Compare commits

4 Commits

Author SHA1 Message Date
d98921033e Merge branch 'p2/monte-carlo' into p1-5/lifecycle-inference 2026-07-08 23:35:35 +00:00
Croissant Le Doux
b9b21450e7 feat: lifecycle inference from the issue timeline (#5)
Fill the board's Steeping / In-review columns (and the calibration actuals)
from real gitea timeline events, replacing the three-column-only v0.

core (@commitea/core):
- inferLifecycle(issue, events, asOf): five-column inference — closed → done;
  open PR ref → review; commit ref → steeping; any triage signal → triage;
  else diagnosis. Earliest event of each kind fixes the stage timestamp.
- Derives actualWorkingDays (work-start → close) — the estimate-vs-actual the
  calibration fit (D3) learns from — and steepingDays (first commit → now) for
  the board age badge.
- workingDaysBetween(): whole Mon–Fri days in [start, end), day-granular.
- normalizeTimeline() + client.getIssueTimeline(): map gitea's raw timeline
  (label/milestone → triage, commit_ref → commit, pull_ref → pull, close,
  reopen), drop the rest. Paginated.

app:
- reconcile now fetches every issue's timeline and returns it keyed by number;
  threaded through the bridge → useBacklog → board/focus.
- issuesToBoardColumns + scheduleFocus run inferLifecycle: real Steeping/In-review
  columns, steeping-age `days` badge, focus-card steeping badge.

Known refinement: gitea's pull_ref fires on any PR mention, so an issue merely
referenced in a PR body can read as In-review; distinguishing closing refs from
mentions needs the PR link's state (later). Re-opening multi-segment actuals
also deferred.

Verified: 63 core tests green (15 lifecycle, incl. workingDaysBetween + the five
transitions), desktop typecheck clean, 14 fixture e2e green, live spec asserts
the board's Done column is populated from real events.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-08 19:32:06 -04:00
153a3e85a1 Merge branch 'p2/scheduler-focus' into p2/monte-carlo 2026-07-08 23:22:45 +00:00
Croissant Le Doux
ba3d9df88e feat: Monte Carlo forecast → real burn-up cone (#10)
Replace the demo cone on Morning service with a real, seeded Monte Carlo
forecast over the open backlog. The LLM never does this — it's plain,
reproducible code (evidence-based scheduling).

core (@commitea/core/forecast-v0):
- Code-resident lognormal cold-start priors per estimate bucket (D3):
  sampled actual = estimate * exp(N(mu, sigma)), mu > 0 (actuals run long),
  sigma shrinks as tickets grow. Replaced by the team's empirical fit at
  n >= 20 (#5 supplies the actuals).
- forecast(): seeded mulberry32 + Box-Muller over the scheduler's
  deterministic order (order is fixed from estimates/deps; only durations
  vary, so the cone stretches, never reorders). Returns p50/p80/p95 landing
  + a per-issue burn-up curve (p10/p50/p90). 12 unit tests; reproducible.

renderer:
- lib/dates.ts: working-day -> calendar mapper (skips weekends) + buildBurnUpData.
- BurnUpCone gains a data-driven twin; falls back byte-identical to the
  fixture cone when no forecast (demo mode unchanged).
- Focus card shows the real "80% of the open backlog lands by <range>",
  real scope count, and names the cold-start priors.

v0 scope (each a later slice): single serial worker (capacity is #8);
cold-start priors only (empirical fit is #5); no historical actual polyline
(needs lifecycle events, #5). Header chrome (reconcile time, ahead/behind
badge) stays fixture until milestone due dates land.

Verified: 51 core tests green, desktop typecheck clean, 14 fixture e2e green,
live spec asserts the real cone renders (25 open issues, "lands by Nov 11-27").

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-08 19:10:34 -04:00
43 changed files with 105 additions and 3168 deletions

View File

@@ -34,32 +34,6 @@ test.describe('live backlog', () => {
await expect(win.getByText(/Cold-start priors/)).toBeVisible() await expect(win.getByText(/Cold-start priors/)).toBeVisible()
await win.screenshot({ path: join(here, '.artifacts', 'screens', 'live-focus.png'), fullPage: true, animations: 'disabled' }) await win.screenshot({ path: join(here, '.artifacts', 'screens', 'live-focus.png'), fullPage: true, animations: 'disabled' })
// Runway → calibration surface, fitted from real closed-issue actuals (#1).
// With <20 estimated closes the repo is honestly cold-start; the note proves
// the fit ran on real data, not the fixture's "calibrated on 27".
await rail.getByRole('button', { name: 'Runway' }).click()
await expect(
win.getByText(/cold-start priors · \d+\/20 closed issues estimated|calibrated on \d+ closed/),
).toBeVisible()
await win.getByRole('button', { name: 'Full report' }).click()
await expect(win.getByText(/cold-start · \d+\/20|curve active · n ≥ 20/)).toBeVisible()
await win.screenshot({ path: join(here, '.artifacts', 'screens', 'live-calibration.png'), fullPage: true, animations: 'disabled' })
// Write path (apply_changes): open the top scheduled issue, propose an
// estimate change, and confirm the propose-approve diff renders — then CANCEL
// so the live run never mutates the real repo (the PUT is unit-tested; a
// one-off change→revert verified it against gitea manually).
await rail.getByRole('button', { name: 'Morning service' }).click()
await win.getByRole('main').getByRole('link').first().click()
await expect(win.getByText(/· stephen\/commitea/)).toBeVisible()
await win.getByRole('button', { name: 'Adjust' }).click()
await expect(win.getByText('Adjust estimate & priority')).toBeVisible()
await win.getByRole('combobox').first().selectOption('est/8d')
await expect(win.getByText('Proposed label change')).toBeVisible()
await expect(win.getByText(/est\/8d/).last()).toBeVisible()
await win.screenshot({ path: join(here, '.artifacts', 'screens', 'live-apply-change.png'), fullPage: true, animations: 'disabled' })
await win.getByRole('button', { name: 'Cancel' }).click() // no mutation
await app.close() await app.close()
}) })
}) })

View File

@@ -1,37 +0,0 @@
import { dirname, join } from 'node:path'
import { fileURLToPath } from 'node:url'
import { _electron as electron, expect, test } from '@playwright/test'
const here = dirname(fileURLToPath(import.meta.url))
const MAIN = join(here, '..', 'out', 'main', 'index.js')
// Opt-in (GITEA_LIVE=1 + COMMITEA_MODEL_LIVE=1 + a local model on :1234). Launches
// WITHOUT COMMITEA_E2E so capture_work runs the real decomposition. It Discards at
// the end so the run never files junk issues (the create-issue POST is unit-tested).
test.describe('live capture_work', () => {
test('decomposes a braindump into a reviewable ticket set', async () => {
test.skip(!process.env.GITEA_LIVE || !process.env.COMMITEA_MODEL_LIVE, 'live model test — opt-in')
test.setTimeout(300_000)
const app = await electron.launch({ args: [MAIN], env: { ...process.env } })
const win = await app.firstWindow()
await win.waitForLoadState('domcontentloaded')
const rail = win.getByRole('navigation', { name: 'Primary' })
await rail.getByRole('button', { name: 'Capture' }).click()
await expect(win.getByRole('heading', { name: 'Capture' })).toBeVisible()
// the braindump is prefilled; run the real decomposition
await win.getByRole('button', { name: 'Brew tickets' }).click()
// capture_work → the review tray with a real, estimated ticket set
await expect(win.getByText(/tickets · ~\d+d of work/)).toBeVisible({ timeout: 240_000 })
await expect(win.getByRole('button', { name: 'Approve all' })).toBeVisible()
await win.screenshot({ path: join(here, '.artifacts', 'screens', 'live-capture.png'), fullPage: true, animations: 'disabled' })
// Discard — never file junk issues into the real repo from a test
await win.getByRole('button', { name: 'Discard' }).click()
await expect(win.getByRole('button', { name: 'Brew tickets' })).toBeVisible()
await app.close()
})
})

View File

@@ -1,32 +0,0 @@
import { dirname, join } from 'node:path'
import { fileURLToPath } from 'node:url'
import { _electron as electron, expect, test } from '@playwright/test'
const here = dirname(fileURLToPath(import.meta.url))
const MAIN = join(here, '..', 'out', 'main', 'index.js')
// Opt-in (GITEA_LIVE=1 + COMMITEA_MODEL_LIVE=1 + a local model + the commitea-pm-state
// repo). Reginald records a standing directive; it's appended to the real pm-state
// ledger. The append is idempotent-ish (a fresh line each run); this only reads back
// that a directive was consulted, and leaves the ledger intact.
test.describe('live record_directive', () => {
test('logs a standing directive to the pm-state ledger', async () => {
test.skip(!process.env.GITEA_LIVE || !process.env.COMMITEA_MODEL_LIVE, 'live model test — opt-in')
test.setTimeout(300_000)
const app = await electron.launch({ args: [MAIN], env: { ...process.env } })
const win = await app.firstWindow()
await win.waitForLoadState('domcontentloaded')
await expect(win.getByText(/· local$/)).toBeVisible({ timeout: 20000 })
const composer = win.getByPlaceholder(/Tell me what to do/)
await composer.fill('Record a standing directive: freeze scope for beta, pilots come first.')
await composer.press('Enter')
// the agent logged it to the ledger (record_directive), not applied a change
await expect(win.getByText(/consulted the directive ledger/)).toBeVisible({ timeout: 240_000 })
await win.screenshot({ path: join(here, '.artifacts', 'screens', 'live-directive.png'), fullPage: true, animations: 'disabled' })
await app.close()
})
})

View File

@@ -1,37 +0,0 @@
import { dirname, join } from 'node:path'
import { fileURLToPath } from 'node:url'
import { _electron as electron, expect, test } from '@playwright/test'
const here = dirname(fileURLToPath(import.meta.url))
const MAIN = join(here, '..', 'out', 'main', 'index.js')
// Opt-in (GITEA_LIVE=1). A real launch persists the snapshot; a second launch with
// gitea unreachable must still show the board + real scheduler output from the
// persisted cache (offline reads). No model needed.
test.describe('live persistence', () => {
test('offline: serves the persisted snapshot', async () => {
test.skip(!process.env.GITEA_LIVE, 'GITEA_LIVE not set — opt-in live test')
test.setTimeout(120_000)
// launch 1 — real reconcile writes the snapshot to disk
const app1 = await electron.launch({ args: [MAIN], env: { ...process.env } })
const w1 = await app1.firstWindow()
await w1.waitForLoadState('domcontentloaded')
// a scheduler-only phrase confirms real data reconciled (never emitted by fixtures)
await expect(w1.getByText(/on the critical path|unblocks #|waits on #|· ready/).first()).toBeVisible({ timeout: 30000 })
await app1.close()
// launch 2 — gitea unreachable; the reconcile must fall back to the persisted snapshot
const app2 = await electron.launch({
args: [MAIN],
env: { ...process.env, GITEA_BASE_URL: 'http://127.0.0.1:9' },
})
const w2 = await app2.firstWindow()
await w2.waitForLoadState('domcontentloaded')
// Focus still renders real scheduler output — proving it came from the cache, offline
await expect(w2.getByText(/on the critical path|unblocks #|waits on #|· ready/).first()).toBeVisible({ timeout: 20000 })
await w2.screenshot({ path: join(here, '.artifacts', 'screens', 'live-offline.png'), fullPage: true, animations: 'disabled' })
await app2.close()
})
})

View File

@@ -1,56 +0,0 @@
import { dirname, join } from 'node:path'
import { fileURLToPath } from 'node:url'
import { _electron as electron, expect, test } from '@playwright/test'
const here = dirname(fileURLToPath(import.meta.url))
const MAIN = join(here, '..', 'out', 'main', 'index.js')
// Opt-in (GITEA_LIVE=1 + COMMITEA_MODEL_LIVE=1 + a local model on :1234). Launches
// WITHOUT COMMITEA_E2E so Reginald runs the real agent loop against the real repo.
test.describe('live Reginald', () => {
test('answers a question by consulting the real project', async () => {
test.skip(!process.env.GITEA_LIVE || !process.env.COMMITEA_MODEL_LIVE, 'live model test — opt-in')
test.setTimeout(300_000) // a big local model is slow: ~2 calls/turn + a reconcile
const app = await electron.launch({ args: [MAIN], env: { ...process.env } })
const win = await app.firstWindow()
await win.waitForLoadState('domcontentloaded')
// model configured → the live greeting + header (the loaded model, not the scripted demo)
await expect(win.getByText(/· local$/)).toBeVisible({ timeout: 20000 })
await expect(win.getByText(/I check the real board before I answer/)).toBeVisible()
const composer = win.getByPlaceholder(/Tell me what to do/)
await composer.fill('What should I work on right now?')
await composer.press('Enter')
// the agent loop ran end-to-end: it consulted the project, then answered
await expect(win.getByText(/consulted the project/)).toBeVisible({ timeout: 240_000 })
await win.screenshot({ path: join(here, '.artifacts', 'screens', 'live-reginald.png'), fullPage: true, animations: 'disabled' })
await app.close()
})
test('proposes an estimate change for inline approval (writes via chat)', async () => {
test.skip(!process.env.GITEA_LIVE || !process.env.COMMITEA_MODEL_LIVE, 'live model test — opt-in')
test.setTimeout(300_000)
const app = await electron.launch({ args: [MAIN], env: { ...process.env } })
const win = await app.firstWindow()
await win.waitForLoadState('domcontentloaded')
await expect(win.getByText(/· local$/)).toBeVisible({ timeout: 20000 })
const composer = win.getByPlaceholder(/Tell me what to do/)
await composer.fill('Set the estimate on issue #3 to est/5d.')
await composer.press('Enter')
// propose_change → an inline propose-approve card (never an auto-write)
await expect(win.getByText('Proposed · #3')).toBeVisible({ timeout: 240_000 })
await expect(win.getByText(/→ est\/5d/)).toBeVisible()
await win.screenshot({ path: join(here, '.artifacts', 'screens', 'live-reginald-propose.png'), fullPage: true, animations: 'disabled' })
// Dismiss so the live run never mutates the repo (the write path itself is #41-tested)
await win.getByRole('button', { name: 'Dismiss' }).click()
await expect(win.getByText(/Left #3 as it was/)).toBeVisible()
await app.close()
})
})

View File

@@ -6,29 +6,12 @@
* properly later. * properly later.
*/ */
import { randomUUID } from 'node:crypto'
import { readFileSync } from 'node:fs' import { readFileSync } from 'node:fs'
import { dirname, join } from 'node:path' import { dirname, join } from 'node:path'
import { import { createGiteaClient, type GiteaConfig, type LifecycleEvent } from '@commitea/core'
appendDirective,
createGiteaClient,
type DirectiveEntry,
type GiteaClient,
type GiteaConfig,
type GiteaLabel,
type IssueChange,
type LifecycleEvent,
makeDirectiveEntry,
parseDirectiveLog,
planIssueChange,
type ProjectSnapshot,
type DirectiveInput,
} from '@commitea/core'
import { ipcMain } from 'electron' import { ipcMain } from 'electron'
import { loadSnapshot, saveSnapshot } from './snapshot-store.js'
/** Walk up from cwd looking for a .env.local with a GITEA_TOKEN (dev convenience). */ /** Walk up from cwd looking for a .env.local with a GITEA_TOKEN (dev convenience). */
function loadEnvLocalToken(): string | undefined { function loadEnvLocalToken(): string | undefined {
let dir = process.cwd() let dir = process.cwd()
@@ -60,210 +43,32 @@ function resolveConfig(): GiteaConfig | null {
} }
} }
// Memoized client so both the gitea and model bridges share one instance.
let sharedClient: GiteaClient | null | undefined
export function getGiteaClient(): GiteaClient | null {
if (sharedClient === undefined) {
const config = resolveConfig()
sharedClient = config ? createGiteaClient(config, fetch) : null
}
return sharedClient
}
// The pm-state repo holds machine-derived state (the directive ledger). Same
// token/host as the work repo, a different repo (the purity split, decisions D4).
let pmStateClient: GiteaClient | null | undefined
export function getPmStateClient(): GiteaClient | null {
if (pmStateClient === undefined) {
const config = resolveConfig()
pmStateClient = config
? createGiteaClient({ ...config, repo: process.env.COMMITEA_PMSTATE_REPO ?? 'commitea-pm-state' }, fetch)
: null
}
return pmStateClient
}
const DIRECTIVE_LOG_PATH = 'directives/log.jsonl'
async function readDirectiveLog(client: GiteaClient): Promise<{ text: string; sha: string | null }> {
const file = await client.getFile(DIRECTIVE_LOG_PATH)
if (!file) return { text: '', sha: null }
return { text: Buffer.from(file.contentBase64, 'base64').toString('utf8'), sha: file.sha }
}
/** Record a directive: read the ledger, append, write it back (concatenation merge). */
export async function appendDirectiveEntry(client: GiteaClient, input: DirectiveInput): Promise<DirectiveEntry> {
const entry = makeDirectiveEntry(input, randomUUID(), new Date().toISOString())
const { text, sha } = await readDirectiveLog(client)
const next = appendDirective(text, entry)
await client.putFile(DIRECTIVE_LOG_PATH, {
contentBase64: Buffer.from(next, 'utf8').toString('base64'),
message: `directive: ${entry.kind}`,
sha: sha ?? undefined,
})
return entry
}
export async function readDirectives(client: GiteaClient) {
const { text } = await readDirectiveLog(client)
return parseDirectiveLog(text)
}
/** Full reconcile: issues + milestones + native deps + lifecycle timelines. */
export async function reconcileSnapshot(
client: GiteaClient,
): Promise<ProjectSnapshot & { milestones: Awaited<ReturnType<GiteaClient['listMilestones']>> }> {
const [issues, milestones] = await Promise.all([client.listIssues(), client.listMilestones()])
// dependency edges among the open scope (the scheduler only plans what's left)
const open = issues.filter((i) => i.state === 'open')
const perIssue = await Promise.all(
open.map(async (i) => ({ issue: i.number, dependsOn: await client.getIssueDependencies(i.number) })),
)
const deps = perIssue.flatMap(({ issue, dependsOn }) => dependsOn.map((d) => ({ issue, dependsOn: d })))
// lifecycle timelines for every issue (open → columns/badges, closed → calibration actuals)
const timelineEntries = await Promise.all(
issues.map(async (i) => [i.number, await client.getIssueTimeline(i.number)] as const),
)
const timelines: Record<number, LifecycleEvent[]> = Object.fromEntries(timelineEntries)
return { issues, milestones, deps, timelines }
}
type Snapshot = Awaited<ReturnType<typeof reconcileSnapshot>>
/**
* A single in-memory reconcile cache shared across the app. A full reconcile is
* ~2N gitea calls (deps + timelines per issue); without this, every agent tool
* call refetched the whole repo. Reads within `maxAgeMs` reuse the cache;
* `getSnapshot({ maxAgeMs: 0 })` forces a fresh pull (the explicit UI reconcile),
* and any write calls `invalidateSnapshot()` so the next read sees it. The cache
* is rebuildable — the durable truth stays in gitea (the purity split, D4).
*/
let snapshotCache: { snap: Snapshot; at: number } | null = null
export async function getSnapshot(client: GiteaClient, opts?: { maxAgeMs?: number }): Promise<Snapshot> {
const maxAgeMs = opts?.maxAgeMs ?? 0
if (snapshotCache && maxAgeMs > 0 && Date.now() - snapshotCache.at <= maxAgeMs) {
return snapshotCache.snap
}
const snap = await reconcileSnapshot(client)
snapshotCache = { snap, at: Date.now() }
saveSnapshot(snap, new Date().toISOString()) // persist for instant boot + offline
return snap
}
/** Drop the cache so the next read reflects a just-made write. */
export function invalidateSnapshot(): void {
snapshotCache = null
}
/**
* The last persisted snapshot (from a previous session), for instant boot. The
* renderer shows it immediately, then a real reconcile supersedes it
* (stale-while-revalidate). Returns null when there's nothing on disk; its
* `savedAt` marks staleness. It does NOT seed the cache — agent tool calls
* always reconcile fresh so they never reason over stale data.
*/
export function bootSnapshot(): (Snapshot & { savedAt: string }) | null {
const persisted = loadSnapshot()
if (!persisted) return null
return {
issues: persisted.issues,
milestones: persisted.milestones,
deps: persisted.deps,
timelines: persisted.timelines,
savedAt: persisted.savedAt,
} as unknown as Snapshot & { savedAt: string }
}
/** Agent tool calls tolerate a slightly stale snapshot (seconds) to stay responsive. */
export const AGENT_SNAPSHOT_TTL_MS = 30_000
export function registerGiteaIpc(): void { export function registerGiteaIpc(): void {
const client = getGiteaClient() const config = resolveConfig()
const repo = client ? `${process.env.GITEA_OWNER ?? 'christian'}/${process.env.GITEA_REPO ?? 'commitea'}` : null const client = config ? createGiteaClient(config, fetch) : null
const repo = config ? `${config.owner}/${config.repo}` : null
ipcMain.handle('gitea:status', () => ({ configured: !!client, repo })) ipcMain.handle('gitea:status', () => ({ configured: !!config, repo }))
// Instant boot: the last persisted snapshot, shown before the fresh reconcile lands.
ipcMain.handle('gitea:boot', () => {
if (!client) return { configured: false }
const persisted = bootSnapshot()
return persisted ? { configured: true, cached: true, ...persisted } : { configured: true, cached: false }
})
ipcMain.handle('gitea:reconcile', async () => { ipcMain.handle('gitea:reconcile', async () => {
if (!client) return { configured: false, issues: [], milestones: [], deps: [], timelines: {} } if (!client) return { configured: false, issues: [], milestones: [], deps: [], timelines: {} }
try { const [issues, milestones] = await Promise.all([client.listIssues(), client.listMilestones()])
// explicit UI sync — force fresh, and warm the cache for agent tool calls // dependency edges among the open scope (the scheduler only plans what's left)
const snap = await getSnapshot(client, { maxAgeMs: 0 }) const open = issues.filter((i) => i.state === 'open')
return { configured: true, stale: false, ...snap } const perIssue = await Promise.all(
} catch (e) { open.map(async (i) => ({ issue: i.number, dependsOn: await client.getIssueDependencies(i.number) })),
// offline / gitea down — serve the last persisted snapshot rather than error out )
const persisted = bootSnapshot() const deps = perIssue.flatMap(({ issue, dependsOn }) => dependsOn.map((d) => ({ issue, dependsOn: d })))
if (persisted) return { configured: true, stale: true, ...persisted } // lifecycle timelines for every issue (open → columns/badges, closed → calibration actuals)
throw e const timelineEntries = await Promise.all(
} issues.map(async (i) => [i.number, await client.getIssueTimeline(i.number)] as const),
)
const timelines: Record<number, LifecycleEvent[]> = Object.fromEntries(timelineEntries)
return { configured: true, issues, milestones, deps, timelines }
}) })
ipcMain.handle('gitea:getIssue', async (_event, index: number) => { ipcMain.handle('gitea:getIssue', async (_event, index: number) => {
if (!client) return null if (!client) return null
return client.getIssue(index) return client.getIssue(index)
}) })
// Cached label list for name→id resolution; refreshed on demand if a name misses.
let labelCache: GiteaLabel[] | null = null
async function resolveLabelIds(names: string[]): Promise<number[]> {
if (!client) return []
const lookup = () => new Map(labelCache!.map((l) => [l.name, l.id]))
if (!labelCache) labelCache = await client.listLabels()
let byName = lookup()
if (names.some((n) => !byName.has(n))) {
labelCache = await client.listLabels() // a name we don't know — refetch once
byName = lookup()
}
return names.map((n) => byName.get(n)).filter((id): id is number => id != null)
}
// The write path (apply_changes). Additive label swaps, applied only after the
// renderer's propose-approve. Returns the plan + the freshly-read issue.
ipcMain.handle('gitea:applyChange', async (_event, change: IssueChange) => {
if (!client) return { ok: false as const, reason: 'unconfigured' as const }
const current = await client.getIssue(change.issue)
const plan = planIssueChange(current.labels, change)
if (plan.noop) return { ok: true as const, plan, issue: current }
const ids = await resolveLabelIds(plan.labels)
await client.setIssueLabels(change.issue, ids)
const issue = await client.getIssue(change.issue)
invalidateSnapshot() // the board + forecast must reflect the label change
return { ok: true as const, plan, issue }
})
// capture_work filing: open each approved issue with its est/* + p/* labels.
// Only touches the CommiTea label namespaces — no invented labels (zero-pollution).
ipcMain.handle(
'gitea:createIssues',
async (_event, issues: { title: string; body?: string; estimate?: string; priority?: string }[]) => {
if (!client) return { ok: false as const, reason: 'unconfigured' as const }
const created: { number: number; title: string }[] = []
for (const it of issues) {
const names = [it.estimate, it.priority].filter((n): n is string => !!n)
const labelIds = await resolveLabelIds(names)
const issue = await client.createIssue({ title: it.title, body: it.body, labelIds })
created.push({ number: issue.number, title: issue.title })
}
if (created.length) invalidateSnapshot() // new issues enter the board/scope
return { ok: true as const, created }
},
)
// Read the directive ledger from the pm-state repo (for the Directives screen).
ipcMain.handle('pmstate:directives', async () => {
const pm = getPmStateClient()
if (!pm) return { ok: false as const, reason: 'unconfigured' as const }
try {
return { ok: true as const, directives: await readDirectives(pm) }
} catch (e) {
return { ok: false as const, reason: 'error' as const, message: e instanceof Error ? e.message : String(e) }
}
})
} }

