jonathan/boardroom-map
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Implement BDEF v1.1 grading: scoring core, per-deck pipeline, ledger, dashboard, StartOS layer

Browse Source 
- Deterministic scoring.py (quant 60 / qual 40 / flags -15, profitability heaviest)
- Per-company JSON ledger with forecast-target chaining deck N-1 -> N
- Single-shot sandbox agent with guided-JSON fallback ladder (no tool loop)
- Portfolio dashboard with sparklines, KPI hit rates, BDEF category bars
- 48 unit tests green; endpoints smoke-tested; npm check+build green

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Jonathan Kirkwood
2026-07-06 14:15:12 -05:00
co-authored by Claude Fable 5
parent 1dde915540
commit b1d7aed9f4
48 changed files with 4907 additions and 971 deletions
Download Patch File Download Diff File Expand all files Collapse all files
startos/actions/configure-companies.ts
+185
View File
@@ -0,0 +1,185 @@
import { sdk } from '../sdk'
import { configFile } from '../file-models/config'
const { InputSpec, Value, List } = sdk
const inputSpec = InputSpec.of({
companies: Value.list(
List.obj(
{
name: 'Portfolio Companies',
description:
'One entry per portfolio company. The SLUG is the folder you drop its ' +
'decks into (inbox/<slug>/2026-Q2-deck.pdf) and the key its running ' +
'scorecard ledger lives under. Pinned targets are the KPIs the scorer ' +
'holds the company to even when a deck goes quiet about them — pin the ' +
'profitability thresholds especially, since they carry the heaviest ' +
'weight (30 of the quant 60).',
default: [],
minLength: 0,
maxLength: 64,
},
{
uniqueBy: 'slug',
displayAs: '{{slug}}',
spec: InputSpec.of({
slug: Value.text({
name: 'Slug',
description:
'Folder name under the inbox and the ledger key. Stable — do not ' +
'rename once decks have been graded.',
required: true,
default: null,
placeholder: 'acme-widgets',
patterns: [
{ regex: '^[a-z0-9][a-z0-9-]{0,40}$',
description: 'Lowercase letters, numbers, dashes (max 41 chars).' },
],
}),
name: Value.text({
name: 'Display Name (optional)',
description: 'Shown on the dashboard and scorecards. Empty = the slug.',
required: false,
default: null,
placeholder: 'Acme Widgets, Inc.',
}),
kpiAliases: Value.textarea({
name: 'KPI Aliases (optional)',
description:
'One line per KPI: canonical=alias1;alias2 — maps the names a deck ' +
'uses onto the canonical KPI name, so "Adj. EBITDA" and "EBITDA ' +
'(adj)" both land on the same pinned target.',
required: false,
default: null,
minRows: 2,
maxRows: 12,
placeholder: 'ebitda=Adj. EBITDA;EBITDA (adj)\nmrr=Monthly Recurring Revenue;MRR',
}),
pinnedTargets: Value.list(
List.obj(
{
name: 'Pinned KPI Targets',
description:
'Targets graded every quarter regardless of what the deck ' +
'chooses to show. Mark profitability KPIs (EBITDA, net margin, ' +
'FCF...) so they score in the heavier profitability bucket.',
default: [],
minLength: 0,
maxLength: 32,
},
{
uniqueBy: 'kpi',
displayAs: '{{kpi}} → {{target}}',
spec: InputSpec.of({
kpi: Value.text({
name: 'KPI Name',
description: 'Canonical KPI name (see the aliases field above).',
required: true,
default: null,
placeholder: 'ebitda',
}),
target: Value.number({
name: 'Target',
description: 'The numeric target for the period.',
required: true,
default: null,
integer: false,
}),
unit: Value.text({
name: 'Unit (optional)',
description: 'For display only, e.g. "USD", "%", "customers".',
required: false,
default: null,
placeholder: 'USD',
}),
direction: Value.select({
name: 'Direction',
description: 'Whether hitting the target means being at-or-above it (revenue) or at-or-below it (churn, burn).',
default: 'gte',
values: {
gte: 'At or above target',
lte: 'At or below target',
},
}),
profitability: Value.toggle({
name: 'Profitability KPI',
description: 'Score this KPI in the profitability bucket (heaviest weight) instead of the general KPI bucket.',
default: false,
}),
}),
},
),
),
}),
},
),
),
})
export const configureCompanies = sdk.Action.withInput(
'configure-companies',
async ({ effects }) => ({
name: 'Configure Companies',
description: 'Define the portfolio companies, their inbox slugs, KPI aliases, and pinned KPI targets.',
warning: null,
allowedStatuses: 'any',
group: 'Grading',
visibility: 'enabled',
}),
inputSpec,
async ({ effects }) => {
const cfg = await configFile.read().const(effects)
if (!cfg) return {}
return {
companies: cfg.companies.map((c) => ({
slug: c.slug,
name: c.name || undefined,
kpiAliases: c.kpiAliases || undefined,
pinnedTargets: c.pinnedTargets.map((t) => ({
kpi: t.kpi,
target: t.target,
unit: t.unit || undefined,
direction: t.direction,
profitability: t.profitability,
})),
})),
}
},
async ({ effects, input }) => {
await configFile.merge(effects, {
companies: input.companies.map((c) => ({
slug: c.slug,
name: c.name ?? '',
kpiAliases: c.kpiAliases ?? '',
pinnedTargets: c.pinnedTargets.map((t) => ({
kpi: t.kpi,
target: t.target,
unit: t.unit ?? '',
direction: t.direction,
profitability: t.profitability,
})),
})),
})
return {
version: '1',
title: 'Companies Configured',
message:
'Saved ' + input.companies.length + ' company(ies). Drop each company\'s ' +
'decks into inbox/<slug>/ (e.g. inbox/' +
(input.companies[0]?.slug || 'acme-widgets') +
'/2026-Q2-deck.pdf), then run "Grade Decks".',
result: {
type: 'single',
value: input.companies.map((c) => c.slug).join(', ') || '(none)',
copyable: false,
qr: false,
masked: false,
},
}
},
)
startos/actions/configure-graders.ts
+31 -28
View File
@@ -4,14 +4,15 @@ import { configFile } from '../file-models/config'
const { InputSpec, Value, List } = sdk
const inputSpec = InputSpec.of({
reviewers: Value.list(
graders: Value.list(
List.obj(
{
name: 'Review Panel',
name: 'Grading Panel',
description:
'Who sits on the panel — one entry per review. Add as many as you like. ' +
'Each reviewer is a model from your catalog plus a PERSONA: the lens it ' +
'reads through, so the same document gets examined from different angles.',
'Who grades the decks — one entry per grader. Add as many as you like. ' +
'Each grader is a model from your catalog plus a PERSONA: the lens it ' +
'grades through, so the same deck gets scored from different angles ' +
'before the deterministic composite is computed.',
default: [],
minLength: 1,
maxLength: 32,
@@ -22,10 +23,10 @@ const inputSpec = InputSpec.of({
spec: InputSpec.of({
name: Value.text({
name: 'Name',
description: 'Unique reviewer name. Becomes its container and report filename.',
description: 'Unique grader name. Becomes its container and grade-sheet filename.',
required: true,
default: null,
placeholder: 'risk-counsel',
placeholder: 'munger-lens',
patterns: [
{ regex: '^[A-Za-z0-9][A-Za-z0-9 _-]{0,40}$',
description: 'Letters, numbers, spaces, dashes, underscores (max 41 chars).' },
@@ -33,31 +34,32 @@ const inputSpec = InputSpec.of({
}),
model: Value.text({
name: 'Model Alias',
