Skip to content
Skip article header Engineering

Parsing Citation Markers Across Streaming Chunks

We kept unfinished markers, code and unknown references literal until the answer supplied its citation list, while containing wide Markdown on phones

5 min read 18 views

Reviewed by Dmytro Nasyrov on October 22, 2026.

The characters [1] can be a source marker, an example inside code or part of an unfinished streamed response. Replacing every bracketed number in the answer would make those different cases look identical. Our Ask renderer instead tied marker behavior to known citation indexes.

The answer supplied the allowed indexes

In the October Ask slice, only a numeric marker present in the answer's citation list became a superscript. It received an accessible Source label with its number. An unknown index stayed ordinary text. That prevented typography from making an unsupported reference look like a recognized source.

We also kept bracket sequences inside code and links unchanged. Their surrounding syntax already assigned them another meaning. A global text replacement could corrupt that structure even when the bracketed number happened to match a real citation elsewhere in the answer.

Input context Recorded rendering policy
Known marker in answer prose Accessible source superscript
Unknown numeric marker Literal text
Marker-like text in code or a link Preserve the existing context
Unfinished bracket sequence Literal text until there is enough information

Streaming text had a weaker contract

The live stream could deliver the opening bracket in one update and the remaining characters later. More importantly, the authoritative citation list belonged to the saved answer. During streaming, marker-like text therefore remained plain text; after the saved response arrived, the renderer could resolve known references against its citations. This avoided presenting a provisional bracket as a working source control before its destination existed. It also kept the rendering rule independent of arbitrary network chunk boundaries. A stream update was an incomplete observation, not a complete Markdown document with final provenance.

The implementation tests enumerated unfinished markers and markers in code or links. Those edge cases matter more than checking a single completed paragraph. The temptation to simplify the parser is strongest when only the finished happy path is visible.

The parser fixture kept the surrounding syntax

In the marker tests, we parsed Markdown into a syntax tree and inspected its pieces after the citation plugin ran. The test helper classified ordinary text, inline code and generated markers separately. A passing result could therefore establish that a recognized citation changed while its neighboring code stayed untouched. The saved cases covered adjacent references, a two-digit index and markers nested in emphasis, list items and table cells. The following reduced examples preserve that fixture's inputs and expected distinctions. They are synthetic strings, not quotations from medical source material.

piecesOf('Earned [1][2] twice.')
// text, marker:1, marker:2, text
piecesOf('See [12] and [0].')
// marker:12; [0] remains text when 0 is not cited
piecesOf('Earned [1')
// unfinished marker remains text
piecesOf('Run `see [1]` and [the manual [1]](https://example.com) [2].')
// code and link words preserved; only final [2] becomes a marker

After Markdown parsing, the input is no longer a flat string. A renderer that transforms only top-level paragraph text could pass a simple sentence test while leaving a valid reference inside a list unrecognized. A renderer that transforms every text descendant could go too far and turn the words of a link into a second source control. The tree traversal needs context as well as an index match.

Screen-reader wording and copied text had different jobs

A second assertion inspected the generated superscript's children. One child carried the accessible words Source 1 with sr-only and select-none. The visible child contained the number and was hidden from assistive technologies. This allowed speech to announce the source's meaning without copying those extra words into a reader's notes beside the visible reference.

The structure assertion covered more than the superscript tag. A renderer could create the correct visual number and still duplicate the label in copied prose, or expose both children to speech. Those are separate regressions that a finished-answer screenshot would be poorly equipped to catch.

The fixture's incomplete bracket case also has a narrow interpretation. It demonstrates that a partial marker survives parsing as literal text. The application's stronger streaming policy still withheld all interactive source decoration until the saved answer supplied its citation list. Incremental syntax recognition and authoritative source availability remained separate gates.

Wide content stayed inside the answer

Markdown tables and code blocks introduced a separate layout failure: a wide answer fragment could make the whole phone page scroll horizontally. We wrapped those elements in their own scrolling boxes. That let the reader inspect the wide content without moving the composer and surrounding interface out of position.

A locally scrolling table does not solve source semantics. It solves containment. We kept that distinction in the tests so a good mobile screenshot would not be mistaken for proof that a marker points to supporting evidence.

The source control evolved later

Initially, the Ask slice rendered superscripts. The later Evidence panel turned markers into actions opening the corresponding answer and citation. A historical explanation needs that date boundary: the earlier implementation did not already contain every later panel interaction. Both stages shared the need to preserve source identity. The displayed number had to resolve within its own answer, rather than borrowing a citation list from whichever message most recently completed.

What our checks establish

The recorded merge includes marker tests, Markdown containment checks and browser scenarios for the Ask interface. It does not establish universal parser security, accessibility certification or factual support for the generated answer. A recognized reference can still point to a passage that fails to support the surrounding claim.