View File

@@ -3,7 +3,6 @@ import { join } from 'node:path'
import { BrowserWindow, app, shell } from 'electron' import { BrowserWindow, app, shell } from 'electron'
import { registerGiteaIpc } from './gitea.js' import { registerGiteaIpc } from './gitea.js'
import { registerModelIpc } from './model.js'
function createWindow(): void { function createWindow(): void {
const win = new BrowserWindow({ const win = new BrowserWindow({
@@ -36,7 +35,6 @@ function createWindow(): void {
void app.whenReady().then(() => { void app.whenReady().then(() => {
registerGiteaIpc() registerGiteaIpc()
registerModelIpc()
createWindow() createWindow()
app.on('activate', () => { app.on('activate', () => {

View File

@@ -1,157 +0,0 @@
/**
* Main-process model bridge — Reginald's brain runs here. Model traffic (like
* gitea's) stays in main: the renderer is CSP-locked and never talks to the
* LLM directly. On `model:chat` it drives the agent loop against the configured
* OpenAI-compatible endpoint, executing `query_project` by reconciling the repo
* and building the requested view. v0 is read-only — writes still go through the
* propose-approve controls.
*/
import {
buildProjectView,
captureWork,
type ChangeProposal,
type ChatMessage,
createChatClient,
describeChange,
type ModelRouter,
type ProjectView,
proposalsFor,
type ProposeChangeArgs,
type QueryFilters,
REGINALD_SYSTEM,
REGINALD_TOOLS,
runAgentTurn,
toDirectiveInput,
} from '@commitea/core'
import { ipcMain } from 'electron'
import {
AGENT_SNAPSHOT_TTL_MS,
appendDirectiveEntry,
getGiteaClient,
getPmStateClient,
getSnapshot,
} from './gitea.js'
/** Small local model for prose + the read tool; big model reserved for later decomposition. */
function resolveModelRouter(): ModelRouter | null {
if (process.env.COMMITEA_E2E === '1') return null // e2e uses the scripted fixture Reginald
const baseUrl = process.env.COMMITEA_MODEL_URL ?? 'http://localhost:1234/v1'
if (!baseUrl) return null
return {
small: { baseUrl, model: process.env.COMMITEA_MODEL_SMALL ?? '' },
big: { baseUrl, model: process.env.COMMITEA_MODEL_BIG ?? '' },
}
}
/**
* Resolve which model to actually ask for. An explicit env override wins;
* otherwise ask the server which model is *loaded* (LM Studio's native
* `/api/v0/models`) so Reginald follows whatever you load — no config churn on a
* model switch. Falls back to the first non-embedding model, then a sane default.
*/
async function resolveLoadedModel(baseUrl: string, override: string): Promise<string> {
if (override) return override
const root = baseUrl.replace(/\/v1\/?$/, '')
try {
const res = await fetch(`${root}/api/v0/models`)
if (res.ok) {
const data = (await res.json()) as { data?: { id: string; state?: string; type?: string }[] }
const loaded = (data.data ?? []).find((m) => m.state === 'loaded' && m.type !== 'embeddings')
if (loaded) return loaded.id
}
} catch {
// native API unavailable — fall through to the OpenAI listing
}
try {
const res = await fetch(`${baseUrl.replace(/\/+$/, '')}/models`)
if (res.ok) {
const data = (await res.json()) as { data?: { id: string }[] }
const first = (data.data ?? []).find((m) => !/embed/i.test(m.id))
if (first) return first.id
}
} catch {
// ignore — use the default
}
return 'google/gemma-4-e4b'
}
export function registerModelIpc(): void {
const router = resolveModelRouter()
ipcMain.handle('model:status', async () => {
if (!router) return { configured: false, model: null }
const model = await resolveLoadedModel(router.small.baseUrl, router.small.model)
return { configured: true, model }
})
ipcMain.handle('model:chat', async (_event, messages: ChatMessage[]) => {
if (!router) return { ok: false as const, reason: 'unconfigured' as const }
const client = getGiteaClient()
const model = await resolveLoadedModel(router.small.baseUrl, router.small.model)
const chat = createChatClient({ ...router.small, model }, fetch)
// Proposals the model formulates this turn; the renderer approves them (the
// write happens through gitea:applyChange, never inside the loop).
const proposals: ChangeProposal[] = []
const execute = async (name: string, args: unknown) => {
if (!client) return { error: 'gitea is not configured' }
if (name === 'query_project') {
// reuse a recent reconcile — a multi-tool turn shouldn't refetch the repo each call
const snap = await getSnapshot(client, { maxAgeMs: AGENT_SNAPSHOT_TTL_MS })
const a = (args ?? {}) as { view: ProjectView; filters?: QueryFilters }
return buildProjectView(a.view, a.filters, snap, new Date())
}
if (name === 'propose_change') {
const a = (args ?? {}) as ProposeChangeArgs
const issue = await client.getIssue(a.issue).catch(() => null)
if (!issue) return { error: `issue #${a.issue} not found` }
const built = proposalsFor(a, issue.labels, issue.title)
proposals.push(...built)
return built.length
? { proposed: built.map((p) => ({ issue: a.issue, diff: describeChange(p.plan) })) }
: { proposed: [], note: 'no change — already at that value' }
}
if (name === 'record_directive') {
const pm = getPmStateClient()
if (!pm) return { error: 'pm-state is not configured' }
try {
const entry = await appendDirectiveEntry(pm, toDirectiveInput(args))
return { recorded: { kind: entry.kind, quote: entry.quote } }
} catch (e) {
return { error: `could not record — is the pm-state repo created? (${e instanceof Error ? e.message : e})` }
}
}
return { error: `unknown tool: ${name}` }
}
try {
const turn = await runAgentTurn({
complete: (m, t) => chat.complete(m, t),
messages: [{ role: 'system', content: REGINALD_SYSTEM }, ...messages],
tools: REGINALD_TOOLS,
execute,
})
return { ok: true as const, content: turn.content, steps: turn.steps, proposals }
} catch (e) {
return { ok: false as const, reason: 'error' as const, message: e instanceof Error ? e.message : String(e) }
}
})
// capture_work — braindump → proposed issue set. The big model does the
// decomposition (with one loaded local model, that's the loaded one). Returns
// a proposal; nothing is filed until the Capture tray approves it.
ipcMain.handle('model:capture', async (_event, braindump: string) => {
if (!router) return { ok: false as const, reason: 'unconfigured' as const }
const model = await resolveLoadedModel(router.big.baseUrl, router.big.model)
const chat = createChatClient({ ...router.big, model }, fetch)
try {
const proposal = await captureWork((m, t) => chat.complete(m, t), braindump)
return { ok: true as const, ...proposal }
} catch (e) {
return { ok: false as const, reason: 'error' as const, message: e instanceof Error ? e.message : String(e) }
}
})
}

View File

@@ -1,47 +0,0 @@
/**
* Durable snapshot store — the reconcile cache, persisted to disk. On boot the
* app shows the last snapshot instantly (stale-while-revalidate) instead of a
* blank board while ~2N gitea calls run; if gitea is unreachable, reads fall
* back to it (offline). It's a rebuildable mirror — the durable truth stays in
* gitea (the purity split, D4). A plain JSON file: the whole snapshot fits in
* memory at this scale, so indexed SQL buys nothing yet (see the PR).
*/
import { readFileSync, writeFileSync } from 'node:fs'
import { join } from 'node:path'
import { app } from 'electron'
/** The shape we persist — kept loose so a schema drift degrades to "no cache", not a crash. */
export interface PersistedSnapshot {
issues: unknown[]
milestones: unknown[]
deps: unknown[]
timelines: Record<number, unknown[]>
/** ISO time the snapshot was reconciled — shown as "cached since". */
savedAt: string
}
function snapshotPath(): string {
return join(app.getPath('userData'), 'commitea-snapshot.json')
}
/** Load the last persisted snapshot, or null if absent/corrupt. Never throws. */
export function loadSnapshot(): PersistedSnapshot | null {
try {
const parsed = JSON.parse(readFileSync(snapshotPath(), 'utf8')) as PersistedSnapshot
if (parsed && Array.isArray(parsed.issues)) return parsed
return null
} catch {
return null // missing file, bad JSON, or drift — treat as no cache
}
}
/** Persist a freshly reconciled snapshot. Best-effort — a write failure never breaks a reconcile. */
export function saveSnapshot(snap: Omit<PersistedSnapshot, 'savedAt'>, savedAt: string): void {
try {
writeFileSync(snapshotPath(), JSON.stringify({ ...snap, savedAt }), 'utf8')
} catch {
// disk full / permissions — the in-memory cache still works this session
}
}

View File

@@ -5,28 +5,10 @@ const api = {
gitea: { gitea: {
/** Whether the main process has a gitea token + target repo configured. */ /** Whether the main process has a gitea token + target repo configured. */
status: () => ipcRenderer.invoke('gitea:status'), status: () => ipcRenderer.invoke('gitea:status'),
/** The last persisted snapshot, for instant boot before the fresh reconcile. */
boot: () => ipcRenderer.invoke('gitea:boot'),
/** Full read of the managed repo — every issue + milestone. */ /** Full read of the managed repo — every issue + milestone. */
reconcile: () => ipcRenderer.invoke('gitea:reconcile'), reconcile: () => ipcRenderer.invoke('gitea:reconcile'),
/** One issue by index, normalized (or null if unconfigured). */ /** One issue by index, normalized (or null if unconfigured). */
getIssue: (index: number) => ipcRenderer.invoke('gitea:getIssue', index), getIssue: (index: number) => ipcRenderer.invoke('gitea:getIssue', index),
/** Apply an estimate/priority change (the write path); resolves to the plan + fresh issue. */
applyChange: (change: unknown) => ipcRenderer.invoke('gitea:applyChange', change),
/** File a set of captured issues with their est/* + p/* labels. */
createIssues: (issues: unknown) => ipcRenderer.invoke('gitea:createIssues', issues),
},
pmstate: {
/** Read the directive ledger from the pm-state repo. */
directives: () => ipcRenderer.invoke('pmstate:directives'),
},
model: {
/** Whether a model endpoint is configured (else the UI keeps the scripted Reginald). */
status: () => ipcRenderer.invoke('model:status'),
/** One agent turn: messages in, Reginald's prose + the tools it consulted out. */
chat: (messages: unknown) => ipcRenderer.invoke('model:chat', messages),
/** Decompose a braindump into a proposed issue set (capture_work). */
capture: (braindump: string) => ipcRenderer.invoke('model:capture', braindump),
}, },
} }

View File

@@ -1,12 +1,11 @@
import React from 'react' import React from 'react'
import { CALIBRATION, type CalibrationData } from '../../data/fixtures.js' import { CALIBRATION } from '../../data/fixtures.js'
import { Badge, Card, Icon } from '../ui/index.js' import { Badge, Card, Icon } from '../ui/index.js'
// Calibration report — estimate-vs-actual evidence behind the cones. // Calibration report — estimate-vs-actual evidence behind the cones
// `data` (real fit from closed-issue actuals) overrides the demo fixture. export function CalibrationScreen({ onBack }: { onBack: () => void }) {
export function CalibrationScreen({ onBack, data }: { onBack: () => void; data?: CalibrationData }) { const c = CALIBRATION
const c = data ?? CALIBRATION
// scatter chart geometry // scatter chart geometry
const W = 420, const W = 420,
@@ -69,11 +68,7 @@ export function CalibrationScreen({ onBack, data }: { onBack: () => void; data?:
<h1 style={{ font: 'var(--text-display)', color: 'var(--ink-1)', margin: 0 }}>Calibration</h1> <h1 style={{ font: 'var(--text-display)', color: 'var(--ink-1)', margin: 0 }}>Calibration</h1>
<p style={{ font: 'var(--text-data)', color: 'var(--ink-3)', margin: '6px 0 0', whiteSpace: 'nowrap' }}>{c.n} closed issues with estimates · evidence, not opinion</p> <p style={{ font: 'var(--text-data)', color: 'var(--ink-3)', margin: '6px 0 0', whiteSpace: 'nowrap' }}>{c.n} closed issues with estimates · evidence, not opinion</p>
</div> </div>
{c.active ? ( <Badge tone="ok" dot>curve active · n 20</Badge>
<Badge tone="ok" dot>curve active · n 20</Badge>
) : (
<Badge tone="warn" dot>cold-start · {c.n}/20</Badge>
)}
</header> </header>
</div> </div>
@@ -175,9 +170,7 @@ export function CalibrationScreen({ onBack, data }: { onBack: () => void; data?:
<span style={{ font: '500 12.5px var(--font-mono)', color: 'var(--ink-1)', whiteSpace: 'nowrap' }}>{c.effect.banded}</span> <span style={{ font: '500 12.5px var(--font-mono)', color: 'var(--ink-1)', whiteSpace: 'nowrap' }}>{c.effect.banded}</span>
</div> </div>
<p style={{ font: 'var(--text-agent)', color: 'var(--ink-2)', margin: '10px 0 0' }}> <p style={{ font: 'var(--text-agent)', color: 'var(--ink-2)', margin: '10px 0 0' }}>
{c.active You are not bad at estimating; you are optimistic in a very stable way. Stable, I can work with.
? 'You are not bad at estimating; you are optimistic in a very stable way. Stable, I can work with.'
: 'Not enough closed history yet — Im forecasting from cold-start priors and widening the cone to stay honest. The curve takes over at 20.'}
</p> </p>
</Card> </Card>
</div> </div>

