refactor: narrow what devup-mcp asks for and what it sends back

[owjs3901]

See the two commit messages for the full reasoning. Summary:

Tools 9 -> 7. devup_figma_to_ui and devup_figma_to_json were devup_figma_export with one entry in outputs. Every client carried three schemas and had to choose between them on each call.

sourcePolicy removed. auto and direct both meant the direct connection; it never branched, and it was part of a cache key it could not affect.

Closed sets published in the schema. action, scope, rootLayout, delivery, match, project-context scope, stack-diff layers - one shared constant read by both the schema and the parser.

Caller mistakes are INVALID_PARAMS. Everything used to arrive as INTERNAL_ERROR, so "you passed a scope this tool does not have" and "Figma stopped answering" were indistinguishable at the protocol level.

Response stops restating itself. Measured: a tsx-only export 2,411 -> 1,405 B; the part carried regardless 1,911 -> 994 B. fidelity/completenessReport are sent when they disagree with a clean grade or when includeDiagnostics asks. deliverable stays - a consumer relies on it.

A lost token is no longer silent. A binding whose variable/style the catalog never named was resolved to a raw value with nothing reported, inside a response graded exact. It now raises DEVUP_CODEGEN_TOKEN_NAME_UNRESOLVED and stops quality.projection reading exact. Generated bytes unchanged; 268 plugin goldens untouched.

Releases stop shipping devup-mcp-visual (harness builds it from source; nothing downloads it), and Cargo.lock is committed at the released version, which stops every release binary reporting its build id as -dirty.

[github-actions]

Changepacks

devup-mcp@0.2.1 → 0.3.0 - crates/devup-mcp/Cargo.toml

Minor

• Narrow what devup-mcp asks for and what it sends back, and make a refusal say which of the two kinds it is. Nine tools become seven: devup_figma_to_ui and devup_figma_to_json were devup_figma_export with a single entry in outputs, so every client carried three schemas in its context and had to decide between them on every call, and the export tool's own description had to spend a sentence saying which to prefer. Use outputs: [tsx] and outputs: [devupJson] instead. sourcePolicy is gone from all of them: auto and direct both meant the direct connection and the parameter never branched, so it only ever offered a caller something to get wrong, and it was also part of the artifact cache key it could not affect. Every remaining closed-set input now publishes its accepted values in the JSON schema - action, scope, rootLayout, delivery, match, project context scope and stack diff layers - from one shared constant the parser reads too, so the schema cannot drift from what is accepted and a caller stops discovering the set one rejection at a time; outputs and the asset format were the only two that already did this. Errors are no longer all INTERNAL_ERROR. A mistake in the call itself - an unknown scope, a node that is not in the file, an expired artifactId - is now JSON-RPC INVALID_PARAMS, and everything behind the call stays INTERNAL_ERROR, so an agent can tell 'fix the arguments and retry' from 'stop and report' without parsing the message; the exact code and retryable are unchanged in data. Pure argument validation that had been reported as DEVUP_THEME_CONFLICT or DEVUP_SNAPSHOT_UNSUPPORTED is DEVUP_INVALID_INPUT, so a real theme conflict is no longer confused with a typo. The response is lighter for the same content. Measured on one export, a tsx-only call went from 2,411 to 1,405 bytes and the part every response carries regardless from 1,911 to 994. fidelity and completenessReport are the drill-down beneath quality and on a clean result restate it - 100% across six axes, six empty arrays - so they are sent when the result is not exact or complete, or when includeDiagnostics asks for them; on a Section export that was per screen. imports, usedTokens, componentImports, responsiveImports and responsiveComponents restated the tsx's own import line and its $tokens and are gone. deliverable stays: it was removed on the reasoning that the needs_figma handoff it guarded against is gone, and a consumer reported relying on it to know which value is the answer, which settles it. The server instructions were the larger cost and are corrected: they told every agent to take tsx, rawSnapshot and sourceMap together, which on the same measurement is about eight times the bytes of the code, and they now say to ask for an output only when it will be read. completeness and themeCompleteness stay - they grade how far token resolution reached, which quality does not say. Releases stop shipping devup-mcp-visual: the render harness builds it from source with cargo and nothing downloads it, so three of six assets were binaries no consumer used, built on every platform of every release. Cargo.lock is committed at the released version, which stops every release binary reporting its build id as -dirty and losing the ability to tell a release from a developer's working tree. Also removes two ErrorCode variants no production code ever constructed, whose only reference was a test pinning their wire strings - a test that would have passed forever whether or not they were reachable. A binding the resource catalog never named is now reported rather than quietly resolved. A fill bound to a variable, or a text carrying a style, is the design saying this is a token; the generator writes the token when the catalog carried that resource and the resolved value when it did not, and it has to write something because the module still has to compile. It said nothing when it did, so a hardcoded #7d7f83 could sit where the design says - identical today, no longer following the theme tomorrow - inside a response graded exact. Each such binding now raises DEVUP_CODEGEN_TOKEN_NAME_UNRESOLVED carrying the node, the property and the resource id, which also stops quality.projection reading exact. The check runs as a pass over the collected subtree rather than inside rendering, so it can name the node without threading an argument through the render functions, and the 268 plugin-parity goldens are unaffected because the generated bytes do not change.

