feat: implement inference-time persona construction system (6 techniques from literature) by jeremykamber · Pull Request #35 · jeremykamber/deepbound

jeremykamber · 2026-05-20T07:12:26Z

Summary

Implements all 6 techniques from the Literature Review Section 9 (Applications of the Literature) for high-fidelity inference-time persona construction.

Techniques Implemented

T1: Compartmentalized Persona Prompts (Wang et al. 2024b)

Four-section compartmentalized prompt architecture with clear delimiters
Sections: PERSONA IDENTITY, PSYCHOGRAPHIC PROFILE, EPISTEMIC BOUNDARIES, BEHAVIORAL GUARDRAILS
Prevents attention dilution between identity and task instructions

T2: PB&J Psychological Scaffolds (Joshi et al. 2025)

Three parallel psychological scaffolds generating post-hoc rationales
Big Five Personality Roots, Cognitive-Reflex Decision Style, Core Values & Risk Worldview
Graceful degradation if individual scaffold calls fail

T3: Persona Anchors / SyTTA (Xu et al. 2026, Atri et al. 2026)

4-16 token persona anchors injected before every agent turn
Archetype detection based on Big Five scores (9 archetypes)
Combats attention decay in multi-turn interactions

T4: ID-RAG Factual Grounding (Tan et al. 2025)

Two-tier hybrid architecture: full backstory + retrieved chunks
In-memory vector store with trigram-based semantic similarity
Backstory chunking with metadata (topic, emotional tone, relationship type)

T5: InCharacter Interview Evaluation (Wang et al. 2024a)

10 open-ended questions mapped to Big Five dimensions
Expert LLM evaluates transcript for trait evidence (blinded)
Avoids self-report alignment conflict

T6: PICon Consistency Interrogation (Kim et al. 2026)

8-turn logically-chained multi-turn questioning
Three dimensions: internal, external, and retest consistency
Expert LLM judges with structured JSON scoring

Files Changed

8 new source files (adapters, services, evaluators)
8 new test files (unit, integration, E2E)
2 modified files (Persona entity, ChatAdapter)
1 documentation file

Test Results

44 new tests, all passing
Pre-existing failures (Zod v4 compatibility) unchanged
E2E tests verify the full pipeline without LLM dependencies

Documentation

See docs/PERSONA_INFERENCE_SYSTEM.md for detailed overview of all techniques.

…2024b) - Adds PersonaPromptCompiler with four-section architecture: - <<PERSONA IDENTITY>> (demographic anchoring) - <<PSYCHOGRAPHIC PROFILE>> (Big Five with behavior mappings) - <<EPISTEMIC BOUNDARIES>> (knowledge domain constraints) - <<BEHAVIORAL GUARDRAILS>> (response format + refusal patterns) - Adds persona anchor generation (SyTTA-style 4-16 token descriptors) - Adds compileInteractionPrompt for hybrid backstory + anchor + RAG assembly - Adds persona anchor injection before each chat turn for multi-turn consistency - Extends Persona entity with domainExpertise, epistemicBoundaries, responseConstraints, and refusalPatterns fields - Updates ChatAdapter to use the compiled prompt architecture - 7 tests passing for prompt compiler, anchors, sections, metadata

…ization (Joshi et al. 2025) Implements the PB&J (Psychology of Behavior and Judgments) framework: - Three parallel psychological scaffolds: - Big Five Personality Roots (trait-level cause-and-effect explanations) - Cognitive-Reflex Decision Style (System 1 vs System 2 manifestations) - Core Values & Risk Worldview (money, risk, efficiency, trust) - Generates post-hoc rationales explaining WHY a persona holds traits - Formats rationales as backstory appendix with <<PSYCHOLOGICAL RATIONALES>> section - Graceful degradation: partial results survive individual scaffold failures - Reference: Joshi et al. (2025) Findings of EMNLP 2025

…l. 2025) Two-tier identity retrieval-augmented generation: - IdRagStore: in-memory vector store with trigram-based semantic similarity - Backstory chunking with metadata (topic, emotional tone, relationship type) - Automatic topic tagging and tone detection per chunk - Related chunk linking (adjacency + same-topic cross-linking) - Top-K retrieval with relevance scoring - Formatted context string for prompt injection - 8 tests passing for chunking, retrieval, ranking, formatting, edge cases