View File

@@ -1,12 +1,8 @@
import React from 'react' import React from 'react'
import type { ProposedIssue } from '@commitea/core'
import { Badge, Button, Card, Icon, Select, Tag } from '../ui/index.js' import { Badge, Button, Card, Icon, Select, Tag } from '../ui/index.js'
// Capture interview — braindump → interview → approved ticket set (< 2 min). // Capture interview — braindump → interview → approved ticket set (< 2 min)
// With a model configured, "Brew tickets" runs real capture_work decomposition
// and "Approve all" files the issues in gitea; otherwise the scripted demo runs.
interface Ticket { interface Ticket {
title: string title: string
@@ -34,64 +30,6 @@ export function CaptureScreen({ onDone }: { onDone: () => void }) {
const [webEst, setWebEst] = React.useState<string | null>(null) const [webEst, setWebEst] = React.useState<string | null>(null)
const [secs, setSecs] = React.useState(0) const [secs, setSecs] = React.useState(0)
// live capture_work path (real model + gitea writes)
const [live, setLive] = React.useState(false)
const [brewing, setBrewing] = React.useState(false)
const [liveTickets, setLiveTickets] = React.useState<ProposedIssue[] | null>(null)
const [filedCount, setFiledCount] = React.useState(0)
const [error, setError] = React.useState<string | null>(null)
React.useEffect(() => {
let alive = true
window.commitea.model.status().then((s) => { if (alive) setLive(s.configured) }).catch(() => {})
return () => { alive = false }
}, [])
const editTicket = (i: number, field: 'estimate' | 'priority', value: string) =>
setLiveTickets((ts) => (ts ? ts.map((t, j) => (j === i ? { ...t, [field]: value } : t)) : ts))
// Decide live-vs-scripted at click time: re-check status if it hasn't resolved
// yet, so a configured model never falls into the scripted interview by a race.
const onBrew = async () => {
const configured = live || (await window.commitea.model.status().then((s) => s.configured).catch(() => false))
if (configured) {
setLive(true)
brew()
} else {
setStage('interview')
}
}
const brew = () => {
setError(null)
setBrewing(true)
window.commitea.model
.capture(dump)
.then((res) => {
setBrewing(false)
if (res.ok && res.issues.length) {
setLiveTickets(res.issues)
setStage('review')
} else {
setError(res.ok ? 'I could not find concrete work in that — try a bit more detail.' : `Capture failed: ${res.reason === 'error' ? res.message : 'no model'}`)
}
})
.catch(() => { setBrewing(false); setError('I could not reach the model.') })
}
const fileLive = () => {
if (!liveTickets) return
setBrewing(true)
window.commitea.gitea
.createIssues(liveTickets)
.then((res) => {
setBrewing(false)
if (res.ok) { setFiledCount(res.created.length); setStage('filed') }
else setError('Filing failed — gitea is not configured.')
})
.catch(() => { setBrewing(false); setError('Filing failed.') })
}
const running = stage === 'interview' || stage === 'review' const running = stage === 'interview' || stage === 'review'
React.useEffect(() => { React.useEffect(() => {
if (!running) return if (!running) return
@@ -125,23 +63,19 @@ export function CaptureScreen({ onDone }: { onDone: () => void }) {
else setStage('review') else setStage('review')
} }
// draft tickets build as the interview progresses (scripted demo path) // draft tickets build as the interview progresses
const scripted: Ticket[] = [] const tickets: Ticket[] = []
if (split === true) { if (split === true) {
scripted.push({ title: 'Token refresh: retry with backoff', est: 'est/2d', p: 'p/2' }) tickets.push({ title: 'Token refresh: retry with backoff', est: 'est/2d', p: 'p/2' })
scripted.push({ title: 'Session storage: stale reads on wake', est: 'est/1d', p: 'p/3' }) tickets.push({ title: 'Session storage: stale reads on wake', est: 'est/1d', p: 'p/3' })
} else if (split === false) { } else if (split === false) {
scripted.push({ title: 'Auth: token refresh + session storage', est: 'est/3d', p: 'p/2' }) tickets.push({ title: 'Auth: token refresh + session storage', est: 'est/3d', p: 'p/2' })
} }
if (webEst) scripted.push({ title: 'Webhook debounce: double-fire guard', est: webEst, p: 'p/1', dep: 'blocked by auth work' }) if (webEst) tickets.push({ title: 'Webhook debounce: double-fire guard', est: webEst, p: 'p/1', dep: 'blocked by auth work' })
if (!live && (stage === 'review' || stage === 'filed')) { if (stage === 'review' || stage === 'filed') {
scripted.push({ title: 'Docs: auth setup guide', est: 'est/1d', p: 'p/4', byReginald: true }) tickets.push({ title: 'Docs: auth setup guide', est: 'est/1d', p: 'p/4', byReginald: true })
} }
// real capture_work output overrides the scripted set when present const totalDays = tickets.reduce((n, t) => n + parseInt(t.est.replace('est/', '')), 0)
const tickets: Ticket[] = liveTickets
? liveTickets.map((i) => ({ title: i.title, est: i.estimate ?? 'est/2d', p: i.priority ?? 'p/3' }))
: scripted
const totalDays = tickets.reduce((n, t) => n + parseInt(t.est.replace('est/', ''), 10), 0)
const estOptions = ['est/1d', 'est/2d', 'est/3d', 'est/5d', 'est/8d'].map((v) => ({ value: v, label: v })) const estOptions = ['est/1d', 'est/2d', 'est/3d', 'est/5d', 'est/8d'].map((v) => ({ value: v, label: v }))
const pOptions = ['p/1', 'p/2', 'p/3', 'p/4'].map((v) => ({ value: v, label: v })) const pOptions = ['p/1', 'p/2', 'p/3', 'p/4'].map((v) => ({ value: v, label: v }))
@@ -162,20 +96,8 @@ export function CaptureScreen({ onDone }: { onDone: () => void }) {
<div style={{ display: 'flex', alignItems: 'center', gap: 8, flexWrap: 'wrap' }}> <div style={{ display: 'flex', alignItems: 'center', gap: 8, flexWrap: 'wrap' }}>
{editable ? ( {editable ? (
<> <>
<Select <Select options={estOptions} defaultValue={t.est} style={{ width: 96 }} />
options={estOptions} <Select options={pOptions} defaultValue={t.p} style={{ width: 76 }} />
value={liveTickets ? t.est : undefined}
defaultValue={liveTickets ? undefined : t.est}
onChange={(e) => editTicket(i, 'estimate', e.target.value)}
style={{ width: 96 }}
/>
<Select
options={pOptions}
value={liveTickets ? t.p : undefined}
defaultValue={liveTickets ? undefined : t.p}
onChange={(e) => editTicket(i, 'priority', e.target.value)}
style={{ width: 76 }}
/>
</> </>
) : ( ) : (
<> <>
@@ -222,12 +144,7 @@ export function CaptureScreen({ onDone }: { onDone: () => void }) {
<p style={{ font: 'var(--text-agent)', color: 'var(--ink-2)', margin: '10px 0 14px' }}> <p style={{ font: 'var(--text-agent)', color: 'var(--ink-2)', margin: '10px 0 14px' }}>
Sentences, fragments, grievances all welcome. I'll sort it into tickets and only ask what I can't infer. Sentences, fragments, grievances all welcome. I'll sort it into tickets and only ask what I can't infer.
</p> </p>
<Button icon="sparkles" onClick={() => void onBrew()} disabled={brewing}> <Button icon="sparkles" onClick={() => setStage('interview')}>Brew tickets</Button>
{brewing ? 'Brewing…' : 'Brew tickets'}
</Button>
{error ? (
<p style={{ font: 'var(--text-agent)', color: 'var(--danger)', margin: '10px 0 0' }}>{error}</p>
) : null}
</Card> </Card>
) : null} ) : null}
@@ -257,26 +174,15 @@ export function CaptureScreen({ onDone }: { onDone: () => void }) {
<div style={{ display: 'grid', gridTemplateColumns: '1fr 1.1fr', gap: 14, alignItems: 'start' }}> <div style={{ display: 'grid', gridTemplateColumns: '1fr 1.1fr', gap: 14, alignItems: 'start' }}>
<Card overline="Consequence" title={`${tickets.length} tickets · ~${totalDays}d of work`} jade <Card overline="Consequence" title={`${tickets.length} tickets · ~${totalDays}d of work`} jade
footer={<> footer={<>
<Button onClick={() => (live ? fileLive() : setStage('filed'))} disabled={brewing}> <Button onClick={() => setStage('filed')}>Approve all</Button>
{brewing ? 'Filing…' : 'Approve all'} <Button variant="ghost" onClick={() => { setStage('dump'); setQi(0); setLog([]); setSplit(null); setWebEst(null); setSecs(0); }}>Discard</Button>
</Button>
<Button variant="ghost" onClick={() => { setStage('dump'); setQi(0); setLog([]); setSplit(null); setWebEst(null); setSecs(0); setLiveTickets(null); setError(null); }}>Discard</Button>
</>}> </>}>
{live ? ( <p style={{ font: 'var(--text-body)', margin: '0 0 8px' }}>
<p style={{ font: 'var(--text-agent)', color: 'var(--ink-2)', margin: 0 }}> Beta's 80% window moves <span style={{ font: 'var(--text-data)' }}>Mar 312 → Mar 514</span>. Capacity absorbs the rest.
{tickets.length} issue{tickets.length === 1 ? '' : 's'} from your braindump, estimated and prioritized. </p>
Adjust the labels, then approve I'll open them in gitea with only est/* and p/* labels. <p style={{ font: 'var(--text-agent)', color: 'var(--ink-2)', margin: 0 }}>
</p> I added the docs ticket you mentioned and wired the dependency. Shall I make it so?
) : ( </p>
<>
<p style={{ font: 'var(--text-body)', margin: '0 0 8px' }}>
Beta's 80% window moves <span style={{ font: 'var(--text-data)' }}>Mar 312 Mar 514</span>. Capacity absorbs the rest.
</p>
<p style={{ font: 'var(--text-agent)', color: 'var(--ink-2)', margin: 0 }}>
I added the docs ticket you mentioned and wired the dependency. Shall I make it so?
</p>
</>
)}
</Card> </Card>
<Tray editable /> <Tray editable />
</div> </div>
@@ -289,7 +195,7 @@ export function CaptureScreen({ onDone }: { onDone: () => void }) {
<Icon name="circle-check" size={22} /> Filed <Icon name="circle-check" size={22} /> Filed
</span> </span>
<p style={{ font: 'var(--text-body)', margin: 0 }}> <p style={{ font: 'var(--text-body)', margin: 0 }}>
{live ? filedCount : tickets.length} issues opened in gitea with <span style={{ font: 'var(--text-data)' }}>est/*</span> and <span style={{ font: 'var(--text-data)' }}>p/*</span> labels nothing else touched. {tickets.length} issues opened in gitea with <span style={{ font: 'var(--text-data)' }}>est/*</span> and <span style={{ font: 'var(--text-data)' }}>p/*</span> labels — nothing else touched.
</p> </p>
<p style={{ font: 'var(--text-agent)', color: 'var(--ink-2)', margin: 0 }}> <p style={{ font: 'var(--text-agent)', color: 'var(--ink-2)', margin: 0 }}>
Elapsed {clock} under budget. No bot comments, no synthetic issues; your repo remains yours. Elapsed {clock} under budget. No bot comments, no synthetic issues; your repo remains yours.

View File

@@ -8,35 +8,6 @@ export function DirectivesScreen() {
const [pending, setPending] = React.useState<DirectivePending | null>(DIRECTIVES.pending) const [pending, setPending] = React.useState<DirectivePending | null>(DIRECTIVES.pending)
const [entries, setEntries] = React.useState<DirectiveEntry[]>(DIRECTIVES.entries) const [entries, setEntries] = React.useState<DirectiveEntry[]>(DIRECTIVES.entries)
// Real ledger from the pm-state repo, when it exists — else the fixture demo.
React.useEffect(() => {
let alive = true
window.commitea.pmstate
.directives()
.then((r) => {
if (!alive || !r.ok || r.directives.length === 0) return
setPending(null)
setEntries(
r.directives
.slice()
.reverse()
.map((d) => ({
seq: d.seq,
who: 'You',
when: new Date(d.ts).toLocaleDateString(),
what: d.quote,
why: d.rationale ?? '',
status: d.status === 'accepted' ? 'applied' : d.status === 'withdrawn' ? 'withdrawn' : 'superseded',
consequence: '',
})),
)
})
.catch(() => {})
return () => {
alive = false
}
}, [])
const resolve = (status: string) => { const resolve = (status: string) => {
setEntries((e) => [{ setEntries((e) => [{
seq: pending!.seq, who: pending!.who, when: pending!.when, what: pending!.what, why: 'pilot demo on the 14th', seq: pending!.seq, who: pending!.who, when: pending!.when, what: pending!.what, why: 'pilot demo on the 14th',

View File

@@ -109,9 +109,7 @@ export function FocusScreen({
<BurnUpCone data={forecast?.cone} /> <BurnUpCone data={forecast?.cone} />
<p style={{ font: 'var(--text-agent)', color: 'var(--ink-2)', margin: '10px 0 0' }}> <p style={{ font: 'var(--text-agent)', color: 'var(--ink-2)', margin: '10px 0 0' }}>
{forecast {forecast
? forecast.coldStart ? `${forecast.scope} open ${forecast.scope === 1 ? 'issue' : 'issues'} in scope. Cold-start priors — the cone tightens as the team closes work.`
? `${forecast.scope} open ${forecast.scope === 1 ? 'issue' : 'issues'} in scope. Cold-start priors — ${forecast.calibratedN}/20 estimated closes so far; the cone tightens as the team closes work.`
: `${forecast.scope} open ${forecast.scope === 1 ? 'issue' : 'issues'} in scope, calibrated on ${forecast.calibratedN} closed ${forecast.calibratedN === 1 ? 'issue' : 'issues'} of your own.`
: 'The cone has narrowed since Friday. Im quietly pleased.'} : 'The cone has narrowed since Friday. Im quietly pleased.'}
</p> </p>
</Card> </Card>

View File

@@ -1,33 +1,17 @@
// Issue detail — human intent (gitea) on the left, machine-derived (pm-state) on the right // Issue detail — human intent (gitea) on the left, machine-derived (pm-state) on the right
import React, { useState } from 'react' import React from 'react'
import {
describeChange,
type EstimateLabel,
ESTIMATE_LABELS,
type IssueChange,
planIssueChange,
type PriorityLabel,
PRIORITY_LABELS,
} from '@commitea/core'
import { ISSUE_DETAIL, type IssueDetail, type IssueRef } from '../../data/fixtures.js' import { ISSUE_DETAIL, type IssueDetail, type IssueRef } from '../../data/fixtures.js'
import { Badge, Button, Card, Dialog, Icon, Select, Tag } from '../ui/index.js' import { Badge, Button, Card, Icon, Tag } from '../ui/index.js'
const NONE = '—'
export function IssueScreen({ export function IssueScreen({
issue, issue,
onBack, onBack,
onOpenIssue, onOpenIssue,
canWrite = false,
onApplyChange,
}: { }: {
issue: IssueRef issue: IssueRef
onBack: () => void onBack: () => void
onOpenIssue: (issue: IssueRef) => void onOpenIssue: (issue: IssueRef) => void
canWrite?: boolean
onApplyChange?: (change: IssueChange) => Promise<{ ok: boolean }>
}) { }) {
const det: IssueDetail = ISSUE_DETAIL[issue.id] || { const det: IssueDetail = ISSUE_DETAIL[issue.id] || {
state: 'triage', state: 'triage',
@@ -56,44 +40,6 @@ export function IssueScreen({
} as Record<string, { tone: 'warn' | 'neutral' | 'info' | 'ok'; label: string }> } as Record<string, { tone: 'warn' | 'neutral' | 'info' | 'ok'; label: string }>
)[det.state] || { tone: 'neutral', label: det.state } )[det.state] || { tone: 'neutral', label: det.state }
// ---- propose-approve write path (apply_changes) ----
const labels = issue.labels ?? []
const curEstimate = labels.find((l) => l.startsWith('est/')) ?? ''
const curPriority = labels.find((l) => l.startsWith('p/')) ?? ''
const [adjustOpen, setAdjustOpen] = useState(false)
const [estimate, setEstimate] = useState(curEstimate)
const [priority, setPriority] = useState(curPriority)
const [applying, setApplying] = useState(false)
const openAdjust = () => {
setEstimate(curEstimate)
setPriority(curPriority)
setAdjustOpen(true)
}
// the concrete changes this dialog would apply, one per axis that differs
const pendingChanges: IssueChange[] = []
if (estimate !== curEstimate)
pendingChanges.push({ kind: 'reestimate', issue: issue.id, estimate: (estimate || null) as EstimateLabel | null })
if (priority !== curPriority)
pendingChanges.push({ kind: 'reprioritize', issue: issue.id, priority: (priority || null) as PriorityLabel | null })
const diffs = pendingChanges.map((c) => describeChange(planIssueChange(labels, c)))
const apply = async () => {
if (!onApplyChange || pendingChanges.length === 0) return
setApplying(true)
try {
for (const c of pendingChanges) await onApplyChange(c)
setAdjustOpen(false)
} finally {
setApplying(false)
}
}
const estOptions = [{ value: '', label: NONE }, ...ESTIMATE_LABELS.map((l) => ({ value: l, label: l }))]
const prioOptions = [{ value: '', label: NONE }, ...PRIORITY_LABELS.map((l) => ({ value: l, label: l }))]
return ( return (
<div style={{ display: 'flex', flexDirection: 'column', gap: 16 }}> <div style={{ display: 'flex', flexDirection: 'column', gap: 16 }}>
{/* breadcrumb + header */} {/* breadcrumb + header */}
@@ -119,69 +65,10 @@ export function IssueScreen({
</span> </span>
</div> </div>
</div> </div>
<div style={{ display: 'flex', gap: 8, flexShrink: 0 }}> <Button variant="secondary" icon="arrow-up-right">Open in Gitea</Button>
{canWrite ? (
<Button variant="secondary" icon="pencil" onClick={openAdjust}>
Adjust
</Button>
) : null}
<Button variant="secondary" icon="arrow-up-right">Open in Gitea</Button>
</div>
</header> </header>
</div> </div>
<Dialog
open={adjustOpen}
onClose={() => setAdjustOpen(false)}
title="Adjust estimate & priority"
footer={
<>
<Button variant="ghost" onClick={() => setAdjustOpen(false)}>
Cancel
</Button>
<Button onClick={apply} disabled={pendingChanges.length === 0 || applying}>
{applying ? 'Applying…' : 'Apply to gitea'}
</Button>
</>
}
>
<div style={{ display: 'flex', gap: 14 }}>
<Select
label="Estimate"
options={estOptions}
value={estimate}
onChange={(e) => setEstimate(e.target.value)}
/>
<Select
label="Priority"
options={prioOptions}
value={priority}
onChange={(e) => setPriority(e.target.value)}
/>
</div>
<div style={{ marginTop: 14, minHeight: 40 }}>
{pendingChanges.length === 0 ? (
<p style={{ font: 'var(--text-agent)', color: 'var(--ink-3)', margin: 0 }}>
No change yet pick a different estimate or priority.
</p>
) : (
<>
<p style={{ font: 'var(--text-overline)', letterSpacing: 'var(--letter-spacing-wide)', textTransform: 'uppercase', color: 'var(--ink-3)', margin: '0 0 6px' }}>
Proposed label change
</p>
{diffs.map((d) => (
<div key={d} style={{ font: '500 13px var(--font-mono)', color: 'var(--ink-1)' }}>
{d}
</div>
))}
<p style={{ font: 'var(--text-agent)', color: 'var(--ink-2)', margin: '8px 0 0' }}>
Writes the label to gitea and re-runs the plan. Nothing else changes.
</p>
</>
)}
</div>
</Dialog>
<div style={{ display: 'grid', gridTemplateColumns: '1fr 300px', gap: 16, alignItems: 'start' }}> <div style={{ display: 'grid', gridTemplateColumns: '1fr 300px', gap: 16, alignItems: 'start' }}>
{/* left: human intent */} {/* left: human intent */}
<div style={{ display: 'flex', flexDirection: 'column', gap: 16 }}> <div style={{ display: 'flex', flexDirection: 'column', gap: 16 }}>

View File

@@ -8,22 +8,15 @@ import { RUNWAY, CAPACITY } from '../../data/fixtures.js'
export function RunwayScreen({ export function RunwayScreen({
onOpenCalibration, onOpenCalibration,
onOpenMilestone, onOpenMilestone,
calibration,
}: { }: {
onOpenCalibration: () => void onOpenCalibration: () => void
onOpenMilestone: () => void onOpenMilestone: () => void
calibration?: { n: number; coldStart: boolean }
}) { }) {
const calibNote = calibration
? calibration.coldStart
? `cold-start priors · ${calibration.n}/20 closed issues estimated`
: `calibrated on ${calibration.n} closed ${calibration.n === 1 ? 'issue' : 'issues'}`
: 'calibrated on 27 closed issues'
return ( return (
<div style={{ display: 'flex', flexDirection: 'column', gap: 16 }}> <div style={{ display: 'flex', flexDirection: 'column', gap: 16 }}>
<header style={{ borderBottom: 'var(--rule-double)', paddingBottom: 14 }}> <header style={{ borderBottom: 'var(--rule-double)', paddingBottom: 14 }}>
<h1 style={{ font: 'var(--text-display)', color: 'var(--ink-1)', margin: 0 }}>Runway</h1> <h1 style={{ font: 'var(--text-display)', color: 'var(--ink-1)', margin: 0 }}>Runway</h1>
<p style={{ font: 'var(--text-data)', color: 'var(--ink-3)', margin: '6px 0 0' }}>capacity vs milestone dates · {calibNote}</p> <p style={{ font: 'var(--text-data)', color: 'var(--ink-3)', margin: '6px 0 0' }}>capacity vs milestone dates · calibrated on 27 closed issues</p>
</header> </header>
<Card overline="Milestones" flush> <Card overline="Milestones" flush>