devup-mcp-devup-ui@0.2.1 → 0.3.0 - crates/devup-mcp-devup-ui/Cargo.toml

Minor

• Narrow what devup-mcp asks for and what it sends back, and make a refusal say which of the two kinds it is. Nine tools become seven: devup_figma_to_ui and devup_figma_to_json were devup_figma_export with a single entry in outputs, so every client carried three schemas in its context and had to decide between them on every call, and the export tool's own description had to spend a sentence saying which to prefer. Use outputs: [tsx] and outputs: [devupJson] instead. sourcePolicy is gone from all of them: auto and direct both meant the direct connection and the parameter never branched, so it only ever offered a caller something to get wrong, and it was also part of the artifact cache key it could not affect. Every remaining closed-set input now publishes its accepted values in the JSON schema - action, scope, rootLayout, delivery, match, project context scope and stack diff layers - from one shared constant the parser reads too, so the schema cannot drift from what is accepted and a caller stops discovering the set one rejection at a time; outputs and the asset format were the only two that already did this. Errors are no longer all INTERNAL_ERROR. A mistake in the call itself - an unknown scope, a node that is not in the file, an expired artifactId - is now JSON-RPC INVALID_PARAMS, and everything behind the call stays INTERNAL_ERROR, so an agent can tell 'fix the arguments and retry' from 'stop and report' without parsing the message; the exact code and retryable are unchanged in data. Pure argument validation that had been reported as DEVUP_THEME_CONFLICT or DEVUP_SNAPSHOT_UNSUPPORTED is DEVUP_INVALID_INPUT, so a real theme conflict is no longer confused with a typo. The response is lighter for the same content. Measured on one export, a tsx-only call went from 2,411 to 1,405 bytes and the part every response carries regardless from 1,911 to 994. fidelity and completenessReport are the drill-down beneath quality and on a clean result restate it - 100% across six axes, six empty arrays - so they are sent when the result is not exact or complete, or when includeDiagnostics asks for them; on a Section export that was per screen. imports, usedTokens, componentImports, responsiveImports and responsiveComponents restated the tsx's own import line and its $tokens and are gone. deliverable stays: it was removed on the reasoning that the needs_figma handoff it guarded against is gone, and a consumer reported relying on it to know which value is the answer, which settles it. The server instructions were the larger cost and are corrected: they told every agent to take tsx, rawSnapshot and sourceMap together, which on the same measurement is about eight times the bytes of the code, and they now say to ask for an output only when it will be read. completeness and themeCompleteness stay - they grade how far token resolution reached, which quality does not say. Releases stop shipping devup-mcp-visual: the render harness builds it from source with cargo and nothing downloads it, so three of six assets were binaries no consumer used, built on every platform of every release. Cargo.lock is committed at the released version, which stops every release binary reporting its build id as -dirty and losing the ability to tell a release from a developer's working tree. Also removes two ErrorCode variants no production code ever constructed, whose only reference was a test pinning their wire strings - a test that would have passed forever whether or not they were reachable. A binding the resource catalog never named is now reported rather than quietly resolved. A fill bound to a variable, or a text carrying a style, is the design saying this is a token; the generator writes the token when the catalog carried that resource and the resolved value when it did not, and it has to write something because the module still has to compile. It said nothing when it did, so a hardcoded #7d7f83 could sit where the design says - identical today, no longer following the theme tomorrow - inside a response graded exact. Each such binding now raises DEVUP_CODEGEN_TOKEN_NAME_UNRESOLVED carrying the node, the property and the resource id, which also stops quality.projection reading exact. The check runs as a pass over the collected subtree rather than inside rendering, so it can name the node without threading an argument through the render functions, and the 268 plugin-parity goldens are unaffected because the generated bytes do not change.

