f0173440e4c75228660066f2262a4bc2437351bf
14 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
|
f0173440e4 |
Put Piggy on Prime Agent, and let it write to the book
Piggy was a hand-rolled OpenAI tool loop. It is now a Prime Agent session — Prime Intellect's own harness, embedded as a Node library — answering from PIG's tools and, for the first time, able to put information into the CRM rather than only read it out. The harness is a coding agent, so the first job was taking the coding agent away from it. `noTools: 'all'` plus an explicit allowlist leaves the model with PIG's ten `pig_*` tools and no bash, no filesystem, no IPython. That holds under attack: a hostile extension, a skill and a settings file planted in the agent's own directory, then `setActiveToolsByName` called with every built-in, still leaves ten tools, all ours. Both lines are load-bearing — `noTools` alone registers nothing, and the allowlist is what admits our own. Writing is gated rather than assumed. A change is proposed, not made: the tool returns a description, the transcript renders a diff card, and nothing reaches the database until someone presses Apply. Contracts, commitments, allocations and compliance always stop for a human whatever the mode. Every write runs through `executeMutation` as the calling user, so their capabilities and the audit trail apply exactly as they would to a human's. Four things about the SDK are wrong in its own documentation and cost a debugging cycle each: models.json does not resolve an env var name for `apiKey`, it sends the literal string; there is no built-in prime-inference provider in 0.84.1; a ResourceLoader you pass in is never reloaded for you; and the stock system prompt is a coding-assistant prompt that must be replaced — but replacing it also silently removes the tool list, because the harness only renders that section when it owns the prompt. AGENTS.md records all four. The expensive one was thinking level. The harness defaults to `medium`, and nemotron spent an entire 4,096-token budget reasoning and returned an empty answer. `low` was worse; `off` omits the parameter so the endpoint's default wins. An explicit `reasoning_effort: none` via `thinkingLevelMap` took a turn from 6,195 output tokens to 149. And a turn is now bounded. The harness loop is `while (true)` with no iteration cap; a runaway on a frontier model would have eaten the credit it is supposed to report on. Ceilings on model calls and tokens, enforced both through the harness hook and independently from the event stream, plus a per-user daily spend limit — and the ledger now records spend on turns that fail, which it previously discarded. Signing in lands on /piggy, which is a workspace: conversations down one side, the agent in the middle, what it did and what it cost beside it. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
99d165b5e5 |
Rebuild Piggy's interface, and give the demo book a business to describe
Piggy answered in raw markdown, threw away every tool result it streamed, and fought the reader's scroll on every token. The three surfaces that made it worth having — what it read, how it reasoned, what it cost — were all on the wire and none of them reached the screen. The transcript is now composed of five parts under components/piggy: answers render through streamdown, the container sticks to the bottom without pinning the reader there, tool steps say what they read and link to the record, and each turn carries its model and token count. Three lifecycle bugs went with them: Stop left a permanent spinner, a truncated stream was indistinguishable from thinking, and a failed send destroyed the message it failed to send. Underneath, the inference path grew timeouts, jittered retries on 429 and 5xx, tolerance of the malformed frames a 30B model emits, and an agent_runs row per turn so chat spend is observable. The system prompt now states that a field ending in Cents is cents — without it nemotron renders costPerGpuHourCents: 189 as "$189 per GPU-hour", which is a 100x error on the most scrutinised number in the room. The demo book was arithmetically incoherent: every deal's value contradicted its own allocation revenue by up to 3.6x, nothing had ever closed, no customer had any paper, and the marketplace was empty. Deal value is now derived from the allocation, the book clears 5.3% across five blocks with one deliberately underwater, and the renewal, compliance and agent-provenance machinery finally has rows to act on. A --clear that deleted every obligation, SLA term and capacity request in the database regardless of origin is scoped to the demo's own ids. Around that: accounts have a detail page, ⌘K searches the book, Settings can mint the API keys it always claimed to, and deploy.sh actually ships the agent instead of silently skipping its compose profile. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
9db53cb36f |
Polish the public auth experience
Replace the stacked sign-in card with a responsive public shell, a local monochrome compute field, restrained grain and reduced-motion-safe drift. Share the anonymous header with Learn so public navigation stays consistent, and carry the corrected spacing through registration and profile setup. |
||
|
|
30171767f7 |
Refine the music: fades, and a mute control on every public screen
