,[w.selectedProvider||w.provider,'requested model '+(w.selectedModel||w.model||'provider default'),w.phase||w.lifecycle||'working',w.startedAt?'elapsed '+duration(Date.now()-Date.parse(w.startedAt)):null,w.quality?'repair '+w.quality.usedRepairs:null].filter(Boolean).join(' · '),w.lifecycle||'running'));if(status.parallel?.integrator){const w=status.parallel.integrator;summary.append(row('Integration: '+(w.storyTitle||w.story),w.phase||'checking','integrating'))}if(!workers.length&&!status.story&&!goal.pendingAttempt)summary.append(el('p','No task currently reported.','empty'));summary.append(el('p','Status refreshes every 5 seconds. Requested models are not proof of the model actually used; reported model identities appear under Usage & time.','muted'));content.append(summary);const tasks=panel('Tasks');for(const task of p.stories||[])tasks.append(row(task.title,task.id+(task.needs?.length?' · after '+task.needs.join(', '):'')+' · '+taskTiming(task,p.estimate),task.passes?'passed':workers.some(w=>w.story===task.id)?'running':'open'));content.append(tasks);const routing=panel('Model selection');for(const [id,d] of Object.entries(status.routingDecisions||{})){routing.append(row(id,d.provider+' / '+(d.model||'provider default')+(d.reasoningEffort?' · '+d.reasoningEffort:''),d.profile));routing.append(el('p',d.reason));routing.append(el('p','Next escalation: '+d.next,'muted'))}if(!Object.keys(status.routingDecisions||{}).length)routing.append(el('p','No recorded model selection for this run.','empty'));content.append(routing);const activity=panel('Recent activity');for(const e of (p.events||[]).slice(-16).reverse())activity.append(row(e.storyId||e.type,e.timestamp+(e.phase?' · '+e.phase:'')+(Number.isFinite(e.durationMs)?' · '+duration(e.durationMs):''),e.outcome||e.type));content.append(activity)}
+function renderUsageHistory(a){const t=a.total;content.append(append(el('div',undefined,'metrics'),metric('Recorded input',tokenText(t.inputTokens),'Output: '+tokenText(t.outputTokens)),metric('Reported cost',costText(t),'Missing charges are not estimated'),metric('Tokens / elapsed minute',rate(t.tokensPerElapsedMinute),'Input + output / entire selected period')));const notes=panel('Measurement coverage');notes.append(el('p',a.coverage));notes.append(el('p','First record in period: '+(a.earliest||'none')+' · latest: '+(a.latest||'none'),'muted'));notes.append(el('p','Measured calls: '+t.measuredCalls+' · calls with unknown usage: '+t.unknownCalls+' · unmeasured attempts: '+t.unmeasuredAttempts));notes.append(el('p','Tokens / recorded call minute: '+rate(t.tokensPerCallMinute)+' · summed call time: '+duration(t.callDurationMs)+'. Parallel calls overlap; this is consumption intensity, not generation speed.'));notes.append(el('p','Cache reads: '+tokenText(t.cachedInputTokens)+' · cache writes: '+tokenText(t.cacheWriteInputTokens)+'. These are reported categories and are not added again to input totals.','muted'));for(const error of a.errors)notes.append(el('p',error,'notice'));content.append(notes);const series=panel('Consumption over time');series.append(usageChart(a.buckets));series.append(el('p','Dark: input · orange: output. Chart shows up to 31 latest periods; table includes all measured periods.','muted'));series.append(table(['UTC '+a.bucket,'Input','Output','Cache reads','Reported cost'],a.buckets.map(b=>[b.label,tokenText(b.inputTokens),tokenText(b.outputTokens),tokenText(b.cachedInputTokens),costText(b)])));if(!a.buckets.length)series.append(el('p','No measurements in this period.','empty'));content.append(series);const models=panel('Reported models in this period');models.append(table(['Provider','Actual model','Role','Input','Output','Call time','Cost'],a.models.map(m=>[m.provider,m.model,m.role,tokenText(m.inputTokens),tokenText(m.outputTokens),duration(m.callDurationMs),costText(m)])));content.append(models);const modelTimeline=panel('Models over time');modelTimeline.append(table(['UTC '+a.bucket,'Provider','Actual model','Role','Input','Output'],a.modelBuckets.map(m=>[m.label,m.provider,m.model,m.role,tokenText(m.inputTokens),tokenText(m.outputTokens)])));content.append(modelTimeline);const tasks=panel('Consumption by task');tasks.append(table(['Task','Input','Output','Attempt time','Cost'],a.tasks.map(t=>[t.storyId,tokenText(t.inputTokens),tokenText(t.outputTokens),duration(t.attemptDurationMs),costText(t)])));content.append(tasks);const phases=panel('Recorded phase time');phases.append(table(['Phase','Summed duration'],a.phases.map(p=>[p.phase,duration(p.durationMs)])));phases.append(el('p','Overlapping worker time is summed. Unrecorded queue time and human waiting time remain unknown.','muted'));content.append(phases)}
