{"name":"isl-workbench.workspace","description":"The ISL workspace agent: the reproduced studies, their papers and reports, reviews and decisions, the simulator and predictor, and experiments. Members of isl-workbench.org read; its stewards act on their standing grant; high-consequence acts also carry a decision case, and every act is recorded.","version":"0.1.0","supportedInterfaces":[{"url":"https://isl-a2a.faithnet.io/api/a2a","protocolBinding":"JSONRPC","protocolVersion":"1.0"}],"capabilities":{"streaming":true,"pushNotifications":false,"extendedAgentCard":false,"extensions":[]},"defaultInputModes":["text/plain","application/json"],"defaultOutputModes":["text/plain","application/json"],"skills":[{"id":"isl.sim.families","name":"List the interface families","description":"The interface families the simulator covers, with their parameters (tool list_families). No input.","tags":["isl","simulator"]},{"id":"isl.sim.simulate","name":"Simulate a stage recipe","description":"Run a recipe of stages (name, duration_s, T_start_C, T_end_C, ambient, pressure_atm, H2_percent) for a family through the simulator (tool simulate_recipe). Input: { family?, wire_radius_nm?, stages[] }.","tags":["isl","simulator"]},{"id":"isl.sim.predict","name":"Predict from an ISL history","description":"Run a process history written in the ISL language through the predictor (tool predict_history). Input: { history, composition_gradient?, all_samples? }.","tags":["isl","simulator"]},{"id":"isl.sim.benchmark","name":"Read the benchmark report","description":"The benchmark report the engine serves (tool benchmark_report). No input.","tags":["isl","simulator"]},{"id":"isl.predict","name":"Predict from a given history","description":"A process history written in the ISL language is run exactly as written, swept over the timing it leaves open (the envelope per readout, and which open step moves it most), checked for transferability against the one parameter table, and frozen with a content commitment. Code only: no model, no measured value; a step the history does not carry is reported, never filled in. Input: { history, supersedes? }. An owner or a client key.","tags":["isl","predict"]},{"id":"isl.intent.route","name":"Route an intent to the experts","description":"The judge of the intent interface: reads a question put to the workspace and chooses which experts to consult (document, comparison, simulator, language, parameters) and in what order.","tags":["isl","intent"]},{"id":"isl.document.read","name":"Read the study's document","description":"The document expert: the paper's text, its tables and figures rebuilt as data with the model's value on every cell, how each value was read, and quote checks.","tags":["isl","reader"]},{"id":"isl.answer.compose","name":"Compose the answer from evidence","description":"Writes the answer from the experts' evidence only, keeping the paper, our reading, the model and a new simulation apart, with citations checked against the paper.","tags":["isl","intent"]},{"id":"isl.study.context","name":"Assemble the study context","description":"For one case of a reproduced study: the published article's parts that state the specimen and the history, and the names of the readouts. Never the committed program, a simulated value or a measured value.","tags":["isl","reproduce"]},{"id":"isl.terms.resolve","name":"Resolve the paper's terms","description":"The paper's terms resolved to the ISL vocabulary (family, orientation, ambients, process kinds); a term with no entry is listed, never guessed.","tags":["isl","reproduce"]},{"id":"isl.history.rules","name":"Run the history rules pass","description":"A deterministic pass over what the paper states: durations to seconds, temperatures to °C, thicknesses to nm, gases to the vocabulary's ambients; a stated bound stays a bound.","tags":["isl","reproduce"]},{"id":"isl.history.write","name":"Write the history from the source","description":"The specimen and process history of a case in the ISL language, written from the article blind to the committed program and to every result, each step tied to the words that state it or to a declared assumption. The study-kind skill (growth kinetics, interface charge, composition profile, confined geometry) is selected by code. Arms: reference-reading, code-baseline, model-from-paper, model-from-paper-critic.","tags":["isl","reproduce"]},{"id":"isl.history.check","name":"Check the history's fidelity","description":"The program parses; its quotes are the article's words; every step the paper states is in it with the paper's values; nothing is tied to nothing.","tags":["isl","reproduce"]},{"id":"isl.sim.run","name":"Run the simulator","description":"The program through the predictor, as written: no refit and no per-experiment constant.","tags":["isl","simulator"]},{"id":"isl.sim.sweep","name":"Sweep the open timing","description":"Every step a history marks bound, range or assumed is moved across its range, one at a time and then at the corners of the steps that matter; per readout the envelope and the ranking of steps. No measured value is read and no point is chosen.","tags":["isl","predict","reproduce"]},{"id":"isl.parameters.check","name":"Check transferability","description":"Every parameter the run used equals the one parameter table (recorded by commitment); no override; no constant fitted to one scored experiment alone; the same programs across the record.","tags":["isl","predict","reproduce"]},{"id":"isl.prediction.freeze","name":"Freeze a prediction","description":"The history, the