View File

@@ -1,10 +1,8 @@
import React, { useEffect, useState } from 'react' import React, { useEffect, useState } from 'react'
import logoIcon from '../../design/assets/logo-icon.png' import logoIcon from '../../design/assets/logo-icon.png'
import type { IssueChange } from '@commitea/core'
import type { IssueRef } from '../../data/fixtures.js' import type { IssueRef } from '../../data/fixtures.js'
import { backlogCalibration, forecastBacklog, issuesToBoardColumns, scheduleFocus } from '../../lib/backlog.js' import { forecastBacklog, issuesToBoardColumns, scheduleFocus } from '../../lib/backlog.js'
import { useBacklog } from '../../lib/use-backlog.js' import { useBacklog } from '../../lib/use-backlog.js'
import { PrimitivesGallery } from '../gallery.js' import { PrimitivesGallery } from '../gallery.js'
import { BoardScreen } from '../screens/board-screen.js' import { BoardScreen } from '../screens/board-screen.js'
@@ -87,17 +85,13 @@ export function AppShell() {
const [offline, setOffline] = useState(false) const [offline, setOffline] = useState(false)
const [issue, setIssue] = useState<IssueRef | null>(null) const [issue, setIssue] = useState<IssueRef | null>(null)
const [readIds, setReadIds] = useState<number[]>([]) const [readIds, setReadIds] = useState<number[]>([])
const [backlog, refetchBacklog] = useBacklog() const backlog = useBacklog()
const boardColumns = const boardColumns =
backlog.status === 'ready' ? issuesToBoardColumns(backlog.issues, backlog.timelines) : undefined backlog.status === 'ready' ? issuesToBoardColumns(backlog.issues, backlog.timelines) : undefined
const focus = const focus =
backlog.status === 'ready' ? scheduleFocus(backlog.issues, backlog.deps, backlog.timelines) : undefined backlog.status === 'ready' ? scheduleFocus(backlog.issues, backlog.deps, backlog.timelines) : undefined
const calibration =
backlog.status === 'ready' ? backlogCalibration(backlog.issues, backlog.timelines) : undefined
const forecast = const forecast =
backlog.status === 'ready' backlog.status === 'ready' ? (forecastBacklog(backlog.issues, backlog.deps) ?? undefined) : undefined
? (forecastBacklog(backlog.issues, backlog.deps, new Date(), calibration?.model) ?? undefined)
: undefined
useEffect(() => { useEffect(() => {
document.documentElement.setAttribute('data-theme', dark ? 'dark' : 'light') document.documentElement.setAttribute('data-theme', dark ? 'dark' : 'light')
@@ -109,17 +103,6 @@ export function AppShell() {
setView('issue') setView('issue')
} }
// The write path: apply through the bridge, reflect the new labels on the open
// issue immediately, and re-reconcile so the board + forecast catch up.
const applyChange = async (change: IssueChange) => {
const res = await window.commitea.gitea.applyChange(change)
if (res.ok) {
setIssue((cur) => (cur && cur.id === res.issue.number ? { ...cur, labels: res.issue.labels } : cur))
refetchBacklog()
}
return res
}
const NAV: NavEntry[] = [ const NAV: NavEntry[] = [
{ id: 'standup', label: 'Standup', icon: 'sun' }, { id: 'standup', label: 'Standup', icon: 'sun' },
{ id: 'focus', label: 'Morning service', icon: 'coffee' }, { id: 'focus', label: 'Morning service', icon: 'coffee' },
@@ -195,11 +178,10 @@ export function AppShell() {
<RunwayScreen <RunwayScreen
onOpenCalibration={() => setView('calibration')} onOpenCalibration={() => setView('calibration')}
onOpenMilestone={() => setView('milestone')} onOpenMilestone={() => setView('milestone')}
calibration={calibration ? { n: calibration.model.n, coldStart: calibration.model.coldStart } : undefined}
/> />
) )
case 'calibration': case 'calibration':
return <CalibrationScreen onBack={() => setView('runway')} data={calibration?.data} /> return <CalibrationScreen onBack={() => setView('runway')} />
case 'milestone': case 'milestone':
return <MilestoneScreen onBack={() => setView('runway')} onOpenIssue={openIssue} /> return <MilestoneScreen onBack={() => setView('runway')} onOpenIssue={openIssue} />
case 'inbox': case 'inbox':
@@ -219,13 +201,7 @@ export function AppShell() {
return <SettingsScreen dark={dark} setDark={setDark} /> return <SettingsScreen dark={dark} setDark={setDark} />
case 'issue': case 'issue':
return issue ? ( return issue ? (
<IssueScreen <IssueScreen issue={issue} onBack={() => setView(prevView)} onOpenIssue={openIssue} />
issue={issue}
onBack={() => setView(prevView)}
onOpenIssue={openIssue}
canWrite={backlog.status === 'ready'}
onApplyChange={applyChange}
/>
) : null ) : null
case 'states': case 'states':
return <StatesScreen onCapture={() => setView('capture')} /> return <StatesScreen onCapture={() => setView('capture')} />
@@ -337,7 +313,7 @@ export function AppShell() {
</div> </div>
</main> </main>
<ChatPanel onOpenDirectives={() => setView('directives')} offline={offline} onApplyChange={applyChange} /> <ChatPanel onOpenDirectives={() => setView('directives')} offline={offline} />
</div> </div>
) )
} }

View File

@@ -1,28 +1,22 @@
import React, { useEffect, useRef, useState } from 'react' import React, { useEffect, useRef, useState } from 'react'
import { describeChange, type IssueChange } from '@commitea/core' import { CANNED_REPLY, CHAT, type ChatMessage } from '../../data/fixtures.js'
import { Icon, IconButton } from '../ui/index.js'
import { useChat } from '../../lib/use-chat.js'
import { Button, Icon, IconButton } from '../ui/index.js'
/** /**
* Reginald's panel — chat is the write-path (decisions.md D1). Wired to the * Reginald's panel — chat is the write-path (decisions.md D1). This is the P3-2
* model bridge via `useChat`: a configured model drives a real agent turn * fixture shell: it echoes a canned reply so the layout + interactions are real,
* (query_project + prose, propose_change for edits); otherwise it echoes the * but no model is wired. P4 replaces `send` with the model router + tools.
* scripted fixture reply. Proposed changes are approved inline here — the write
* runs through `onApplyChange`, the same guarded handler the Issue screen uses.
*/ */
export interface ChatPanelProps { export interface ChatPanelProps {
onOpenDirectives?: () => void onOpenDirectives?: () => void
offline?: boolean offline?: boolean
onApplyChange?: (change: IssueChange) => Promise<{ ok: boolean }>
} }
export function ChatPanel({ onOpenDirectives, offline, onApplyChange }: ChatPanelProps) { export function ChatPanel({ onOpenDirectives, offline }: ChatPanelProps) {
const { msgs, thinking, live, model, steps, proposals, send: sendChat, approve, dismiss } = useChat(onApplyChange) const [msgs, setMsgs] = useState<ChatMessage[]>(CHAT)
// shorten "google/gemma-4-26b-a4b-qat" → "gemma-4-26b" for the header chip
const modelLabel = model ? (model.split('/').pop() ?? model).replace(/-(qat|instruct|it|gguf)$/i, '') : 'gemma-4'
const [text, setText] = useState('') const [text, setText] = useState('')
const [thinking, setThinking] = useState(false)
const scrollRef = useRef<HTMLDivElement>(null) const scrollRef = useRef<HTMLDivElement>(null)
useEffect(() => { useEffect(() => {
@@ -33,8 +27,13 @@ export function ChatPanel({ onOpenDirectives, offline, onApplyChange }: ChatPane
const send = () => { const send = () => {
const t = text.trim() const t = text.trim()
if (!t) return if (!t) return
setMsgs((m) => [...m, { from: 'user', text: t }])
setText('') setText('')
sendChat(t) setThinking(true)
setTimeout(() => {
setThinking(false)
setMsgs((m) => [...m, { from: 'agent', text: CANNED_REPLY }])
}, 900)
} }
return ( return (
@@ -62,7 +61,7 @@ export function ChatPanel({ onOpenDirectives, offline, onApplyChange }: ChatPane
<Icon name="sparkles" size={16} style={{ color: offline ? 'var(--ink-3)' : 'var(--jade)' }} /> <Icon name="sparkles" size={16} style={{ color: offline ? 'var(--ink-3)' : 'var(--jade)' }} />
<span style={{ font: 'var(--text-body-strong)', color: 'var(--ink-1)' }}>Reginald</span> <span style={{ font: 'var(--text-body-strong)', color: 'var(--ink-1)' }}>Reginald</span>
<span style={{ font: '400 11px var(--font-mono)', color: 'var(--ink-3)', marginLeft: 'auto' }}> <span style={{ font: '400 11px var(--font-mono)', color: 'var(--ink-3)', marginLeft: 'auto' }}>
{offline ? 'offline · queueing' : live ? `${modelLabel} · local` : 'demo · scripted'} {offline ? 'offline · queueing' : 'gemma-4b · local'}
</span> </span>
<IconButton icon="history" label="Directive log" size="sm" onClick={onOpenDirectives} /> <IconButton icon="history" label="Directive log" size="sm" onClick={onOpenDirectives} />
</header> </header>
@@ -99,38 +98,6 @@ export function ChatPanel({ onOpenDirectives, offline, onApplyChange }: ChatPane
</div> </div>
) : null} ) : null}
{thinking ? <div style={{ font: 'var(--text-agent)', color: 'var(--ink-3)' }}>considering</div> : null} {thinking ? <div style={{ font: 'var(--text-agent)', color: 'var(--ink-3)' }}>considering</div> : null}
{!thinking && steps.length ? (
<div style={{ font: 'var(--text-caption)', color: 'var(--ink-3)', display: 'flex', alignItems: 'center', gap: 5 }}>
<Icon name="eye" size={11} /> consulted {Array.from(new Set(steps.map((s) => s.replace('query_project', 'the project').replace('propose_change', 'the labels').replace('record_directive', 'the directive ledger')))).join(', ')}
</div>
) : null}
{proposals.map((p) => (
<div
key={`${p.change.issue}:${p.change.kind}`}
style={{
border: '1px solid var(--line-2)',
borderRadius: 'var(--radius-2)',
background: 'var(--paper-0)',
padding: '10px 12px',
display: 'flex',
flexDirection: 'column',
gap: 8,
}}
>
<div style={{ font: 'var(--text-caption)', color: 'var(--ink-3)', textTransform: 'uppercase', letterSpacing: 'var(--letter-spacing-wide)' }}>
Proposed · #{p.change.issue}
</div>
<div style={{ font: '500 13px var(--font-mono)', color: 'var(--ink-1)' }}>{describeChange(p.plan)}</div>
<div style={{ display: 'flex', gap: 8 }}>
<Button size="sm" onClick={() => approve(p)} disabled={offline}>
Approve
</Button>
<Button size="sm" variant="ghost" onClick={() => dismiss(p)}>
Dismiss
</Button>
</div>
</div>
))}
</div> </div>
<div style={{ padding: 14, borderTop: '1px solid var(--line-1)', flexShrink: 0 }}> <div style={{ padding: 14, borderTop: '1px solid var(--line-1)', flexShrink: 0 }}>

View File

@@ -1,83 +1,17 @@
import type { import type { DependencyEdge, GiteaIssue, GiteaMilestone, LifecycleEvent } from '@commitea/core'
AgentStep,
ChangeProposal,
ChatMessage,
CaptureProposal,
DependencyEdge,
DirectiveRecord,
GiteaIssue,
GiteaMilestone,
IssueChange,
LabelPlan,
LifecycleEvent,
ProposedIssue,
} from '@commitea/core'
/** The result of a write through the bridge. */
export type ApplyChangeResult =
| { ok: false; reason: 'unconfigured' }
| { ok: true; plan: LabelPlan; issue: GiteaIssue }
/** The result of filing captured issues. */
export type CreateIssuesResult =
| { ok: false; reason: 'unconfigured' }
| { ok: true; created: { number: number; title: string }[] }
/** The result of a capture_work decomposition. */
export type CaptureResult =
| { ok: false; reason: 'unconfigured' | 'error'; message?: string }
| ({ ok: true } & CaptureProposal)
/** A reconciled snapshot as it crosses the bridge. */
export interface SnapshotPayload {
configured: boolean
issues: GiteaIssue[]
milestones: GiteaMilestone[]
deps: DependencyEdge[]
/** Normalized lifecycle events keyed by issue number. */
timelines: Record<number, LifecycleEvent[]>
/** true when served from the persisted cache (offline / instant boot). */
stale?: boolean
/** ISO time the persisted snapshot was reconciled (present on cached reads). */
savedAt?: string
}
/** Boot payload — the persisted snapshot, or a marker that there's none yet. */
export type BootPayload =
| { configured: false }
| { configured: true; cached: false }
| ({ configured: true; cached: true } & Omit<SnapshotPayload, 'configured'>)
/** The gitea bridge exposed by the preload over IPC (main-process backed). */ /** The gitea bridge exposed by the preload over IPC (main-process backed). */
export interface GiteaBridge { export interface GiteaBridge {
status(): Promise<{ configured: boolean; repo: string | null }> status(): Promise<{ configured: boolean; repo: string | null }>
boot(): Promise<BootPayload> reconcile(): Promise<{
reconcile(): Promise<SnapshotPayload> configured: boolean
issues: GiteaIssue[]
milestones: GiteaMilestone[]
deps: DependencyEdge[]
/** Normalized lifecycle events keyed by issue number. */
timelines: Record<number, LifecycleEvent[]>
}>
getIssue(index: number): Promise<GiteaIssue | null> getIssue(index: number): Promise<GiteaIssue | null>
applyChange(change: IssueChange): Promise<ApplyChangeResult>
createIssues(issues: ProposedIssue[]): Promise<CreateIssuesResult>
}
/** One agent turn's result. */
export type ChatResult =
| { ok: false; reason: 'unconfigured' | 'error'; message?: string }
| { ok: true; content: string; steps: AgentStep[]; proposals: ChangeProposal[] }
/** The model bridge (Reginald) exposed by the preload over IPC. */
export interface ModelBridge {
status(): Promise<{ configured: boolean; model: string | null }>
chat(messages: ChatMessage[]): Promise<ChatResult>
capture(braindump: string): Promise<CaptureResult>
}
/** The result of reading the directive ledger. */
export type DirectivesResult =
| { ok: false; reason: 'unconfigured' | 'error'; message?: string }
| { ok: true; directives: DirectiveRecord[] }
/** The pm-state bridge (machine-derived state) exposed by the preload over IPC. */
export interface PmStateBridge {
directives(): Promise<DirectivesResult>
} }
declare global { declare global {
@@ -85,8 +19,6 @@ declare global {
commitea: { commitea: {
platform: string platform: string
gitea: GiteaBridge gitea: GiteaBridge
model: ModelBridge
pmstate: PmStateBridge
} }
} }
} }

View File

@@ -1,24 +1,17 @@
import { import {
type CalibrationModel,
type CalibrationSample,
calibrationSamples,
COLD_START_THRESHOLD,
type DependencyEdge, type DependencyEdge,
fitCalibration,
forecast, forecast,
type GiteaIssue, type GiteaIssue,
inferLifecycle, inferLifecycle,
type LifecycleColumn, type LifecycleColumn,
type LifecycleEvent, type LifecycleEvent,
type LifecycleInference, type LifecycleInference,
PRIOR_BUCKETS,
schedule, schedule,
type ScheduledItem, type ScheduledItem,
selectFocus, selectFocus,
toDurationModel,
} from '@commitea/core' } from '@commitea/core'
import { type BoardColumn, type BoardIssue, type CalibrationData, type FocusIssue } from '../data/fixtures.js' import { type BoardColumn, type BoardIssue, type FocusIssue } from '../data/fixtures.js'
import { type BurnUpData, buildBurnUpData } from './dates.js' import { type BurnUpData, buildBurnUpData } from './dates.js'
type Timelines = Record<number, LifecycleEvent[]> type Timelines = Record<number, LifecycleEvent[]>
@@ -107,109 +100,22 @@ export interface ForecastView {
cone: BurnUpData cone: BurnUpData
p80Label: string p80Label: string
rangeLabel: string rangeLabel: string
/** true while the forecast still runs on code priors (calibration not yet trusted). */
coldStart: boolean
/** Closed-with-estimate issues feeding calibration so far. */
calibratedN: number
} }
/** /**
* Monte Carlo forecast over the open backlog, mapped onto a calendar-anchored * Monte Carlo forecast over the open backlog, mapped onto a calendar-anchored
* burn-up cone. When a calibration model is supplied and past cold-start, its * burn-up cone. Returns null when there's nothing to forecast (no open scope) —
* fitted params drive the sim. Returns null when there's nothing to forecast. * the UI then falls back to the demo cone. `today` is injectable for tests.
* `today` is injectable for tests.
*/ */
export function forecastBacklog( export function forecastBacklog(
issues: GiteaIssue[], issues: GiteaIssue[],
deps: DependencyEdge[], deps: DependencyEdge[],
today: Date = new Date(), today: Date = new Date(),
calibration?: CalibrationModel,
): ForecastView | null { ): ForecastView | null {
const model = calibration ? toDurationModel(calibration) : undefined const f = forecast(toSchedulable(issues), deps)
const f = forecast(toSchedulable(issues), deps, model ? { model } : {})
const cone = buildBurnUpData(f, today) const cone = buildBurnUpData(f, today)
if (!cone) return null if (!cone) return null
return { return { scope: f.scope, cone, p80Label: cone.p80Label, rangeLabel: cone.rangeLabel }
scope: f.scope,
cone,
p80Label: cone.p80Label,
rangeLabel: cone.rangeLabel,
coldStart: f.coldStart,
calibratedN: calibration?.n ?? 0,
}
}
/** Fit the calibration model from the closed backlog's inferred actuals (#1). */
export function calibrateBacklog(
issues: GiteaIssue[],
timelines: Timelines = {},
asOf: Date = new Date(),
): CalibrationModel {
return fitCalibration(calibrationSamples(issues, timelines, asOf))
}
/** Calibration model + its screen view in one pass over the closed backlog. */
export function backlogCalibration(
issues: GiteaIssue[],
timelines: Timelines = {},
asOf: Date = new Date(),
): { model: CalibrationModel; data: CalibrationData } {
const samples = calibrationSamples(issues, timelines, asOf)
const model = fitCalibration(samples)
return { model, data: calibrationData(model, samples, issues) }
}
const pctFromMu = (mu: number) => Math.round((Math.exp(mu) - 1) * 100)
/**
* Shape the calibration model + its samples into the screen's view. Buckets and
* people only earn a bias once their sample clears the fit floor; everything
* degrades honestly on a thin (cold-start) dataset.
*/
export function calibrationData(
model: CalibrationModel,
samples: CalibrationSample[],
openIssues: GiteaIssue[],
): CalibrationData {
const labels = PRIOR_BUCKETS.map((b) => {
const inBucket = samples.filter((s) => s.bucket === b)
const fit = model.byBucket[b]
const mu = fit ? fit.mu : model.global.mu
return {
label: `est/${b}d`,
n: fit ? fit.n : inBucket.length,
median: inBucket.length ? `${(b * Math.exp(mu)).toFixed(1)}d` : '—',
bias: fit ? pctFromMu(fit.mu) : null,
}
})
const people = Object.entries(model.byPerson).map(([who, pb]) => ({
who,
n: pb.n,
bias: pctFromMu(model.global.mu + pb.biasMu),
note: '',
}))
const openEst = openIssues
.filter((i) => i.state === 'open')
.reduce((sum, i) => sum + (i.facts.estimateDays ?? 2), 0)
const effect = model.coldStart
? { raw: `${model.n}/${COLD_START_THRESHOLD} estimated closes`, banded: 'cold-start priors', p50: '—' }
: {
raw: `${openEst}d estimated`,
banded: `×${Math.exp(model.global.mu).toFixed(2)} median drift`,
p50: `${Math.round(openEst * Math.exp(model.global.mu))}d`,
}
return {
n: model.n,
active: !model.coldStart,
labels,
people,
scatter: samples.map((s) => [s.estimateDays, s.actualWorkingDays]),
fit: Number(Math.exp(model.global.mu).toFixed(2)),
effect,
}
} }
/** /**

View File

@@ -1,4 +1,4 @@
import { useCallback, useEffect, useState } from 'react' import { useEffect, useState } from 'react'
import type { DependencyEdge, GiteaIssue, GiteaMilestone, LifecycleEvent } from '@commitea/core' import type { DependencyEdge, GiteaIssue, GiteaMilestone, LifecycleEvent } from '@commitea/core'
@@ -12,50 +12,18 @@ export type BacklogState =
milestones: GiteaMilestone[] milestones: GiteaMilestone[]
deps: DependencyEdge[] deps: DependencyEdge[]
timelines: Record<number, LifecycleEvent[]> timelines: Record<number, LifecycleEvent[]>
/** true while showing the persisted snapshot (instant boot / offline). */
stale: boolean
/** ISO time the shown snapshot was reconciled, when stale. */
savedAt?: string
} }
/** /**
* Reconcile the managed repo through the main-process bridge, stale-while- * Reconcile the managed repo once on mount, through the main-process bridge.
* revalidate: on mount it shows the persisted snapshot instantly (marked stale), * `unconfigured` means no token — the UI falls back to demo fixtures. Errors
* then a fresh reconcile supersedes it. If gitea is unreachable, the fresh * (network, bad token) surface as `error`.
* reconcile falls back to the persisted snapshot (offline). `refetch` re-syncs
* after a write. `unconfigured` means no token — the UI uses demo fixtures.
*/ */
export function useBacklog(): [BacklogState, () => void] { export function useBacklog(): BacklogState {
const [state, setState] = useState<BacklogState>({ status: 'loading' }) const [state, setState] = useState<BacklogState>({ status: 'loading' })
const [nonce, setNonce] = useState(0)
const refetch = useCallback(() => setNonce((n) => n + 1), [])
useEffect(() => { useEffect(() => {
let alive = true let alive = true
// instant boot from the persisted snapshot (only on first mount, not refetch)
if (nonce === 0) {
window.commitea.gitea
.boot()
.then((b) => {
if (!alive || !('cached' in b) || !b.cached) return
setState((prev) =>
prev.status === 'ready' && !prev.stale
? prev // a fresh reconcile already won the race
: {
status: 'ready',
issues: b.issues,
milestones: b.milestones,
deps: b.deps,
timelines: b.timelines,
stale: true,
savedAt: b.savedAt,
},
)
})
.catch(() => {})
}
window.commitea.gitea window.commitea.gitea
.reconcile() .reconcile()
.then((r) => { .then((r) => {
@@ -68,24 +36,17 @@ export function useBacklog(): [BacklogState, () => void] {
milestones: r.milestones, milestones: r.milestones,
deps: r.deps, deps: r.deps,
timelines: r.timelines, timelines: r.timelines,
stale: r.stale ?? false,
savedAt: r.savedAt,
} }
: { status: 'unconfigured' }, : { status: 'unconfigured' },
) )
}) })
.catch((e: unknown) => { .catch((e: unknown) => {
if (alive) { if (alive) setState({ status: 'error', message: e instanceof Error ? e.message : String(e) })
// keep a shown boot snapshot rather than clobbering it with an error
setState((prev) =>
prev.status === 'ready' ? prev : { status: 'error', message: e instanceof Error ? e.message : String(e) },
)
}
}) })
return () => { return () => {
alive = false alive = false
} }
}, [nonce]) }, [])
return [state, refetch] return state
} }