The renderer needed both a recognized marker and the saved answer's citation list before it could create a source action. Whether the cited passage supported the claim remained a separate evaluation.

FAQ

Last updated:

Quick answers to common questions about custom software development, pricing, process and technology.

  • How long have you been in business?

    Pharos Production has been in business since 2013, with over 13 years of experience in custom software development. During this time, we have delivered over 110 applications for 200+ clients across 28 industries, including FinTech, healthcare, crypto and e-commerce. We are rated 5/5 on Clutch based on 107 verified reviews (2026).

  • What services do you provide?

    Pharos Production provides six core service categories: AI Development (LLM applications, AI agents, machine learning and computer vision), Blockchain and Web3 (smart contracts, DeFi, tokenization on Ethereum, Solana, TON and other chains), FinTech Development (payment platforms, digital banking, KYC and AML integration), Software Development (mobile apps, web platforms, database design, UI/UX), Security and QA (code audits, penetration testing, smart contract audits, manual and automated testing) and Consulting (architecture design, MVP validation, startup consulting).

  • Where is Pharos Production located?

    Pharos Production is headquartered in Las Vegas, Nevada, USA (5348 Vegas Dr, Las Vegas, NV 89108), with an engineering office in Kyiv, Ukraine (44-B Eugene Konovalets Str. Suite 201, Kyiv 01133). We work with clients worldwide and provide remote collaboration across all time zones. Visit our contact page for directions and scheduling options.

  • How big is your team?

    Pharos Production has a team of 90+ engineers, including software developers, blockchain specialists, QA engineers, DevOps experts, UI/UX designers, project managers and solution architects. Our founder, Dr. Dmytro Nasyrov, holds a PhD in Artificial Intelligence and leads the technical direction of all projects.

  • What types of customers do you serve?

    We serve a wide range of clients, from startups and product companies to mid-sized enterprises and large institutions. Our clients include crypto exchanges, FinTech providers (like Pleenk), healthcare organizations, sportsbook operators (like Pro Gambling), e-commerce platforms and SaaS companies. Pharos Production has worked with 200+ clients across 28 industries since 2013, adapting engagement models to match each client's stage, whether it is MVP validation for a startup or enterprise-scale development for an established business.

  • How is a custom software development company different from an agency?

    A custom software development company like Pharos Production assigns one dedicated engineering team that owns your product across multiple release cycles, instead of handing it off once a contract ends. Agencies more often rotate staff between clients and optimize for fast delivery over long-term product ownership.

    Pharos Production keeps the same team on your codebase through 2-week sprints, so there is no re-onboarding cost each time you request a new feature.

  • How much does custom software development cost?

    Custom software development costs vary based on project scope and complexity. At Pharos Production, typical project ranges are: MVP development ($10,000-$25,000), suitable for startups validating a product idea; full-fledged production ($25,000-$50,000), for established businesses scaling a proven concept; and full-cycle development ($50,000-$80,000+), for complex enterprise-grade systems. These ranges include architecture design, development, QA testing and deployment. Hourly rates range from $50 to $99 depending on role and seniority. Final pricing depends on technology stack, number of integrations and engagement model (staff augmentation, dedicated team or project outsourcing).

  • How long does it take to develop a custom software application?

    Development timelines depend on scope and complexity. At Pharos Production, a typical MVP takes 2-4 months, a production-ready application takes 4-8 months and a complex enterprise system can take 8-12+ months. We use an agile methodology with 2-week sprints, delivering working increments after each sprint. Every sprint includes a retrospective, progress report and planning session for the next iteration. This approach ensures transparency and allows businesses to launch faster by prioritizing high-impact features first. Get a timeline estimate for your project.

  • What industries does Pharos Production serve?

    Pharos Production serves 28 industries: FinTech, MiCA Compliance, Banking, Insurance, Crypto, Healthcare, Fitness, E-Commerce, Food & Restaurant, On-Demand, Manufacturing, Automotive, Energy, Oil & Gas, Supply Chain, Construction, Real Estate, Gaming, Streaming, Media, Telecom, Education, Aviation, Travel, Logistics, Marketing, Agriculture and Recommender Systems. Our deepest expertise is in FinTech, blockchain and healthcare, where we have delivered compliance-ready platforms (HIPAA, PCI DSS, GDPR) and high-load systems handling thousands of concurrent users. For the latest industry insights, read our guides on FinTech trends in 2026 and the Web3 technology stack.

  • Why hire a software development company instead of building in-house?

    Hiring a software development company offers faster time-to-market, lower upfront costs and access to specialized expertise without long-term employment commitments. According to Deloitte's 2024 Global Outsourcing Survey, 57% of companies outsource software development to access skills they cannot hire internally.

