SpecPilot

Previous value: -"The complete SpecPilot answer set to generate from - everything collected through specpilot_next_questions. projectName and projectDescription are required; every other field falls back to a sensible default."New value: +"The complete SpecPilot answer set to generate from - everything collected through specpilot_next_questions, whose schema describes each field. projectName and projectDescription are required; every other field falls back to a sensible default."

Removed value: -"The access control model. Drives the security spec auth/authorization section and the permission model."

Removed value: -"Anything further on accessibility or constraints, in free text."

Removed value: -"Roughly how many active users are expected, as a range."

Removed value: -"Target API response time."

Removed value: -"API style - REST, GraphQL, gRPC or tRPC. Shapes how the architecture spec documents client-server communication."

Removed value: -"Auth approach - a protocol built in-house (JWT/OAuth/SAML) or a managed service (Clerk, Auth0, Firebase). Feeds the security spec."

Removed value: -"Availability SLA target as a fraction of uptime; higher percentages allow far less downtime per year."

Removed value: -"How long the build is expected to take."

Removed value: -"CI/CD practices - automatically running tests and deploying on every change."

Removed value: -"Compliance regimes that apply - GDPR, HIPAA, SOC 2. Pick by the actual situation (EU users, health data, payments), since getting it wrong has legal consequences."

Removed value: -"More detail on whatever was named in technicalConstraints."

Removed value: -"A user type in free text, when none of the userTypes options fit."

Removed value: -"How conflicting local and server state gets reconciled once the device is back online."

Removed value: -"Database kinds in use - SQL, NoSQL, cache/key-value, vector. As many as apply."

Removed value: -"Where this ships - cloud hosting, a package registry, a browser store. The option list depends on the project type."

Removed value: -"The developer GitHub handle. Optional; it namespaces generated task IDs (e.g. CD-jsmith-001). Infer from git config or the origin remote."

Removed value: -"The editor or AI IDE in use - claudecode, cursor, copilot, codex, windsurf. You are the IDE, so set this yourself; it decides which rules and config files are generated."

Removed value: -"Third-party integrations keyed by category, e.g. { payments: [\"stripe\"] }. Only categories relevant to the project type apply."

Removed value: -"True for a greenfield project, false when adding onto an existing codebase. Decides which onboarding analysis is generated at the end."

Removed value: -"Primary language, when it should override what SpecPilot infers from the repo."

Removed value: -"On-device stores backing offline support. Leave empty when offline is not needed."

Removed value: -"What this project explicitly will NOT do. Becomes the non-goals section of the specs."

Removed value: -"Whether this has to work offline. Set automatically when localDatabases is non-empty."

Removed value: -"External APIs or services not covered by integrations."

Removed value: -"Platforms this should run on, e.g. web, ios, android, desktop. Infer from the dependency manifests and repo layout."

Removed value: -"Project archetype. Normally inferred from projectDescription when it exactly matches a returned chip label - send it only if you already know it."

Removed value: -"One line saying what the project is. Required by specpilot_generate_specs. Sending one of the chip labels returned by specpilot_next_questions verbatim is what infers projectCategory and gates every later question; free prose infers nothing."

Removed value: -"Short name for the project. Required by specpilot_generate_specs. Infer from the package manifest or the folder name."

Removed value: -"Whether anything updates live without a refresh. Set automatically when realtimeTypes is non-empty."

Removed value: -"Realtime transports - WebSockets, SSE, polling. Leave empty when nothing needs to update live."

Removed value: -"Expected scale of the system. Drives infrastructure and architecture choices."

Removed value: -"Security measures to plan for - encryption, rate limiting, audit logging."

Removed value: -"Cross-cutting concerns that apply, such as accessibility, internationalisation or offline support."

Removed value: -"Architecture pattern - monolith, modular monolith, or microservices."

Removed value: -"How many people are building this."

Removed value: -"Hard constraints - budget, existing infrastructure, legacy systems, a fixed deadline."

Removed value: -"Testing approaches this project will use."

Removed value: -"Who is going to use this system, e.g. end users, admins, internal staff."

Previous value: -"The access control model. Drives the security spec auth/authorization section and the permission model."New value: +"The access control model."

Previous value: -"API style - REST, GraphQL, gRPC or tRPC. Shapes how the architecture spec documents client-server communication."New value: +"API style - REST, GraphQL, gRPC or tRPC."

Previous value: -"Auth approach - a protocol built in-house (JWT/OAuth/SAML) or a managed service (Clerk, Auth0, Firebase). Feeds the security spec."New value: +"Auth approach - a protocol built in-house (JWT/OAuth/SAML) or a managed service (Clerk, Auth0, Firebase)."

Previous value: -"Availability SLA target as a fraction of uptime; higher percentages allow far less downtime per year."New value: +"Availability SLA target as a fraction of uptime."

Previous value: -"Compliance regimes that apply - GDPR, HIPAA, SOC 2. Pick by the actual situation (EU users, health data, payments), since getting it wrong has legal consequences."New value: +"Compliance regimes that apply - GDPR, HIPAA, SOC 2. Pick by the actual situation (EU users, health data, payments)."

Previous value: -"The developer GitHub handle. Optional; it namespaces generated task IDs (e.g. CD-jsmith-001). Infer from git config or the origin remote."New value: +"The developer GitHub handle. Optional. Infer from git config or the origin remote."

Previous value: -"The editor or AI IDE in use - claudecode, cursor, copilot, codex, windsurf. You are the IDE, so set this yourself; it decides which rules and config files are generated."New value: +"The editor or AI IDE in use - claudecode, cursor, copilot, codex, windsurf. You are the IDE, so set this yourself."

Previous value: -"True for a greenfield project, false when adding onto an existing codebase. Decides which onboarding analysis is generated at the end."New value: +"True for a greenfield project, false when adding onto an existing codebase."

Previous value: -"What this project explicitly will NOT do. Becomes the non-goals section of the specs."New value: +"What this project explicitly will NOT do."

Previous value: -"Expected scale of the system. Drives infrastructure and architecture choices."New value: +"Expected scale of the system."

Previous value: -"The access control model. Drives the security spec auth/authorization section and the permission model."New value: +"The access control model."

Previous value: -"API style - REST, GraphQL, gRPC or tRPC. Shapes how the architecture spec documents client-server communication."New value: +"API style - REST, GraphQL, gRPC or tRPC."

Previous value: -"Auth approach - a protocol built in-house (JWT/OAuth/SAML) or a managed service (Clerk, Auth0, Firebase). Feeds the security spec."New value: +"Auth approach - a protocol built in-house (JWT/OAuth/SAML) or a managed service (Clerk, Auth0, Firebase)."

Previous value: -"Availability SLA target as a fraction of uptime; higher percentages allow far less downtime per year."New value: +"Availability SLA target as a fraction of uptime."

Previous value: -"Compliance regimes that apply - GDPR, HIPAA, SOC 2. Pick by the actual situation (EU users, health data, payments), since getting it wrong has legal consequences."New value: +"Compliance regimes that apply - GDPR, HIPAA, SOC 2. Pick by the actual situation (EU users, health data, payments)."

Previous value: -"The developer GitHub handle. Optional; it namespaces generated task IDs (e.g. CD-jsmith-001). Infer from git config or the origin remote."New value: +"The developer GitHub handle. Optional. Infer from git config or the origin remote."

Previous value: -"The editor or AI IDE in use - claudecode, cursor, copilot, codex, windsurf. You are the IDE, so set this yourself; it decides which rules and config files are generated."New value: +"The editor or AI IDE in use - claudecode, cursor, copilot, codex, windsurf. You are the IDE, so set this yourself."

Previous value: -"True for a greenfield project, false when adding onto an existing codebase. Decides which onboarding analysis is generated at the end."New value: +"True for a greenfield project, false when adding onto an existing codebase."

Previous value: -"What this project explicitly will NOT do. Becomes the non-goals section of the specs."New value: +"What this project explicitly will NOT do."

Previous value: -"Expected scale of the system. Drives infrastructure and architecture choices."New value: +"Expected scale of the system."

Added value: +"The complete SpecPilot answer set to generate from - everything collected through specpilot_next_questions. projectName and projectDescription are required; every other field falls back to a sensible default."

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "fileCount": {
+      "description": "How many files were generated.",
+      "type": "number"
+    },
+    "files": {
+      "description": "Every file to write - spec files, the .specs/ README, and IDE or repository config.",
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "content": {
+            "description": "Full file contents to write verbatim.",
+            "type": "string"
+          },
+          "path": {
+            "description": "Path to write, relative to the repository root. Do not rename it.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "path",
+          "content"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "nextSteps": {
+      "description": "What to do after writing the files, including where each path belongs.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "files",
+    "fileCount",
+    "nextSteps"
+  ],
+  "type": "object"
+}

Added value: +"Every SpecPilot onboarding answer collected so far. The server is stateless, so resend the whole object on every call; omit it entirely on the first call to get step 1."

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "answers": {
+      "additionalProperties": false,
+      "description": "Every answer as the server now understands it, including defaults and seeded values. Send this back on the next call.",
+      "properties": {
+        "accessControl": {
+          "description": "The access control model. Drives the security spec auth/authorization section and the permission model.",
+          "type": "string"
+        },
+        "accessibilityNotes": {
+          "description": "Anything further on accessibility or constraints, in free text.",
+          "type": "string"
+        },
+        "activeUsers": {
+          "description": "Roughly how many active users are expected, as a range.",
+          "type": "string"
+        },
+        "apiResponseTime": {
+          "description": "Target API response time.",
+          "type": "string"
+        },
+        "apiStyle": {
+          "description": "API style - REST, GraphQL, gRPC or tRPC. Shapes how the architecture spec documents client-server communication.",
+          "type": "string"
+        },
+        "authStrategy": {
+          "description": "Auth approach - a protocol built in-house (JWT/OAuth/SAML) or a managed service (Clerk, Auth0, Firebase). Feeds the security spec.",
+          "type": "string"
+        },
+        "availability": {
+          "description": "Availability SLA target as a fraction of uptime; higher percentages allow far less downtime per year.",
+          "type": "string"
+        },
+        "buildTimeline": {
+          "description": "How long the build is expected to take.",
+          "type": "string"
+        },
+        "cicd": {
+          "description": "CI/CD practices - automatically running tests and deploying on every change.",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "compliance": {
+          "description": "Compliance regimes that apply - GDPR, HIPAA, SOC 2. Pick by the actual situation (EU users, health data, payments), since getting it wrong has legal consequences.",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "constraintDescription": {
+          "description": "More detail on whatever was named in technicalConstraints.",
+          "type": "string"
+        },
+        "customUserType": {
+          "description": "A user type in free text, when none of the userTypes options fit.",
+          "type": "string"
+        },
+        "dataSyncStrategy": {
+          "description": "How conflicting local and server state gets reconciled once the device is back online.",
+          "type": "string"
+        },
+        "databases": {
+          "description": "Database kinds in use - SQL, NoSQL, cache/key-value, vector. As many as apply.",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "deploymentTargets": {
+          "description": "Where this ships - cloud hosting, a package registry, a browser store. The option list depends on the project type.",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "handle": {
+          "description": "The developer GitHub handle. Optional; it namespaces generated task IDs (e.g. CD-jsmith-001). Infer from git config or the origin remote.",
+          "type": "string"
+        },
+        "ideAgent": {
+          "description": "The editor or AI IDE in use - claudecode, cursor, copilot, codex, windsurf. You are the IDE, so set this yourself; it decides which rules and config files are generated.",
+          "type": "string"
+        },
+        "integrations": {
+          "additionalProperties": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "description": "Third-party integrations keyed by category, e.g. { payments: [\"stripe\"] }. Only categories relevant to the project type apply.",
+          "propertyNames": {
+            "type": "string"
+          },
+          "type": "object"
+        },
+        "isNewBuild": {
+          "description": "True for a greenfield project, false when adding onto an existing codebase. Decides which onboarding analysis is generated at the end.",
+          "type": "boolean"
+        },
+        "languageOverride": {
+          "description": "Primary language, when it should override what SpecPilot infers from the repo.",
+          "type": "string"
+        },
+        "localDatabases": {
+          "description": "On-device stores backing offline support. Leave empty when offline is not needed.",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "nonGoals": {
+          "description": "What this project explicitly will NOT do. Becomes the non-goals section of the specs.",
+          "type": "string"
+        },
+        "offlineSupport": {
+          "description": "Whether this has to work offline. Set automatically when localDatabases is non-empty.",
+          "type": "boolean"
+        },
+        "otherApis": {
+          "description": "External APIs or services not covered by integrations.",
+          "type": "string"
+        },
+        "platforms": {
+          "description": "Platforms this should run on, e.g. web, ios, android, desktop. Infer from the dependency manifests and repo layout.",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "projectCategory": {
+          "anyOf": [
+            {
+              "enum": [
+                "saas",
+                "api",
+                "mobile",
+                "cli",
+                "pipeline",
+                "ml",
+                "static",
+                "docs",
+                "extension",
+                "library",
+                "other"
+              ],
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "description": "Project archetype. Normally inferred from projectDescription when it exactly matches a returned chip label - send it only if you already know it."
+        },
+        "projectDescription": {
+          "description": "One line saying what the project is. Required by specpilot_generate_specs. Sending one of the chip labels returned by specpilot_next_questions verbatim is what infers projectCategory and gates every later question; free prose infers nothing.",
+          "type": "string"
+        },
+        "projectName": {
+          "description": "Short name for the project. Required by specpilot_generate_specs. Infer from the package manifest or the folder name.",
+          "type": "string"
+        },
+        "realtimeEnabled": {
+          "description": "Whether anything updates live without a refresh. Set automatically when realtimeTypes is non-empty.",
+          "type": "boolean"
+        },
+        "realtimeTypes": {
+          "description": "Realtime transports - WebSockets, SSE, polling. Leave empty when nothing needs to update live.",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "scaleTier": {
+          "description": "Expected scale of the system. Drives infrastructure and architecture choices.",
+          "type": "string"
+        },
+        "securityConcerns": {
+          "description": "Security measures to plan for - encryption, rate limiting, audit logging.",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "specialConsiderations": {
+          "description": "Cross-cutting concerns that apply, such as accessibility, internationalisation or offline support.",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "systemPattern": {
+          "description": "Architecture pattern - monolith, modular monolith, or microservices.",
+          "type": "string"
+        },
+        "teamSize": {
+          "description": "How many people are building this.",
+          "type": "string"
+        },
+        "technicalConstraints": {
+          "description": "Hard constraints - budget, existing infrastructure, legacy systems, a fixed deadline.",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "testingStrategy": {
+          "description": "Testing approaches this project will use.",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "userTypes": {
+          "description": "Who is going to use this system, e.g. end users, admins, internal staff.",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        }
+      },
+      "type": "object"
+    },
+    "done": {
+      "description": "True when every applicable question is answered and specpilot_generate_specs can be called.",
+      "type": "boolean"
+    },
+    "questions": {
+      "description": "The still-unanswered questions of the next incomplete step. Empty when done.",
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "allowCustom": {
+            "description": "True when a value outside the listed options is accepted.",
+            "type": "boolean"
+          },
+          "field": {
+            "description": "The answers field this question fills - send the reply under this key.",
+            "type": "string"
+          },
+          "groups": {
+            "description": "Choices arranged into groups, for grouped questions.",
+            "items": {
+              "additionalProperties": false,
+              "properties": {
+                "group": {
+                  "description": "Group heading.",
+                  "type": "string"
+                },
+                "items": {
+                  "description": "Options within this group.",
+                  "items": {
+                    "additionalProperties": false,
+                    "properties": {
+                      "badge": {
+                        "description": "recommended marks a suggested choice; flagged marks one that needs care.",
+                        "enum": [
+                          "recommended",
+                          "flagged"
+                        ],
+                        "type": "string"
+                      },
+                      "description": {
+                        "description": "Longer explanation of what choosing this means.",
+                        "type": "string"
+                      },
+                      "group": {
+                        "description": "Group this option belongs to.",
+                        "type": "string"
+                      },
+                      "id": {
+                        "description": "Value to send back for this option.",
+                        "type": "string"
+                      },
+                      "label": {
+                        "description": "Human-readable label shown to the developer.",
+                        "type": "string"
+                      },
+                      "warning": {
+                        "description": "Caveat to surface to the developer before they pick this.",
+                        "type": "string"
+                      }
+                    },
+                    "required": [
+                      "id",
+                      "label"
+                    ],
+                    "type": "object"
+                  },
+                  "type": "array"
+                }
+              },
+              "required": [
+                "group",
+                "items"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "id": {
+            "description": "Stable question id.",
+            "type": "string"
+          },
+          "optional": {
+            "description": "True when the question may be answered with an empty value to decline it.",
+            "type": "boolean"
+          },
+          "options": {
+            "description": "Choices for a select-style question.",
+            "items": {
+              "additionalProperties": false,
+              "properties": {
+                "badge": {
+                  "description": "recommended marks a suggested choice; flagged marks one that needs care.",
+                  "enum": [
+                    "recommended",
+                    "flagged"
+                  ],
+                  "type": "string"
+                },
+                "description": {
+                  "description": "Longer explanation of what choosing this means.",
+                  "type": "string"
+                },
+                "group": {
+                  "description": "Group this option belongs to.",
+                  "type": "string"
+                },
+                "id": {
+                  "description": "Value to send back for this option.",
+                  "type": "string"
+                },
+                "label": {
+                  "description": "Human-readable label shown to the developer.",
+                  "type": "string"
+                },
+                "warning": {
+                  "description": "Caveat to surface to the developer before they pick this.",
+                  "type": "string"
+                }
+              },
+              "required": [
+                "id",
+                "label"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "prompt": {
+            "description": "The question text, rendered against the answers so far.",
+            "type": "string"
+          },
+          "required": {
+            "description": "True when a non-empty answer is needed to move on.",
+            "type": "boolean"
+          },
+          "todoSentinel": {
+            "description": "Send this exact value when the developer does not know yet.",
+            "type": "string"
+          },
+          "type": {
+            "description": "Shape of the expected answer, e.g. text, single-select, multi-select.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "field",
+          "type",
+          "prompt"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "step": {
+      "description": "Number of the step these questions belong to.",
+      "type": "number"
+    },
+    "stepLabel": {
+      "description": "Human-readable name of that step, e.g. \"Scale & deploy\".",
+      "type": "string"
+    }
+  },
+  "required": [
+    "done",
+    "questions",
+    "answers"
+  ],
+  "type": "object"
+}

Added value: +"The access control model. Drives the security spec auth/authorization section and the permission model."

Added value: +"Anything further on accessibility or constraints, in free text."

Added value: +"Roughly how many active users are expected, as a range."

Added value: +"Target API response time."

Added value: +"API style - REST, GraphQL, gRPC or tRPC. Shapes how the architecture spec documents client-server communication."

Added value: +"Auth approach - a protocol built in-house (JWT/OAuth/SAML) or a managed service (Clerk, Auth0, Firebase). Feeds the security spec."

Added value: +"Availability SLA target as a fraction of uptime; higher percentages allow far less downtime per year."

Added value: +"How long the build is expected to take."

Added value: +"CI/CD practices - automatically running tests and deploying on every change."

Added value: +"Compliance regimes that apply - GDPR, HIPAA, SOC 2. Pick by the actual situation (EU users, health data, payments), since getting it wrong has legal consequences."

Added value: +"More detail on whatever was named in technicalConstraints."

Added value: +"A user type in free text, when none of the userTypes options fit."

Added value: +"How conflicting local and server state gets reconciled once the device is back online."

Added value: +"Database kinds in use - SQL, NoSQL, cache/key-value, vector. As many as apply."

Added value: +"Where this ships - cloud hosting, a package registry, a browser store. The option list depends on the project type."

Added value: +"The developer GitHub handle. Optional; it namespaces generated task IDs (e.g. CD-jsmith-001). Infer from git config or the origin remote."

Added value: +"The editor or AI IDE in use - claudecode, cursor, copilot, codex, windsurf. You are the IDE, so set this yourself; it decides which rules and config files are generated."

Added value: +"Third-party integrations keyed by category, e.g. { payments: [\"stripe\"] }. Only categories relevant to the project type apply."

Added value: +"True for a greenfield project, false when adding onto an existing codebase. Decides which onboarding analysis is generated at the end."

Added value: +"Primary language, when it should override what SpecPilot infers from the repo."

Added value: +"On-device stores backing offline support. Leave empty when offline is not needed."

Added value: +"What this project explicitly will NOT do. Becomes the non-goals section of the specs."

Added value: +"Whether this has to work offline. Set automatically when localDatabases is non-empty."

Added value: +"External APIs or services not covered by integrations."

Added value: +"Platforms this should run on, e.g. web, ios, android, desktop. Infer from the dependency manifests and repo layout."

Added value: +"Project archetype. Normally inferred from projectDescription when it exactly matches a returned chip label - send it only if you already know it."

Added value: +"One line saying what the project is. Required by specpilot_generate_specs. Sending one of the chip labels returned by specpilot_next_questions verbatim is what infers projectCategory and gates every later question; free prose infers nothing."

Added value: +"Short name for the project. Required by specpilot_generate_specs. Infer from the package manifest or the folder name."