View File

@@ -1,141 +0,0 @@
import { useCallback, useEffect, useRef, useState } from 'react'
import type { ChangeProposal, ChatMessage as WireMessage, IssueChange } from '@commitea/core'
import { CANNED_REPLY, CHAT, type ChatMessage } from '../data/fixtures.js'
const LIVE_GREETING: ChatMessage = {
from: 'agent',
text: 'Morning. Ask me anything about the project — I check the real board before I answer.',
}
export interface ChatState {
msgs: ChatMessage[]
thinking: boolean
/** true once a model endpoint is confirmed; otherwise the panel echoes the demo reply. */
live: boolean
/** The loaded model's id when live (for the header). */
model: string | null
/** Tools Reginald consulted on the last turn (for a subtle activity line). */
steps: string[]
/** Changes Reginald has proposed and is awaiting approval on. */
proposals: ChangeProposal[]
send: (text: string) => void
approve: (p: ChangeProposal) => void
dismiss: (p: ChangeProposal) => void
}
/**
* Reginald's conversation. When a model is configured, `send` drives one agent
* turn through the main-process bridge (which runs the tool loop). Otherwise it
* echoes the scripted fixture reply, so the layout stays real with no model and
* fixture e2e is unaffected. The fixture greeting is display-only — only real
* turns (`convo`) are sent to the model as history. `onApplyChange` performs an
* approved write (the same handler the Issue screen uses — it refetches).
*/
export function useChat(onApplyChange?: (change: IssueChange) => Promise<{ ok: boolean }>): ChatState {
const [seed, setSeed] = useState<ChatMessage[]>(CHAT)
const [convo, setConvo] = useState<ChatMessage[]>([])
const [thinking, setThinking] = useState(false)
const [live, setLive] = useState(false)
const [model, setModel] = useState<string | null>(null)
const [steps, setSteps] = useState<string[]>([])
const [proposals, setProposals] = useState<ChangeProposal[]>([])
const convoRef = useRef(convo)
convoRef.current = convo
const proposalKey = (p: ChangeProposal) => `${p.change.issue}:${p.change.kind}`
const drop = (p: ChangeProposal) => setProposals((ps) => ps.filter((x) => proposalKey(x) !== proposalKey(p)))
useEffect(() => {
let alive = true
window.commitea.model
.status()
.then((s) => {
if (alive && s.configured) {
setLive(true)
setModel(s.model)
setSeed([LIVE_GREETING])
}
})
.catch(() => {})
return () => {
alive = false
}
}, [])
const send = useCallback(
(raw: string) => {
const text = raw.trim()
if (!text) return
const nextConvo: ChatMessage[] = [...convoRef.current, { from: 'user', text }]
setConvo(nextConvo)
setThinking(true)
setSteps([])
setProposals([])
if (!live) {
window.setTimeout(() => {
setThinking(false)
setConvo((c) => [...c, { from: 'agent', text: CANNED_REPLY }])
}, 900)
return
}
const wire: WireMessage[] = nextConvo.map((m) => ({
role: m.from === 'user' ? 'user' : 'assistant',
content: m.text,
}))
window.commitea.model
.chat(wire)
.then((res) => {
setThinking(false)
if (res.ok) {
setSteps(res.steps.map((s) => s.tool))
setProposals(res.proposals)
setConvo((c) => [...c, { from: 'agent', text: res.content || '…' }])
} else {
setConvo((c) => [
...c,
{
from: 'agent',
text: res.reason === 'error' ? `I hit a snag: ${res.message ?? 'unknown error'}` : 'No model is configured.',
},
])
}
})
.catch(() => {
setThinking(false)
setConvo((c) => [...c, { from: 'agent', text: 'I could not reach the model.' }])
})
},
[live],
)
const approve = useCallback(
(p: ChangeProposal) => {
if (!onApplyChange) return
drop(p)
const label = p.plan.added[0] ?? p.plan.removed[0] ?? 'change'
void onApplyChange(p.change).then((res) => {
setConvo((c) => [
...c,
{
from: 'agent',
text: res.ok
? `Done — #${p.change.issue} is now ${label}. The plan's been re-run.`
: `That didn't take — #${p.change.issue} is unchanged.`,
},
])
})
},
[onApplyChange],
)
const dismiss = useCallback((p: ChangeProposal) => {
drop(p)
setConvo((c) => [...c, { from: 'agent', text: `Left #${p.change.issue} as it was.` }])
}, [])
return { msgs: [...seed, ...convo], thinking, live, model, steps, proposals, send, approve, dismiss }
}

View File

@@ -1,103 +0,0 @@
import { beforeAll, describe, expect, it } from 'vitest'
import { extractLabelFacts } from '../labels/label-schema.js'
import type { FetchLike, GiteaIssue } from '../gitea/types.js'
import { runAgentTurn } from './agent-loop.js'
import { REGINALD_SYSTEM, REGINALD_TOOLS } from './agent-tools.js'
import { createChatClient } from './chat-client.js'
import { buildProjectView, type ProjectSnapshot } from './query-project.js'
/**
* Opt-in (COMMITEA_MODEL_LIVE=1). Drives the real chat client + agent loop
* against a local OpenAI-compatible server (LM Studio on :1234 by default),
* proving the model calls the tools and narrates the real result. The model is
* whatever is loaded (via LM Studio's native API), so it never JIT-swaps.
*/
const LIVE = !!process.env.COMMITEA_MODEL_LIVE
const BASE = process.env.COMMITEA_MODEL_URL ?? 'http://localhost:1234/v1'
let MODEL = process.env.COMMITEA_MODEL_SMALL ?? ''
beforeAll(async () => {
if (!LIVE || MODEL) return
const root = BASE.replace(/\/v1\/?$/, '')
const loaded = await fetch(`${root}/api/v0/models`)
.then((r) => (r.ok ? (r.json() as Promise<{ data?: { id: string; state?: string; type?: string }[] }>) : null))
.then((d) => d?.data?.find((m) => m.state === 'loaded' && m.type !== 'embeddings')?.id)
.catch(() => undefined)
MODEL = loaded ?? 'google/gemma-4-e4b'
})
function issue(over: Partial<GiteaIssue>): GiteaIssue {
const labels = over.labels ?? []
return {
number: 1, title: '#1', body: '', state: 'open', labels, facts: extractLabelFacts(labels),
milestone: null, assignee: null, assignees: [], createdAt: '2026-01-05T09:00:00Z',
updatedAt: '2026-01-05T09:00:00Z', closedAt: null, url: '', ...over,
}
}
const SNAP: ProjectSnapshot = {
issues: [
issue({ number: 2, title: 'ChangeSource interface + polling source', labels: ['est/3d', 'p/1'] }),
issue({ number: 3, title: 'SQLite cache bootstrap', labels: ['est/2d', 'p/1'] }),
],
timelines: {},
deps: [{ issue: 3, dependsOn: 2 }],
}
describe('agent loop (live model)', () => {
it.skipIf(!LIVE)(
'calls query_project and narrates the real focus',
async () => {
const client = createChatClient({ baseUrl: BASE, model: MODEL }, globalThis.fetch as unknown as FetchLike)
const turn = await runAgentTurn({
complete: (m, t) => client.complete(m, t),
messages: [
{ role: 'system', content: REGINALD_SYSTEM },
{ role: 'user', content: 'What should I work on right now?' },
],
tools: REGINALD_TOOLS,
execute: async (name, args) =>
name === 'query_project'
? buildProjectView((args as { view: any }).view, (args as any).filters, SNAP, new Date())
: { error: `unknown tool ${name}` },
})
// it consulted the project, then answered in prose about the real top item (#2)
expect(turn.steps.some((s) => s.tool === 'query_project')).toBe(true)
expect(turn.content.trim().length).toBeGreaterThan(0)
expect(turn.content).toMatch(/#?2\b|ChangeSource/i)
},
60_000,
)
it.skipIf(!LIVE)(
'records a standing instruction via record_directive',
async () => {
const client = createChatClient({ baseUrl: BASE, model: MODEL }, globalThis.fetch as unknown as FetchLike)
const recorded: unknown[] = []
const turn = await runAgentTurn({
complete: (m, t) => client.complete(m, t),
messages: [
{ role: 'system', content: REGINALD_SYSTEM },
{ role: 'user', content: 'Log this standing directive: pilots come first, everything else waits.' },
],
tools: REGINALD_TOOLS,
execute: async (name, args) => {
if (name === 'record_directive') {
recorded.push(args)
return { recorded: { kind: (args as { kind?: string }).kind ?? 'note' } }
}
return name === 'query_project'
? buildProjectView((args as { view: any }).view, (args as any).filters, SNAP, new Date())
: { error: `unknown tool ${name}` }
},
})
// the model logged the directive rather than trying to apply it
expect(turn.steps.some((s) => s.tool === 'record_directive')).toBe(true)
expect(recorded.length).toBeGreaterThan(0)
},
60_000,
)
})

View File

@@ -1,69 +0,0 @@
/**
* The agent turn loop. Given a model `complete` fn, the conversation, the tool
* declarations, and an `execute` that actually runs a tool, it drives the
* call→tool→result→call cycle until the model answers in prose (or a step
* budget is hit). Pure orchestration with injected I/O — the model and the tool
* executor are both stubbable, so the loop is fully unit-testable offline.
*/
import type { ChatMessage, CompletionResult, ToolDecl } from './chat-client.js'
/** A tool the loop ran, with the raw args and its stringified result — for the UI's activity trail. */
export interface AgentStep {
tool: string
arguments: string
result: string
}
export type ToolExecutor = (name: string, args: unknown) => Promise<unknown>
export interface AgentTurn {
content: string
steps: AgentStep[]
/** The full conversation including this turn's assistant/tool messages. */
messages: ChatMessage[]
}
const DEFAULT_MAX_STEPS = 4
function stringify(result: unknown): string {
return typeof result === 'string' ? result : JSON.stringify(result)
}
export async function runAgentTurn(opts: {
complete: (messages: ChatMessage[], tools?: ToolDecl[]) => Promise<CompletionResult>
messages: ChatMessage[]
tools: ToolDecl[]
execute: ToolExecutor
maxSteps?: number
}): Promise<AgentTurn> {
const maxSteps = opts.maxSteps ?? DEFAULT_MAX_STEPS
const convo: ChatMessage[] = [...opts.messages]
const steps: AgentStep[] = []
for (let step = 0; step < maxSteps; step++) {
const { content, toolCalls } = await opts.complete(convo, opts.tools)
if (toolCalls.length === 0) {
convo.push({ role: 'assistant', content })
return { content, steps, messages: convo }
}
convo.push({ role: 'assistant', content, toolCalls })
for (const tc of toolCalls) {
let result: unknown
try {
const args = tc.arguments ? JSON.parse(tc.arguments) : {}
result = await opts.execute(tc.name, args)
} catch (e) {
result = { error: e instanceof Error ? e.message : String(e) }
}
const resultStr = stringify(result)
steps.push({ tool: tc.name, arguments: tc.arguments, result: resultStr })
convo.push({ role: 'tool', toolCallId: tc.id, name: tc.name, content: resultStr })
}
}
// Out of tool budget — force a final prose answer with tools withheld.
const final = await opts.complete(convo, [])
convo.push({ role: 'assistant', content: final.content })
return { content: final.content, steps, messages: convo }
}

View File

@@ -1,91 +0,0 @@
/**
* Reginald's tool surface. v0 ships the one read tool (`query_project`); the
* three write tools (capture_work, apply_changes, record_directive) layer on
* later against the same loop. Few, fat tools so a small local model survives
* with one thing to reach for (docs/agent-tools.md).
*/
import type { ToolDecl } from './chat-client.js'
export const QUERY_PROJECT_TOOL: ToolDecl = {
name: 'query_project',
description:
'Read the current project state. A `view` selects the shape; deterministic code (scheduler, ' +
'lifecycle inference, calibration) backs every number — you report it, you never compute it.',
parameters: {
type: 'object',
properties: {
view: {
type: 'string',
enum: ['focus', 'board', 'calibration', 'issue', 'search'],
description:
'focus = Now/Next/Later; board = issues by lifecycle column; calibration = estimate-vs-actual; ' +
'issue = one issue (needs filters.issueId); search = issues matching filters.query.',
},
filters: {
type: 'object',
properties: {
issueId: { type: 'number' },
query: { type: 'string' },
limit: { type: 'number' },
},
},
},
required: ['view'],
},
}
export const PROPOSE_CHANGE_TOOL: ToolDecl = {
name: 'propose_change',
description:
"Propose an estimate and/or priority change to an issue. This does NOT apply anything — it shows the " +
'human a diff to approve. Use it whenever the user asks to re-estimate or reprioritize. After calling it, ' +
"tell the user you've *proposed* the change for approval — never say it is done.",
parameters: {
type: 'object',
properties: {
issue: { type: 'number', description: 'the issue number to change' },
estimate: { type: 'string', enum: ['est/1d', 'est/2d', 'est/3d', 'est/5d', 'est/8d'] },
priority: { type: 'string', enum: ['p/1', 'p/2', 'p/3', 'p/4'] },
},
required: ['issue'],
},
}
export const RECORD_DIRECTIVE_TOOL: ToolDecl = {
name: 'record_directive',
description:
'Log a standing instruction from the PM to the durable directive ledger — a reprioritization, ' +
'a re-estimate policy, a deadline, a scope or capacity call, or a plain note. Use it when the user ' +
'states intent that should persist ("pilots come first", "freeze scope for beta"). This records the ' +
'intent verbatim; the actual issue edits still go through propose_change.',
parameters: {
type: 'object',
properties: {
kind: { type: 'string', enum: ['reprioritize', 'reestimate', 'set-deadline', 'scope', 'capacity', 'note'] },
quote: { type: 'string', description: "the PM's own words, stored verbatim" },
target: {
type: 'object',
properties: {
issue: { type: 'number' },
milestone: { type: 'number' },
member: { type: 'string' },
},
},
rationale: { type: 'string', description: 'why (optional)' },
},
required: ['kind', 'quote'],
},
}
export const REGINALD_TOOLS: ToolDecl[] = [QUERY_PROJECT_TOOL, PROPOSE_CHANGE_TOOL, RECORD_DIRECTIVE_TOOL]
export const REGINALD_SYSTEM = [
'You are Reginald, the calm, dry project manager inside CommiTea — a tool that runs projects on Gitea.',
'Call query_project to ground every answer in the real project; never invent issues, numbers, or dates.',
'The scheduler and forecasts are deterministic code — report their output, do not recompute it.',
'To change an estimate or priority, call propose_change — it shows the human a diff to approve.',
'When the PM states standing intent ("pilots first", "freeze scope"), call record_directive to log it.',
'Never claim a change is applied; you propose, the human approves. Forecasts are ranges, never single dates.',
'Refer to issues as #<number>. Be brief and plain — a sentence or two. No preamble, no bullet dumps.',
].join(' ')

View File

@@ -1,239 +0,0 @@
import { describe, expect, it } from 'vitest'
import { extractLabelFacts } from '../labels/label-schema.js'
import type { GiteaIssue } from '../gitea/types.js'
import type { FetchLike } from '../gitea/types.js'
import { type ChatMessage, type CompletionResult, createChatClient, type ToolDecl } from './chat-client.js'
import { runAgentTurn } from './agent-loop.js'
import { pickModel } from './model-router.js'
import { buildProjectView, type ProjectSnapshot } from './query-project.js'
// ---- chat client ----
describe('createChatClient', () => {
function stub(body: unknown) {
const calls: { url: string; body: unknown }[] = []
const fetch: FetchLike = (url, init) => {
calls.push({ url, body: init?.body ? JSON.parse(init.body) : undefined })
return Promise.resolve({
ok: true,
status: 200,
json: () => Promise.resolve(body),
text: () => Promise.resolve(''),
})
}
return { fetch, calls }
}
it('POSTs to /chat/completions and parses content', async () => {
const { fetch, calls } = stub({ choices: [{ message: { content: 'the focus is #2' } }] })
const client = createChatClient({ baseUrl: 'http://localhost:1234/v1', model: 'gemma' }, fetch)
const res = await client.complete([{ role: 'user', content: 'what now?' }])
expect(res.content).toBe('the focus is #2')
expect(res.toolCalls).toEqual([])
expect(calls[0].url).toBe('http://localhost:1234/v1/chat/completions')
expect((calls[0].body as { model: string }).model).toBe('gemma')
})
it('parses tool calls from the wire shape', async () => {
const { fetch } = stub({
choices: [
{
message: {
content: null,
tool_calls: [{ id: 'c1', function: { name: 'query_project', arguments: '{"view":"focus"}' } }],
},
},
],
})
const client = createChatClient({ baseUrl: 'http://x/v1', model: 'm' }, fetch)
const res = await client.complete([{ role: 'user', content: 'x' }], [{ name: 'query_project', description: '', parameters: {} }])
expect(res.toolCalls).toEqual([{ id: 'c1', name: 'query_project', arguments: '{"view":"focus"}' }])
})
it('serializes assistant tool_calls + tool results in the request', async () => {
const { fetch, calls } = stub({ choices: [{ message: { content: 'ok' } }] })
const client = createChatClient({ baseUrl: 'http://x/v1', model: 'm' }, fetch)
const convo: ChatMessage[] = [
{ role: 'user', content: 'hi' },
{ role: 'assistant', content: '', toolCalls: [{ id: 'c1', name: 'query_project', arguments: '{}' }] },
{ role: 'tool', toolCallId: 'c1', name: 'query_project', content: '{"now":null}' },
]
await client.complete(convo)
const sent = (calls[0].body as { messages: Record<string, unknown>[] }).messages
expect(sent[1].tool_calls).toBeDefined()
expect(sent[2]).toEqual({ role: 'tool', tool_call_id: 'c1', content: '{"now":null}' })
})
})
// ---- model router ----
describe('pickModel', () => {
const router = { small: { baseUrl: 'u', model: 'small' }, big: { baseUrl: 'u', model: 'big' } }
it('routes plan → big, everything else → small', () => {
expect(pickModel(router, 'plan').model).toBe('big')
expect(pickModel(router, 'ritual').model).toBe('small')
})
})
// ---- agent loop ----
describe('runAgentTurn', () => {
const tools: ToolDecl[] = [{ name: 'query_project', description: '', parameters: {} }]
it('runs a tool then returns the model prose, recording the step', async () => {
// first completion asks for a tool; second answers in prose
const scripted: CompletionResult[] = [
{ content: '', toolCalls: [{ id: 'c1', name: 'query_project', arguments: '{"view":"focus"}' }] },
{ content: 'Right now: #2.', toolCalls: [] },
]
let i = 0
const executed: { name: string; args: unknown }[] = []
const turn = await runAgentTurn({
complete: async () => scripted[i++],
messages: [{ role: 'user', content: 'what now?' }],
tools,
execute: async (name, args) => {
executed.push({ name, args })
return { now: { issue: 2 } }
},
})
expect(turn.content).toBe('Right now: #2.')
expect(turn.steps).toEqual([
{ tool: 'query_project', arguments: '{"view":"focus"}', result: '{"now":{"issue":2}}' },
])
expect(executed).toEqual([{ name: 'query_project', args: { view: 'focus' } }])
// conversation carries user → assistant(tool) → tool → assistant(prose)
expect(turn.messages.map((m) => m.role)).toEqual(['user', 'assistant', 'tool', 'assistant'])
})
it('answers directly when the model needs no tool', async () => {
const turn = await runAgentTurn({
complete: async () => ({ content: 'Hello.', toolCalls: [] }),
messages: [{ role: 'user', content: 'hi' }],
tools,
execute: async () => ({}),
})
expect(turn.content).toBe('Hello.')
expect(turn.steps).toEqual([])
})
it('captures a tool executor error as the tool result instead of throwing', async () => {
const scripted: CompletionResult[] = [
{ content: '', toolCalls: [{ id: 'c1', name: 'query_project', arguments: '{}' }] },
{ content: 'Something went wrong reading that.', toolCalls: [] },
]
let i = 0
const turn = await runAgentTurn({
complete: async () => scripted[i++],
messages: [{ role: 'user', content: 'x' }],
tools,
execute: async () => {
throw new Error('boom')
},
})
expect(turn.steps[0].result).toContain('boom')
expect(turn.content).toBe('Something went wrong reading that.')
})
it('forces a final prose answer when the step budget is exhausted', async () => {
// always asks for a tool; the loop must still terminate with prose
let toolRounds = 0
const turn = await runAgentTurn({
complete: async (_m, tls) => {
if (tls && tls.length) {
toolRounds++
return { content: '', toolCalls: [{ id: `c${toolRounds}`, name: 'query_project', arguments: '{}' }] }
}
return { content: 'final answer', toolCalls: [] } // called with tools withheld
},
messages: [{ role: 'user', content: 'x' }],
tools,
execute: async () => ({}),
maxSteps: 2,
})
expect(toolRounds).toBe(2)
expect(turn.content).toBe('final answer')
})
})
// ---- query_project view builder ----
describe('buildProjectView', () => {
const asOf = new Date('2026-02-01T00:00:00Z')
function issue(over: Partial<GiteaIssue>): GiteaIssue {
const labels = over.labels ?? []
return {
number: 1,
title: '#1',
body: '',
state: 'open',
labels,
facts: extractLabelFacts(labels),
milestone: null,
assignee: null,
assignees: [],
createdAt: '2026-01-05T09:00:00Z',
updatedAt: '2026-01-05T09:00:00Z',
closedAt: null,
url: '',
...over,
}
}
const snap: ProjectSnapshot = {
issues: [
issue({ number: 2, title: 'ChangeSource', labels: ['est/3d', 'p/1'] }),
issue({ number: 3, title: 'SQLite cache', labels: ['est/2d', 'p/1'] }),
issue({ number: 9, title: 'Done thing', state: 'closed', labels: ['est/2d'], closedAt: '2026-01-12T09:00:00Z' }),
],
timelines: { 9: [{ type: 'commit', at: '2026-01-07T09:00:00Z' }, { type: 'close', at: '2026-01-12T09:00:00Z' }] },
deps: [{ issue: 3, dependsOn: 2 }],
}
it('focus returns Now/Next/Later grounded in the scheduler', () => {
const v = buildProjectView('focus', undefined, snap, asOf) as {
now: { issue: number } | null
openCount: number
}
expect(v.now?.issue).toBe(2) // #3 depends on #2, so #2 comes first
expect(v.openCount).toBe(2)
})
it('board groups issues by lifecycle column', () => {
const v = buildProjectView('board', undefined, snap, asOf) as {
columns: { column: string; count: number }[]
}
const done = v.columns.find((c) => c.column === 'done')
expect(done?.count).toBe(1) // #9
const triage = v.columns.find((c) => c.column === 'triage')
expect(triage?.count).toBe(2) // #2, #3 labelled, no commits yet
})
it('calibration reports n + cold-start honestly', () => {
const v = buildProjectView('calibration', undefined, snap, asOf) as { n: number; coldStart: boolean }
expect(v.n).toBe(1) // one closed, estimated, with an actual
expect(v.coldStart).toBe(true)
})
it('issue returns intent + derived for a specific id', () => {
const v = buildProjectView('issue', { issueId: 3 }, snap, asOf) as {
issue: number
blockedBy: number[]
}
expect(v.issue).toBe(3)
expect(v.blockedBy).toEqual([2])
})
it('search matches title/labels', () => {
const v = buildProjectView('search', { query: 'sqlite' }, snap, asOf) as { results: { issue: number }[] }
expect(v.results.map((r) => r.issue)).toEqual([3])
})
it('unbuilt views return a notImplemented marker, not fabricated data', () => {
expect(buildProjectView('standup', undefined, snap, asOf)).toEqual({ notImplemented: 'standup' })
})
})