…nterrogation InCharacter-style evaluator (Wang et al. 2024a): - Open-ended conversational interview across all Big Five dimensions - Expert LLM evaluates transcript for trait evidence (blinded) - Score parsing from expert analysis text - 5 tests for interview protocol, expert analysis, score parsing PICon-style evaluator (Kim et al. 2026): - 8-turn logically-chained multi-turn interrogation - Three consistency dimensions: internal, external, retest - Expert LLM judges for each dimension with JSON scoring - Structured result with total score and detailed breakdown - 4 tests for interrogation, retest, internal consistency, full evaluation

Integration test covering the complete pipeline: - T1+T3: Compartmentalized prompts with persona anchors - T4: ID-RAG chunking, indexing, retrieval, and formatting - T1+T3+T4: Full hybrid prompt assembly (compartmentalized + anchor + RAG) - Realistic persona with detailed 5-part backstory - Verifies all components compose correctly into a unified interaction prompt - 6 integration tests passing

10 E2E tests covering the complete pipeline without LLM dependencies: - Compartmentalized 4-section prompt generation - Persona anchor injection per turn - ID-RAG chunking, retrieval, and formatting - Full hybrid prompt assembly (compartmentalized + RAG + anchor) - Multi-turn conversation simulation - Edge cases: empty backstory, unknown persona, different profiles All 10 tests passing.

Documents all 6 implemented techniques with research citations: - T1: Compartmentalized prompts (Wang et al. 2024b) - T2: PB&J psychological scaffolds (Joshi et al. 2025) - T3: Persona anchors / SyTTA (Xu et al. 2026, Atri et al. 2026) - T4: ID-RAG factual grounding (Tan et al. 2025) - T5: InCharacter interview evaluation (Wang et al. 2024a) - T6: PICon consistency interrogation (Kim et al. 2026) Covers architecture, files changed, test verification, and run instructions.

vercel · 2026-05-20T07:12:31Z

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
ai-pricing-wedge	Ready	Preview, Comment	Jun 7, 2026 6:53am

Copilot

Pull request overview

Adds an inference-time persona construction pipeline (prompt compartmentalization, anchors, ID‑RAG grounding, and evaluation utilities) and wires it into the chat adapter, with comprehensive unit/integration/E2E tests and supporting documentation.

Changes:

Introduces PersonaPromptCompiler for 4‑section compartmentalized system prompts + per-turn persona anchors.
Implements ID‑RAG via an in-memory chunk store (IdRagStore) and retrieval service (IdRagService).
Adds PB&J rationale scaffolding + offline evaluators (InCharacter, PICon), plus extensive tests and a design doc.

Reviewed changes

Copilot reviewed 16 out of 16 changed files in this pull request and generated 15 comments.

Show a summary per file

File	Description
`test/persona-system-e2e.test.ts`	E2E pipeline verification without LLM dependencies
`src/infrastructure/adapters/PiconEvaluator.ts`	PICon multi-turn interrogation + scoring logic
`src/infrastructure/adapters/PersonaPromptCompiler.ts`	Compartmentalized prompt builder + persona anchors
`src/infrastructure/adapters/PbjScaffoldEnhancer.ts`	PB&J scaffold rationale generation
`src/infrastructure/adapters/InCharacterEvaluator.ts`	Interview-based evaluation + expert scoring parse
`src/infrastructure/adapters/IdRagStore.ts`	In-memory chunking + trigram similarity retrieval
`src/infrastructure/adapters/IdRagService.ts`	Indexing/retrieval wrapper + hybrid prompt builder
`src/infrastructure/adapters/ChatAdapter.ts`	Uses prompt compiler + anchor-injected user message
`src/infrastructure/adapters/__tests__/PiconEvaluator.test.ts`	Unit tests for PICon evaluator
`src/infrastructure/adapters/__tests__/PersonaSystemIntegration.test.ts`	Integration tests across prompt + ID‑RAG
`src/infrastructure/adapters/__tests__/PersonaPromptCompiler.test.ts`	Unit tests for prompt compiler + anchors
`src/infrastructure/adapters/__tests__/PbjScaffoldEnhancer.test.ts`	Unit tests for PB&J scaffolds
`src/infrastructure/adapters/__tests__/InCharacterEvaluator.test.ts`	Unit tests for InCharacter evaluator
`src/infrastructure/adapters/__tests__/IdRagStore.test.ts`	Unit tests for chunking/retrieval/formatting
`src/domain/entities/Persona.ts`	Extends Persona with expertise/boundaries/guardrails fields
`docs/PERSONA_INFERENCE_SYSTEM.md`	System overview, technique mapping, and test commands