devup-mcp-figma@0.2.1 → 0.3.0 - crates/devup-mcp-figma/Cargo.toml

Minor

• Narrow what devup-mcp asks for and what it sends back, and make a refusal say which of the two kinds it is. Nine tools become seven: devup_figma_to_ui and devup_figma_to_json were devup_figma_export with a single entry in outputs, so every client carried three schemas in its context and had to decide between them on every call, and the export tool's own description had to spend a sentence saying which to prefer. Use outputs: [tsx] and outputs: [devupJson] instead. sourcePolicy is gone from all of them: auto and direct both meant the direct connection and the parameter never branched, so it only ever offered a caller something to get wrong, and it was also part of the artifact cache key it could not affect. Every remaining closed-set input now publishes its accepted values in the JSON schema - action, scope, rootLayout, delivery, match, project context scope and stack diff layers - from one shared constant the parser reads too, so the schema cannot drift from what is accepted and a caller stops discovering the set one rejection at a time; outputs and the asset format were the only two that already did this. Errors are no longer all INTERNAL_ERROR. A mistake in the call itself - an unknown scope, a node that is not in the file, an expired artifactId - is now JSON-RPC INVALID_PARAMS, and everything behind the call stays INTERNAL_ERROR, so an agent can tell 'fix the arguments and retry' from 'stop and report' without parsing the message; the exact code and retryable are unchanged in data. Pure argument validation that had been reported as DEVUP_THEME_CONFLICT or DEVUP_SNAPSHOT_UNSUPPORTED is DEVUP_INVALID_INPUT, so a real theme conflict is no longer confused with a typo. The response is lighter for the same content. Measured on one export, a tsx-only call went from 2,411 to 1,405 bytes and the part every response carries regardless from 1,911 to 994. fidelity and completenessReport are the drill-down beneath quality and on a clean result restate it - 100% across six axes, six empty arrays - so they are sent when the result is not exact or complete, or when includeDiagnostics asks for them; on a Section export that was per screen. imports, usedTokens, componentImports, responsiveImports and responsiveComponents restated the tsx's own import line and its $tokens and are gone. deliverable stays: it was removed on the reasoning that the needs_figma handoff it guarded against is gone, and a consumer reported relying on it to know which value is the answer, which settles it. The server instructions were the larger cost and are corrected: they told every agent to take tsx, rawSnapshot and sourceMap together, which on the same measurement is about eight times the bytes of the code, and they now say to ask for an output only when it will be read. completeness and themeCompleteness stay - they grade how far token resolution reached, which quality does not say. Releases stop shipping devup-mcp-visual: the render harness builds it from source with cargo and nothing downloads it, so three of six assets were binaries no consumer used, built on every platform of every release. Cargo.lock is committed at the released version, which stops every release binary reporting its build id as -dirty and losing the ability to tell a release from a developer's working tree. Also removes two ErrorCode variants no production code ever constructed, whose only reference was a test pinning their wire strings - a test that would have passed forever whether or not they were reachable. A binding the resource catalog never named is now reported rather than quietly resolved. A fill bound to a variable, or a text carrying a style, is the design saying this is a token; the generator writes the token when the catalog carried that resource and the resolved value when it did not, and it has to write something because the module still has to compile. It said nothing when it did, so a hardcoded #7d7f83 could sit where the design says - identical today, no longer following the theme tomorrow - inside a response graded exact. Each such binding now raises DEVUP_CODEGEN_TOKEN_NAME_UNRESOLVED carrying the node, the property and the resource id, which also stops quality.projection reading exact. The check runs as a pass over the collected subtree rather than inside rendering, so it can name the node without threading an argument through the render functions, and the 268 plugin-parity goldens are unaffected because the generated bytes do not change.