View File

@@ -1,65 +0,0 @@
import { describe, expect, it } from 'vitest'
import type { CompletionResult } from './chat-client.js'
import { captureWork, parseCaptureArgs } from './capture-work.js'
describe('parseCaptureArgs', () => {
it('validates issues and keeps only real titles + valid labels', () => {
const p = parseCaptureArgs({
issues: [
{ title: 'Fix token refresh', body: 'dies silently', estimate: 'est/2d', priority: 'p/1' },
{ title: ' ', body: 'blank title dropped' },
{ title: 'Docs', estimate: 'est/9d', priority: 'urgent' }, // invalid labels → dropped to undefined
],
consequence: 'Beta slips a day',
})
expect(p.issues).toHaveLength(2)
expect(p.issues[0]).toEqual({ title: 'Fix token refresh', body: 'dies silently', estimate: 'est/2d', priority: 'p/1' })
expect(p.issues[1]).toEqual({ title: 'Docs', body: '', estimate: undefined, priority: undefined })
expect(p.consequence).toBe('Beta slips a day')
})
it('tolerates a missing/!array issues field', () => {
expect(parseCaptureArgs({}).issues).toEqual([])
expect(parseCaptureArgs({ issues: 'nope' }).issues).toEqual([])
})
})
describe('captureWork', () => {
it('forces propose_issues and returns the validated set', async () => {
const result: CompletionResult = {
content: '',
toolCalls: [
{
id: 'c1',
name: 'propose_issues',
arguments: JSON.stringify({
issues: [{ title: 'Retry token refresh with backoff', body: '', estimate: 'est/2d', priority: 'p/2' }],
consequence: 'no material shift',
}),
},
],
}
let sawTool = ''
const proposal = await captureWork(async (_m, tools) => {
sawTool = tools?.[0]?.name ?? ''
return result
}, 'auth is flaky, token refresh dies')
expect(sawTool).toBe('propose_issues')
expect(proposal.issues[0].title).toBe('Retry token refresh with backoff')
expect(proposal.consequence).toBe('no material shift')
})
it('returns an empty set when the model answers without the tool', async () => {
const proposal = await captureWork(async () => ({ content: 'I need more detail.', toolCalls: [] }), 'vague')
expect(proposal.issues).toEqual([])
})
it('survives malformed tool arguments', async () => {
const proposal = await captureWork(
async () => ({ content: '', toolCalls: [{ id: 'c1', name: 'propose_issues', arguments: '{not json' }] }),
'x',
)
expect(proposal.issues).toEqual([])
})
})

View File

@@ -1,109 +0,0 @@
/**
* capture_work — braindump → a small set of concrete issues. This is the one
* place the big model earns its keep (decomposition + estimate negotiation).
* It returns a *proposal*; nothing is filed until the human approves it in the
* Capture tray and it goes through the create-issue write path. Pure
* orchestration over an injected `complete` — stubbable, so it's testable offline.
*/
import {
type EstimateLabel,
ESTIMATE_LABELS,
type PriorityLabel,
PRIORITY_LABELS,
} from '../labels/label-schema.js'
import type { ChatMessage, CompletionResult, ToolDecl } from './chat-client.js'
export interface ProposedIssue {
title: string
body: string
estimate?: EstimateLabel
priority?: PriorityLabel
}
export interface CaptureProposal {
issues: ProposedIssue[]
/** One-line schedule impact, if the model offered one. */
consequence?: string
}
export const PROPOSE_ISSUES_TOOL: ToolDecl = {
name: 'propose_issues',
description: 'Return the decomposed issue set for a braindump. Call this exactly once.',
parameters: {
type: 'object',
properties: {
issues: {
type: 'array',
items: {
type: 'object',
properties: {
title: { type: 'string', description: 'a clear imperative title' },
body: { type: 'string', description: 'one or two lines of detail' },
estimate: { type: 'string', enum: ['est/1d', 'est/2d', 'est/3d', 'est/5d', 'est/8d'] },
priority: { type: 'string', enum: ['p/1', 'p/2', 'p/3', 'p/4'] },
},
required: ['title'],
},
},
consequence: { type: 'string', description: 'one-line note on the schedule impact' },
},
required: ['issues'],
},
}
export const CAPTURE_SYSTEM = [
'You are Reginald, decomposing a rough braindump into a small set of concrete Gitea issues.',
'Call propose_issues exactly once. Split genuinely separate work; merge trivially-coupled work; invent no scope.',
'Each issue gets an imperative title, a one-line body, an estimate (est/1d…8d) and a priority (p/1…4).',
'Estimate honestly — a "quick" task is rarely one day. Keep the set tight; three good issues beat eight vague ones.',
].join(' ')
function isEstimate(v: unknown): v is EstimateLabel {
return typeof v === 'string' && (ESTIMATE_LABELS as readonly string[]).includes(v)
}
function isPriority(v: unknown): v is PriorityLabel {
return typeof v === 'string' && (PRIORITY_LABELS as readonly string[]).includes(v)
}
/** Coerce the model's raw propose_issues args into a validated proposal. */
export function parseCaptureArgs(args: unknown): CaptureProposal {
const a = (args ?? {}) as { issues?: unknown[]; consequence?: unknown }
const issues: ProposedIssue[] = []
for (const raw of Array.isArray(a.issues) ? a.issues : []) {
const r = (raw ?? {}) as Record<string, unknown>
const title = typeof r.title === 'string' ? r.title.trim() : ''
if (!title) continue
issues.push({
title,
body: typeof r.body === 'string' ? r.body : '',
estimate: isEstimate(r.estimate) ? r.estimate : undefined,
priority: isPriority(r.priority) ? r.priority : undefined,
})
}
return { issues, consequence: typeof a.consequence === 'string' ? a.consequence : undefined }
}
/**
* Run one decomposition turn. Forces the model to answer via propose_issues and
* returns the validated set. An empty set means the model declined to structure it.
*/
export async function captureWork(
complete: (messages: ChatMessage[], tools?: ToolDecl[]) => Promise<CompletionResult>,
braindump: string,
): Promise<CaptureProposal> {
const res = await complete(
[
{ role: 'system', content: CAPTURE_SYSTEM },
{ role: 'user', content: braindump },
],
[PROPOSE_ISSUES_TOOL],
)
const call = res.toolCalls.find((t) => t.name === 'propose_issues')
if (!call) return { issues: [] }
try {
return parseCaptureArgs(JSON.parse(call.arguments || '{}'))
} catch {
return { issues: [] }
}
}

View File

@@ -1,123 +0,0 @@
/**
* Reginald's model client — a thin OpenAI-wire chat-completions client over an
* injected fetch (the same seam the gitea client uses). `@commitea/core` stays
* pure: no network, no globals. The desktop main process passes the real
* `fetch`; tests pass a stub. Points at any OpenAI-compatible endpoint (LM
* Studio, Ollama, the OpenAI API) — the model router picks which.
*/
import type { FetchLike } from '../gitea/types.js'
/** Where a model lives + which model to ask for. */
export interface ModelConfig {
/** OpenAI-compatible base, including the version segment, e.g. `http://localhost:1234/v1`. */
baseUrl: string
model: string
/** Bearer key; omitted for local servers that don't check it. */
apiKey?: string
}
/** A model's request to run a tool. `arguments` is a raw JSON string (OpenAI shape). */
export interface ToolCall {
id: string
name: string
arguments: string
}
/** One turn in the conversation, in our normalized shape. */
export interface ChatMessage {
role: 'system' | 'user' | 'assistant' | 'tool'
content: string
/** assistant turns that requested tools. */
toolCalls?: ToolCall[]
/** tool turns: which call they answer. */
toolCallId?: string
/** tool turns: the function name. */
name?: string
}
/** A tool the model may call — name, description, and a JSON-Schema parameter spec. */
export interface ToolDecl {
name: string
description: string
parameters: object
}
export interface CompletionResult {
content: string
toolCalls: ToolCall[]
}
export interface ChatClient {
complete(messages: ChatMessage[], tools?: ToolDecl[]): Promise<CompletionResult>
}
/** Map our message shape to the OpenAI wire shape. */
function toWireMessage(m: ChatMessage): Record<string, unknown> {
if (m.role === 'assistant' && m.toolCalls?.length) {
return {
role: 'assistant',
content: m.content || null,
tool_calls: m.toolCalls.map((tc) => ({
id: tc.id,
type: 'function',
function: { name: tc.name, arguments: tc.arguments },
})),
}
}
if (m.role === 'tool') {
return { role: 'tool', tool_call_id: m.toolCallId, content: m.content }
}
return { role: m.role, content: m.content }
}
function toWireTool(t: ToolDecl): Record<string, unknown> {
return { type: 'function', function: { name: t.name, description: t.description, parameters: t.parameters } }
}
/** Shape of the one choice we read back. */
interface RawChoiceMessage {
content: string | null
tool_calls?: { id: string; function: { name: string; arguments: string } }[]
}
export function createChatClient(config: ModelConfig, fetchImpl: FetchLike): ChatClient {
const url = `${config.baseUrl.replace(/\/+$/, '')}/chat/completions`
return {
async complete(messages, tools) {
const body: Record<string, unknown> = {
model: config.model,
messages: messages.map(toWireMessage),
temperature: 0,
}
if (tools?.length) {
body.tools = tools.map(toWireTool)
body.tool_choice = 'auto'
}
const res = await fetchImpl(url, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
Accept: 'application/json',
...(config.apiKey ? { Authorization: `Bearer ${config.apiKey}` } : {}),
},
body: JSON.stringify(body),
})
if (!res.ok) {
const text = await res.text().catch(() => '')
throw new Error(`model completion failed (${res.status}): ${text.slice(0, 200)}`)
}
const json = (await res.json()) as { choices?: { message: RawChoiceMessage }[] }
const msg = json.choices?.[0]?.message
return {
content: msg?.content ?? '',
toolCalls: (msg?.tool_calls ?? []).map((tc) => ({
id: tc.id,
name: tc.function.name,
arguments: tc.function.arguments,
})),
}
},
}
}

View File

@@ -1,22 +0,0 @@
/**
* Model router (per PLAN.md / decisions.md): prose + the read tool run on a
* small local model; decomposition/negotiation earns the big one. Reginald v0
* only exercises the small model (read + prose); the `big` slot is declared so
* `capture_work` / `record_directive` can route to it without a rewrite.
*/
import type { ModelConfig } from './chat-client.js'
export type TaskKind = 'ritual' | 'plan'
export interface ModelRouter {
/** Small local model — standups, focus prose, the read tool. */
small: ModelConfig
/** Big model — capture decomposition, directive negotiation. */
big: ModelConfig
}
/** `plan` → the big model; everything else → the small one. */
export function pickModel(router: ModelRouter, kind: TaskKind): ModelConfig {
return kind === 'plan' ? router.big : router.small
}

View File

@@ -1,146 +0,0 @@
/**
* `query_project` — Reginald's single read tool. It selects a compact,
* model-friendly view over the reconciled backlog. Every number comes from
* deterministic code (scheduler, lifecycle inference, calibration); the model
* only requests a shape and narrates it — it never computes (decisions.md).
*
* v0 serves focus / board / calibration / issue. The remaining views
* (milestone / runway / standup / search) return a `notImplemented` marker so
* the model degrades honestly instead of inventing data.
*/
import { fitCalibration, calibrationSamples } from '../calibration/calibration-v0.js'
import type { GiteaIssue } from '../gitea/types.js'
import { inferLifecycle, type LifecycleColumn, type LifecycleEvent } from '../lifecycle/lifecycle-v0.js'
import { type DependencyEdge, schedule, selectFocus } from '../scheduler/scheduler-v0.js'
export type ProjectView =
| 'focus'
| 'board'
| 'calibration'
| 'issue'
| 'milestone'
| 'runway'
| 'standup'
| 'search'
export interface QueryFilters {
issueId?: number
query?: string
limit?: number
}
/** The reconciled inputs a view is built from. */
export interface ProjectSnapshot {
issues: GiteaIssue[]
timelines: Record<number, LifecycleEvent[]>
deps: DependencyEdge[]
}
const COLUMN_ORDER: LifecycleColumn[] = ['diagnosis', 'triage', 'steeping', 'review', 'done']
function toSchedulable(issues: GiteaIssue[]) {
return issues
.filter((i) => i.state === 'open')
.map((i) => ({
number: i.number,
title: i.title,
labels: i.labels,
estimateDays: i.facts.estimateDays,
priority: i.facts.priority,
}))
}
function focusView(snap: ProjectSnapshot) {
const plan = schedule(toSchedulable(snap.issues), snap.deps)
const f = selectFocus(plan)
const slot = (item: (typeof plan.items)[number] | null) =>
item ? { issue: item.number, title: item.title, rationale: item.rationale } : null
return { now: slot(f.now), next: slot(f.next), later: slot(f.later), openCount: plan.items.length }
}
function boardView(snap: ProjectSnapshot, asOf: Date) {
const columns: Record<string, { issue: number; title: string; labels: string[] }[]> = {}
for (const key of COLUMN_ORDER) columns[key] = []
for (const issue of snap.issues) {
const inf = inferLifecycle(issue, snap.timelines[issue.number] ?? [], asOf)
columns[inf.column].push({ issue: issue.number, title: issue.title, labels: issue.labels })
}
return {
columns: COLUMN_ORDER.map((key) => ({ column: key, count: columns[key].length, issues: columns[key] })),
}
}
function calibrationView(snap: ProjectSnapshot, asOf: Date) {
const model = fitCalibration(calibrationSamples(snap.issues, snap.timelines, asOf))
return {
n: model.n,
coldStart: model.coldStart,
globalMultiplier: Number(Math.exp(model.global.mu).toFixed(2)),
byBucket: Object.entries(model.byBucket).map(([bucket, fit]) => ({
estimate: `est/${bucket}d`,
n: fit.n,
multiplier: Number(Math.exp(fit.mu).toFixed(2)),
})),
}
}
function issueView(snap: ProjectSnapshot, filters: QueryFilters, asOf: Date) {
const issue = snap.issues.find((i) => i.number === filters.issueId)
if (!issue) return { notFound: filters.issueId ?? null }
const inf = inferLifecycle(issue, snap.timelines[issue.number] ?? [], asOf)
const blockedBy = snap.deps.filter((d) => d.issue === issue.number).map((d) => d.dependsOn)
const blocks = snap.deps.filter((d) => d.dependsOn === issue.number).map((d) => d.issue)
return {
issue: issue.number,
title: issue.title,
state: issue.state,
column: inf.column,
labels: issue.labels,
assignee: issue.assignee,
milestone: issue.milestone?.title ?? null,
estimateDays: issue.facts.estimateDays,
priority: issue.facts.priority,
steepingDays: inf.steepingDays,
blockedBy,
blocks,
}
}
function searchView(snap: ProjectSnapshot, filters: QueryFilters) {
const q = (filters.query ?? '').toLowerCase().trim()
const limit = Math.min(filters.limit ?? 20, 100)
const hits = q
? snap.issues.filter(
(i) => i.title.toLowerCase().includes(q) || i.labels.some((l) => l.toLowerCase().includes(q)),
)
: []
return {
query: filters.query ?? '',
results: hits.slice(0, limit).map((i) => ({ issue: i.number, title: i.title, state: i.state, labels: i.labels })),
}
}
/** Build the compact payload for one view. Unknown/unbuilt views return a marker. */
export function buildProjectView(
view: ProjectView,
filters: QueryFilters | undefined,
snap: ProjectSnapshot,
asOf: Date,
): unknown {
const f = filters ?? {}
switch (view) {
case 'focus':
return focusView(snap)
case 'board':
return boardView(snap, asOf)
case 'calibration':
return calibrationView(snap, asOf)
case 'issue':
return issueView(snap, f, asOf)
case 'search':
return searchView(snap, f)
default:
return { notImplemented: view }
}
}