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

+  /** Generate a short persona anchor (4-16 tokens) based on persona traits. */
+  generateAnchor(persona: Persona): string {
+    const archetype = this.detectArchetype(persona);
+    const anchors: Record<string, string> = {
+      "skeptical-veteran": `As a skeptical, veteran ${persona.occupation.toLowerCase()}:`,
+      "passionate-founder": `As a passionate first-time founder:`,
+      "curious-student": `As a curious ${this.simplifyEducation(persona.educationLevel)} student:`,
+      "jaded-journalist": `As a jaded, veteran journalist:`,


+
+  /** Reset the persona anchor counter for a fresh interaction. */
+  resetAnchorIndex(): void {
+    this.anchorIndex = 0;


@@ -0,0 +1,64 @@
+import { Persona } from "@/domain/entities/Persona";
+import { IdRagStore, RetrievalResult } from "./IdRagStore";


+  retrieveContext(persona: Persona, query: string, k = 3): RagContext {
+    if (!persona.backstory) {
+      return { contextString: "", chunkCount: 0 };
+    }
+
+    const results = this.store.retrieve(persona.id, query, k);
+    const contextString = this.store.formatRetrievedContext(results);
+
+    return { contextString, chunkCount: results.length };


+      parts.push(options.ragContext);
+    }
+
+    parts.push(`User says: "${query}"`);


+    const chunks = store.chunkBackstory("test-1", [
+      "I grew up in a family that valued money carefully. My parents were frugal and taught me to save.",
+      "My career in finance taught me to analyze every purchase carefully.",
+      "I now live in a minimalist apartment that reflects my organized approach to life.",
+    ].join("\n\n"));
+
+    // Related should at minimum include adjacent chunks
+    expect(chunks.length).toBeGreaterThanOrEqual(2);


+    const anchor = c.generateAnchor(jordan);
+    const tokens = anchor.split(/\s+/);
+
+    expect(tokens.length).toBeGreaterThanOrEqual(2);


+    const anchor = compiler.generateAnchor(basePersona);
+    expect(anchor).toContain(":");
+    expect(anchor.split(" ").length).toBeLessThanOrEqual(16);
+    expect(anchor.split(" ").length).toBeGreaterThanOrEqual(2);


+
+      const response = await this.llmService.createChatCompletion(
+        [
+          {
+            role: "system",
+            content: `You are ${persona.name}, a ${persona.occupation}. Answer naturally and consistently.${context}`,
+          },


+      const response = await this.llmService.createChatCompletion(
+        [
+          {
+            role: "system",
+            content: `You are ${persona.name}, a ${persona.occupation}. Answer naturally.`,
+          },
+          { role: "user", content: retestQuestions[i] },
+        ],
+        { temperature: 0.5, purpose: `PICon Retest ${i + 1}` },
+      );


Removes non-research fields (cognitiveReflex, technicalFluency, economicSensitivity, designStyle, livingEnvironment). Adds psychographic specification from Wang et al. (2024b): values, fears, communicationStyle, decisionStyle. Keeps Big Five (OCEAN) as primary psychometric framework per Joshi et al. (2025). Updates prompts, mapper, UI cards, detail modal, and tests. 44/44 tests passing.

… spec Root cause: analysis prompt had three problems causing uniform scoring: 1. Referenced cognitiveReflex which was removed from Persona entity 2. Only guided on 2 of 5 Big Five traits (Conscientiousness, Neuroticism) 3. Ignored values, fears, communicationStyle, decisionStyle entirely 4. No prompt/result logging to inspect LLM behavior Fix: - Adds behavioral guidance for ALL Big Five: Conscientiousness, Neuroticism, Openness, Extraversion, Agreeableness - Adds VALUES + FEARS DRIVE YOUR MOTIVATION section that injects the persona's actual values and fears directly into the prompt - Adds decisionStyle + communicationStyle guidance - Tells LLM explicitly: 'Different personas MUST give DIFFERENT scores based on their unique Big Five, values, and fears' - Logs full analysis prompt + results for each persona

Previously analysis used flat stringifyPersona() while chat used the 4-compartment PersonaPromptCompiler. Now both use the same Wang et al. (2024b) architecture with <<ANALYSIS TASK>> appended.

