a3b12982575ef681ca3cac6cfa453b42d41ab396
8 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 claude
|
a3b1298257 |
Count the accounts, so Piggy stops counting deals instead
Asked how many accounts were on the book, Piggy answered "7 demand deals (accounts)". Production holds 17 accounts and 7 demand deals. The number was real and the payload had scoped it correctly as deals; the prose relabelled it on the way out. This is the other half of the scope fix. That one stopped a filtered count being read as a total. This one is a total that was simply absent being filled from the nearest available noun: /accounts resolves to the workspace summary, which carried commitments, deals, margin and idle capacity and no count of accounts anywhere. The route's own label admitted it — "Piggy reads the book here, not the account rows" — which named the gap without closing it, and a model given a question about accounts and a payload with no account figure will always find something else to count. So the summary now counts accounts and contacts in SQL, and the headline leads with them, because the defective answer was assembled from the first countable thing in that sentence. Archived accounts are excluded to match what /api/accounts returns — Piggy disagreeing with the list on screen is the failure that costs the tool its credibility — but they are reported separately so the difference stays reconcilable. The side breakdown ships with a note saying the tabs do not partition, since supply and demand tabs each include "both" and therefore do not sum to the total: that is the next reconciliation bug, pre-empted. Five routes that genuinely have no data tool now say so in their guide rather than naming a subject they cannot reach. Proven live: /accounts answers 23 of 23; a question about geography is refused rather than guessed; /team refuses without substituting a nearby number. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
claude
|
f2ef403ee9 |
Make every tool result say what it counted
Asked how many capacity commitments were on the book, Piggy answered "3". Production holds 5. It had called the idle-capacity tool, which filters to blocks above an idle threshold, and read the length of that list as the size of the book. The system prompt already forbade this in terms — "never report a filtered count as a total; pig_get_idle_capacity returns the blocks with idle hours, not the book" — and the model did it anyway. That is the second time this argument has been lost in the prompt, so it is settled in the payload instead: a result that cannot describe its own scope will be misread eventually, however firmly the prompt objects. Every tool that returns a count or a collection now carries one shape: what it covers, how many matched, out of how many, under which filters, and whether the list was truncated. The denominators are read from the database rather than inferred. The pre-formatted headline states the scope too, since that is the sentence a small model quotes most readily — the idle tool now opens "3 of 5 live capacity commitments on the book", which is the sentence that makes the original mistake impossible to phrase. Two details worth keeping. Record reads enumerate rather than filter, so their scope states a boundary instead of a ratio: these are that record's own figures, never book-wide totals. And the workspace summary's idle threshold is deliberately recorded as 0, distinct from the idle tool's 0.25 — that mismatch is why three different idle figures appeared across the UI, and naming it in the data is how it stops being invisible. Verified against the live model: the failing question now answers 5, demand deals 13 and contracts 20 — each drawn from a payload whose filtered figure was smaller — while "which blocks are sitting idle" still names exactly the blocks that are. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
claude
|
18d5f5bfc0 |
Make Piggy part of the product rather than a guest in it
Piggy arrived as a chat panel bolted onto a CRM and then grew a workspace around it. The layout was already right — the audit found the approval card to be the best-designed object in the repo, and the account page's empty panels less finished than anything in the workspace. What was wrong was vocabulary: nobody had written the small things down, so both halves kept inventing them. Piggy was drawn with five different marks — a pig in the dock, a sparkle in the sidebar and again on the model picker, a speech bubble on the Ask buttons, and a stock robot glyph on every assistant message, which is the one people look at most. There is now one mark. The composer, which is the first control in the product since sign-in lands on /piggy, was the only un-adapted shadcn field left: 6px radius against a 12px Send button it sat 8px from. A stat tile had been reinvented six times at three numeral scales, and the same uppercase micro-label existed in five variants, two of them one tab apart in the same rail. There were 63 hand-written font sizes: not a scale, sixty-three opinions. Underneath that, the focus ring was invisible. The global rule used ring-accent, which Tailwind deliberately aliases onto the hover tint, so the ring measured 1.01:1 against the light canvas — no visible focus indicator anywhere in the product, for any accent, in either theme. It is ring-brand now and measures 17:1. The warning, positive and info tones were darkened until each clears 4.5:1 on a card, on inset and on its own chip, and the light canvas moved to 98% so a card lifts without leaning on its shadow. The mobile work is the part worth reading. A landscape phone gave the transcript 28% of the viewport and a keyboard-up phone 16%, against a 45% floor — and the fixed tab bar painted over the composer, covering the safety sentence and half the Send button, because two source comments asserted the bar stood down on short viewports and it never had. Both fixed and measured by hit-testing rather than by screenshot. The composer itself was 64px tall for a blank second line nobody typed, because the auto-resize effect sizes to scrollHeight and scrollHeight counts rows — a CSS height could not win against an inline style, so the attribute was the honest lever. Verified across both themes driven through the app's own control: no horizontal overflow on 15 routes at four viewports, 672 stat values that fit, 297 labels at exactly 11px/500, Escape returning focus to its opener rather than the body on every overlay, and a rejected write no longer reporting "Succeeded" with a green check. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
claude
|
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> |
||
|
claude
|
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> |
||
 karti
|
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> |
||
|
karti
|
74e37f3e76 |
Lay the HubSpot and customer-lifecycle foundation
Work in progress from the Codex session, committed so nothing sits undeployed. Verified before committing: typecheck clean across all packages, 139 unit tests and the e2e suite green, migrations apply to an empty Postgres. Adds the HubSpot integration boundary (OAuth, client, contracts, webhook signature verification, sync), a growth route, customer-lifecycle service, Piggy lifecycle tools, a Growth page, and shared lifecycle/hubspot types. Two things are deliberately incomplete and should not be mistaken for finished: `packages/db/src/schema/hubspot.ts` is NOT exported from the schema index, so it is inert — no tables, no migration. That is the correct order (the shape can settle before it becomes a migration), but it does mean the HubSpot routes have no persistence behind them yet. `pnpm-workspace.yaml` and `pnpm-lock.yaml` are left uncommitted on purpose. The workspace file contains a literal unanswered placeholder — "esbuild: set this to true or false" — and this repository installs with npm, which is also what CI runs. Committing a second package manager's lockfile would make the install ambiguous. If the move to pnpm is intended it should be a deliberate change that updates CI and the Dockerfile together. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
karti
|
853bde2265 |
Build the agent-native compute CRM platform
CI / verify (push) Successful in 3m6s
|