description: 'Which catalog model this reviewer uses (must match an alias from "Configure Models").',
description: 'Which catalog model this grader uses (must match an alias from "Configure Models").',
required: true,
default: null,
placeholder: 'reviewer-a',
placeholder: 'grader-a',
}),
persona: Value.textarea({
name: 'Persona / Lens',
description:
'How THIS reviewer should read the documents — its priorities and ' +
'weighting. Injected into its system prompt. e.g. "You are skeptical ' +
'legal counsel: weight liability, ambiguous obligations, and missing ' +
'clauses above everything." Leave empty for a neutral reviewer.',
'How THIS grader should read the deck — its priorities and ' +
'weighting within the BDEF rubric. Injected into its system prompt. ' +
'e.g. "You are a Munger-style inversion skeptic: ask what would have ' +
'to be true for this deck to be hiding a deteriorating business." ' +
'Leave empty for a neutral grader.',
required: false,
default: null,
minRows: 3,
maxRows: 16,
placeholder:
'You are a financial-controls reviewer. Focus on numbers that do not ' +
'reconcile, unstated assumptions behind projections, and anything that ' +
'would concern an auditor. Organize findings by severity.',
'You are a Girdley-style operator. Weight unit economics, owner ' +
'accountability, and whether the KPIs the board was promised last ' +
'quarter are still being reported. Flag every silently dropped metric.',
}),
temperature: Value.number({
name: 'Sampling Temperature (optional)',
description:
'Best-effort per-reviewer sampling temperature for extra diversity. ' +
'Best-effort per-grader sampling temperature for extra diversity. ' +
'Persona is the primary lever. Leave empty to use the model default.',
required: false,
default: null,
@@ -71,15 +73,15 @@ const inputSpec = InputSpec.of({
),
})
export const configureReviewers = sdk.Action.withInput(
'configure-reviewers',
export const configureGraders = sdk.Action.withInput(
'configure-graders',
async ({ effects }) => ({
name: 'Configure Reviewers',
description: 'Define the review panel: which models and which personas, and how many reviews.',
name: 'Configure Graders',
description: 'Define the grading panel: which models and which personas grade each deck.',
warning: null,
allowedStatuses: 'any',
group: null,
group: 'Grading',
visibility: 'enabled',
}),
@@ -88,22 +90,23 @@ export const configureReviewers = sdk.Action.withInput(
async ({ effects }) => {
const cfg = await configFile.read().const(effects)
if (!cfg) return {}
return { reviewers: cfg.reviewers }
return { graders: cfg.graders }
},
async ({ effects, input }) => {
await configFile.merge(effects, { reviewers: input.reviewers })
await configFile.merge(effects, { graders: input.graders })
return {
version: '1',
title: 'Panel Configured',
message:
'Saved a panel of ' + input.reviewers.length + ' reviewer(s). Each model ' +
'alias must exist in "Configure Models". Set the rubric in "Configure ' +
'Review", then drop documents and run a review.',
'Saved a panel of ' + input.graders.length + ' grader(s). Each model ' +
'alias must exist in "Configure Models". Set the scoring knobs in ' +
'"Configure Grading", add companies in "Configure Companies", then drop ' +
'decks into inbox/<company-slug>/ and run "Grade Decks".',
result: {
type: 'single',
value: input.reviewers.map((r) => r.name).join(', '),
value: input.graders.map((g) => g.name).join(', '),
copyable: false,
qr: false,
masked: false,
startos/actions/configure-grading.ts
+171 -48
View File
@@ -4,26 +4,33 @@ import { configFile } from '../file-models/config'
const { InputSpec, Value } = sdk
const inputSpec = InputSpec.of({
reviewInstructions: Value.textarea({
name: 'Review Rubric',
bdefOverride: Value.textarea({
name: 'BDEF Rubric Override (optional)',
description:
'What every reviewer should look for and produce. Layered above each ' +
'reviewer\'s persona. Be concrete about the structure you want back.',
required: true,
'Leave EMPTY to grade against the baked-in BDEF v1.1 framework ' +
'(Girdley + Munger/Buffett). Non-empty text replaces the rubric wholesale, ' +
'so include the qualitative categories A-H if you customize it.',
required: false,
default: null,
minRows: 5,
maxRows: 20,
placeholder:
'Review the attached document(s). Produce: a short summary, key findings, ' +
'risks/red flags, open questions, and recommendations. Cite the document and ' +
'section for each point. Never invent facts not present in the documents.',
maxRows: 24,
placeholder: '(empty = the built-in BDEF v1.1 rubric)',
}),
extractorModel: Value.text({
name: 'Extractor Model (optional)',
description:
'Catalog alias of the model that runs the stage-1 structured KPI ' +
'extraction over each deck. Empty = use the first model.',
required: false,
default: null,
placeholder: 'grader-a',
}),
networkMode: Value.select({
name: 'Network Mode',
description:
'Air-gapped: reviewers reach ONLY the on-Spark model proxy — zero internet, ' +
'documents never leave your hardware (models must be pre-pulled into the ' +
'Spark HF cache, all on the head Spark). Local services: reviewers may also ' +
'Air-gapped: graders reach ONLY the on-Spark model proxy — zero internet, ' +
'board decks never leave your hardware (models must be pre-pulled into the ' +
'Spark HF cache, all on the head Spark). Local services: graders may also ' +
'reach LAN services like SearXNG and the second Spark (this network has ' +
'egress unless you firewall it).',
default: 'airgapped',
@@ -34,59 +41,151 @@ const inputSpec = InputSpec.of({
}),
searxngUrl: Value.text({
name: 'SearXNG URL (local-services only)',
description: 'JSON-search endpoint to give reviewers a web_search tool. Ignored in air-gapped mode. Empty = no web search.',
description: 'JSON-search endpoint to give graders a web_search tool. Ignored in air-gapped mode. Empty = no web search.',
required: false,
default: null,
placeholder: 'https://searxng.local',
}),
synthesisEnabled: Value.toggle({
name: 'Synthesize a Consolidated Report',
adjudicatorEnabled: Value.toggle({
name: 'Run an Adjudicator',
description:
'After the panel finishes, run a local "lead reviewer" that reads all the ' +
'individual reports and writes one consolidated report (themes, conflicts, ' +
'consensus, recommendation). No frontier model — stays on the Sparks.',
'After the panel finishes, run a local "lead grader" that reads every ' +
'grade sheet, reconciles disagreements, and settles the qualitative scores ' +
'the deterministic composite uses. No frontier model — stays on the Sparks.',
default: true,
}),
synthesisModel: Value.text({
name: 'Lead Reviewer Model (optional)',
description: 'Catalog alias of the model that writes the consolidated report. Empty = use the first model.',
adjudicatorModel: Value.text({
name: 'Adjudicator Model (optional)',
description: 'Catalog alias of the model that adjudicates the panel. Empty = use the first model.',
