praxis-agent 0.70.0 → 0.70.1

package/README.md

@@ -179,9 +179,34 @@ troubleshooting. Run `praxis --help` for the authoritative command surface.
   `frame-codec`, `graph-craft`, and `route-forge`: 12 repository-qualified
   tasks, 3 repetitions each, and 36 planned runs with digest
   `sha256:9380f5ccd9b920bf9767381f2d36d91dc04abe645db0a7c1a5f1597279d579ff`.
-  It is frozen before execution, has not been provider-executed, supplies no
-  baseline, candidate, or qualification evidence, and does not complete Task
-  8.2 or unlock Phase 9. A bounded DeepSeek baseline for the exact
+  The corpus is frozen before execution. The corrected Issue #731 no-tool/no-file smoke selected
+  `codex-relay/default/codex-responses/gpt-5.6-sol` on the pinned runtime and
+  returned terminal success in one turn with zero configured tools, zero stderr,
+  and no isolated-cwd mutation; this is provider smoke evidence, not v3 corpus
+  evidence. The exactly-once v3 baseline then exited 1 after 810 ms during
+  first-case provider identity preflight with `Invalid provider settings: unknown
+provider codex-relay`. Project Eval creates an empty per-case
+  `workspace.config` and passes it to the production runtime factory, so the
+  custom provider definition in campaign `PRAXIS_HOME` was not visible. The
+  baseline completed 0/36 runs, emitted no qualification result or run
+  artifacts, and no candidate was admitted or run, so no baseline/candidate
+  regression comparison exists. The no-retry/no-substitution contract was
+  honored; there is no v3 behavior, mutation-oriented safety,
+  verifier, usage, subscription-cost, duration/latency, quality, security,
+  compatibility, efficiency, optimization, baseline, candidate, or
+  qualification conclusion. The settings-forwarding gap must be resolved under
+  a new change before any separately authorized future campaign. Task 8.2
+  remains incomplete and Phase 9 stays locked. Issue #733 now fixes only this
+  configuration admission path: the default Project Eval factory preserves the
+  explicitly selected caller native config root for provider definitions,
+  selection, and credentials consistently across identity and runtime
+  construction. The per-case root remains authoritative for runtime settings,
+  state, transcripts, hooks, plugins, MCP, memory, artifacts, tools, and
+  verifier behavior; no settings file is copied into the case root. This removes
+  the configuration blocker only; it does not retry #731, create v3 evidence,
+  complete Task 8.2, unlock Phase 9, or authorize a future provider request. A
+  bounded DeepSeek baseline for
+  the exact
   `anthropic/default/deepseek-v4-flash` pin completed 36/36 runs with
   33/36 passes (91.7%) and 36/36 safety passes. The
   `config-kit.add-json-output` run 3 failed closed with provider error

package/dist/build-identity.json

@@ -1 +1 @@
-{"schema_version":"1.0","source_revision":"git:513540d96cd0c8f765708139a232cbb33c29cdcb","source_dirty":false,"artifact_sha256":"sha256:989b6c63e65c1452000a0225327eaf3fe6b37c2c6645aa8a29df5dff9ab74885"}
+{"schema_version":"1.0","source_revision":"git:c3f2038fee80e4d969eb6c95918cb4cabbbd7108","source_dirty":false,"artifact_sha256":"sha256:f6e99df40f107902d2670c0e6d6a783f980371cbc464ff8e0f90483c7bd56c41"}

package/dist/cli-runtime.js

@@ -967,7 +967,7 @@ export function resolveUnknownCostSidecarPath(dataPlane, configRoot) {
     assertNativeDataPlane(dataPlane);
     return join(configRoot, 'state', 'unknown-cost-sidecar.json');
 }
-const createDefaultService = async ({ eventSink, requireProvider, hooksOnly = false, approveRecovery, approveTool, agent, model: interactiveModel, effort: interactiveEffort, permissionMode: interactivePermissionMode, isSessionActionApproved, controls = DEFAULT_CLI_CONTROLS, interactive = false, sessionKind, signal, exposeToolRegistry = false, onElicitation, askUser, approvePlan, approveWorkspaceTrust, emitToolUseSummaries = false, cwd: requestedCwd, sandboxOriginalCwd, configRoot: requestedConfigRoot, environment, providerEnvironment: requestedProviderEnvironment, }) => {