+function renderResults(p,a){const t=a.total;content.append(append(el('div',undefined,'metrics'),metric('Accepted in period',t.accepted,'Recorded acceptance events'),metric('Repair phases',t.repairs,'Routing escalations: '+t.escalations),metric('Tokens / acceptance',rate(t.tokensPerAccepted),'Reported input + output, including failed work')));const attempts=panel('Measured outcomes');attempts.append(el('p','Ended attempts: '+t.attempts+' · explicitly successful attempts: '+t.successfulAttempts+' · average summed attempt time per acceptance: '+duration(t.timePerAcceptedMs)));attempts.append(el('p','Worker termination alone is not counted as successful acceptance. Rates only describe recorded activity in the selected period.','muted'));attempts.append(table(['Task','Attempts','Accepted','Repairs','Escalations','Tokens / acceptance'],a.tasks.map(v=>[v.storyId,v.attempts,v.accepted,v.repairs,v.escalations,rate(v.tokensPerAccepted)])));content.append(attempts);const checks=panel('Latest saved acceptance evidence');if(p.check){checks.append(el('p',p.check.summary));for(const c of p.check.criteria){const item=row(c.text,c.id,c.status);item.firstChild.append(append(el('details'),el('summary','View evidence'),el('p',c.summary)));checks.append(item)}checks.append(el('p','Checked '+p.check.generatedAt+' · historical evidence; independent of the selected statistics period.','muted'))}else checks.append(el('p','No saved independent check.','empty'));content.append(checks);const goals=panel('Saved goal attempts');for(const attempt of p.goal?.attempts||[])goals.append(row(attempt.provider||'Agent',(attempt.summary||'')+' · '+duration(attempt.durationMs)+' · input '+tokenText(attempt.inputTokens)+' / output '+tokenText(attempt.outputTokens),attempt.success?'finished':'failed'));content.append(goals)}
+async function showProject(id){const version=++requestVersion;selected=id;nav();try{const p=await api('/api/projects/'+id);const a=projectView==='now'?null:await api('/api/projects/'+id+'/analytics?'+queryPeriod());if(version!==requestVersion||selected!==id)return;heading(p.name,p.goal?.objective||'Saved project work');content.append(el('p',p.root,'path'));for(const error of p.errors)content.append(el('p',error,'notice'));const tabs=el('div',undefined,'actions');for(const [view,label] of [['now','Now'],['usage','Usage & time'],['results','Results']]){const b=button(label,()=>{projectView=view;showProject(id)},projectView===view);b.setAttribute('aria-pressed',String(projectView===view));tabs.append(b)}if(p.goal&&!['complete','paused'].includes(p.goal.status))tabs.append(button('Request pause',async()=>{await api('/api/projects/'+id+'/pause',{method:'POST',headers:{'x-yoke-token':sessionToken}});showProject(id)}));content.append(tabs);if(projectView==='now'){const tasks=p.stories||[];content.append(append(el('div',undefined,'metrics'),metric('Accepted tasks',tasks.filter(t=>t.passes).length+' / '+tasks.length,'Saved acceptance state'),metric('Remaining time',p.estimate?.available?duration(p.estimate.lowerMs)+' – '+duration(p.estimate.upperMs):'Unknown',p.estimate?.available?p.estimate.sampleCount+' samples · empirical range':'No reliable duration history'),metric('Project status',p.goal?.status||p.status?.state||'unknown','Latest reported state')));renderNow(p)}else{periodControls(id);if(projectView==='usage')renderUsageHistory(a);else renderResults(p,a)}}catch(error){if(version===requestVersion&&selected===id)heading('Project unavailable',error.message)}}
+if(typeof setInterval==='function')setInterval(()=>{if(selected&&projectView==='now'&&typeof document.hidden!=='undefined'&&!document.hidden&&!['INPUT','SELECT','TEXTAREA'].includes(document.activeElement?.tagName)&&!document.activeElement?.matches?.(':focus-visible'))showProject(selected)},5000);
+`;
+}

package/dist/dashboard/server.js

@@ -9,9 +9,10 @@ import { dashboardPage } from './page.js';
 import { readEvents } from '../observability/events.js';
 import { estimateSchedule } from '../estimation/schedule.js';
 import { pauseProjectGoal } from '../goals/command.js';
+import { parsePeriod, projectAnalytics } from './analytics.js';
 const text = z.string().max(16000);
 const number = z.number().finite().nonnegative();
-const Goal = z.object({ objective: text, status: z.enum(['active', 'running', 'paused', 'blocked', 'complete']), reason: text.optional(), attempts: z.array(z.object({ durationMs: number.optional(), provider: text.optional(), success: z.boolean().optional(), summary: text.optional(), inputTokens: number.optional(), outputTokens: number.optional() })).max(200).default([]) });
+const Goal = z.object({ objective: text, status: z.enum(['active', 'running', 'paused', 'blocked', 'complete']), reason: text.optional(), pendingAttempt: z.object({ provider: text, model: text.optional(), startedAt: text }).optional(), attempts: z.array(z.object({ durationMs: number.optional(), provider: text.optional(), success: z.boolean().optional(), summary: text.optional(), inputTokens: number.optional(), outputTokens: number.optional() })).max(200).default([]) });
 const Status = z.object({ state: text, phase: text.optional(), reason: text.optional(), progress: z.object({ passed: number, total: number }).optional(), tokens: z.object({ inputTokens: number, outputTokens: number, totalCostUsd: number.optional(), measurementComplete: z.boolean().optional(), model: text.optional(), calls: z.array(z.object({ usageAvailable: z.boolean().optional() })).max(10000).optional() }).optional(), measurement: z.object({ costAvailable: z.enum(['unknown', 'partial', 'measured']), measuredCalls: number.optional(), unknownCalls: number.optional(), unmeasuredAttempts: number.optional() }).passthrough().optional(), parallel: z.object({ maxConcurrency: number }).passthrough().optional() }).passthrough();
 const Stories = z.array(z.object({ id: text, title: text, passes: z.boolean(), priority: number.optional(), area: text.optional(), writes: z.array(text).optional(), needs: z.array(text).optional() })).max(2000);
 const Check = z.object({ id: text, status: z.enum(['passed', 'failed', 'unverified']), generatedAt: text, summary: text, criteria: z.array(z.object({ id: text, text, status: z.enum(['passed', 'failed', 'unverified']), summary: text })).max(500) });
@@ -120,18 +121,34 @@ export async function startDashboard(options = {}) {
                 send(200, listProjects().map(project => snapshot(project, false)));
                 return;
             }
-            const match = /^\/api\/projects\/([a-f0-9]{32})(\/pause)?$/u.exec(path);
+            const match = /^\/api\/projects\/([a-f0-9]{32})(\/pause|\/analytics)?$/u.exec(path);
             if (match) {
                 const project = listProjects().find(project => project.id === match[1]);
                 if (!project) {
                     send(404, { error: 'Unknown project' });
                     return;
                 }
+                if (req.method === 'GET' && match[2] === '/analytics') {
+                    if (project.error) {
+                        send(409, { error: project.error });
+                        return;
+                    }
+                    let period;
+                    try {
+                        period = parsePeriod(new URL(req.url, origin).searchParams);
+                    }
+                    catch (error) {
+                        send(400, { error: error.message });
+                        return;
+                    }
+                    send(200, projectAnalytics(project.root, period));
+                    return;
+                }
                 if (req.method === 'GET' && !match[2]) {
                     send(200, snapshot(project, true));
                     return;
                 }
-                if (req.method === 'POST' && match[2]) {
+                if (req.method === 'POST' && match[2] === '/pause') {
                     if (project.error || !snapshot(project, false).goal) {
                         send(409, { error: 'No readable project goal' });
                         return;