THE BUG. An anonymous visitor to / — the sign-in page, which is what the link in an email opens — got music with ZERO mute controls. The provider moved above the router so it covers the signed-out screens, but those render outside Shell and therefore have no app header to host the toggle. Audio a visitor cannot switch off is the worst version of this feature. Every unauthenticated screen now carries the control pinned bottom-right; Learn keeps the one in its own chrome rather than getting a second. FADES. Volume ramps 0 -> 0.14 over 1.1s on start and back down over 0.42s on mute, easeOutQuad so a mute feels prompt while a start feels like the room was already there. Snapping to full volume on the first click reads as a glitch. Measured: 0.076 at +0.4s, 0.14 at +2.2s, 0.025 at +0.25s after mute, paused by +0.85s. NO CHANGE TO THE TRACKS, and this reverses what I said earlier. I claimed pig-tech would splice audibly every 28 seconds and offered to crossfade the loop. That came from comparing 0.4-second mean levels, which measures musical content rather than continuity. Measured properly — the wrap discontinuity against each track's own 99.9th-percentile sample delta — all three already loop cleanly (0.03-0.10x, i.e. quieter than their own ordinary transients), and a folded crossfade made them WORSE (0.09-1.32x). The originals ship unchanged. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
afce0dda28 |
Play the platform music on the shared Learn page too
Reversing yesterday's call at Karti's direction. The provider moves from Shell up above the router in App, so a share-code visitor gets the same character as a member rather than a silent page. The reason that is safe is the same reason "autoplay" was never really autoplay: the browser refuses audio until the page has had a real gesture, so nothing plays the instant a link opens — it starts once someone is actually using the page. The anonymous page renders OUTSIDE Shell and therefore has no app header, so the mute control is added to its own chrome. Music with no way to stop it is the worst version of this feature, and a visitor who cannot find the switch does not conclude the site has taste. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
13dec6b4b8 |
Rebuild the shell, add Calendar and Learn, and govern reads
Seven parallel agents and an adversarial verification pass. The three things worth knowing before reading the diff: RBAC WAS ALREADY BUILT. docs/build-plan.md marks F2 and F3 outstanding and is stale — packages/core/src/permissions.ts and lib/mutation.ts shipped long ago. So this does not rebuild them; it closes the gaps an audit found. The big one is that reads were entirely ungoverned: every GET was "any authenticated member", so a junior demand rep and a research contractor could both pull per-block supplier cost and break-even prices from /api/capacity/margin, and every contract's negotiated terms. For a company whose margin is the business, that was the hole that mattered. Adds book:read / economics:read / team:read, a readGuard middleware, and a `viewer` role below member. THE BUTTON AND THE 403 DISAGREED — the exact thing F3 said must never happen. Contracts.tsx never called can() at all, so its save button was always enabled against a server requiring contract:sign; Capacity.tsx gated commitment creation on deal:write/demand while the server wanted commitment:write/supply. POST /api/activities was the one write bypassing executeMutation: no capability check, and any member could mutate accounts.lastActivityAt as a side effect. It is now a proper mutation() behind activity:write. The shell becomes three panes — a collapsible shadcn sidebar with an account switcher on the Piggy accent, a header with real search, and Piggy docked to the right, page-aware and persistent across navigation. The phone keeps its bottom tab bar, which is the thing this product already beat trycompai/crm on, and gains the sidebar as a sheet. Calendar is a projection over thirteen dated sources rather than a new table, because a table would duplicate dates that already live on contracts, deals and commitments and would drift — and one ledger answering the question is the whole argument. It surfaces export_authorizations and compliance_artifacts, which had indexed expires_at columns, schema comments saying they must be alerted on, and no read endpoint or UI anywhere. Learn carries two tracks. Concepts are members-only; the platform track can be opened with a share code by someone with no account. The code mints a scoped learn-only token and never a Principal — every route here resolves a principal and then checks capabilities, so a principal-minting code would be one missing check away from leaking the book. "Only platform-track rows may be code-visible" is a database CHECK constraint as well as a write-path rule, and a test asserts a valid learn token still gets 401 on /api/dashboard, /api/accounts and /api/contracts — the same invariant scripts/deploy.sh refuses to ship without. CD becomes tag-to-ship. CI publishes an image to the Gitea registry on a release-* tag and cloud-2 pulls it, so no credential on the shared runner can execute anything on production — by construction rather than by policy. Both halves of deploy.sh's original rule survive: nothing on the runner reaches the host, and a human still decides when it ships. deploy.sh gains a rollback and a public-origin check, and PIG_IMAGE now reaches compose through `sudo env`, without which sudo's env_reset silently resolved every release to pig:local. Tests 141 -> 261. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