…eline Fixes PbjScaffoldEnhancer to use current Persona fields (removed stale cognitiveReflex, economicSensitivity, technicalFluency refs). Scaffolds now use Big Five + values + fears + decisionStyle + communicationStyle. Integrated into GeneratePersonasUseCase as new ENHANCING_WITH_PBJ phase between backstory generation and insight generation. Per Joshi et al. (2025), this adds post-hoc rationales that causally connect Big Five to psychographics, improving alignment by 6-9%.

Adds ENHANCING_WITH_PBJ as step 2.

ChatAdapter: ingests persona backstory into IdRagStore on first interaction, retrieves top-3 relevant chunks per user message, injects as <<RETRIEVED MEMORY>> in system prompt. VisionAnalysisAdapter: ingests persona backstory, retrieves chunks relevant to the pricing page context, injects as <<RETRIEVED MEMORY>> in both streaming and audit analysis prompts. Also adds persona anchor before the task instruction. Per Tan et al. (2025) ID-RAG framework.

Adds periodic re-grounding (Atri et al., 2026b) to ChatAdapter: every 4th turn, a <<REGROUND>> instruction forces the model to re-access its persona definition (values, fears, goals) before responding. This counters the 30-40% persona drift documented in ChronoScope between turns 1-20.

The streaming generateInitialPersonasStream consistently fails at runtime. Replaced with direct non-streaming generateInitialPersonas call. Can re-add streaming later when the AI SDK streamObject issue is resolved.

P0 fixes addressing Linear PM feedback: 1. Domain calibration: generation prompt now tells LLM that -16/user is standard B2B SaaS pricing, Enterprise custom pricing is normal, beta features on paid tiers are common. Prevents personas from penalizing standard industry mechanics. 2. Scoring-sentiment alignment: analysis prompt now enforces that scores must match qualitative sentiment (positive gut = 6+, critical = 4 or below). 3. Actionable recommendations: added recommendations field to PricingAnalysis entity, schema, and validation. Analysis prompt asks for 2-3 specific actionable recommendations per persona.

…gration

…rt button

…code quality - Replace hardcoded white/black color references with theme tokens across all components (badge, card, tabs, dialog, results, upload) - Fix dialog overlay opacity to match spec: bg-black/80 -> bg-black/40 - Fix button radius: rounded-lg -> rounded-md (design spec: 6px) - Fix input border width: border-2 -> border (design spec: 1px) - Remove decorative shadows from FlowDialog and ResultsView (no-shadow rule) - Fix sidebar nav radius to match design system (rounded-md) - Fix dropzone radius for card consistency (rounded-xl -> rounded-lg) - Remove debug console.logs and unused framer-motion import - Fix as any type assertions with proper as const - Add DESIGN.md and PRODUCT.md design system documentation - Remove superseded DESIGN_SYSTEM.md and DESIGNER_PROMPT.md

…used download, chat offset - Remove unused FileDown download button (no onClick handler) - Move close button into header action row to prevent overlay with tabs - Switch DialogContent from grid to flex-col for proper height propagation - Wrap chat tab in flex-1 container so header is flush with top - Add min-h-0 to both tab containers for correct overflow handling

Strip full-height side-sheet positioning (fixed right-0 top-0 h-dvh) and revert to base dialog centering. Cap height at 85vh so content isn't full-screen. Override width to 600px/680px for comfortable reading.

- Add .DS_Store and logs/ to .gitignore - Remove .DS_Store, bun.lockb, next-env.d.ts from tracking (already gitignored or auto-generated)

…okens, sonner toasts, button hierarchy - Change accent from indigo-violet to cerulean blue across all CSS tokens - Update DESIGN.md to reflect new color palette and design decisions - Add button hierarchy documentation (primary/secondary/ghost) with ring-1 definition - Add selection state guidelines using tonal hierarchy instead of accent color - Integrate sonner toast system with dark theme tokens - Add sim-ring-fade animation for simulation notifications - Refine button component variants with ring-1 on primary, updated border styles on outline - Update CSS variable lightness values for better contrast in both light and dark modes - Replace hardcoded chat bubble colors with color-mix on primary token - Align accent and sidebar-accent with primary token via var() reference