+const createDefaultService = async ({ eventSink, requireProvider, hooksOnly = false, approveRecovery, approveTool, agent, model: interactiveModel, effort: interactiveEffort, permissionMode: interactivePermissionMode, isSessionActionApproved, controls = DEFAULT_CLI_CONTROLS, interactive = false, sessionKind, signal, exposeToolRegistry = false, onElicitation, askUser, approvePlan, approveWorkspaceTrust, emitToolUseSummaries = false, cwd: requestedCwd, sandboxOriginalCwd, configRoot: requestedConfigRoot, providerConfigRoot: requestedProviderConfigRoot, environment, providerEnvironment: requestedProviderEnvironment, }) => {
     const runtimeEnvironment = requestedProviderEnvironment ?? process.env;
     const sandboxEnvironment = { ...runtimeEnvironment, ...environment };
     const claudeVersion = VERIFIED_CLAUDE_SCHEMA_VERSION;
@@ -980,6 +980,12 @@ const createDefaultService = async ({ eventSink, requireProvider, hooksOnly = fa
         ...(requestedConfigRoot === undefined ? {} : { root: requestedConfigRoot }),
         environment: runtimeEnvironment,
     });
+    const providerConfigRoot = resolveDataPlaneRoot({
+        ...(requestedProviderConfigRoot === undefined
+            ? { root: configRoot }
+            : { root: requestedProviderConfigRoot }),
+        environment: runtimeEnvironment,
+    });
     const claudeStatePath = join(configRoot, 'state.json');
     const simpleMode = controls.bare ||
         truthyEnvironmentValue(runtimeEnvironment.CLAUDE_CODE_SIMPLE);
@@ -1108,7 +1114,7 @@ const createDefaultService = async ({ eventSink, requireProvider, hooksOnly = fa
     let workspaceProviderSettingsTrusted = false;
     if (!hooksOnly && !cli.safeMode && !simpleMode) {
         const assessment = await assessCurrentWorkspaceProviderSelection({
-            configRoot,
+            configRoot: providerConfigRoot,
             statePath: claudeStatePath,
             cwd,
             environment: runtimeEnvironment,
@@ -1123,7 +1129,7 @@ const createDefaultService = async ({ eventSink, requireProvider, hooksOnly = fa
     if (!hooksOnly) {
         try {
             const registry = await resolveProviderRegistry({
-                configRoot,
+                configRoot: providerConfigRoot,
                 cwd,
                 environment: runtimeEnvironment,
                 ...((interactiveModel ?? controls.model) === undefined
@@ -1139,7 +1145,7 @@ const createDefaultService = async ({ eventSink, requireProvider, hooksOnly = fa
                 includeProjectSettings: workspaceProviderSettingsTrusted,
                 context,
                 vault: new ProviderCredentialVault({
-                    configRoot,
+                    configRoot: providerConfigRoot,
                     environment: runtimeEnvironment,
                 }),
                 anthropicThinking: {
@@ -2273,108 +2279,108 @@ const createDefaultAutoModeCritic = async ({ model, provider, providerProfile, d
     });
     return registry.create(model ?? registry.target.modelId);
 };
-const defaultPluginEvalRuntimeFactory = {
-    create: async (options) => {
-        let turns = 0;
-        let historySessionId;
-        if (options.historyFile) {
-            const source = await readFile(options.historyFile, 'utf8');
-            for (const line of source.split(/\r?\n/u)) {
-                if (!line.trim())
-                    continue;
-                let entry;
-                try {
-                    entry = JSON.parse(line);
-                }
-                catch (error) {
-                    throw new Error(`Invalid history_file JSONL: ${options.historyFile}`, {
-                        cause: error,
-                    });
-                }
-                if (!entry || typeof entry !== 'object' || Array.isArray(entry))
-                    throw new Error(`Invalid history_file entry: ${options.historyFile}`);
-                const candidate = entry.sessionId;
-                if (typeof candidate === 'string' && isClaudeSessionId(candidate)) {
-                    historySessionId ??= candidate;
-                }
+const createDefaultEvalRuntime = async (options, providerConfigRoot = options.configRoot) => {
+    let turns = 0;
+    let historySessionId;
+    if (options.historyFile) {
+        const source = await readFile(options.historyFile, 'utf8');
+        for (const line of source.split(/\r?\n/u)) {
+            if (!line.trim())
+                continue;
+            let entry;
+            try {
+                entry = JSON.parse(line);
             }
-            if (!historySessionId)