    Factor In-house team Software development company
    Time to assemble 3-6 months (recruiting + onboarding) 1-2 weeks
    Upfront cost High (salaries, benefits, equipment) Lower (project-based pricing)
    Specialized expertise Limited to who you can hire locally Access to 90+ engineers across blockchain, AI, FinTech
    Scalability Slow (each new hire takes months) Fast (scale up or down per sprint)
    Long-term commitment Full-time employment contracts Flexible engagement models
    Risk High if key engineers leave Company ensures continuity and knowledge transfer

    For businesses that need blockchain, AI or high-load architecture expertise, outsourcing to a specialized firm like Pharos Production reduces risk and accelerates delivery.

  • What projects does Pharos Production not take on?

    Pharos Production focuses on mid-to-large custom software projects with budgets starting at $10,000. We do not take on template-based websites, WordPress theme customization or short-term contracts under one month. We also do not provide non-technical staffing (marketing, sales or design-only roles). Our strongest fit is blockchain, FinTech and healthcare projects where security, compliance and high-load architecture are critical. For smaller projects or MVPs under $10,000, we recommend exploring freelance platforms or no-code tools as a more cost-effective starting point.

  • Why does Pharos Production use agile methodology?

    We use agile with 2-week sprints because it reduces the risk of building features that miss the mark. Each sprint ends with a working demo, a retrospective and a plan for the next iteration.

    This means clients see progress every 14 days and can adjust priorities based on real results, not assumptions. We chose this approach after years of experience showing that rigid, fixed-scope contracts lead to scope creep, missed deadlines and products that do not match market needs by launch day.

  • When should you NOT hire a custom software development company?

    Custom development is not the right choice in every situation. You should not hire a custom software company if: your problem is fully solved by an existing SaaS product (e.g. Shopify for e-commerce, Salesforce for CRM); your budget is under $10,000 and timeline is under 4 weeks; you need a simple landing page or marketing website (WordPress or Webflow is faster and cheaper); or you are still validating the idea and have not spoken to potential users yet.

    In these cases, off-the-shelf tools or no-code platforms offer better ROI. Custom development makes sense when you need unique workflows, regulatory compliance, high-load architecture or competitive differentiation that packaged software cannot provide.

  • What kind of projects has Pharos Production delivered?

    Here are three anonymized examples from our recent delivery history:

    FinTech startup - payment platform (MVP)
    Scope: mobile app + backend API with bank-grade encryption. Team: 4 engineers, 1 QA. Timeline: 10 weeks. Budget: $38,000. Result: launched on schedule, processed $2M+ in transactions within the first quarter.

    Healthcare provider - patient portal (Full product)
    Scope: HIPAA-aligned web platform with EHR integration, appointment scheduling and telemedicine. Team: 6 engineers, 1 DevOps, 2 QA. Timeline: 6 months. Budget: $120,000. Result: 15,000+ active patients, zero compliance violations in two annual audits.

    Crypto exchange - trading engine (Complex)
    Scope: high-load matching engine handling 50,000+ orders per second, multi-chain wallet infrastructure on Ethereum and Solana. Team: 8 engineers, 2 QA, 1 security auditor. Timeline: 11 months. Budget: $340,000. Result: 99.97% uptime, passed three independent security audits.

    See more projects: NoMoreBets, Pulse, Sagas, Gambit Stream and Pleenk. For the full portfolio, visit our case studies. Learn more about the technology behind these projects in our guide to stablecoins and crypto infrastructure.

Stas Rysin is the Lead Frontend Developer at Pharos Production. His work covers the design system, reader interfaces and administration workflows of a professional learning platform for aesthetic medicine.

Dmytro Nasyrov, Founder and CTO at Pharos Production
Dmytro Nasyrov Founder & CTO Let's work together!

Your business results matter

Achieve them with minimized risk through our bespoke innovation capabilities

Your contact details
Please enter your name
Please enter a valid email address
Please enter your message

We use your details only to reply to your request. Data Privacy and Legal Notice

We typically reply within 24 hours

What happens next?

  1. Contact us

    Contact us today to discuss your project. We're ready to review your request promptly and guide you on the best next steps for collaboration

    Same day
  2. NDA

    We're committed to keeping your information confidential, so we'll sign a Non-Disclosure Agreement

    1 day
  3. Plan the Goals

    After we chat about your goals and needs, we'll craft a comprehensive proposal detailing the project scope, team, timeline and budget

    3-5 days
  4. Finalize the Details

    Let's connect on Google Meet to go through the proposal and confirm all the details together!

    1-2 days
  5. Sign the Contract

    As soon as the contract is signed, our dedicated team will jump into action on your project!

    Same day