required: false,
default: null,
placeholder: 'reviewer-a',
placeholder: 'grader-a',
}),
synthesisPersona: Value.textarea({
name: 'Lead Reviewer Instructions (optional)',
description: 'Override how the consolidated report is written. Empty = a sensible built-in default.',
adjudicatorPersona: Value.textarea({
name: 'Adjudicator Instructions (optional)',
description: 'Override how the adjudicator reconciles the panel. Empty = a sensible built-in default.',
required: false,
default: null,
minRows: 3,
maxRows: 14,
}),
wipeRemoteDocs: Value.toggle({
name: 'Wipe Documents From Sparks After Review',
name: 'Wipe Decks From Sparks After Grading',
description:
'Delete the extracted document text from the Sparks when a job finishes. ' +
'Reports are always kept on this StartOS box. Recommended for confidential material.',
'Delete the extracted deck text from the Sparks when a job finishes. ' +
'Scorecards and ledgers are always kept on this StartOS box. Recommended ' +
'for confidential board material.',
default: true,
}),
autoRunOnDrop: Value.toggle({
name: 'Auto-run When Documents Are Dropped',
name: 'Auto-grade When Decks Are Dropped',
description:
'Start a review automatically (after a short debounce) whenever new files ' +
'land in the inbox. Off by default so you trigger reviews explicitly.',
'Start grading automatically (after a short debounce) whenever new decks ' +
'land in the inbox. Off by default so you trigger grading explicitly.',
default: false,
}),
// --- Deterministic-scorer weights (composite = quant 60 + qual 40 - flags) ---
profitabilityKpi: Value.number({
name: 'Weight: Profitability KPIs',
description: 'Points for the profitability KPI attainment bucket — the heaviest slice of the quant 60. Default 30.',
required: true,
default: 30,
integer: false,
min: 0,
max: 100,
}),
otherKpi: Value.number({
name: 'Weight: Other KPIs',
description: 'Points for the non-profitability measurable-KPI bucket. Default 20.',
required: true,
default: 20,
integer: false,
min: 0,
max: 100,
}),
forecastIntegrity: Value.number({
name: 'Weight: Forecast Integrity',
description: 'Points for deck N actuals hitting what deck N-1 promised. Default 10.',
required: true,
default: 10,
integer: false,
min: 0,
max: 100,
}),
qualCategoryMax: Value.number({
name: 'Weight: Max Per Qualitative Category',
description: 'Max points per BDEF category A-H (8 categories x 5 = the qualitative 40). Default 5.',
required: true,
default: 5,
integer: false,
min: 0,
max: 100,
}),
redFlagCap: Value.number({
name: 'Red-flag Penalty Cap',
description: 'Maximum total points red flags can subtract from the composite. Default 15.',
required: true,
default: 15,
integer: false,
min: 0,
max: 100,
}),
kpiCreditFloor: Value.number({
name: 'KPI Credit Floor',
description: 'actual/target ratio below which a KPI earns zero credit (linear credit above it). Default 0.5.',
required: true,
default: 0.5,
integer: false,
min: 0,
max: 1,
}),
droppedKpiPenalty: Value.number({
name: 'Dropped-KPI Penalty',
description: 'Penalty per KPI that silently disappeared from the deck. Default 2.',
required: true,
default: 2,
integer: false,
min: 0,
max: 100,
}),
droppedKpiMax: Value.number({
name: 'Dropped-KPI Flag Limit',
description: 'Count at most this many dropped-KPI flags per deck. Default 3.',
required: true,
default: 3,
integer: true,
min: 0,
max: 50,
}),
evidenceFullCredit: Value.number({
name: 'Evidence Full-credit Threshold',
description: 'Quote characters a qualitative finding needs for full weight (thinner evidence scales down). Default 400.',
required: true,
default: 400,
integer: true,
min: 0,
max: 100000,
}),
singleSourceFlagFactor: Value.number({
name: 'Single-source Flag Damping',
description: 'Multiplier applied to red flags raised by only one grader. Default 0.5.',
required: true,
default: 0.5,
integer: false,
min: 0,
max: 1,
}),
})
export const configureReview = sdk.Action.withInput(
'configure-review',
export const configureGrading = sdk.Action.withInput(
'configure-grading',
async ({ effects }) => ({
name: 'Configure Review',
description: 'Set the rubric, air-gap mode, synthesis, and document retention.',
name: 'Configure Grading',
description: 'Set the BDEF rubric, air-gap mode, adjudication, retention, and the scoring weights.',
warning: null,
allowedStatuses: 'any',
group: null,
group: 'Grading',
visibility: 'enabled',
}),
@@ -96,36 +195,60 @@ export const configureReview = sdk.Action.withInput(
const cfg = await configFile.read().const(effects)
if (!cfg) return {}
return {
reviewInstructions: cfg.reviewInstructions,
bdefOverride: cfg.bdefOverride || undefined,
extractorModel: cfg.extractorModel || undefined,
networkMode: cfg.networkMode,
searxngUrl: cfg.searxngUrl || undefined,
synthesisEnabled: cfg.synthesisEnabled,
synthesisModel: cfg.synthesisModel || undefined,
synthesisPersona: cfg.synthesisPersona || undefined,
adjudicatorEnabled: cfg.adjudicatorEnabled,
adjudicatorModel: cfg.adjudicatorModel || undefined,
adjudicatorPersona: cfg.adjudicatorPersona || undefined,
wipeRemoteDocs: cfg.wipeRemoteDocs,
autoRunOnDrop: cfg.autoRunOnDrop,
profitabilityKpi: cfg.weights.profitabilityKpi,
otherKpi: cfg.weights.otherKpi,
forecastIntegrity: cfg.weights.forecastIntegrity,
qualCategoryMax: cfg.weights.qualCategoryMax,
redFlagCap: cfg.weights.redFlagCap,
kpiCreditFloor: cfg.weights.kpiCreditFloor,
droppedKpiPenalty: cfg.weights.droppedKpiPenalty,
droppedKpiMax: cfg.weights.droppedKpiMax,
evidenceFullCredit: cfg.weights.evidenceFullCredit,
singleSourceFlagFactor: cfg.weights.singleSourceFlagFactor,
}
},
async ({ effects, input }) => {
await configFile.merge(effects, {
reviewInstructions: input.reviewInstructions,
bdefOverride: input.bdefOverride ?? '',
extractorModel: input.extractorModel ?? '',
networkMode: input.networkMode,
searxngUrl: input.searxngUrl ?? '',
synthesisEnabled: input.synthesisEnabled,
synthesisModel: input.synthesisModel ?? '',
synthesisPersona: input.synthesisPersona ?? '',
adjudicatorEnabled: input.adjudicatorEnabled,
adjudicatorModel: input.adjudicatorModel ?? '',
adjudicatorPersona: input.adjudicatorPersona ?? '',
wipeRemoteDocs: input.wipeRemoteDocs,
autoRunOnDrop: input.autoRunOnDrop,
weights: {
profitabilityKpi: input.profitabilityKpi,
otherKpi: input.otherKpi,
forecastIntegrity: input.forecastIntegrity,
qualCategoryMax: input.qualCategoryMax,
redFlagCap: input.redFlagCap,
kpiCreditFloor: input.kpiCreditFloor,
droppedKpiPenalty: input.droppedKpiPenalty,
droppedKpiMax: input.droppedKpiMax,
evidenceFullCredit: input.evidenceFullCredit,
singleSourceFlagFactor: input.singleSourceFlagFactor,
},
})
return {
version: '1',
title: 'Review Settings Saved',
title: 'Grading Settings Saved',
message:
input.networkMode === 'airgapped'
? 'Saved. Reviewers will run air-gapped (no internet). Ensure all models are on the head Spark and pre-pulled into its HF cache.'