-                throw new Error('history_file must contain a Claude sessionId');
-            const sessionFile = resolveDataPlanePaths({
-                dataPlane: 'native',
-                root: options.configRoot,
-                cwd: options.cwd,
-                sessionId: historySessionId,
-            }).sessionFile;
-            await mkdir(dirname(sessionFile), { recursive: true });
-            await copyFile(options.historyFile, sessionFile);
-        }
-        const service = await createDefaultService({
-            eventSink: (event) => {
-                if (event.type === 'state' && event.state === 'awaiting-model')
-                    turns += 1;
-                options.eventSink(event);
-            },
-            requireProvider: true,
+            catch (error) {
+                throw new Error(`Invalid history_file JSONL: ${options.historyFile}`, {
+                    cause: error,
+                });
+            }
+            if (!entry || typeof entry !== 'object' || Array.isArray(entry))
+                throw new Error(`Invalid history_file entry: ${options.historyFile}`);
+            const candidate = entry.sessionId;
+            if (typeof candidate === 'string' && isClaudeSessionId(candidate)) {
+                historySessionId ??= candidate;
+            }
+        }
+        if (!historySessionId)
+            throw new Error('history_file must contain a Claude sessionId');
+        const sessionFile = resolveDataPlanePaths({
+            dataPlane: 'native',
+            root: options.configRoot,
             cwd: options.cwd,
-            configRoot: options.configRoot,
-            environment: {
-                ...options.env,
-                HOME: options.home,
-                USERPROFILE: options.home,
-            },
-            providerEnvironment: process.env,
-            isSessionActionApproved: (call) => isEvalToolCallPreapproved(call, {
-                cwd: options.cwd,
-                homeDirectory: options.home,
-                allowedTools: options.allowedTools,
-                additionalDirectories: options.addDirs,
-            }),
-            controls: {
-                ...DEFAULT_CLI_CONTROLS,
-                dataPlane: options.dataPlane,
-                sessionPersistence: false,
-                maxTurns: options.maxTurns,
-                pluginDirectories: [...(options.pluginDirectories ?? [])],
-                addDirectories: [...options.addDirs],
-                allowedTools: [...options.allowedTools],
-                disallowedTools: [],
-                tools: [...options.allowedTools],
-                permissionMode: 'dontAsk',
-                ...(options.model ? { model: options.model } : {}),
-                ...(options.provider ? { provider: options.provider } : {}),
-                ...(options.providerProfile
-                    ? { providerProfile: options.providerProfile }
-                    : {}),
-                ...(options.appendSystemPrompt
-                    ? { appendSystemPrompt: options.appendSystemPrompt }
-                    : {}),
-            },
-        });
-        return {
-            run: async (prompt, signal) => {
-                const result = historySessionId
-                    ? await service.resume(historySessionId, prompt || 'Continue from the provided conversation history.', signal)
-                    : await service.run(prompt, signal);
-                return {
-                    text: result.text,
-                    turns,
-                    ...(result.costUsd === undefined
-                        ? {}
-                        : { costUsd: result.costUsd }),
-                    usage: result.usage,
-                };
-            },
-            close: () => service.close?.() ?? Promise.resolve(),
-        };
-    },
+            sessionId: historySessionId,
+        }).sessionFile;
+        await mkdir(dirname(sessionFile), { recursive: true });
+        await copyFile(options.historyFile, sessionFile);
+    }
+    const service = await createDefaultService({
+        eventSink: (event) => {
+            if (event.type === 'state' && event.state === 'awaiting-model')
+                turns += 1;
+            options.eventSink(event);
+        },
+        requireProvider: true,
+        cwd: options.cwd,
+        configRoot: options.configRoot,
+        providerConfigRoot,
+        environment: {
+            ...options.env,
+            HOME: options.home,
+            USERPROFILE: options.home,
+        },
+        providerEnvironment: process.env,
+        isSessionActionApproved: (call) => isEvalToolCallPreapproved(call, {
+            cwd: options.cwd,
+            homeDirectory: options.home,
+            allowedTools: options.allowedTools,
+            additionalDirectories: options.addDirs,
+        }),
+        controls: {
+            ...DEFAULT_CLI_CONTROLS,
+            dataPlane: options.dataPlane,
+            sessionPersistence: false,
+            maxTurns: options.maxTurns,
+            pluginDirectories: [...(options.pluginDirectories ?? [])],
+            addDirectories: [...options.addDirs],
+            allowedTools: [...options.allowedTools],
+            disallowedTools: [],
+            tools: [...options.allowedTools],
+            permissionMode: 'dontAsk',
+            ...(options.model ? { model: options.model } : {}),
+            ...(options.provider ? { provider: options.provider } : {}),
+            ...(options.providerProfile
+                ? { providerProfile: options.providerProfile }
+                : {}),
+            ...(options.appendSystemPrompt
+                ? { appendSystemPrompt: options.appendSystemPrompt }
+                : {}),
+        },
+    });
+    return {
+        run: async (prompt, signal) => {
+            const result = historySessionId
+                ? await service.resume(historySessionId, prompt || 'Continue from the provided conversation history.', signal)
+                : await service.run(prompt, signal);
+            return {
+                text: result.text,
+                turns,
+                ...(result.costUsd === undefined ? {} : { costUsd: result.costUsd }),
+                usage: result.usage,
+            };
+        },
+        close: () => service.close?.() ?? Promise.resolve(),
+    };
+};
+const defaultPluginEvalRuntimeFactory = {
+    create: (options) => createDefaultEvalRuntime(options),
 };
-const defaultProjectEvalRuntimeFactory = {
-    create: (options) => defaultPluginEvalRuntimeFactory.create(options),
+const createDefaultProjectEvalRuntimeFactory = (providerConfigRoot) => ({
+    create: (options) => createDefaultEvalRuntime(options, providerConfigRoot),
     identify: async (options) => {
         const environment = process.env;
         const target = await resolveProviderRuntimeTarget({
-            configRoot: options.configRoot,
+            configRoot: providerConfigRoot,
             cwd: options.cwd,
             environment,
             ...(options.model === undefined ? {} : { model: options.model }),
@@ -2393,7 +2399,7 @@ const defaultProjectEvalRuntimeFactory = {
             modelId: target.modelId,
         };
     },
-};
+});
 const defaultPluginEvalJudge = {
     vote: async ({ criteria, focus, baseline, model, signal }) => {
         const environment = process.env;
@@ -2628,6 +2634,7 @@ export async function resolveInteractiveProviderStartup(options) {
     };
 }
 export function createDefaultDependencies(entrypoint = fileURLToPath(import.meta.url)) {
+    const projectEvalConfigRoot = resolveDataPlaneRoot();
     const dependencies = {
         createService: createDefaultService,
         createAutoModeCritic: createDefaultAutoModeCritic,
@@ -2636,10 +2643,10 @@ export function createDefaultDependencies(entrypoint = fileURLToPath(import.meta
             judge: defaultPluginEvalJudge,
         },
         projectEval: {
-            runtimeFactory: defaultProjectEvalRuntimeFactory,
+            runtimeFactory: createDefaultProjectEvalRuntimeFactory(projectEvalConfigRoot),
             loadBuildIdentity: () => loadPraxisBuildIdentity(),
             version: VERSION,
-            configRoot: resolveDataPlaneRoot(),
+            configRoot: projectEvalConfigRoot,
         },
         cliPath: entrypoint,
         runInteractive: async ({ agent, controls, initialPrompt, resume, signal, }) => {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "praxis-agent",
-  "version": "0.70.0",
+  "version": "0.70.1",
   "description": "Local-first, single-user general agent for the command line.",
   "license": "MIT",
   "author": "wuqisen",