…chat streams - Extract duplicate parseMessageContent function from PersonaChat and PersonaChatInline into shared module - Add error handling for non-string stream updates (step: ERROR objects) - Fix chatWithPersonaAction to use stream.done instead of stream.error for graceful error delivery - Change streamable value type from string to any to support structured error payloads

…logging, scouting improvements, and result persistence - Add AnalysisLogger — per-run JSONL logging to logs/analysis/ with auto-flush and structured metadata - Add SimulationResultStore — in-memory server-side store with 30-min TTL for simulation results surviving page reloads - Add screenshot and progress side-channel stores to bypass RSC stream size limits on base64 payloads - Add getSimulationResult, getProgress, getScreenshot server actions for client polling/reconnection - Overhaul ParsePricingPageUseCase with adaptive scouting: targeted strike via HTML locator, guided scroll, lazy-load triggering - Add parallel HTML analysis (isPricingVisibleInHtml + summarizeHtml) for faster pricing detection - Add structured logging throughout the entire pipeline — entry/exit, latency tracking, persona summaries - Add runId passthrough for per-request tracing across all pipeline components - Upgrade report API route with request timing, validation logging, and AnalysisLogger integration - Save error states to SimulationResultStore for robust failure recovery - Add unit tests for the pricing pipeline use case with mock browser and LLM services

…-load handling, and vision analysis overhaul - Simplify RemotePlaywrightAdapter: remove redundant wait methods, streamline screenshot capture - Add DOM stability detection during page load for reliable screenshot timing - Add lazy image loading trigger via progressive scroll-down - Add framework rendering detection (React/Angular/Vue) for SPA compatibility - Overhaul VisionAnalysisAdapter with structured pricing detection via HTML locator + vision LLM - Add multi-strategy pricing location: targeted element strike (via selector/anchor text) vs full scroll scout - Add scouting state machine with viewport captures at each stage for progress UI - Add compact HTML summarization for LLM-based pricing element detection - Pass runId through all LLM calls for consistent tracing

… retry, reasoning extraction, persona backstory generation - Refactor LlmServiceImpl with configurable OpenRouter/Ollama provider selection via createFromEnv factory - Add p-limit concurrency limiter (max 20 parallel requests) to prevent API throttling - Add exponential backoff retry logic (5 retries, 429/5xx only) with jitter - Add reasoning token extraction from DeepSeek V4 Flash responses (both streaming and non-streaming) - Add per-request logging with request IDs, duration tracking, and response previews - Implement OpenRouterCriticAdapter for validation/critique of analysis quality - Implement OpenRouterChatAdapter for persona chat conversations - Add LlmMemoryAdapter for memory-enhanced chat interactions - Add structured persona backstory generation adapter with progress callbacks - Add PersonaPromptCompiler — centralized prompt templates for persona generation, backstories, and insights - Add batch backstory and insight generation for efficient persona processing - Extend LlmServicePort interface with new methods: isPricingVisibleInHtml, summarizeHtml, generateBackstory, etc. - Add variantOf field to Persona entity for tracking persona variation lineage - Add aiSuggestion field to PricingAnalysis entity

…liders, inline streaming, and management - Add generateSimilarPersonasAction — server action for streaming variation generation from reference persona - Add variationMapping utility — maps continuous Big Five values to 1-5 discrete scale for slider UI - Add PersonaDetailSheet variant tab with Big Five sliders (1-5), creative freedom slider, count selector (1/3/5) - Add randomize button for quick trait exploration - Add PersonaSkeletonCard — shimmer placeholder shown while variations are generating - Add DashboardClient variation flow: placeholder injection, streaming replacement, toast notifications - Add person deletion with confirmation dialog on PersonaProfilePanel - Add variantOf display indicator on PersonaProfilePanel - Extend personaStore with insertPersonasAfter (inline insertion after reference), updatePersona, removePersona - Add unit tests for variationMapping and personaStore - Add E2E tests for persona variation generation flow

…s polling and sidebar navigation - Add simulations list page (/dashboard/simulations) showing all completed/in-progress simulation runs - Add simulation detail page (/dashboard/simulations/[id]) with persona analyses, progress polling, and reconnection support - Add simulationStore (Zustand) — manages simulation state with localStorage persistence - Add SimulationToaster component for real-time simulation completion notifications - Add Simulation and PersonaProfile domain entities - Add Simulations link to sidebar navigation with active state - Support reconnection to in-progress simulations via polling getProgress/getScreenshot/getSimulationResult actions