: 'Saved. Reviewers run in local-services mode and may reach the network — make sure that is acceptable for these documents.',
? 'Saved. Graders will run air-gapped (no internet). Ensure all models are on the head Spark and pre-pulled into its HF cache.'
: 'Saved. Graders run in local-services mode and may reach the network — make sure that is acceptable for these board decks.',
result: { type: 'single', value: input.networkMode, copyable: false, qr: false, masked: false },
}
},
startos/actions/configure-models.ts
+8 -8
View File
@@ -9,7 +9,7 @@ const inputSpec = InputSpec.of({
{
name: 'Model Catalog',
description:
'The local models this service can serve on your Sparks. Each reviewer ' +
'The local models this service can serve on your Sparks. Each grader ' +
'references one of these by its alias. The job runner loads models in ' +
'waves so you can run a panel across more models than fit in GPU memory ' +
'at once.',
@@ -23,10 +23,10 @@ const inputSpec = InputSpec.of({
spec: InputSpec.of({
alias: Value.text({
name: 'Alias',
description: 'Short name reviewers use to pick this model (e.g. "qwen-32b").',
description: 'Short name graders use to pick this model (e.g. "qwen-32b").',
required: true,
default: null,
placeholder: 'reviewer-a',
placeholder: 'grader-a',
patterns: [
{ regex: '^[a-z0-9][a-z0-9-]{0,30}$',
description: 'Lowercase letters, numbers, dashes (max 31 chars).' },
@@ -42,7 +42,7 @@ const inputSpec = InputSpec.of({
spark: Value.select({
name: 'Served On',
description:
'Which Spark serves this model. Air-gapped review mode requires the ' +
'Which Spark serves this model. Air-gapped grading mode requires the ' +
'head (primary) Spark; the secondary is used only in local-services mode.',
default: 'primary',
values: { primary: 'Primary (head) Spark', secondary: 'Secondary Spark' },
@@ -68,7 +68,7 @@ const inputSpec = InputSpec.of({
}),
maxModelLen: Value.number({
name: 'Max Model Length',
description: 'vLLM --max-model-len (context window). Documents are chunked to fit.',
description: 'vLLM --max-model-len (context window). Deck text is chunked to fit.',
required: true,
default: 32768,
integer: true,
@@ -77,7 +77,7 @@ const inputSpec = InputSpec.of({
toolCallParser: Value.text({
name: 'Tool-Call Parser',
description:
'vLLM tool-call parser for the reviewer\'s read-file tool loop. Match the ' +
'vLLM tool-call parser for the grader\'s read-file tool loop. Match the ' +
'served model family (Qwen3 → "hermes"). Empty disables native tool-calling.',
required: false,
default: 'hermes',
@@ -112,7 +112,7 @@ export const configureModels = sdk.Action.withInput(
description: 'Define the local model catalog served on your Sparks and the serving knobs.',
warning: null,
allowedStatuses: 'any',
group: null,
group: 'Setup',
visibility: 'enabled',
}),
@@ -146,7 +146,7 @@ export const configureModels = sdk.Action.withInput(
title: 'Models Configured',
message:
'Saved ' + input.models.length + ' model(s). Make sure each is present in ' +
'the Spark HF cache for air-gapped runs, then set "Configure Reviewers".',
'the Spark HF cache for air-gapped runs, then set "Configure Graders".',
result: {
type: 'single',
value: input.models.map((m) => m.alias).join(', '),
startos/actions/configure-sparks.ts
+8 -8
View File
@@ -7,7 +7,7 @@ const { InputSpec, Value } = sdk
const inputSpec = InputSpec.of({
primarySparkHost: Value.text({
name: 'Primary Spark Host',
description: 'Hostname or IP of the head DGX Spark (reachable over SSH). Serves models, hosts the model proxy, and runs the reviewer panel.',
description: 'Hostname or IP of the head DGX Spark (reachable over SSH). Serves models, hosts the model proxy, and runs the grading panel.',
required: true,
default: null,
placeholder: 'spark-01.local',
@@ -46,8 +46,8 @@ const inputSpec = InputSpec.of({
name: 'Use Both Sparks',
description:
'Allow models to be served on a second Spark (over ConnectX/200GbE) for ' +
'extra capacity. NOTE: in air-gapped review mode all models must run on the ' +
'head Spark; the second Spark is used only in local-services mode.',
'extra capacity. NOTE: in air-gapped grading mode all models must run on ' +
'the head Spark; the second Spark is used only in local-services mode.',
default: false,
}),
secondarySparkHost: Value.text({
@@ -67,7 +67,7 @@ const inputSpec = InputSpec.of({
}),
remoteWorkDir: Value.text({
name: 'Remote Work Directory',
description: 'Absolute path on the head Spark for staged document text, the HF cache, and logs.',
description: 'Absolute path on the head Spark for staged deck text, the HF cache, and logs.',
required: true,
default: '/home/nvidia/boardroom-map',
}),
@@ -78,8 +78,8 @@ const inputSpec = InputSpec.of({
default: 'boardroom-vllm:latest',
}),
graderImage: Value.text({
name: 'Reviewer Image Tag',
description: 'The sandboxed reviewer image built on the head Spark from sandbox/build.sh.',
name: 'Grader Image Tag',
description: 'The sandboxed grader image built on the head Spark from sandbox/build.sh.',
required: true,
default: 'boardroom-grader:latest',
}),
@@ -103,7 +103,7 @@ export const configureSparks = sdk.Action.withInput(
description: 'Set the DGX Spark connection details, SSH credentials, and image tags.',
warning: null,
allowedStatuses: 'any',
group: null,
group: 'Setup',
visibility: 'enabled',
}),
@@ -154,7 +154,7 @@ export const configureSparks = sdk.Action.withInput(
title: 'Sparks Configured',
message:
'Saved. Use "Test Spark Connection" to verify SSH + GPU access, then set ' +
'"Configure Models" and "Configure Reviewers".',
'"Configure Models" and "Configure Graders".',
result: { type: 'single', value: input.primarySparkHost, copyable: false, qr: false, masked: false },
}
},
startos/actions/grade-decks.ts
+12 -12
View File
@@ -2,17 +2,17 @@ import { startSdk } from '@start9labs/start-sdk'
import { sdk } from '../sdk'
/**
* Trigger a review of whatever is currently in the inbox. The running job-runner
* Trigger grading of whatever is currently in the inbox. The running job-runner
* thread polls for /data/state/run_request and starts a job when it appears, so
* this action just drops that request file (decoupled from the daemon — no need
* to reach its HTTP port from the action's one-shot container).
*/
export const runReview = sdk.Action.withoutInput(
'run-review',
export const gradeDecks = sdk.Action.withoutInput(
'grade-decks',
async ({ effects }) => ({
name: 'Run Review',
description: 'Convene the panel now over the documents currently in the inbox.',
name: 'Grade Decks',
description: 'Grade all decks currently in the inbox (inbox/<company-slug>/...).',
warning: null,
allowedStatuses: 'only-running',
group: null,
@@ -36,23 +36,23 @@ export const runReview = sdk.Action.withoutInput(
'sh',
'-c',
'mkdir -p /data/state && date +%s > /data/state/run_request && ' +
'n=$(ls -1 /data/inbox 2>/dev/null | wc -l | tr -d " "); ' +
'echo "Review requested. $n file(s) in the inbox."',
'n=$(find /data/inbox -type f 2>/dev/null | wc -l | tr -d " "); ' +
'echo "Grading requested. $n deck file(s) in the inbox."',
],
{ mounts, env: { BM_DATA_DIR: '/data' } },
'run-review',
'grade-decks',
)
output = (stdout?.toString() || '').trim() || 'Review requested.'
output = (stdout?.toString() || '').trim() || 'Grading requested.'
} catch (e: any) {
output = 'Could not request a review: ' + (e?.message || String(e))
output = 'Could not request grading: ' + (e?.message || String(e))
}
return {
version: '1',
title: 'Review Requested',
title: 'Grading Requested',
message:
output +
' Watch the Web UI for progress; reports appear there and via "View Latest Report".',
' Watch the Web UI for progress; scorecards appear there and via "View Latest Scorecard".',
result: { type: 'single', value: output, copyable: false, qr: false, masked: false },
}
},
startos/actions/index.ts
+15 -10
View File
@@ -1,17 +1,22 @@
import { sdk } from '../sdk'
import { configureSparks } from './configure-sparks'
import { configureModels } from './configure-models'
import { configureReviewers } from './configure-reviewers'
import { configureReview } from './configure-review'
import { runReview } from './run-review'
import { testConnection } from './test-connection'
import { latestReport } from './latest-report'
import { configureModels } from './configure-models'
import { configureGraders } from './configure-graders'
import { configureGrading } from './configure-grading'
import { configureCompanies } from './configure-companies'
import { gradeDecks } from './grade-decks'
import { latestScorecard } from './latest-scorecard'
// Setup group: Sparks -> connection test -> model catalog.
// Grading group: panel -> scoring knobs -> portfolio companies.
// Ungrouped (day-to-day): grade the inbox, read the latest scorecard.
export const actions = sdk.Actions.of()
.addAction(configureSparks)
.addAction(configureModels)
.addAction(configureReviewers)
.addAction(configureReview)
.addAction(runReview)
.addAction(testConnection)
.addAction(latestReport)
.addAction(configureModels)
.addAction(configureGraders)
.addAction(configureGrading)
.addAction(configureCompanies)
.addAction(gradeDecks)
.addAction(latestScorecard)
startos/actions/latest-scorecard.ts
+21 -14
View File
@@ -2,17 +2,18 @@ import { startSdk } from '@start9labs/start-sdk'
import { sdk } from '../sdk'
/**
* Returns the latest report as a copyable result, so you can read it straight
* from the StartOS service page without opening the Web UI. The job runner saves
* the most recent report (consolidated if synthesis is on, else the panel
* digest) to /data/reports/latest.md on the StartOS host — no Spark round-trip.
* Returns the latest scorecard as a copyable result, so you can read it straight
* from the StartOS service page without opening the dashboard. The job runner
* saves the most recent scorecard to /data/reports/latest-scorecard.md (with
* /data/reports/latest.md as the legacy fallback) on the StartOS host — no
* Spark round-trip.
*/
export const latestReport = sdk.Action.withoutInput(
'latest-report',
export const latestScorecard = sdk.Action.withoutInput(
'latest-scorecard',
async ({ effects }) => ({
name: 'View Latest Report',
description: 'Show the most recent review report produced by the panel.',
name: 'View Latest Scorecard',
description: 'Show the most recent deck scorecard produced by the grading panel.',
warning: null,
allowedStatuses: 'any',
group: null,
@@ -32,19 +33,25 @@ export const latestReport = sdk.Action.withoutInput(
const { stdout } = await startSdk.runCommand<typeof sdk.manifest>(
effects,
{ imageId: 'main' },
['sh', '-c', 'cat /data/reports/latest.md 2>/dev/null || echo "(no report yet — drop documents in the inbox and run a review)"'],
[
'sh',
'-c',
'cat /data/reports/latest-scorecard.md 2>/dev/null || ' +
'cat /data/reports/latest.md 2>/dev/null || ' +
'echo "(no scorecard yet — drop decks into inbox/<company-slug>/ and run Grade Decks)"',
],
{ mounts, env: { BM_DATA_DIR: '/data' } },
'latest-report',
'latest-scorecard',
)
report = (stdout?.toString() || '').trim() || '(no report yet)'
report = (stdout?.toString() || '').trim() || '(no scorecard yet)'
} catch (e: any) {
report = 'Could not read report: ' + (e?.message || String(e))
report = 'Could not read scorecard: ' + (e?.message || String(e))
}
return {
version: '1',
title: 'Latest Boardroom Map Report',
message: 'The panel\'s most recent review.',
title: 'Latest Scorecard',
message: 'The panel\'s most recent deck scorecard.',
result: { type: 'single', value: report, copyable: true, qr: false, masked: false },
}
},
startos/actions/test-connection.ts
+5 -4
View File
@@ -3,18 +3,19 @@ import { sdk } from '../sdk'
/**
* Runs a one-shot in the orchestrator image that SSHes into the configured
* Spark(s) and reports `nvidia-smi` plus whether the vLLM + reviewer images are
* built. Reuses orchestrator/spark_client.py so SSH logic lives in one place.