e12d27edd1 |
Polish every product workflow across desktop and mobile
CI / verify (push) Successful in 3m32s
Reframe each screen around the decisions compute brokers make: sellable capacity, full-cost margin, pipeline movement, contract deadlines, evidence review, staged imports, and controlled agent access. Group the shell by operating domain, strengthen mobile navigation and sheets, add responsive record treatments, and make loading, error, empty, readiness, and retry states explicit. The visual audit exposed sortable table targets and an unnamed file input only after exercising the rendered app, so this commit also pins those accessibility decisions at their actual interaction boundaries. Manrope is self-hosted as a single Latin variable subset to keep the stronger hierarchy without shipping unused font payloads. |
||
|
|
1318c0b841 |
Ship growth intelligence and demo polish
CI / verify (push) Successful in 3m51s
|
||
|
|
c2c7fb9c19 |
Make mutations confirm themselves, and seed the evidence trail
CI / verify (push) Successful in 2m51s
Two demo gaps, both of which made working features look like they were not there. **Toasts fired into nothing.** RecordSheets already called toast.success on every save, but <Toaster /> was never mounted, so nothing appeared. It could not be mounted, either: the shadcn original imports next-themes, which PIG does not use — it has its own provider so a chosen theme is persisted server-side and follows a user between devices. Rewired to PIG's useTheme, mounted inside ThemeProvider, and offset clear of the phone tab bar and the home indicator. Feedback added where the interface otherwise gives none: allocation and hold report the GPU-hours actually written, because the sheet closes on success and the only other evidence is a number moving off-screen; releasing a hold says the capacity is sellable again; fact decisions say what the decision meant, and that approving evidence is not the same as writing it to a record; the profile form confirms rather than just clearing itself, which otherwise reads as the input being discarded. **The fact table was empty**, so the review queue and every provenance tooltip had nothing to show — the mechanism that makes an agent-written CRM trustworthy, invisible. Six agent-derived facts seeded with a deliberate mix: two applied, showing what a confident agent writes unprompted, and four proposed, including one weak claim that a reviewer should reject, so the queue is not a row of obvious approvals. Each carries a score, a band, evidence and where available a source. Idempotent on subject+field+value; verified over two runs. Verified: toast confirmed firing in a real browser on a 393px viewport, 135 unit tests and e2e green, typecheck clean, CSP hash unchanged, 0px horizontal overflow across 12 routes at both breakpoints. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
853bde2265 |
Build the agent-native compute CRM platform
CI / verify (push) Successful in 3m6s
|
||
|
|
7719850fc5 |
Let people register with a personal email and an invite code
The invite gate was unreachable. PIG shares its identity provider with another application, and self-registration there is deliberately switched off — so somebody with a personal address and a valid invite code could never obtain a token, and therefore could never reach the endpoint that accepts the code. The gate was real and nothing could ever arrive at it. Opening self-registration on the provider would have opened it for the neighbouring application too, which is precisely why it was closed. So PIG now mints the account itself through the provider's admin API, and only after the invite validates. The provider stays shut; the invite becomes the actual gate. Order is deliberate: validate the invite, create the auth account, create the profile, consume the invite. If the profile write fails the auth account is deleted again — otherwise someone could sign in with no profile and no way to obtain one, because their invite would look spent. An administrator's address does NOT bypass this. The bypass in /api/signup exists to bootstrap the first admin from an account that already exists; here an account is created from nothing, and an ungated version of that is simply an open registration endpoint. Registration signs the person in on success rather than returning them to a login form to retype the password they entered ten seconds earlier. An address that already exists in the provider but has no PIG profile is detected and pointed at sign-in, since /api/signup handles that case properly. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
045e51bc5c |
Polish: team page title, and accent swatches that match the theme
The accent swatches always previewed the light-mode value, which made the near-black "Pig" swatch effectively invisible on a dark card — the one place the preview needed to be accurate. Each accent is tuned twice because a colour that reads well on white is usually too dark on near-black; the swatch now shows the value for the theme actually in effect. Team and the placeholder routes also set document titles, so every route in the app is now distinguishable in history and in a tab strip. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