View File

@@ -1,121 +0,0 @@
import { describe, expect, it } from 'vitest'
import { extractLabelFacts } from '../labels/label-schema.js'
import type { LifecycleEvent } from '../lifecycle/lifecycle-v0.js'
import type { GiteaIssue } from '../gitea/types.js'
import {
CALIBRATION_BUCKET_FLOOR,
calibrationSamples,
type CalibrationSample,
COLD_START_THRESHOLD,
fitCalibration,
toDurationModel,
} from './calibration-v0.js'
function sample(over: Partial<CalibrationSample> = {}): CalibrationSample {
return { issue: 1, estimateDays: 2, actualWorkingDays: 2, bucket: 2, person: null, ...over }
}
describe('fitCalibration', () => {
it('is cold-start below the threshold and reports the honest n', () => {
const m = fitCalibration([sample(), sample({ actualWorkingDays: 4 })])
expect(m.n).toBe(2)
expect(m.coldStart).toBe(true)
})
it('flips off cold-start at the threshold', () => {
const many = Array.from({ length: COLD_START_THRESHOLD }, (_, i) =>
sample({ issue: i, estimateDays: 2, actualWorkingDays: 3, bucket: 2 }),
)
const m = fitCalibration(many)
expect(m.n).toBe(COLD_START_THRESHOLD)
expect(m.coldStart).toBe(false)
})
it('recovers the global median ratio (mu = mean log-ratio)', () => {
// every actual is exactly 2x its estimate → mu = ln 2
const m = fitCalibration(Array.from({ length: 25 }, (_, i) => sample({ issue: i, estimateDays: 2, actualWorkingDays: 4 })))
expect(m.global.mu).toBeCloseTo(Math.log(2), 6)
})
it('fits a bucket only once it clears the floor', () => {
const twos = Array.from({ length: CALIBRATION_BUCKET_FLOOR }, (_, i) =>
sample({ issue: i, estimateDays: 2, actualWorkingDays: 3, bucket: 2 }),
)
const oneThin = [sample({ issue: 99, estimateDays: 5, actualWorkingDays: 9, bucket: 5 })]
const m = fitCalibration([...twos, ...oneThin])
expect(m.byBucket[2]?.n).toBe(CALIBRATION_BUCKET_FLOOR)
expect(m.byBucket[5]).toBeUndefined() // only 1 sample, below floor
})
it('drops non-positive estimates/actuals', () => {
const m = fitCalibration([sample({ actualWorkingDays: 0 }), sample({ estimateDays: 0 }), sample()])
expect(m.n).toBe(1)
})
it('derives a per-person bias relative to global', () => {
// one person consistently runs longer than the mean
const base = Array.from({ length: 20 }, (_, i) => sample({ issue: i, actualWorkingDays: 2, person: 'ak' }))
const slow = Array.from({ length: 3 }, (_, i) => sample({ issue: 100 + i, actualWorkingDays: 6, person: 'sm' }))
const m = fitCalibration([...base, ...slow])
expect(m.byPerson['sm'].biasMu).toBeGreaterThan(0)
expect(m.byPerson['ak'].biasMu).toBeLessThan(0)
})
})
describe('toDurationModel', () => {
it('projects the fit down to the params forecast needs', () => {
const m = fitCalibration(
Array.from({ length: 25 }, (_, i) => sample({ issue: i, estimateDays: 2, actualWorkingDays: 3, bucket: 2 })),
)
const dm = toDurationModel(m)
expect(dm.coldStart).toBe(false)
expect(dm.byBucket[2].mu).toBeCloseTo(m.byBucket[2].mu, 6)
expect(dm.global.mu).toBeCloseTo(m.global.mu, 6)
})
})
describe('calibrationSamples', () => {
const asOf = new Date('2026-02-01T00:00:00Z')
function issue(over: Partial<GiteaIssue>): GiteaIssue {
const labels = over.labels ?? []
return {
number: 1,
title: '#1',
body: '',
state: 'closed',
labels,
facts: extractLabelFacts(labels),
milestone: null,
assignee: null,
assignees: [],
createdAt: '2026-01-05T09:00:00Z',
updatedAt: '2026-01-12T09:00:00Z',
closedAt: '2026-01-12T09:00:00Z',
url: '',
...over,
}
}
const events = (i: number): Record<number, LifecycleEvent[]> => ({
[i]: [{ type: 'commit', at: '2026-01-07T09:00:00Z' }, { type: 'close', at: '2026-01-12T09:00:00Z' }],
})
it('samples closed, estimated issues with a resolvable actual', () => {
const i = issue({ number: 7, labels: ['est/2d'], assignee: 'sm', closedAt: '2026-01-12T09:00:00Z' })
const [s] = calibrationSamples([i], events(7), asOf)
expect(s.issue).toBe(7)
expect(s.estimateDays).toBe(2)
expect(s.bucket).toBe(2)
expect(s.person).toBe('sm')
// Wed 2026-01-07 → Mon 2026-01-12 = Wed,Thu,Fri = 3 working days
expect(s.actualWorkingDays).toBe(3)
})
it('skips open issues and closed ones without an estimate', () => {
const open = issue({ number: 8, state: 'open', labels: ['est/2d'], closedAt: null })
const noEst = issue({ number: 9, labels: [] })
expect(calibrationSamples([open, noEst], { ...events(8), ...events(9) }, asOf)).toEqual([])
})
})

View File

@@ -1,127 +0,0 @@
/**
* Calibration, v0 — fit the team's own estimate-vs-actual history so the
* forecast stops guessing (D3). The "actual" is the working time lifecycle
* inference derives from git events (#5), never manual tracking. Fit a
* lognormal on log(actual / estimate) globally and per estimate bucket; until
* the sample clears the cold-start threshold, the forecast keeps using the
* code-resident priors and this model just reports progress toward it.
*/
import { type DurationModel, type LognormalPrior, nearestBucket } from '../forecast/forecast-v0.js'
import { inferLifecycle, type LifecycleEvent } from '../lifecycle/lifecycle-v0.js'
import type { GiteaIssue } from '../gitea/types.js'
/** Global sample size at which the fit takes over from the cold-start priors. */
export const COLD_START_THRESHOLD = 20
/** Minimum per-bucket sample before that bucket earns its own fit. */
export const CALIBRATION_BUCKET_FLOOR = 3
/** Fallback spread when a group is too small to estimate one. */
const DEFAULT_SIGMA = 0.4
/** One closed issue's estimate vs its inferred actual. */
export interface CalibrationSample {
issue: number
estimateDays: number
actualWorkingDays: number
bucket: number
person: string | null
}
export interface BucketFit extends LognormalPrior {
n: number
}
export interface PersonBias {
/** Additive to global mu (log space). */
biasMu: number
n: number
}
export interface CalibrationModel {
/** Closed issues with an estimate + a resolvable actual. */
n: number
/** true while n < COLD_START_THRESHOLD — forecast keeps the code priors. */
coldStart: boolean
global: LognormalPrior
byBucket: Record<number, BucketFit>
byPerson: Record<string, PersonBias>
}
function mean(xs: number[]): number {
return xs.reduce((a, b) => a + b, 0) / xs.length
}
/** Sample standard deviation; falls back to DEFAULT_SIGMA below 2 points. */
function stddev(xs: number[], mu: number): number {
if (xs.length < 2) return DEFAULT_SIGMA
const variance = xs.reduce((a, x) => a + (x - mu) ** 2, 0) / (xs.length - 1)
return Math.sqrt(variance) || DEFAULT_SIGMA
}
/** Fit a calibration model from estimate-vs-actual samples. Pure. */
export function fitCalibration(samples: CalibrationSample[]): CalibrationModel {
const usable = samples.filter((s) => s.estimateDays > 0 && s.actualWorkingDays > 0)
const n = usable.length
const coldStart = n < COLD_START_THRESHOLD
const logRatios = usable.map((s) => Math.log(s.actualWorkingDays / s.estimateDays))
const globalMu = n ? mean(logRatios) : 0
const global: LognormalPrior = { mu: globalMu, sigma: n ? stddev(logRatios, globalMu) : DEFAULT_SIGMA }
const byBucket: Record<number, BucketFit> = {}
const byPerson: Record<string, PersonBias> = {}
const groups = new Map<number, number[]>()
const people = new Map<string, number[]>()
for (const s of usable) {
const lr = Math.log(s.actualWorkingDays / s.estimateDays)
;(groups.get(s.bucket) ?? groups.set(s.bucket, []).get(s.bucket)!).push(lr)
if (s.person) (people.get(s.person) ?? people.set(s.person, []).get(s.person)!).push(lr)
}
for (const [bucket, lrs] of groups) {
if (lrs.length < CALIBRATION_BUCKET_FLOOR) continue
const mu = mean(lrs)
byBucket[bucket] = { mu, sigma: stddev(lrs, mu), n: lrs.length }
}
for (const [person, lrs] of people) {
if (lrs.length < CALIBRATION_BUCKET_FLOOR) continue
byPerson[person] = { biasMu: mean(lrs) - globalMu, n: lrs.length }
}
return { n, coldStart, global, byBucket, byPerson }
}
/** The subset of a model `forecast` consumes. */
export function toDurationModel(model: CalibrationModel): DurationModel {
const byBucket: Record<number, LognormalPrior> = {}
for (const [bucket, fit] of Object.entries(model.byBucket)) {
byBucket[Number(bucket)] = { mu: fit.mu, sigma: fit.sigma }
}
return { coldStart: model.coldStart, global: model.global, byBucket }
}
/**
* Extract calibration samples from the closed backlog: each closed issue that
* carries an estimate and yields an inferred actual working duration.
*/
export function calibrationSamples(
issues: GiteaIssue[],
timelines: Record<number, LifecycleEvent[]>,
asOf: Date,
): CalibrationSample[] {
const out: CalibrationSample[] = []
for (const issue of issues) {
if (issue.state !== 'closed') continue
const estimateDays = issue.facts.estimateDays
if (estimateDays == null) continue
const inf = inferLifecycle(issue, timelines[issue.number] ?? [], asOf)
if (inf.actualWorkingDays == null || inf.actualWorkingDays <= 0) continue
out.push({
issue: issue.number,
estimateDays,
actualWorkingDays: inf.actualWorkingDays,
bucket: nearestBucket(estimateDays),
person: issue.assignee,
})
}
return out
}

View File

@@ -1,79 +0,0 @@
import { describe, expect, it } from 'vitest'
import { describeChange, type IssueChange, planIssueChange, proposalsFor } from './apply-changes-v0.js'
describe('planIssueChange', () => {
it('swaps the estimate label, keeping non-axis labels', () => {
const plan = planIssueChange(['est/2d', 'p/1', 'backend'], { kind: 'reestimate', issue: 1, estimate: 'est/5d' })
expect(plan.removed).toEqual(['est/2d'])
expect(plan.added).toEqual(['est/5d'])
expect(plan.labels).toEqual(['p/1', 'backend', 'est/5d'])
expect(plan.noop).toBe(false)
})
it('adds an estimate when none was set', () => {
const plan = planIssueChange(['p/2'], { kind: 'reestimate', issue: 1, estimate: 'est/1d' })
expect(plan.removed).toEqual([])
expect(plan.added).toEqual(['est/1d'])
expect(plan.labels).toEqual(['p/2', 'est/1d'])
})
it('clears the axis when the target is null', () => {
const plan = planIssueChange(['est/3d', 'p/1'], { kind: 'reprioritize', issue: 1, priority: null })
expect(plan.removed).toEqual(['p/1'])
expect(plan.added).toEqual([])
expect(plan.labels).toEqual(['est/3d'])
})
it('is a noop when the target already holds the axis alone', () => {
const plan = planIssueChange(['est/2d', 'p/1'], { kind: 'reestimate', issue: 1, estimate: 'est/2d' })
expect(plan.noop).toBe(true)
expect(plan.labels).toEqual(['p/1', 'est/2d'])
})
it('cleans up a duplicated axis down to the target', () => {
// two est/* labels — the change collapses to one
const plan = planIssueChange(['est/2d', 'est/5d', 'p/1'], { kind: 'reestimate', issue: 1, estimate: 'est/5d' })
expect(plan.removed).toEqual(['est/2d'])
expect(plan.added).toEqual([]) // est/5d already present
expect(plan.labels).toEqual(['p/1', 'est/5d'])
expect(plan.noop).toBe(false)
})
it('reprioritize only touches the priority axis', () => {
const plan = planIssueChange(['est/2d', 'p/3'], { kind: 'reprioritize', issue: 1, priority: 'p/1' })
expect(plan.labels).toEqual(['est/2d', 'p/1'])
})
it('describeChange renders the diff', () => {
const change: IssueChange = { kind: 'reestimate', issue: 1, estimate: 'est/5d' }
expect(describeChange(planIssueChange(['est/2d'], change))).toBe('est/2d → est/5d')
expect(describeChange(planIssueChange(['p/1'], { kind: 'reprioritize', issue: 1, priority: null }))).toBe('p/1 → ∅')
expect(describeChange(planIssueChange(['est/5d'], change))).toBe('no change')
})
})
describe('proposalsFor', () => {
it('builds one proposal per changed axis, carrying the concrete change + diff', () => {
const props = proposalsFor({ issue: 2, estimate: 'est/5d', priority: 'p/1' }, ['est/2d', 'p/3'], 'ChangeSource')
expect(props).toHaveLength(2)
expect(props[0].change).toEqual({ kind: 'reestimate', issue: 2, estimate: 'est/5d' })
expect(describeChange(props[0].plan)).toBe('est/2d → est/5d')
expect(props[1].change).toEqual({ kind: 'reprioritize', issue: 2, priority: 'p/1' })
expect(props[0].issueTitle).toBe('ChangeSource')
})
it('drops a noop axis (already at the requested value)', () => {
const props = proposalsFor({ issue: 2, estimate: 'est/2d', priority: 'p/1' }, ['est/2d', 'p/3'])
expect(props.map((p) => p.change.kind)).toEqual(['reprioritize']) // estimate unchanged
})
it('ignores invalid label values from the model', () => {
const props = proposalsFor({ issue: 2, estimate: 'est/4d' as never, priority: 'high' as never }, [])
expect(props).toEqual([])
})
it('returns nothing when no axis is provided', () => {
expect(proposalsFor({ issue: 2 }, ['est/2d'])).toEqual([])
})
})

View File

@@ -1,104 +0,0 @@
/**
* Apply-changes, v0 — the write path's planning half. Estimates and priority
* live as exclusive label axes (`est/*`, `p/*`); a change swaps the axis label.
* This computes the resulting label set + a human-readable diff *purely*, so the
* UI can show a propose-approve consequence before the write and tests can pin
* the semantics. The actual PUT (name→id resolution + network) is the bridge's
* job — additive here, never assumed.
*/
import {
type EstimateLabel,
ESTIMATE_LABELS,
type PriorityLabel,
PRIORITY_LABELS,
} from '../labels/label-schema.js'
export type IssueChange =
| { kind: 'reestimate'; issue: number; estimate: EstimateLabel | null }
| { kind: 'reprioritize'; issue: number; priority: PriorityLabel | null }
export interface LabelPlan {
/** The full resulting label-name set (order: kept labels, then the new axis label). */
labels: string[]
/** Axis labels being added (0 or 1). */
added: string[]
/** Axis labels being removed (includes clearing a duplicated axis). */
removed: string[]
/** true when the change would leave the labels unchanged. */
noop: boolean
}
function axisFor(change: IssueChange): { labels: readonly string[]; target: string | null } {
return change.kind === 'reestimate'
? { labels: ESTIMATE_LABELS, target: change.estimate }
: { labels: PRIORITY_LABELS, target: change.priority }
}
/**
* Plan the label mutation for a single change. Removes every label on the
* change's axis except the target, adds the target if absent. Setting the axis
* to null clears it. Cleans up a duplicated axis (two `est/*`) as a side effect.
*/
export function planIssueChange(current: string[], change: IssueChange): LabelPlan {
const { labels: axis, target } = axisFor(change)
const onAxis = current.filter((l) => axis.includes(l))
const removed = onAxis.filter((l) => l !== target)
const added = target && !current.includes(target) ? [target] : []
const kept = current.filter((l) => !axis.includes(l))
const labels = target ? [...kept, target] : kept
return { labels, added, removed, noop: added.length === 0 && removed.length === 0 }
}
/** A short "est/2d → est/3d" (or "+p/1" / "est/5d") summary for the confirm UI. */
export function describeChange(plan: LabelPlan): string {
if (plan.noop) return 'no change'
const from = plan.removed.length ? plan.removed.join(', ') : '∅'
const to = plan.added.length ? plan.added.join(', ') : '∅'
return `${from}${to}`
}
/** A change the agent proposes: the concrete op + its diff, ready for approve-then-apply. */
export interface ChangeProposal {
change: IssueChange
plan: LabelPlan
issueTitle?: string
}
/** What the `propose_change` tool accepts — a target issue and the axes to set. */
export interface ProposeChangeArgs {
issue: number
estimate?: EstimateLabel
priority?: PriorityLabel
}
function isEstimate(v: unknown): v is EstimateLabel {
return typeof v === 'string' && (ESTIMATE_LABELS as readonly string[]).includes(v)
}
function isPriority(v: unknown): v is PriorityLabel {
return typeof v === 'string' && (PRIORITY_LABELS as readonly string[]).includes(v)
}
/**
* Build the concrete, non-noop proposals for a `propose_change` request against
* an issue's current labels. Invalid or unchanged axes are dropped — the agent
* proposes only real changes, and never a label outside the est/* · p/* axes.
*/
export function proposalsFor(
args: ProposeChangeArgs,
currentLabels: string[],
issueTitle?: string,
): ChangeProposal[] {
const out: ChangeProposal[] = []
if (isEstimate(args.estimate)) {
const change: IssueChange = { kind: 'reestimate', issue: args.issue, estimate: args.estimate }
const plan = planIssueChange(currentLabels, change)
if (!plan.noop) out.push({ change, plan, issueTitle })
}
if (isPriority(args.priority)) {
const change: IssueChange = { kind: 'reprioritize', issue: args.issue, priority: args.priority }
const plan = planIssueChange(currentLabels, change)
if (!plan.noop) out.push({ change, plan, issueTitle })
}
return out
}

View File

@@ -1,66 +0,0 @@
import { describe, expect, it } from 'vitest'
import {
appendDirective,
makeDirectiveEntry,
parseDirectiveLog,
serializeDirective,
toDirectiveInput,
} from './record-directive-v0.js'
describe('toDirectiveInput', () => {
it('keeps a valid kind + target and drops an empty target', () => {
const input = toDirectiveInput({ kind: 'reprioritize', quote: 'pilots first', target: { issue: 87 }, rationale: 'blocked' })
expect(input).toEqual({ kind: 'reprioritize', quote: 'pilots first', target: { issue: 87 }, params: undefined, rationale: 'blocked' })
expect(toDirectiveInput({ kind: 'note', quote: 'x', target: {} }).target).toBeUndefined()
})
it('falls back to note for an unknown kind', () => {
expect(toDirectiveInput({ kind: 'nonsense', quote: 'hmm' }).kind).toBe('note')
})
})
describe('serialize + parse round-trip', () => {
const entry = makeDirectiveEntry(
{ kind: 'reprioritize', quote: 'pilots come first', target: { issue: 87 } },
'id-1',
'2026-02-01T09:00:00Z',
)
it('serializes to one JSON line', () => {
const line = serializeDirective(entry)
expect(line).not.toContain('\n')
expect(JSON.parse(line)).toMatchObject({ id: 'id-1', kind: 'reprioritize', status: 'accepted' })
})
it('parses a log, orders by ts, and assigns a 1-based seq', () => {
const a = serializeDirective(makeDirectiveEntry({ kind: 'note', quote: 'later' }, 'b', '2026-02-02T00:00:00Z'))
const b = serializeDirective(makeDirectiveEntry({ kind: 'note', quote: 'earlier' }, 'a', '2026-02-01T00:00:00Z'))
const records = parseDirectiveLog(`${a}\n${b}\n`)
expect(records.map((r) => r.quote)).toEqual(['earlier', 'later'])
expect(records.map((r) => r.seq)).toEqual([1, 2])
})
it('skips blank and corrupt lines without losing the rest', () => {
const good = serializeDirective(entry)
const records = parseDirectiveLog(`\n{not json\n${good}\n\n`)
expect(records).toHaveLength(1)
expect(records[0].id).toBe('id-1')
})
})
describe('appendDirective', () => {
it('concatenates a newline-terminated entry, normalizing a missing trailing newline', () => {
const e1 = makeDirectiveEntry({ kind: 'note', quote: 'one' }, 'i1', '2026-01-01T00:00:00Z')
const e2 = makeDirectiveEntry({ kind: 'note', quote: 'two' }, 'i2', '2026-01-02T00:00:00Z')
let log = appendDirective('', e1)
log = appendDirective(log, e2)
expect(parseDirectiveLog(log).map((r) => r.quote)).toEqual(['one', 'two'])
expect(log.endsWith('\n')).toBe(true)
})
it('handles existing text without a trailing newline', () => {
const e = makeDirectiveEntry({ kind: 'note', quote: 'x' }, 'i', '2026-01-01T00:00:00Z')
expect(appendDirective('{"id":"prev","ts":"2025-01-01T00:00:00Z"}', e).split('\n').filter(Boolean)).toHaveLength(2)
})
})