* Spark(s) and reports `nvidia-smi` plus whether the vLLM (boardroom-vllm) and
* grader (boardroom-grader) images are built. Reuses orchestrator/spark_client.py
* so SSH logic lives in one place.
*/
export const testConnection = sdk.Action.withoutInput(
'test-connection',
async ({ effects }) => ({
name: 'Test Spark Connection',
description: 'SSH into the configured Spark(s) and verify GPU + serving/reviewer image access.',
description: 'SSH into the configured Spark(s) and verify GPU + serving/grader image access.',
warning: null,
allowedStatuses: 'any',
group: null,
group: 'Setup',
visibility: 'enabled',
}),
startos/file-models/config.ts
+124 -43
View File
@@ -3,16 +3,21 @@ import { FileHelper, z } from '@start9labs/start-sdk'
/**
* Boardroom Map configuration, persisted to the `main` volume as config.json.
*
* Written by the StartOS actions (Configure Sparks / Models / Reviewers /
* Review) and read by the Python orchestrator inside the container, which mounts
* the same volume at /data and reads /data/config.json. Keep field names in sync
* with orchestrator/bm_config.py (CONFIG_DEFAULTS).
* Written by the StartOS actions (Configure Sparks / Models / Graders /
* Grading / Companies) and read by the Python orchestrator inside the
* container, which mounts the same volume at /data and reads /data/config.json.
* Keep field names in sync with orchestrator/bm_config.py (CONFIG_DEFAULTS).
*
* Boardroom Map is a CONTROL PLANE: a GPU-free orchestrator on StartOS that SSHes into
* one or two DGX Sparks to serve local models and run a panel of sandboxed
* "reviewer" containers over confidential documents you drop in. There is NO
* frontier model and NO cloud key — everything stays on your hardware. The only
* secrets are the Spark SSH key and an optional Hugging Face token (secrets.ts).
* Boardroom Map is a CONTROL PLANE: a GPU-free orchestrator on StartOS that
* SSHes into one or two DGX Sparks to serve local models and grade the board
* decks you drop into /data/inbox/<company-slug>/. A panel of sandboxed
* "grader" containers scores each deck against the BDEF v1.1 framework
* (Girdley + Munger/Buffett); Python then computes a deterministic composite
* (quant KPI attainment 60 incl. profitability 30, qualitative categories 40,
* red-flag penalties up to -15) and appends it to the company's running
* ledger. There is NO frontier model and NO cloud key — everything stays on
* your hardware. The only secrets are the Spark SSH key and an optional
* Hugging Face token (secrets.ts).
*/
export const configShape = z.object({
// --- Spark connection (mirrors LLaMA-Factory / Nightshift) ---
@@ -35,20 +40,21 @@ export const configShape = z.object({
// --- Serving (vLLM on the Sparks) ---
gpuMemoryUtilization: z.string().default('0.85'),
maxModelLen: z.number().int().positive().default(32768),
// vLLM tool-call parser for native function-calling (the reviewer's read-file
// vLLM tool-call parser for native function-calling (the grader's read-file
// tool loop relies on it). Must match the served model family — Qwen3 →
// 'hermes'. Empty disables native tool-calling (reviewers fall back to a
// 'hermes'. Empty disables native tool-calling (graders fall back to a
// JSON-action text protocol).
toolCallParser: z.string().default('hermes'),
// LiteLLM router exposing every model alias on one OpenAI-compatible endpoint.
proxyPort: z.number().int().positive().default(4000),
// How many distinct models may be co-resident on the HEAD Spark at once. The
// job runner loads models in WAVES so it never exceeds this — letting you run a
// panel across more models than fit in GPU memory simultaneously. 1 is safest.
// job runner loads models in WAVES so it never exceeds this — letting you run
// a panel across more models than fit in GPU memory simultaneously. 1 is
// safest.
maxConcurrentModels: z.number().int().positive().default(1),
// The MODEL CATALOG: the set of local models the service can serve. Each
// reviewer (below) references one of these by `alias`. Mirrors
// grader (below) references one of these by `alias`. Mirrors
// bm_config.py CONFIG_DEFAULTS["models"].
models: z
.array(
@@ -62,13 +68,14 @@ export const configShape = z.object({
}),
)
.default([
{ alias: 'reviewer-a', hfModel: 'Qwen/Qwen3-32B-FP8', spark: 'primary', port: 8001 },
{ alias: 'grader-a', hfModel: 'Qwen/Qwen3-32B-FP8', spark: 'primary', port: 8001 },
]),
// --- The review panel: one entry per reviewer ("number of reviews") ---
// Each reviewer is a model + a persona (the lens it reads through) + an
// optional temperature. Mirrors bm_config.py CONFIG_DEFAULTS["reviewers"].
reviewers: z
// --- The grading panel: one entry per grader ---
// Each grader is a model + a persona (the lens it grades through — e.g. a
// Munger-style inversion skeptic or a Girdley-style operator) + an optional
// temperature. Mirrors bm_config.py CONFIG_DEFAULTS["graders"].
graders: z
.array(
z.object({
name: z.string(),
@@ -79,50 +86,124 @@ export const configShape = z.object({
}),
)
.default([
{ name: 'reviewer-1', model: 'reviewer-a', persona: '', temperature: null },
{ name: 'munger-lens', model: 'grader-a', persona: '', temperature: null },
]),
// --- Review job settings ---
// The rubric: what every reviewer should look for / produce. Layered above
// each reviewer's persona.
reviewInstructions: z.string().default(
'Review the attached document(s). Produce a structured report: a 3-5 sentence ' +
'summary, the key findings and insights, risks or red flags, open questions, ' +
'and concrete recommendations. Cite the document and section for each point. ' +
'Be honest about uncertainty; never invent facts not present in the documents.',
),
// Confidentiality posture for the reviewer containers:
// 'airgapped' — reviewers join an --internal Docker network: they can
// Which catalog model runs the stage-1 structured KPI extractor over each
// deck. Empty = first model in the catalog.