7bb8835974 |
Add profile creation — close the gap between signing in and being a member
Deploying and then trying to actually use it surfaced a dead end: /api/signup was exempted from auth but never implemented, so a real person could sign in, receive 403 needs_profile, and have nowhere to go. Authentication worked; joining did not. The route is mounted before the auth middleware, because requiring membership to reach the route that grants membership is circular. It verifies the token itself and then requires one of two things: - A valid invite code. Stored hashed, optionally pinned to an address, optionally expiring, consumed on redemption with the redeemer recorded. - Presence in PIG_ADMIN_EMAILS. The bootstrap path, which exists because on a fresh deployment nobody can issue an invite since nobody can sign in to issue one. The bootstrap path is narrow by construction: the address must be listed in server-side configuration AND match the verified email claim on the token. Admin rights are never read from the request body, so a crafted payload cannot grant them. Two behaviours worth noting. A row that was invited but never signed into is claimed rather than rejected, binding it to the identity that just proved ownership of the address. And a resubmitted form returns the existing user instead of erroring, because a double-tap should be harmless. The front end now treats needs_profile as a step in the flow rather than an error, showing a team picker. Sending someone back to a login screen they have already completed is a loop with no exit. Also: the seed no longer creates the dev@localhost admin row under NODE_ENV=production. It was unreachable (no auth subject, so nobody can sign in as it), but an admin-flagged placeholder in a real deployment is a trap. Verified: rejects a missing token, rejects an invalid body, claims a pre-existing row, and is idempotent on resubmission. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
de33a03524 |
Add the web app, seed data, and user-selectable theming
apps/web — React, Vite, Tailwind, shadcn-idiom components. Mobile Safari is a first-class target, not an afterthought: - Two navigation treatments rather than one compromise. A bottom tab bar on phones, because the top of a large phone is out of thumb reach; a persistent sidebar from lg upward, so an iPad in portrait gets it too. - Safe-area insets throughout, so the tab bar clears the home indicator and the last row of a list is actually reachable. - Inputs are pinned to a 16px minimum, which is the correct fix for Safari zooming on focus. user-scalable=no is not used: it breaks pinch-zoom for everyone and recent iOS ignores it anyway. - The pipeline board becomes a stage picker on phones. An eight-column board scrolling horizontally on a 390px screen is technically responsive and practically useless. Theming: users pick an accent and the whole interface re-tints. Accent values live once, in @pig/core, and are written onto the root element at runtime — there is no CSS copy to drift from the TypeScript. Preferences are stored server-side so they follow a person between laptop and phone, mirrored into localStorage only so the pre-paint script can avoid a white flash. Status colours stay fixed regardless of accent: if "at risk" re-tinted to whatever someone picked, the signal would be gone. Seed data is public research, every record carrying a confidence grade and a source URL. No email addresses are seeded or inferred — none are published, and guessing them from a name and a domain is unreliable and rude. Authorship is not promoted to employment: contributors, residency participants and alumni are recorded as what the evidence actually shows, and a name that could not be sourced at all is listed as unresolved rather than invented. Three defects found and fixed by actually running it rather than assuming: 1. The seed was not idempotent. onConflictDoNothing() with no target is a no-op without a matching unique constraint, so a second run duplicated 27 contacts. There is deliberately no unique index on (account, name) — two people at one company can share a name — so idempotency is enforced in the seed instead of by bending the schema. 2. /capacity scrolled sideways on a phone. Grid items default to min-width:auto and `truncate` sets nowrap, so a long title became unshrinkable content and widened the track. Fixed with min-w-0 on every truncating grid child. 3. The idle-capacity alert silently failed to fire at exactly 80% utilisation, losing a float comparison against a 0.2 threshold. Moved to 0.15, which is also a more sensible line for "worth attention". The worked example is tuned to teach rather than to flatter: 70% sold at a 53% markup lands at +6.7% margin with 20% still idle, so both the healthy number and the alert are visible. Drop the sold share to 55% and the same block goes underwater — that sensitivity is the argument for the product. Verified in a real browser at 393px and 1440px, light and dark: zero horizontal overflow on every route, zero console errors. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |