dsh-chem

Deterministic chemistry math for DeepSeek Harness (dsh) — zero runtime dependencies, pure arithmetic over IUPAC data.

中文简介：化学计量数学工具箱。七个零依赖确定性工具——化学式解析与摩尔质量（支持嵌套括号、结晶水、离子电荷）、质量/摩尔/粒子数换算、溶液浓度（摩尔浓度、稀释 C1V1=C2V2、百分比浓度）、pH/pOH 与缓冲溶液、配平化学方程式（精确有理数运算，含电荷守恒）、理想气体定律（PV=nRT 求解、摩尔体积、气体密度与由密度反推摩尔质量）。专门替代 LLM 高频出错的化学心算。

Why this plugin

Agents get chemistry arithmetic wrong in predictable ways:

• Molar-mass sums — miscounted subscripts, dropped hydrates (CuSO4·5H2O is 249.68 g/mol, not 159.61).
• Element case sensitivity — "Co" is cobalt (58.93), "CO" is carbon monoxide (28.01).
• Dilution math — C1V1 = C2V2 with a wrong or missing factor.
• pH log/antilog arithmetic — pH of 0.01 M HCl is 2, not 12.
• Limiting-reagent reasoning — dividing two amounts by the coefficients and comparing, then carrying the extent of reaction through every product.

These tools replace all of it with deterministic tables and formulas. No network, no state, no dependencies — install and call.

Tools

formula_mass — parse a formula and compute molar mass

Accepts nested parentheses, hydrate dots (CuSO4·5H2O, * also works), leading coefficients (2H2O) and ionic charges. Uses IUPAC standard atomic weights; elements without stable isotopes use the most-stable-isotope mass number (flagged with usedMassNumber).

{ "formula": "H2SO4" }

{
  "valid": true,
  "formula": "H2SO4",
  "molarMass": 98.072,
  "elements": [
    { "symbol": "H", "name": "Hydrogen", "count": 2, "atomicMass": 1.008, "massContribution": 2.016, "massFraction": 0.02056 },
    { "symbol": "O", "name": "Oxygen", "count": 4, "atomicMass": 15.999, "massContribution": 63.996, "massFraction": 0.65254 },
    { "symbol": "S", "name": "Sulfur", "count": 1, "atomicMass": 32.06, "massContribution": 32.06, "massFraction": 0.32690 }
  ],
  "usedMassNumber": false
}

Charge disambiguation rule (documented, deterministic): digits immediately before a trailing +/- belong to the ionic charge only when every element parsed so far is the same single element — Fe3+ is Fe with 3+, S2- is S with 2-, Ca2+ is Ca with 2+. Otherwise they are a subscript and the bare sign is a 1-unit charge — NH4+ is N + H4 with +, NO3- is N + O3 with -. The explicit form SO4^2- is always the charge, and O2^+ escapes the rule for subscript-before-charge. Single lowercase symbols are auto-corrected (h2o → H2O); multi-letter lowercase runs are rejected with a case-sensitivity hint.

mass_moles — mass / amount / particle conversions

Six modes (mass_to_moles, moles_to_mass, mass_to_particles, particles_to_mass, moles_to_particles, particles_to_moles), molar mass from a formula or given directly, Avogadro constant 6.02214076e23.

{ "mode": "mass_to_moles", "value": 98, "formula": "H2SO4" }

{ "valid": true, "mode": "mass_to_moles", "molarMass": 98.072, "avogadro": 6.02214076e+23, "formula": "H2SO4", "moles": 0.9992658455012644 }

solution — concentration math

Four operations:

• molarity — mass of solute + volume → mol/L: { "operation": "molarity", "massG": 58.44, "volumeMl": 250, "formula": "NaCl" } → molarity: 4
• prepare — target molarity + volume → solute mass: { "operation": "prepare", "molarity": 0.1, "volumeMl": 500, "formula": "NaOH" } → massG: 1.99985
• dilute — C1V1 = C2V2, give any three of c1/v1/c2/v2 (M, mL) and the missing one is computed: { "operation": "dilute", "c1": 2, "c2": 0.5, "v2": 250 } → v1: 62.5, solved: "v1"
• percent — wv (g per 100 mL), vv (mL per 100 mL) or mass percent: { "operation": "percent", "percentType": "wv", "soluteG": 5, "solutionMl": 200 } → percent: 2.5

ph — pH chemistry at 25 °C (Kw = 1e-14)

Five operations:

• from_h — { "operation": "from_h", "hConc": 0.001 } → pH: 3, pOH: 11, ohConc: 1e-11
• from_oh — [OH-] → pH/pOH
• from_ph — pH → [H+]
• from_poh — pOH → [OH-]
• buffer — Henderson–Hasselbalch: { "operation": "buffer", "pKa": 4.76, "acidConc": 0.2, "baseConc": 0.1 } → pH: 4.4589700043360185, bufferRatio: 0.5

Negative pH for >1 M acids is supported ([H+] = 2 → pH −0.301).

balance_equation — balance an equation (exact integer coefficients)

The solver runs entirely over BigInt-backed rationals, so coefficients are exact integers — never 2.9999997. Write species separated by + and one arrow (->, =, →); input coefficients like 2H2 are accepted and ignored (scaling a column cannot change the solution).

{ "equation": "C3H8 + O2 -> CO2 + H2O" }

{
  "valid": true,
  "balanced": true,
  "unique": true,
  "equation": "C3H8 + 5 O2 -> 3 CO2 + 4 H2O",
  "reactants": [{ "formula": "C3H8", "coefficient": 1 }, { "formula": "O2", "coefficient": 5 }],
  "products": [{ "formula": "CO2", "coefficient": 3 }, { "formula": "H2O", "coefficient": 4 }],
  "elements": [
    { "symbol": "C", "left": 3, "right": 3 },
    { "symbol": "H", "left": 8, "right": 8 },
    { "symbol": "O", "left": 10, "right": 10 }
  ],
  "chargeBalanced": false
}

Deterministic behaviour worth knowing:

• Charged species force charge conservation too — MnO4- + Fe2+ + H+ -> Mn2+ + Fe3+ + H2O → 1/5/8/1/5/4 with chargeBalanced: true.
• Hydrate water counts as water — CuSO4·5H2O -> CuSO4 + H2O → 1/1/5.
• Separation rule: a bare + next to a symbol is a charge, so Na+ + Cl- keeps its ions while the compact form Fe+O2->Fe2O3 splits. Charged species must use the spaced form (the compact form is ambiguous by construction).
• Honest failures: H2 + O2 -> H2O + N2 returns valid: true, balanced: false with the reason (“at least one species would need coefficient 0”) instead of silently dropping N2. Equations with several independent balances (Fe + O2 -> Fe2O3 + Fe3O4) return unique: false plus the smallest solution by total coefficient sum. Malformed input (no arrow, unknown element) returns valid: false.

gas_law — ideal gas arithmetic with unit conversions

Fixed units, no unit guessing: pressure atm (also reported in kPa/mmHg), volume L (also mL), amount mol, temperature K (also °C). Four operations:

• ideal — give exactly three of pressureAtm, volumeL, moles, temperatureK and the fourth is solved from PV = nRT: { "operation": "ideal", "moles": 1, "temperatureK": 273.15, "volumeL": 22.4 } → pressureAtm: 1.0006236404024167.
• molar_volume — V/n = RT/P, defaults 0 °C / 1 atm: { "operation": "molar_volume" } → molarVolumeLPerMol: 22.413969545014133 (textbook 22.414).
• density — ρ = P·M/(R·T) from formula or molarMass: { "operation": "density", "formula": "CO2", "pressureAtm": 1, "temperatureK": 273.15 } → densityGPerL: 1.9634630051413435.
• molar_mass — M = ρ·R·T/P from a measured density: { "operation": "molar_mass", "densityGPerL": 1.96, "pressureAtm": 1, "temperatureK": 273.15 } → molarMass: 43.9313803082277.