extractorModel: z.string().default(''),
// --- Grading job settings ---
// The rubric override. Empty = the baked-in BDEF v1.1 framework
// (orchestrator/bdef.md — Girdley + Munger/Buffett). Non-empty text replaces
// it wholesale, so include scoring categories A-H if you customize.
bdefOverride: z.string().default(''),
// Deterministic-scorer knobs. The composite is 0-100 = quant 60 (profitability
// 30 + other KPIs 20 + forecast integrity 10) + qualitative 40 (8 BDEF
// categories x 5) - red-flag penalties (capped at 15). Mirrors
// bm_config.py WEIGHTS_DEFAULTS; keep both in sync.
weights: z
.object({
// Points for the profitability KPI attainment bucket (heaviest weight).
profitabilityKpi: z.number().default(30),
// Points for the non-profitability measurable-KPI bucket.
otherKpi: z.number().default(20),
// Points for forecast integrity: deck N actuals vs deck N-1 stated targets.
forecastIntegrity: z.number().default(10),
// Max points per qualitative BDEF category A-H (8 x 5 = 40).
qualCategoryMax: z.number().default(5),
// Cap on total red-flag penalty.
redFlagCap: z.number().default(15),
// actual/target ratio below which a KPI earns zero credit.
kpiCreditFloor: z.number().default(0.5),
// Penalty per KPI that silently disappeared from the deck.
droppedKpiPenalty: z.number().default(2),
// Count at most this many dropped-KPI flags.
droppedKpiMax: z.number().default(3),
// Quote characters required for full qualitative-evidence weight.
evidenceFullCredit: z.number().default(400),
// Damping factor for red flags raised by a single grader only.
singleSourceFlagFactor: z.number().default(0.5),
})
.default({
profitabilityKpi: 30,
otherKpi: 20,
forecastIntegrity: 10,
qualCategoryMax: 5,
redFlagCap: 15,
kpiCreditFloor: 0.5,
droppedKpiPenalty: 2,
droppedKpiMax: 3,
evidenceFullCredit: 400,
singleSourceFlagFactor: 0.5,
}),
// Confidentiality posture for the grader containers:
// 'airgapped' — graders join an --internal Docker network: they can
// reach ONLY the on-Spark model proxy, with zero internet
// egress. Models must be pre-pulled into the Spark's HF
// cache (no live download). All models must be on the head
// Spark. Strongest confidentiality.
// 'local_services' — reviewers may also reach configured LAN services
// 'local_services' — graders may also reach configured LAN services
// (e.g. SearXNG) and the second Spark. NOTE: this network
// has egress unless you firewall it — use only when you
// accept that reviewers can reach the network.
// accept that graders can reach the network.
networkMode: z.enum(['airgapped', 'local_services']).default('airgapped'),
// SearXNG JSON endpoint, used ONLY in local_services mode to give reviewers a
// SearXNG JSON endpoint, used ONLY in local_services mode to give graders a
// web_search tool. Empty = no web search.
searxngUrl: z.string().default(''),
// --- Synthesis (a local lead reviewer; no frontier model) ---
synthesisEnabled: z.boolean().default(true),
// Alias of the model that writes the consolidated report. Empty = first model.
synthesisModel: z.string().default(''),
// Optional persona/instructions for the lead reviewer. Empty = built-in default.
synthesisPersona: z.string().default(''),
// --- Adjudication (a local lead grader; no frontier model) ---
adjudicatorEnabled: z.boolean().default(true),
// Alias of the model that reconciles the panel's grades. Empty = first model.
adjudicatorModel: z.string().default(''),
// Optional persona/instructions for the adjudicator. Empty = built-in default.
adjudicatorPersona: z.string().default(''),
// --- Document handling ---
// After a job, wipe the extracted document text from the Sparks. Reports are
// After a job, wipe the extracted deck text from the Sparks. Scorecards are
// kept on the StartOS box regardless. Default true for confidentiality.
wipeRemoteDocs: z.boolean().default(true),
// Watch /data/inbox and auto-start a review when files land (debounced).
// Default false: you trigger reviews explicitly with "Run Review".
// Watch /data/inbox and auto-start grading when decks land (debounced).
// Default false: you trigger grading explicitly with "Grade Decks".
autoRunOnDrop: z.boolean().default(false),
// Name of the per-job Docker network created on the head Spark.
networkName: z.string().default('boardroom-net'),
// --- Portfolio companies ---
// The authoritative source of pinned KPI targets and KPI-name aliases. Decks
// are dropped into /data/inbox/<slug>/ and each company keeps its own running
// scorecard ledger. Mirrors bm_config.py CONFIG_DEFAULTS["companies"].
companies: z
.array(
z.object({
// Directory name under /data/inbox and the ledger key. Stable — do not
// rename once decks have been graded.
slug: z.string(),
// Display name for the dashboard. Empty = the slug.
name: z.string().default(''),
// Newline-separated "canonical=alias1;alias2" lines mapping the names a
// deck uses for a KPI onto its canonical name.
kpiAliases: z.string().default(''),
// Targets the scorer holds the company to even when a deck goes quiet
// about them. `profitability: true` marks the KPI as part of the
// heavier profitability bucket.
pinnedTargets: z
.array(
z.object({
kpi: z.string(),
target: z.number(),
unit: z.string().default(''),
direction: z.enum(['gte', 'lte']).default('gte'),
profitability: z.boolean().default(false),
}),
)
.default([]),
}),
)
.default([]),
// --- Auth flags (the secret itself lives in secrets.ts) ---
hfTokenSet: z.boolean().default(false),
})
startos/interfaces.ts
+3 -2
View File
@@ -13,8 +13,9 @@ export const setInterfaces = sdk.setupInterfaces(async ({ effects }) => {
name: 'Web UI',
id: 'webui',
description:
'The Boardroom Map control panel: drop documents in, convene the reviewer ' +
'panel, watch the job run on your Sparks, and read the reports.',
'The Boardroom Map control panel: drop board decks into each company\'s ' +
'inbox, run the grading panel on your Sparks, and watch per-company ' +
'scorecard trends.',
type: 'ui',
username: null,
path: '',
startos/main.ts
+6 -5
View File
@@ -3,8 +3,8 @@ import { WEB_UI_PORT } from './interfaces'
export const main = sdk.setupMain(async ({ effects }) => {
// Mount the persistent volume at /data: config.json, ssh key, optional HF
// token, the dropped-document inbox, job run state, and saved reports all live
// here.
// token, the per-company deck inbox, job run state, and saved scorecards /
// ledgers all live here.
const mounts = sdk.Mounts.of().mountVolume({
volumeId: 'main',
mountpoint: '/data',
@@ -19,9 +19,10 @@ export const main = sdk.setupMain(async ({ effects }) => {
'boardroom-webui',
)
// The web UI runs the FastAPI app AND, in a background thread, the Boardroom Map job
// runner (which extracts dropped documents, serves the chosen models on the
// Sparks in waves, runs the reviewer panel, and synthesizes a report).