View File

@@ -1,106 +0,0 @@
/**
* record_directive — the PM's standing instructions ("pilots come first"),
* appended to an append-only JSONL ledger in the pm-state repo (decisions.md D4,
* pm-state.md). A directive is *intent*: it's logged verbatim; its effects land
* later through apply_changes. Merge is concatenation — order derives from `ts`
* at read time, so two writers never conflict. `seq` is a display ordinal
* computed on read, never stored. This module is pure serialize/parse; the
* append (read → concat → write) is the bridge's job.
*/
export type DirectiveKind = 'reprioritize' | 'reestimate' | 'set-deadline' | 'scope' | 'capacity' | 'note'
export type DirectiveStatus = 'proposed' | 'accepted' | 'amended' | 'withdrawn'
export interface DirectiveTarget {
issue?: number
milestone?: number
member?: string
}
/** What the record_directive tool captures. */
export interface DirectiveInput {
kind: DirectiveKind
/** Verbatim PM words, shown in the ledger. */
quote: string
target?: DirectiveTarget
/** Structured effect the scheduler applies, e.g. { priority: 1 }. */
params?: Record<string, unknown>
rationale?: string
}
/** A ledger entry — an input plus its durable id/ts/status. */
export interface DirectiveEntry extends DirectiveInput {
id: string
ts: string
status: DirectiveStatus
}
/** A ledger entry as read back, with a computed display ordinal. */
export interface DirectiveRecord extends DirectiveEntry {
seq: number
}
const DIRECTIVE_KINDS: readonly DirectiveKind[] = [
'reprioritize',
'reestimate',
'set-deadline',
'scope',
'capacity',
'note',
]
/** Normalize a raw tool payload into a DirectiveInput (unknown kind → note). */
export function toDirectiveInput(raw: unknown): DirectiveInput {
const r = (raw ?? {}) as Record<string, unknown>
const kind = DIRECTIVE_KINDS.includes(r.kind as DirectiveKind) ? (r.kind as DirectiveKind) : 'note'
const target = (r.target ?? undefined) as DirectiveTarget | undefined
return {
kind,
quote: typeof r.quote === 'string' ? r.quote : '',
target: target && (target.issue || target.milestone || target.member) ? target : undefined,
params: (r.params && typeof r.params === 'object' ? (r.params as Record<string, unknown>) : undefined),
rationale: typeof r.rationale === 'string' ? r.rationale : undefined,
}
}
/** Build a full entry from an input + externally-supplied id/ts (Date/uuid live in the caller). */
export function makeDirectiveEntry(
input: DirectiveInput,
id: string,
ts: string,
status: DirectiveStatus = 'accepted',
): DirectiveEntry {
return { ...input, id, ts, status }
}
/** One JSONL line (no trailing newline — the caller joins). */
export function serializeDirective(entry: DirectiveEntry): string {
return JSON.stringify(entry)
}
/**
* Parse a JSONL log into records ordered by `ts` (then id for stability), with a
* 1-based `seq` assigned on read. Blank/corrupt lines are skipped, not fatal.
*/
export function parseDirectiveLog(text: string): DirectiveRecord[] {
const entries: DirectiveEntry[] = []
for (const line of text.split('\n')) {
const trimmed = line.trim()
if (!trimmed) continue
try {
const e = JSON.parse(trimmed) as DirectiveEntry
if (e && typeof e.id === 'string' && typeof e.ts === 'string') entries.push(e)
} catch {
// skip a corrupt line rather than lose the whole ledger
}
}
entries.sort((a, b) => (a.ts === b.ts ? a.id.localeCompare(b.id) : a.ts.localeCompare(b.ts)))
return entries.map((e, i) => ({ ...e, seq: i + 1 }))
}
/** Append a serialized entry to existing log text (concatenation merge). */
export function appendDirective(existing: string, entry: DirectiveEntry): string {
const base = existing.endsWith('\n') || existing === '' ? existing : existing + '\n'
return `${base}${serializeDirective(entry)}\n`
}

View File

@@ -97,27 +97,4 @@ describe('forecast', () => {
expect(f.scope).toBe(2) expect(f.scope).toBe(2)
expect(f.p50Day).toBeGreaterThan(0) expect(f.p50Day).toBeGreaterThan(0)
}) })
it('a cold-start model changes nothing — the code priors still drive it', () => {
const priors = forecast(scope, [], { trials: 1000, seed: 7 })
const cold = forecast(scope, [], {
trials: 1000,
seed: 7,
model: { coldStart: true, global: { mu: 5, sigma: 0.1 }, byBucket: {} },
})
expect(cold.coldStart).toBe(true)
expect(cold.p50Day).toBeCloseTo(priors.p50Day, 6)
})
it('a fitted model drives the sim once past cold-start', () => {
// an optimistic fit (mu < 0, tight sigma) should land the scope sooner than the pessimistic priors
const priors = forecast(scope, [], { trials: 2000, seed: 7 })
const fitted = forecast(scope, [], {
trials: 2000,
seed: 7,
model: { coldStart: false, global: { mu: -0.2, sigma: 0.1 }, byBucket: {} },
})
expect(fitted.coldStart).toBe(false)
expect(fitted.p50Day).toBeLessThan(priors.p50Day)
})
}) })

View File

@@ -41,29 +41,15 @@ export const COLD_START_PRIORS: Record<number, LognormalPrior> = {
8: { mu: 0.16, sigma: 0.36 }, 8: { mu: 0.16, sigma: 0.36 },
} }
export const PRIOR_BUCKETS = [1, 2, 3, 5, 8] const PRIOR_BUCKETS = [1, 2, 3, 5, 8]
/** Nearest estimate bucket (ties resolve to the smaller bucket). */ /** Nearest estimate bucket (ties resolve to the smaller bucket). */
export function nearestBucket(days: number): number { export function priorForEstimate(days: number): LognormalPrior {
let best = PRIOR_BUCKETS[0] let best = PRIOR_BUCKETS[0]
for (const b of PRIOR_BUCKETS) { for (const b of PRIOR_BUCKETS) {
if (Math.abs(b - days) < Math.abs(best - days)) best = b if (Math.abs(b - days) < Math.abs(best - days)) best = b
} }
return best return COLD_START_PRIORS[best]
}
/** The cold-start prior for the bucket nearest to `days`. */
export function priorForEstimate(days: number): LognormalPrior {
return COLD_START_PRIORS[nearestBucket(days)]
}
/** The lognormal parameters `forecast` needs, per estimate bucket. */
export interface DurationModel {
coldStart: boolean
/** Fallback params (used when a bucket lacks its own fit). */
global: LognormalPrior
/** Per-bucket fitted params; missing buckets fall back to `global`. */
byBucket: Record<number, LognormalPrior>
} }
export interface ForecastOptions { export interface ForecastOptions {
@@ -71,19 +57,6 @@ export interface ForecastOptions {
trials?: number trials?: number
/** PRNG seed. Fixed by default so a forecast is reproducible. */ /** PRNG seed. Fixed by default so a forecast is reproducible. */
seed?: number seed?: number
/**
* Fitted duration model. When present and not cold-start, its params drive
* the sim; otherwise the code-resident cold-start priors do.
*/
model?: DurationModel
}
/** Resolve the lognormal params for an estimate, preferring a fitted model. */
export function durationParams(days: number, model?: DurationModel): LognormalPrior {
if (model && !model.coldStart) {
return model.byBucket[nearestBucket(days)] ?? model.global
}
return priorForEstimate(days)
} }
export interface BurnUpPoint { export interface BurnUpPoint {
@@ -148,14 +121,13 @@ export function forecast(
): Forecast { ): Forecast {
const trials = options.trials ?? DEFAULT_TRIALS const trials = options.trials ?? DEFAULT_TRIALS
const seed = options.seed ?? DEFAULT_SEED const seed = options.seed ?? DEFAULT_SEED
const coldStart = options.model ? options.model.coldStart : true
const order = schedule(issues, edges).items // empty when a dependency cycle exists const order = schedule(issues, edges).items // empty when a dependency cycle exists
const n = order.length const n = order.length
if (n === 0) { if (n === 0) {
return { scope: 0, trials, coldStart, p50Day: 0, p80Day: 0, p95Day: 0, curve: [] } return { scope: 0, trials, coldStart: true, p50Day: 0, p80Day: 0, p95Day: 0, curve: [] }
} }
const priors = order.map((it) => durationParams(it.durationDays, options.model)) const priors = order.map((it) => priorForEstimate(it.durationDays))
const rng = mulberry32(seed) const rng = mulberry32(seed)
// endByRank[k][t] = working day the (k+1)-th scheduled issue completes on trial t. // endByRank[k][t] = working day the (k+1)-th scheduled issue completes on trial t.
@@ -184,7 +156,7 @@ export function forecast(
return { return {
scope: n, scope: n,
trials, trials,
coldStart, coldStart: true,
p50Day: percentile(total, 0.5), p50Day: percentile(total, 0.5),
p80Day: percentile(total, 0.8), p80Day: percentile(total, 0.8),
p95Day: percentile(total, 0.95), p95Day: percentile(total, 0.95),

View File

@@ -123,63 +123,6 @@ describe('createGiteaClient.getIssue', () => {
) )
}) })
it('setIssueLabels PUTs the label ids to the issue labels endpoint', async () => {
const { fetch, calls } = stubFetch(null, 204)
await createGiteaClient(CONFIG, fetch).setIssueLabels(9, [3, 7])
expect(calls).toHaveLength(1)
expect(calls[0].url).toBe('https://gitea.stephenmann.io/api/v1/repos/christian/commitea/issues/9/labels')
expect(calls[0].init?.method).toBe('PUT')
expect(calls[0].init?.headers?.['Content-Type']).toBe('application/json')
expect(JSON.parse(calls[0].init?.body ?? '{}')).toEqual({ labels: [3, 7] })
})
it('listLabels returns id+name pairs', async () => {
const { fetch } = stubFetch([
{ id: 3, name: 'est/2d', color: 'fff' },
{ id: 7, name: 'p/1', color: '000' },
])
const labels = await createGiteaClient(CONFIG, fetch).listLabels()
expect(labels).toEqual([
{ id: 3, name: 'est/2d' },
{ id: 7, name: 'p/1' },
])
})
it('getFile returns null on 404 and content+sha on hit', async () => {
const miss = stubFetch('nope', 404)
expect(await createGiteaClient(CONFIG, miss.fetch).getFile('directives/log.jsonl')).toBeNull()
const hit = stubFetch({ content: 'aGVsbG8=\n', sha: 'abc123' })
const file = await createGiteaClient(CONFIG, hit.fetch).getFile('directives/log.jsonl')
expect(file).toEqual({ contentBase64: 'aGVsbG8=', sha: 'abc123' })
expect(hit.calls[0].url).toContain('/contents/directives/log.jsonl')
})
it('putFile POSTs to create and PUTs to update (with sha)', async () => {
const create = stubFetch({}, 201)
await createGiteaClient(CONFIG, create.fetch).putFile('directives/log.jsonl', { contentBase64: 'eA==', message: 'seed' })
expect(create.calls[0].init?.method).toBe('POST')
expect(JSON.parse(create.calls[0].init?.body ?? '{}')).toEqual({ content: 'eA==', message: 'seed' })
const update = stubFetch({}, 200)
await createGiteaClient(CONFIG, update.fetch).putFile('directives/log.jsonl', { contentBase64: 'eQ==', message: 'append', sha: 's1' })
expect(update.calls[0].init?.method).toBe('PUT')
expect(JSON.parse(update.calls[0].init?.body ?? '{}')).toEqual({ content: 'eQ==', message: 'append', sha: 's1' })
})
it('createIssue POSTs title/body/labels and returns a normalized issue', async () => {
const created = { ...RAW_ISSUE, number: 44, title: 'Retry token refresh', labels: [{ name: 'est/2d' }, { name: 'p/2' }] }
const { fetch, calls } = stubFetch(created, 201)
const issue = await createGiteaClient(CONFIG, fetch).createIssue({ title: 'Retry token refresh', body: 'backoff', labelIds: [3, 7] })
expect(calls[0].url).toBe('https://gitea.stephenmann.io/api/v1/repos/christian/commitea/issues')
expect(calls[0].init?.method).toBe('POST')
expect(JSON.parse(calls[0].init?.body ?? '{}')).toEqual({ title: 'Retry token refresh', body: 'backoff', labels: [3, 7] })
expect(issue.number).toBe(44)
expect(issue.labels).toEqual(['est/2d', 'p/2'])
})
it('throws GiteaApiError carrying status + body on a non-2xx response', async () => { it('throws GiteaApiError carrying status + body on a non-2xx response', async () => {
const { fetch } = stubFetch('not found', 404) const { fetch } = stubFetch('not found', 404)
const client = createGiteaClient(CONFIG, fetch) const client = createGiteaClient(CONFIG, fetch)

View File

@@ -13,7 +13,6 @@ import {
type FetchLike, type FetchLike,
type GiteaConfig, type GiteaConfig,
type GiteaIssue, type GiteaIssue,
type GiteaLabel,
type GiteaMilestone, type GiteaMilestone,
type GiteaMilestoneRef, type GiteaMilestoneRef,
} from './types.js' } from './types.js'
@@ -99,16 +98,6 @@ export interface GiteaClient {
getIssueDependencies(index: number): Promise<number[]> getIssueDependencies(index: number): Promise<number[]>
/** Normalized lifecycle events for one issue (all pages of its timeline). */ /** Normalized lifecycle events for one issue (all pages of its timeline). */
getIssueTimeline(index: number): Promise<LifecycleEvent[]> getIssueTimeline(index: number): Promise<LifecycleEvent[]>
/** Every label defined on the repo (id + name), for name→id resolution. */
listLabels(): Promise<GiteaLabel[]>
/** Replace an issue's entire label set with the given label ids. Write. */
setIssueLabels(index: number, labelIds: number[]): Promise<void>
/** Open a new issue with a title, optional body, and label ids. Write. */
createIssue(input: { title: string; body?: string; labelIds?: number[] }): Promise<GiteaIssue>
/** Read a repo file's base64 content + blob sha; null if it (or the repo) is absent. */
getFile(path: string): Promise<{ contentBase64: string; sha: string } | null>
/** Create or update a repo file with base64 content (pass `sha` to update). Write. */
putFile(path: string, input: { contentBase64: string; message: string; sha?: string }): Promise<void>
} }
/** Map raw gitea issue JSON to the normalized domain shape. Pure. */ /** Map raw gitea issue JSON to the normalized domain shape. Pure. */
@@ -155,24 +144,18 @@ export function createGiteaClient(config: GiteaConfig, fetchImpl: FetchLike): Gi
const apiBase = `${config.baseUrl.replace(/\/+$/, '')}/api/v1` const apiBase = `${config.baseUrl.replace(/\/+$/, '')}/api/v1`
const repoBase = `${apiBase}/repos/${config.owner}/${config.repo}` const repoBase = `${apiBase}/repos/${config.owner}/${config.repo}`
async function request(path: string, init?: { method?: string; body?: unknown }): Promise<unknown> { async function request(path: string): Promise<unknown> {
const method = init?.method ?? 'GET'
const hasBody = init?.body !== undefined
const res = await fetchImpl(`${repoBase}${path}`, { const res = await fetchImpl(`${repoBase}${path}`, {
method,
headers: { headers: {
Authorization: `token ${config.token}`, Authorization: `token ${config.token}`,
Accept: 'application/json', Accept: 'application/json',
...(hasBody ? { 'Content-Type': 'application/json' } : {}),
}, },
body: hasBody ? JSON.stringify(init!.body) : undefined,
}) })
if (!res.ok) { if (!res.ok) {
const body = await res.text().catch(() => '') const body = await res.text().catch(() => '')
throw new GiteaApiError(res.status, `${method} ${path} failed (${res.status})`, body) throw new GiteaApiError(res.status, `GET ${path} failed (${res.status})`, body)
} }
// writes may reply 204 No Content return res.json()
return res.status === 204 ? null : res.json()
} }
/** Follow gitea's page-limit pagination until a short page is returned. */ /** Follow gitea's page-limit pagination until a short page is returned. */
@@ -217,44 +200,5 @@ export function createGiteaClient(config: GiteaConfig, fetchImpl: FetchLike): Gi
) )
return normalizeTimeline(raw) return normalizeTimeline(raw)
}, },
async listLabels() {
const raw = await requestAll<{ id: number; name: string }>(
(page) => `/labels?page=${page}&limit=${PAGE_LIMIT}`,
)
return raw.map((l) => ({ id: l.id, name: l.name }))
},
async setIssueLabels(index, labelIds) {
await request(`/issues/${index}/labels`, { method: 'PUT', body: { labels: labelIds } })
},
async createIssue(input) {
const raw = (await request('/issues', {
method: 'POST',
body: { title: input.title, body: input.body ?? '', labels: input.labelIds ?? [] },
})) as RawIssue
return normalizeIssue(raw)
},
async getFile(path) {
const res = await fetchImpl(`${repoBase}/contents/${path}`, {
headers: { Authorization: `token ${config.token}`, Accept: 'application/json' },
})
if (res.status === 404) return null
if (!res.ok) {
const body = await res.text().catch(() => '')
throw new GiteaApiError(res.status, `GET contents/${path} failed (${res.status})`, body)
}
const json = (await res.json()) as { content?: string; sha: string }
return { contentBase64: (json.content ?? '').replace(/\n/g, ''), sha: json.sha }
},
async putFile(path, input) {
await request(`/contents/${path}`, {
method: input.sha ? 'PUT' : 'POST',
body: { content: input.contentBase64, message: input.message, ...(input.sha ? { sha: input.sha } : {}) },
})
},
} }
} }

View File

@@ -35,12 +35,6 @@ export interface GiteaHttpResponse {
export type FetchLike = (url: string, init?: GiteaRequestInit) => Promise<GiteaHttpResponse> export type FetchLike = (url: string, init?: GiteaRequestInit) => Promise<GiteaHttpResponse>
/** A repo label — just the id + name we need for name→id resolution. */
export interface GiteaLabel {
id: number
name: string
}
/** Milestone as referenced from an issue (not the full milestone resource). */ /** Milestone as referenced from an issue (not the full milestone resource). */
export interface GiteaMilestoneRef { export interface GiteaMilestoneRef {
id: number id: number

View File

@@ -17,15 +17,11 @@ export type {
GiteaConfig, GiteaConfig,
GiteaHttpResponse, GiteaHttpResponse,
GiteaIssue, GiteaIssue,
GiteaLabel,
GiteaMilestone, GiteaMilestone,
GiteaMilestoneRef, GiteaMilestoneRef,
GiteaRequestInit, GiteaRequestInit,
} from './gitea/types.js' } from './gitea/types.js'
export { describeChange, planIssueChange, proposalsFor } from './changes/apply-changes-v0.js'
export type { ChangeProposal, IssueChange, LabelPlan, ProposeChangeArgs } from './changes/apply-changes-v0.js'
export { export {
inferColumnV0, inferColumnV0,
inferLifecycle, inferLifecycle,
@@ -49,66 +45,5 @@ export type {
SchedulePlan, SchedulePlan,
} from './scheduler/scheduler-v0.js' } from './scheduler/scheduler-v0.js'
export { export { COLD_START_PRIORS, forecast, priorForEstimate } from './forecast/forecast-v0.js'
COLD_START_PRIORS, export type { BurnUpPoint, Forecast, ForecastOptions, LognormalPrior } from './forecast/forecast-v0.js'
durationParams,
forecast,
nearestBucket,
PRIOR_BUCKETS,
priorForEstimate,
} from './forecast/forecast-v0.js'
export type {
BurnUpPoint,
DurationModel,
Forecast,
ForecastOptions,
LognormalPrior,
} from './forecast/forecast-v0.js'
export {
CALIBRATION_BUCKET_FLOOR,
calibrationSamples,
COLD_START_THRESHOLD,
fitCalibration,
toDurationModel,
} from './calibration/calibration-v0.js'
export type {
BucketFit,
CalibrationModel,
CalibrationSample,
PersonBias,
} from './calibration/calibration-v0.js'
export { createChatClient } from './agent/chat-client.js'
export type { ChatClient, ChatMessage, CompletionResult, ModelConfig, ToolCall, ToolDecl } from './agent/chat-client.js'
export { pickModel } from './agent/model-router.js'
export type { ModelRouter, TaskKind } from './agent/model-router.js'
export { runAgentTurn } from './agent/agent-loop.js'
export type { AgentStep, AgentTurn, ToolExecutor } from './agent/agent-loop.js'
export {
PROPOSE_CHANGE_TOOL,
QUERY_PROJECT_TOOL,
RECORD_DIRECTIVE_TOOL,
REGINALD_SYSTEM,
REGINALD_TOOLS,
} from './agent/agent-tools.js'
export { buildProjectView } from './agent/query-project.js'
export type { ProjectSnapshot, ProjectView, QueryFilters } from './agent/query-project.js'
export { CAPTURE_SYSTEM, captureWork, parseCaptureArgs, PROPOSE_ISSUES_TOOL } from './agent/capture-work.js'
export type { CaptureProposal, ProposedIssue } from './agent/capture-work.js'
export {
appendDirective,
makeDirectiveEntry,
parseDirectiveLog,
serializeDirective,
toDirectiveInput,
} from './directives/record-directive-v0.js'
export type {
DirectiveEntry,
DirectiveInput,
DirectiveKind,
DirectiveRecord,
DirectiveStatus,
DirectiveTarget,
} from './directives/record-directive-v0.js'