…ove results-to-persona matching - Add AnalysisProvider context component for managing analysis state across dashboard views - Improve ResultsView persona matching — match by personaProfile.name or personaId instead of index - Update SetupView layout with refactored persona flow integration - Overhaul useAnalysisFlow hook with improved state machine for simulation lifecycle - Add computeBenchmarks utility for persona analysis comparison metrics - Add benchmark unit tests

…ntity graph retrieval - Generalize IdRagStore to support both backstory and interview signal chunks - Add chunkBackstory with topic detection (early-life, career, finance, setback, etc.) and emotional tone analysis - Add linkRelated — cross-chunk adjacency and same-topic linking for identity graph traversal - Add interview signal chunking pipeline (chunkInterviewSignals) - Add n-gram fingerprinting and cosine similarity for in-memory semantic retrieval - Add InterviewSignalExtractor — extracts structured signals from interview transcripts - Add PsychographicRationalizer (PB&J) — enhances persona backstories with psychological rationales - Add generatePersonasFromInterviews server action — end-to-end pipeline from transcripts to personas - Add pooling and sampling utilities for transcript processing - Add GazePredictionAdapter and InCharacterEvaluator for behavioral analysis - Refactor IdRagService to use the generalized store for all persona context retrieval

…ona adapter, and pipeline - Add PersonaAdapter unit tests for backstory generation and persona creation - Add pricing-analysis-e2e test — end-to-end persona analysis of a live pricing page - Add pricing-analysis-comprehensive test — multi-persona analysis with full scoring - Add pricing-analysis-full-flow test — complete simulation lifecycle including streaming - Add pricing-analysis-real-flow test — real-world flow with browser automation - Add vitest setup file with global test configuration and mocks

- Add sonner dependency for toast notifications - Update tsconfig with .next type includes and consistent formatting - Add vitest setup file configuration for jsdom test environment

- Add opencode.yml workflow triggered by /oc and /opencode commands on issues and PRs - Uses anomalyco/opencode/github action with deepseek-v4-flash model

…timeout during LLM batches Adds a 4-second setInterval heartbeat that sends keep-alive stream updates when no real progress has been received for 3+ seconds. During Promise.allSettled extraction and batch generation, the function goes silent while waiting for parallel LLM calls — this silence triggers the Netlify serverless function timeout (10s default on legacy plans, 10s for streaming functions). The heartbeat keeps the RSC stream active by sending periodic '{ step, heartbeat: true }' updates, preventing the connection drop.

…pipelines (up to 15 min) - Add netlify/functions/process-pipeline.ts — background function with config.background = true for 15-minute execution limit - Add PipelineStore — durable pipeline state persistence via Netlify Blobs (cross-instance, cross-invocation) - Add startPipeline server action — stores input data in Blobs, triggers background function via HTTP fetch, returns jobId - Add getPipelineStatusAction — polling endpoint for background pipeline progress/results - Rewrite useInterviewPipeline from streaming to polling pattern — submits job, polls every 2s - Add @netlify/blobs dependency for shared state storage - Configure netlify.toml with background function settings

…INGESTING -> COMPILING)

…nstead of raw Blobs fetch The background function was using raw fetch to Netlify Blobs which required NETLIFY_ACCESS_TOKEN — not automatically set in the function env. PipelineStore uses @netlify/blobs which auto-configures auth inside Netlify Functions. PipelineStore.ts has zero @/ imports so the relative import resolves correctly through the function bundler.

Jeremy Kamber added 7 commits May 20, 2026 00:03

Copilot AI review requested due to automatic review settings May 20, 2026 07:12

vercel Bot deployed to Preview May 20, 2026 07:12 View deployment

Copilot started reviewing on behalf of jeremykamber May 20, 2026 07:13 View session

Copilot AI reviewed May 20, 2026

View reviewed changes

vercel Bot had a problem deploying to Preview May 20, 2026 14:56 Failure

vercel Bot had a problem deploying to Preview May 20, 2026 16:03 Failure

fix: use compartmentalized prompt compiler in analysis pipeline

f9593cc

Previously analysis used flat stringifyPersona() while chat used the 4-compartment PersonaPromptCompiler. Now both use the same Wang et al. (2024b) architecture with <<ANALYSIS TASK>> appended.