// The web UI runs the FastAPI app AND, in a background thread, the Boardroom
// Map job runner (which extracts dropped decks, serves the chosen models on
// the Sparks in waves, runs the grading panel + adjudicator, computes the
// deterministic composite, and updates each company's scorecard ledger).
return sdk.Daemons.of(effects).addDaemon('webui', {
subcontainer: sub,
exec: {
startos/manifest/index.ts
+33 -24
View File
@@ -7,16 +7,19 @@ import { setupManifest } from '@start9labs/start-sdk'
* does not run any GPU workload itself. It is a small web UI + job runner that
* SSHes into one or two NVIDIA DGX Sparks to:
* 1. serve a panel of local LLMs with vLLM (loaded in waves to fit GPU memory),
* 2. extract text from documents you drop in (PDF/DOCX/TXT/MD — done on the
* StartOS box), ship it to the Sparks, and launch a panel of sandboxed
* "reviewer" containers (each a model + a persona) that read the documents
* and write a report,
* 3. optionally run a local "lead reviewer" that synthesizes the panel's
* reports into one consolidated report.
* 2. extract text from the board decks you drop into inbox/<company-slug>/
* (PDF/DOCX/TXT/MD — done on the StartOS box), ship it to the Sparks, and
* launch a panel of sandboxed "grader" containers (each a model + a
* persona) that grade each deck against the BDEF v1.1 framework
* (Girdley + Munger/Buffett),
* 3. optionally run a local "adjudicator" that reconciles the panel, after
* which Python computes a deterministic composite (quant KPI attainment 60
* incl. profitability 30, qualitative categories 40, red-flag penalties
* up to -15) and appends it to the company's running scorecard ledger.
*
* There is NO frontier model and NO cloud API key. In the default `airgapped`
* network mode the reviewer containers can reach ONLY the on-Spark model proxy —
* the documents and their reviews never touch the internet.
* network mode the grader containers can reach ONLY the on-Spark model proxy —
* the decks and their grades never touch the internet.
*
* NOTE: s9pk.mk extracts the package identifier from the single-quoted value on
* the line below, so keep that field on one line and avoid stray quotes above it.
@@ -30,17 +33,21 @@ export const manifest = setupManifest({
marketingUrl: 'https://github.com/ten31/boardroom-map',
donationUrl: null,
description: {
short: 'A private panel of local LLMs that reviews your confidential documents on your DGX Sparks',
short: 'Grade portfolio-company board decks with local LLMs on your DGX Sparks — BDEF scoring, per-company running scorecards',
long:
'Boardroom Map lets you drop confidential documents in and convene a panel of ' +
'local LLMs running on your NVIDIA DGX Sparks to review them. You choose ' +
'which models and which personas (lenses) sit on the panel and how many ' +
'reviews to run. Each reviewer reads the documents and writes a report; an ' +
'optional local lead reviewer synthesizes them into one consolidated ' +
'report. There is no frontier model and no cloud key: in the default ' +
'air-gapped mode the reviewers reach only the on-Spark model endpoint, so ' +
'your documents and their reviews never leave your hardware. No GPU is ' +
'needed on the StartOS host.',
'Boardroom Map turns your DGX Sparks into a private board-deck grading ' +
'panel. Drop each portfolio company\'s deck into its inbox folder and a ' +
'panel of local LLMs (each a model + a persona) grades it against the ' +
'BDEF v1.1 framework (Girdley + Munger/Buffett); an optional local ' +
'adjudicator reconciles the panel, then a deterministic scorer computes a ' +
'0-100 composite — quantitative KPI attainment worth 60 (profitability ' +
'alone 30, plus forecast integrity: deck N actuals vs deck N-1 promises), ' +
'qualitative categories worth 40, and red-flag penalties up to -15. Each ' +
'company keeps a running scorecard ledger, and a web dashboard shows the ' +
'trends. There is no frontier model and no cloud key: in the default ' +
'air-gapped mode the graders reach only the on-Spark model endpoint, so ' +
'your confidential decks never leave your hardware. No GPU is needed on ' +
'the StartOS host.',
},
// Arch-agnostic orchestrator. Docker build paths are relative to the PROJECT
// ROOT (where the Makefile runs), matching the Start9 convention.
@@ -53,7 +60,7 @@ export const manifest = setupManifest({
},
},
arch: ['x86_64', 'aarch64'],
// The orchestrator only SSHes out + extracts document text on CPU; it never
// The orchestrator only SSHes out + extracts deck text on CPU; it never
// touches a local GPU.
nvidiaContainer: false,
},
@@ -66,10 +73,12 @@ export const manifest = setupManifest({
alerts: {
install:
'Boardroom Map drives work on REMOTE machines (your DGX Sparks) over SSH; ' +
'nothing serves or runs on your StartOS server. After install: ' +
'(1) "Configure Sparks" for SSH access, (2) "Configure Models" for the ' +
'local models to serve, (3) "Configure Reviewers" for the panel + personas, ' +
'(4) "Configure Review" for the rubric and air-gap mode. Then drop ' +
'documents in the inbox and run "Run Review".',
'nothing serves or runs on your StartOS server, and your confidential ' +
'board decks stay on your LAN. After install: (1) "Configure Sparks" for ' +
'SSH access, (2) "Configure Models" for the local models to serve, ' +
'(3) "Configure Graders" for the panel + personas, (4) "Configure Grading" ' +
'for the BDEF rubric, air-gap mode, and scoring weights, (5) "Configure ' +
'Companies" for slugs and pinned KPI targets. Then drop decks into ' +
'inbox/<company-slug>/ and run "Grade Decks".',
},
})
startos/versions/v_0_1_0.ts
+7 -5
View File
@@ -7,10 +7,12 @@ import { VersionInfo } from '@start9labs/start-sdk'
export const v_0_1_0 = VersionInfo.of({
version: '0.1.0:0',
releaseNotes:
'Initial release: drop confidential documents in and convene a panel of ' +
'local LLMs on your DGX Sparks to review them. Choose the models, the ' +
'personas, and how many reviews; an optional local lead reviewer ' +
'synthesizes a consolidated report. Default air-gapped mode keeps documents ' +
'and reviews entirely on your hardware.',
'Initial version — BDEF v1.1 deck grading with per-company scorecards. ' +
'Drop board decks into inbox/<company-slug>/ and a panel of local LLMs on ' +
'your DGX Sparks grades them against the BDEF framework (Girdley + ' +
'Munger/Buffett); a deterministic scorer computes the 0-100 composite ' +
'(quant 60 incl. profitability 30, qualitative 40, red flags to -15) and ' +
'appends it to each company\'s running ledger. Default air-gapped mode ' +
'keeps decks and grades entirely on your hardware.',
migrations: {},
})