R = 8.31446261815324 / 101.325 L·atm/(mol·K). Missing operands and non-positive values are reported as errors rather than guessed.

stoichiometry — limiting reagent, yield and leftovers

Give the equation plus how much of each reactant you actually have (moles or grams) and the tool answers the questions that follow: the extent of reaction, which reactant runs out first, how much of every product forms, what is left over — and, with product + actualYieldG, the theoretical and percent yield.

{ "equation": "C3H8 + O2 -> CO2 + H2O",
  "reactants": [{ "formula": "C3H8", "moles": 0.5 }, { "formula": "O2", "moles": 2 }],
  "product": "CO2", "actualYieldG": 44 }

{
  "valid": true,
  "equation": "C3H8 + 5O2 -> 3CO2 + 4H2O",
  "extent": 0.4,
  "limiting": ["O2"],
  "reactants": [
    { "formula": "C3H8", "coefficient": 1, "molarMass": 44.097, "availableMoles": 0.5,
      "availableGrams": 22.0485, "consumedMoles": 0.4, "leftoverMoles": 0.1,
      "leftoverGrams": 4.4097, "limiting": false },
    { "formula": "O2", "coefficient": 5, "molarMass": 31.998, "availableMoles": 2,
      "availableGrams": 63.996, "consumedMoles": 2, "leftoverMoles": 0,
      "leftoverGrams": 0, "limiting": true }
  ],
  "products": [
    { "formula": "CO2", "coefficient": 3, "molarMass": 44.009, "moles": 1.2, "grams": 52.8108 },
    { "formula": "H2O", "coefficient": 4, "molarMass": 18.015, "moles": 1.6, "grams": 28.824 }
  ],
  "yieldProduct": "CO2",
  "theoreticalYieldMol": 1.2,
  "theoreticalYieldG": 52.8108,
  "actualYieldG": 44,
  "percentYield": 83.3162913646
}

Deterministic behaviour worth knowing:

• Every reactant needs an amount — an unstated amount would make the limiting reagent undefined, so it is an error naming the missing species instead of an assumption about “excess”.
• Co-limiting is reported, not broken by a tie-break: at exactly 2 mol H2 : 1 mol O2 both are returned in limiting, and nothing is left over.
• Grams are converted with the same IUPAC molar masses formula_mass reports, so 6.54 g Zn is the same number everywhere.
• Coefficients come from the exact rational balancer — this tool balances first (C3H8 + O2 -> … works as written), charge and hydrate included.
• Honest failures: a species that is not a reactant, both/neither of moles/grams, a duplicate entry, a non-positive amount, a product that is not in the equation, or actualYieldG without product all return valid: false with the reason.

Install

dsh plugin --profile <profile> add github:TYEclipse/dsh-chem

(Requires pnpm on PATH — dsh plugin forwards installs to it.)

Verify

dsh plugin --profile <profile> list      # dsh-chem present
dsh --dump-config --profile <profile>    # == dsh-chem layer present

Development

pnpm install
pnpm build     # tsc -> dist/ (committed; git installs do not build)
pnpm test      # vitest, 136 tests
pnpm lint      # oxlint src test

All numeric anchors are generated by the independent Python oracle test/anchors-chem.py (own periodic table + own tokenizer + own Fraction-based equation balancer) and cross-validated against published textbook values (H2O 18.015, H2SO4 98.08, NaCl 58.44, Ca(OH)2 74.09, CuSO4·5H2O 249.68, C6H12O6 180.16, KMnO4 158.03, NH3 17.03; propane 1/5/3/4; permanganate/HCl 2/16/2/2/5/8; 22.414 L/mol at STP). Run it with python3 test/anchors-chem.py.

License

MIT