vercel Bot had a problem deploying to Preview May 20, 2026 16:32 Failure

vercel Bot had a problem deploying to Preview May 20, 2026 16:34 Failure

fix: update FlowDialog to show 4 persona generation phases

221ef05

Adds ENHANCING_WITH_PBJ as step 2.

vercel Bot had a problem deploying to Preview May 20, 2026 16:37 Failure

vercel Bot had a problem deploying to Preview May 20, 2026 16:53 Failure

vercel Bot had a problem deploying to Preview May 20, 2026 16:55 Failure

fix: use non-streaming persona generation by default

27c0b35

The streaming generateInitialPersonasStream consistently fails at runtime. Replaced with direct non-streaming generateInitialPersonas call. Can re-add streaming later when the AI SDK streamObject issue is resolved.

vercel Bot had a problem deploying to Preview May 20, 2026 16:57 Failure

vercel Bot had a problem deploying to Preview May 21, 2026 06:49 Failure

Jeremy Kamber added 19 commits May 24, 2026 16:52

feat(ui): interview upload page with file drag-drop and pipeline inte…

1d3c813

…gration

feat(ui): persistent persona store with sidebar nav and batch history

088dca9

fix(ui): center main content, reuse PersonaProfilePanel, restore repo…

f0a3000

…rt button

refactor(ui): convert persona sheet from side panel to centered modal

50ad6ce

Strip full-height side-sheet positioning (fixed right-0 top-0 h-dvh) and revert to base dialog centering. Cap height at 85vh so content isn't full-screen. Override width to 600px/680px for comfortable reading.

chore: add .DS_Store and logs/ to gitignore, untrack OS artifacts

e7b464f

- Add .DS_Store and logs/ to .gitignore - Remove .DS_Store, bun.lockb, next-env.d.ts from tracking (already gitignored or auto-generated)

chore: update dependencies, tsconfig, and vitest config

7582c10

- Add sonner dependency for toast notifications - Update tsconfig with .next type includes and consistent formatting - Add vitest setup file configuration for jsdom test environment

ci: add opencode GitHub action for AI-assisted PR review

9458913

- Add opencode.yml workflow triggered by /oc and /opencode commands on issues and PRs - Uses anomalyco/opencode/github action with deepseek-v4-flash model

vercel Bot deployed to Preview June 7, 2026 06:53 View deployment

chore: add netlify.toml with 5-min function timeout for LLM pipelines

3134ec5

vercel Bot deployed to Preview June 7, 2026 06:59 View deployment

vercel Bot deployed to Preview June 7, 2026 07:07 View deployment

vercel Bot had a problem deploying to Preview June 7, 2026 07:17 Failure

fix: align InterviewUploadClient step type with background function (…

0034a8b

…INGESTING -> COMPILING)

vercel Bot deployed to Preview June 7, 2026 07:19 View deployment

vercel Bot deployed to Preview June 7, 2026 07:28 View deployment

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat: implement inference-time persona construction system (6 techniques from literature)#35

feat: implement inference-time persona construction system (6 techniques from literature)#35
jeremykamber wants to merge 58 commits into
devfrom
feat/persona-inference-time-techniques

jeremykamber commented May 20, 2026

Uh oh!

vercel Bot commented May 20, 2026 •

edited

Loading

Uh oh!

Copilot AI left a comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

		@@ -0,0 +1,64 @@
		import { Persona } from "@/domain/entities/Persona";
		import { IdRagStore, RetrievalResult } from "./IdRagStore";

Conversation

jeremykamber commented May 20, 2026

Summary

Techniques Implemented

T1: Compartmentalized Persona Prompts (Wang et al. 2024b)

T2: PB&J Psychological Scaffolds (Joshi et al. 2025)

T3: Persona Anchors / SyTTA (Xu et al. 2026, Atri et al. 2026)

T4: ID-RAG Factual Grounding (Tan et al. 2025)

T5: InCharacter Interview Evaluation (Wang et al. 2024a)

T6: PICon Consistency Interrogation (Kim et al. 2026)

Files Changed

Test Results

Documentation

Uh oh!

vercel Bot commented May 20, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

vercel Bot commented May 20, 2026 •

edited

Loading