predictions with their support labels, the envelope, the parameter table's commitment, the program digests and the checks, committed once and never edited; a correction is a new record naming the old one.","tags":["isl","predict"]},{"id":"isl.sim.compare","name":"Compare with the measurements","description":"The prediction beside the measured values by the harness's own verdict rule and tolerances, and beside the harness's committed reproduction of the same case.","tags":["isl","reproduce"]},{"id":"isl.reproduction.assess","name":"Assess a committed reproduction","description":"Read a reproduction the harness committed: the comparison as stored, a rerun of the simulator, or a model reading the article and saying with exact quotes whether the simulation is faithful to the paper. Arms: stored-floor, rerun, model-assess, model-assess-critic.","tags":["isl","assess"]},{"id":"isl.assessment.check","name":"Check an assessment","description":"Every claim names a real row; the standing claims no more than the rows show; every quote is the article's words; a rerun equals the committed numbers.","tags":["isl","assess"]},{"id":"isl.review.critique","name":"Critique independently","description":"A second model reads the program against the article (or the assessment against the rows) without the writer's reasoning.","tags":["isl","review"]},{"id":"isl.review.submit","name":"Submit for review","description":"A checked reproduction is marked for the workbench's blind review.","tags":["isl","review"]},{"id":"isl.parameters.label","name":"Label the parameters","description":"Every parameter of a prediction labelled by the organisers' rule (constant, sourced, computed, fitted, fitted to scored data, hypothesis), decided per prediction: a sourced constant becomes fitted when the data it came from also score that prediction.","tags":["isl","predict","governance"]},{"id":"isl.comparison.select","name":"Select what a comparison counts as","description":"Held-out, development, training or unscored, decided by code from the dataset partition and the parameter table before any measured value is read.","tags":["isl","evaluation"]},{"id":"isl.model.transfer","name":"Check against another laboratory","description":"The model run unchanged on another laboratory's data for the same interface, as a test of transfer.","tags":["isl","evaluation"]},{"id":"isl.model.revise","name":"Revise the model","description":"A change to the model proposed with its evidence and its effect on every scored comparison, never fitted to one experiment alone.","tags":["isl","model"]},{"id":"isl.data.read","name":"Read measurements from a paper","description":"Measured values read from a published paper with the page, figure or table and the words they come from; read, never invented.","tags":["isl","data"]},{"id":"isl.scope.decline","name":"Decline an out-of-scope ask","description":"Asks to change or invent measured values, about materials systems outside the interface families the harness covers, for production recipes or vendor advice, or naming no study are declined with the nearest thing the agent can do.","tags":["isl","scope"]},{"id":"isl.me","name":"Who am I here","description":"The caller as this workspace admits them: whether they read, whether they act, and why not. Input: {}. Access: any signed-in person.","tags":["isl","workspace","person","tier:ReadOrDraft"]},{"id":"isl.workspace.info","name":"The workspace","description":"The ISL workspace and its governing organisation, the caller's relationship to them as the Home reports it, and whether the door can sign as the workspace. Input: {}. Access: any signed-in person.","tags":["isl","workspace","person","tier:ReadOrDraft"]},{"id":"isl.studies.list","name":"List the reproduced studies","description":"Every reproduced study with its verdicts, its latest assessment and review state, and its report's status. Input: {}. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.study.get","name":"Read one study","description":"One study: its specimen and history readings, cases, comparison, timing and its records. Input: { studyId }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.case.get","name":"Read one case","description":"One case of a study: steps, samples, readouts and its ISL program. Input: { studyId, caseId }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.comparison.get","name":"Read a comparison","description":"The comparison rows of a study or one case, with their indices. Input: { studyId, caseId?, aligned? }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.evaluations.get","name":"Read the parameter table and scorecard","description":"The one parameter table and the predictor scorecard as loaded. Input: {}. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.assumptions.get","name":"Read the assumptions register","description":"Every assumption: timing, readings of specimen and history, the model's parameters, the questions' defaults and the modelling decisions. Input: {}. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.emily.questions","name":"Read the questions for the reviewing physicist","description":"The questions page as a working list, with every recorded answer. Input: {}. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.emily.answer","name":"Record an answer","description":"Record the reviewing physicist's answer to a question; append-only. Input: { no, status, answer, source? }. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.reader.get","name":"Read a study's reader document","description":"The paper's text blocks, its tables and figures rebuilt as data with the model's value on every cell, and the comparison rows' links. Input: { studyId }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.reader.ask","name":"Ask the workspace about a study's paper","description":"An intent run in the harness: the judge chooses the experts (document, comparison, simulator, language, parameters), each step governed by its skill; the answer is composed from their evidence and its quotes checked. Input: { studyId, question, page?, object? }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.intent","name":"Ask the workspace a question","description":"The workspace's intent interface: the same expert plan, for any question about the studies, the model or the language. Input: { question, studyId? }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.emily.page","name":"Read one of the physicist's pages","description":"One of the published pages written for the reviewing physicist. Input: { slug }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.emily.page.part","name":"Read one part of a page","description":"One part of such a page, its commitments recomputed. Input: { slug, n }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.emily.page.quote","name":"Verify a quote on a page","description":"Whether words are those of such a page. Input: { slug, quote, part? }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.readiness.get","name":"Read the submission readiness","description":"The committed readiness, with the answers, frozen predictions and census added live. Input: {}. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.hypotheses.get","name":"Read the hypotheses register","description":"The committed hypotheses register. Input: {}. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.research.directory","name":"Read the people and labs directory","description":"Historical affiliations, currently listed roles, research interests and local paper holdings, with uncertainty preserved. Input: {}. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.report.get","name":"Read a study's report","description":"Our reproduction report of a study at the publishing gateway, any release. Input: { studyId, version? }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.report.part","name":"Read one part of a report","description":"One part of a report, every commitment recomputed from the relayed text. Input: { studyId, n, version? }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.quote.verify","name":"Verify a quote","description":"Whether words are a report's, block by block. Input: { studyId, quote, part?, version? }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.sources.anchors","name":"Link a study's facts to its paper","description":"Each reading, comparison row and step of a study linked to the paragraph, figure or table of the published original paper it comes from, with every quotation verified to a block. Members-only papers resolve only for members. Input: { studyId }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.papers.list","name":"List a study's original papers","description":"The original papers a report names as reproduced, pinned to their releases, and every reference resolved to a page. Papers published for members only are listed by name to a non-member. Input: { studyId }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.paper.page","name":"Read one page of a paper","description":"One page of an original paper: its text layer, anchors and the name of its image. Input: { studyId, slug, page, version? }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.paper.image","name":"Read one page image","description":"The page image, re-hashed against the name its signed page gives it, as a file part. Input: { studyId, slug, page, version? }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.assessments.list","name":"List assessments","description":"Stored assessments with their review state. Input: { studyId?, arm?, status?, limit? }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.assessment.get","name":"Read an assessment","description":"One assessment with its view, trail, review, attestations and run. Input: { assessmentId }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.budget.get","name":"The model budget","description":"What the runtime's model calls have cost against MODEL_SPEND_CAP_USD; at the cap no model call starts (refused as spend_cap_reached). Input: {}. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.ontology.get","name":"Read the ontology","description":"The classes, mechanisms, programs and vocabularies the runtime reasons with. A term (\"Qss\", \"wet O2\") answers the classes it names; an observable answers the mechanisms that govern or influence it and the programs a miss may lie at; no input answers the whole outline. Input: { term? | class? | enginePath? }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.reproductions.list","name":"List reproductions","description":"Stored reproductions with their review state. Input: { studyId?, caseId?, arm?, status?, limit? }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.reproduction.get","name":"Read a reproduction","description":"One reproduction with its view, the harness program, review, attestations and run. Input: { reproductionId }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.predictions.list","name":"List frozen predictions","description":"Frozen predictions, newest first. Input: {}. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.prediction.get","name":"Read a frozen prediction","description":"One frozen prediction with its commitment checked. Input: { predictionId }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.run.get","name":"Read a run, summarised","description":"A run's record reduced to its steps, governing skills and warnings. Input: { runRef }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.run.record","name":"Read a run record by ref","description":"A run's stored record by its ref: an ask's or an experiment's run. Input: { runRef, hydrate? }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.backlog.get","name":"Read the backlog","description":"Failing checks and change requests. Input: {}. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.changes.list","name":"List change requests","description":"Change requests with their rendered rows. Input: {}. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.release.get","name":"Read the release manifest","description":"Every decided record in a release manifest. Input: {}. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.lab.sets","name":"List the study sets","description":"The study sets an experiment can run over. Input: {}. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.lab.arms","name":"List the arms","description":"The arms with their model defaults. Input: {}. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.experiment.status","name":"Read an experiment's status","description":"Where an experiment stands. Input: { id }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.experiment.result","name":"Read an experiment's result","description":"An experiment's per-arm result. Input: { id }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.experiment.runs","name":"List an experiment's runs","description":"Every run of an experiment, by ref. Input: { id }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.census.status","name":"Read the parameter census job","description":"Where the parameter census job stands. Input: {}. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.review.record","name":"Record a review","description":"A reviewer receipt on an assessment or a reproduction, bound to its commitment. Input: { kind, id, verdict, note? }. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.ruling.record","name":"Record a ruling","description":"The chair's ruling on a split review. Input: { kind, id, chosen, reasoning }. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.decision.record","name":"Record a decision","description":"Record the decision the review authorises. High consequence: a decision case in metadata.decision. Input: { kind, id }. Access: a steward (their standing grant); HIGH CONSEQUENCE: a decision case in metadata.decision ({ approvedBy, approvedAt, why, restsOn }).","tags":["isl","workspace","act","tier:HighConsequence"]},{"id":"isl.change.open","name":"Open a change request","description":"A change request against a reading, a comparison row, a parameter or the language. Input: { kind, title, payload, studyId?, assessmentId?, reproductionId? }. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.change.handoff","name":"Hand off an adopted program change for applying","description":"An accepted program change request, adopted by code, handed off to be committed and the engine redeployed. High consequence: a decision case in metadata.decision. Input: { id }. Access: a steward (their standing grant); HIGH CONSEQUENCE: a decision case in metadata.decision ({ approvedBy, approvedAt, why, restsOn }).","tags":["isl","workspace","act","tier:HighConsequence"]},{"id":"isl.change.handoffs","name":"Program changes handed off","description":"Each handoff: the program, the change job holding the evaluated replacement (read it with isl.engine.report.get), the digest that must end up running, and whether it is verified. Input: {}. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.change.verify","name":"Verify an applied program change","description":"Reads the program the engine now runs; only if its digest equals the evaluated one is the request marked applied with the commit. Otherwise it stays open, with both digests. Input: { id, commit }. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.change.decide","name":"Decide a change request","description":"Accept, reject, withdraw or mark applied. Input: { id, action, ref?, note? }. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.assess","name":"Assess a study","description":"Run an assessment arm on a study. Input: { studyId, arm, caseId?, aligned?, direction? }. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.assessment.ask","name":"Ask a model about an assessment","description":"A model reads an assessment against the stored comparison. Input: { assessmentId }. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.reproduce","name":"Reproduce a case","description":"Run a reproduce arm on one case. Input: { studyId, caseId, arm, direction? }. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.rerun","name":"Rerun a case","description":"The predictor on a case's committed program, beside the committed numbers. Input: { studyId, caseId }. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.simulator.families","name":"List the simulator's families","description":"The interface families the simulator covers. Input: {}. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.simulator.simulate","name":"Simulate a recipe","description":"A stage recipe through the simulator. Input: { family?, wire_radius_nm?, stages[] }. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.simulator.preview","name":"Preview a prediction","description":"The predictor on a history; nothing is swept, checked or frozen. Input: { history, composition_gradient?, all_samples? }. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.checks.grid","name":"Run a grid of directional checks","description":"A grid of histories through the engine in chunks, every check evaluated over all of them; failed checks are the findings the discovery loop starts from. Governed by run-directional-checks. Input: { preset } | { histories: [{ id, history }], checks: [{ name, a, b, path, expect }], chunk? }. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.change.evaluate","name":"Evaluate one proposed change","description":"One change to one ISL program under experiments/, scored by the engine on training and held-out data and on every interface; adopted or rejected BY CODE (held-out improves, nothing worse, no check newly failing, parameters labelled, at most one added). Governed by revise-the-model. Input: { changeId, kind: \"physics\", program, replacement, rationale?, findingRefs?, parameters? }. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.discover","name":"Run the discovery loop","description":"From a completed grid: failed checks grouped by program; for each changeable program a model diagnoses and proposes ONE change (governed by revise-the-model and label-parameters, counted against the model budget); the engine evaluates it; code adopts or rejects. Adopted changes become program change requests; rejected ones are kept as negative results. Input: { gridRunRef, maxProposals? (1–6, default 3), model? }. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.discover.get","name":"Read a discovery run","description":"The loop's findings, each program's diagnosis and proposal, the change job, the decision with its reasons, and the change request opened. Input: { id }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.predict.freeze","name":"Predict and freeze","description":"A history run as written, swept over its open timing, checked for transferability and frozen. High consequence: a decision case in metadata.decision. Input: { history, supersedes? }. Access: a steward (their standing grant); HIGH CONSEQUENCE: a decision case in metadata.decision ({ approvedBy, approvedAt, why, restsOn }).","tags":["isl","workspace","act","tier:HighConsequence"]},{"id":"isl.experiment.start","name":"Start an experiment","description":"Studies × arms × repeats walked by a Durable Object. Input: { arms[], set? (as-stated|aligned), studies?, limit?, repeats?, id?, confirmSpend? } or { experiment }. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.experiment.cancel","name":"Cancel an experiment","description":"Stop an experiment's walk. Input: { id }. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.checks.directional","name":"Run the directional checks","description":"The published directional checks through the engine (about 30 s), each scored on sign alone; kept with the engine commit that produced it. Governed by skill:isl-agent/run-directional-checks. Input: {}. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.scorecard.run","name":"Regenerate the scorecard","description":"The predictor scorecard regenerated by the engine (over five minutes): a job, run by the door's driver; poll isl.engine.report.get with the run ref. Input: {}. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]},{"id":"isl.derived.get","name":"Derive quantities from a history","description":"The quantities the engine derives for one ISL history, each with its formula, support and what it is from; illustrative values are labelled as not predicted. Kept with the engine commit. Input: { history, window_eV? }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.engine.report.get","name":"Read an engine report","description":"One directional or scorecard report by run ref, with the engine commit that produced it. Input: { runRef }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.engine.reports.list","name":"List engine reports","description":"Directional and scorecard reports, newest first. Input: { kind?, limit? }. Access: a member or steward.","tags":["isl","workspace","read","tier:ReadOrDraft"]},{"id":"isl.census.run","name":"Run the parameter census","description":"Start or resume the parameter census job: one study per step, warmed, retried through a cold engine, resumable. Input: { restart? }. Access: a steward (their standing grant).","tags":["isl","workspace","act","tier:ProtectedMutation"]}],"provider":{"organization":"ISL discovery harness","url":"https://isl-a2a.faithnet.io"},"securitySchemes":{"bearer":{"httpAuthSecurityScheme":{"scheme":"Bearer","bearerFormat":"a faithnet Home id_token","description":"A person's Home session: the grants the Home reports decide (a member reads, a steward acts on their standing stewardship grant)."}},"A2A-Session":{"httpAuthSecurityScheme":{"scheme":"A2A-Session","bearerFormat":"0x51 session-wrapped caller assertion over an on-chain delegation","description":"An agent's session wire, verified on chain when this deployment is configured for it."}},"homeSession":{"httpAuthSecurityScheme":{"scheme":"bearer","bearerFormat":"home-session","description":"A Home session presented as a bearer names the asking person; it grants nothing (spec 372 §0)."}}},"securityRequirements":[{"schemes":{"homeSession":{"list":[]}}}],"agentAddress":"0x37407683b224e15029fdae24ad0b7509681af17c","protocolVersion":"1.0"}