devup-mcp-visual@0.2.1 → 0.2.2 - crates/devup-mcp-visual/Cargo.toml

Patch

• Narrow what devup-mcp asks for and what it sends back, and make a refusal say which of the two kinds it is. Nine tools become seven: devup_figma_to_ui and devup_figma_to_json were devup_figma_export with a single entry in outputs, so every client carried three schemas in its context and had to decide between them on every call, and the export tool's own description had to spend a sentence saying which to prefer. Use outputs: [tsx] and outputs: [devupJson] instead. sourcePolicy is gone from all of them: auto and direct both meant the direct connection and the parameter never branched, so it only ever offered a caller something to get wrong, and it was also part of the artifact cache key it could not affect. Every remaining closed-set input now publishes its accepted values in the JSON schema - action, scope, rootLayout, delivery, match, project context scope and stack diff layers - from one shared constant the parser reads too, so the schema cannot drift from what is accepted and a caller stops discovering the set one rejection at a time; outputs and the asset format were the only two that already did this. Errors are no longer all INTERNAL_ERROR. A mistake in the call itself - an unknown scope, a node that is not in the file, an expired artifactId - is now JSON-RPC INVALID_PARAMS, and everything behind the call stays INTERNAL_ERROR, so an agent can tell 'fix the arguments and retry' from 'stop and report' without parsing the message; the exact code and retryable are unchanged in data. Pure argument validation that had been reported as DEVUP_THEME_CONFLICT or DEVUP_SNAPSHOT_UNSUPPORTED is DEVUP_INVALID_INPUT, so a real theme conflict is no longer confused with a typo. The response is lighter for the same content. Measured on one export, a tsx-only call went from 2,411 to 1,405 bytes and the part every response carries regardless from 1,911 to 994. fidelity and completenessReport are the drill-down beneath quality and on a clean result restate it - 100% across six axes, six empty arrays - so they are sent when the result is not exact or complete, or when includeDiagnostics asks for them; on a Section export that was per screen. imports, usedTokens, componentImports, responsiveImports and responsiveComponents restated the tsx's own import line and its $tokens and are gone. deliverable stays: it was removed on the reasoning that the needs_figma handoff it guarded against is gone, and a consumer reported relying on it to know which value is the answer, which settles it. The server instructions were the larger cost and are corrected: they told every agent to take tsx, rawSnapshot and sourceMap together, which on the same measurement is about eight times the bytes of the code, and they now say to ask for an output only when it will be read. completeness and themeCompleteness stay - they grade how far token resolution reached, which quality does not say. Releases stop shipping devup-mcp-visual: the render harness builds it from source with cargo and nothing downloads it, so three of six assets were binaries no consumer used, built on every platform of every release. Cargo.lock is committed at the released version, which stops every release binary reporting its build id as -dirty and losing the ability to tell a release from a developer's working tree. Also removes two ErrorCode variants no production code ever constructed, whose only reference was a test pinning their wire strings - a test that would have passed forever whether or not they were reachable. A binding the resource catalog never named is now reported rather than quietly resolved. A fill bound to a variable, or a text carrying a style, is the design saying this is a token; the generator writes the token when the catalog carried that resource and the resolved value when it did not, and it has to write something because the module still has to compile. It said nothing when it did, so a hardcoded #7d7f83 could sit where the design says - identical today, no longer following the theme tomorrow - inside a response graded exact. Each such binding now raises DEVUP_CODEGEN_TOKEN_NAME_UNRESOLVED carrying the node, the property and the resource id, which also stops quality.projection reading exact. The check runs as a pass over the collected subtree rather than inside rendering, so it can name the node without threading an argument through the render functions, and the 268 plugin-parity goldens are unaffected because the generated bytes do not change.