Added value: +"Whether anything updates live without a refresh. Set automatically when realtimeTypes is non-empty."

Added value: +"Realtime transports - WebSockets, SSE, polling. Leave empty when nothing needs to update live."

Added value: +"Expected scale of the system. Drives infrastructure and architecture choices."

Added value: +"Security measures to plan for - encryption, rate limiting, audit logging."

Added value: +"Cross-cutting concerns that apply, such as accessibility, internationalisation or offline support."

Added value: +"Architecture pattern - monolith, modular monolith, or microservices."

Added value: +"How many people are building this."

Added value: +"Hard constraints - budget, existing infrastructure, legacy systems, a fixed deadline."

Added value: +"Testing approaches this project will use."

Added value: +"Who is going to use this system, e.g. end users, admins, internal staff."

Added value: +"The access control model. Drives the security spec auth/authorization section and the permission model."

Added value: +"Anything further on accessibility or constraints, in free text."

Added value: +"Roughly how many active users are expected, as a range."

Added value: +"Target API response time."

Added value: +"API style - REST, GraphQL, gRPC or tRPC. Shapes how the architecture spec documents client-server communication."

Added value: +"Auth approach - a protocol built in-house (JWT/OAuth/SAML) or a managed service (Clerk, Auth0, Firebase). Feeds the security spec."

Added value: +"Availability SLA target as a fraction of uptime; higher percentages allow far less downtime per year."

Added value: +"How long the build is expected to take."

Added value: +"CI/CD practices - automatically running tests and deploying on every change."

Added value: +"Compliance regimes that apply - GDPR, HIPAA, SOC 2. Pick by the actual situation (EU users, health data, payments), since getting it wrong has legal consequences."

Added value: +"More detail on whatever was named in technicalConstraints."

Added value: +"A user type in free text, when none of the userTypes options fit."

Added value: +"How conflicting local and server state gets reconciled once the device is back online."

Added value: +"Database kinds in use - SQL, NoSQL, cache/key-value, vector. As many as apply."

Added value: +"Where this ships - cloud hosting, a package registry, a browser store. The option list depends on the project type."

Added value: +"The developer GitHub handle. Optional; it namespaces generated task IDs (e.g. CD-jsmith-001). Infer from git config or the origin remote."

Added value: +"The editor or AI IDE in use - claudecode, cursor, copilot, codex, windsurf. You are the IDE, so set this yourself; it decides which rules and config files are generated."

Added value: +"Third-party integrations keyed by category, e.g. { payments: [\"stripe\"] }. Only categories relevant to the project type apply."

Added value: +"True for a greenfield project, false when adding onto an existing codebase. Decides which onboarding analysis is generated at the end."

Added value: +"Primary language, when it should override what SpecPilot infers from the repo."

Added value: +"On-device stores backing offline support. Leave empty when offline is not needed."

Added value: +"What this project explicitly will NOT do. Becomes the non-goals section of the specs."

Added value: +"Whether this has to work offline. Set automatically when localDatabases is non-empty."

Added value: +"External APIs or services not covered by integrations."

Added value: +"Platforms this should run on, e.g. web, ios, android, desktop. Infer from the dependency manifests and repo layout."

Added value: +"Project archetype. Normally inferred from projectDescription when it exactly matches a returned chip label - send it only if you already know it."

Added value: +"One line saying what the project is. Required by specpilot_generate_specs. Sending one of the chip labels returned by specpilot_next_questions verbatim is what infers projectCategory and gates every later question; free prose infers nothing."

Added value: +"Short name for the project. Required by specpilot_generate_specs. Infer from the package manifest or the folder name."

Added value: +"Whether anything updates live without a refresh. Set automatically when realtimeTypes is non-empty."

Added value: +"Realtime transports - WebSockets, SSE, polling. Leave empty when nothing needs to update live."

Added value: +"Expected scale of the system. Drives infrastructure and architecture choices."

Added value: +"Security measures to plan for - encryption, rate limiting, audit logging."

Added value: +"Cross-cutting concerns that apply, such as accessibility, internationalisation or offline support."

Added value: +"Architecture pattern - monolith, modular monolith, or microservices."

Added value: +"How many people are building this."

Added value: +"Hard constraints - budget, existing infrastructure, legacy systems, a fixed deadline."

Added value: +"Testing approaches this project will use."

Added value: +"Who is going to use this system, e.g. end users, admins, internal staff."