praxis-agent 0.70.1 → 0.70.3

package/README.md

@@ -179,7 +179,7 @@ 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`.
-  The corpus is frozen before execution. The corrected Issue #731 no-tool/no-file smoke selected
+  The corpus was frozen before the campaign. 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
@@ -187,24 +187,58 @@ troubleshooting. Run `praxis --help` for the authoritative command surface.
   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
+  custom provider definition in campaign `PRAXIS_HOME` was not visible. This
+  historical #731 baseline completed 0/36 runs and admitted no candidate; its
+  no-retry/no-substitution contract was honored. 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
+  the configuration blocker only; it does not retry #731 or authorize a future
+  provider request. Issue #738 completed the v3 campaign: candidate behavior
+  and verifier satisfaction fell from 24/36 to 18/36, with 13 newly failing
+  runs, while mutation-oriented safety remained 36/36. Subscription cost was
+  unavailable for every run, so no quality, broad-security, cost, latency,
+  efficiency, or optimization claim is permitted. Task 8.2 and Phase 9 remain
+  locked; result-informed remediation or requalification remains separately
+  scoped. [Issue #740](https://github.com/Forest-Isle/Praxis/issues/740)
+  now freezes `praxis-held-out-v4` for `csv-lens`, `memo-lru`, and `patch-tree`,
+  with 12 repository-qualified tasks, 3 repetitions each, and 36 planned runs
+  at digest `sha256:a32cb478cd6a99971cb57964c82affa3296546c387a4f1dacf4df7d313480b53`.
+  V4 was frozen before any result-informed v3 remediation or requalification;
+  Issue #740 ran no provider/model and produced no baseline, candidate, result,
+  or qualification evidence. Task 8.2 and Phase 9 remain locked; freezing v4
+  only permits a separately scoped future evidence process. Exact identities,
+  digests, usage, timing, and evidence boundaries are recorded in [Native
+  Fixture Contracts](docs/NATIVE_FIXTURE_CONTRACTS.md).
+  Issue #742's exactly-once pre-corpus smoke returned HTTP 404 and failed closed;
+  the baseline and candidate did not run, and no qualification exists. No
+  retry, substitution, or result selection occurred. The v4 corpus remains
+  unexecuted, so Task 8.2/Phase 9 remain locked; see [Native Fixture
+  Contracts](docs/NATIVE_FIXTURE_CONTRACTS.md) for exact evidence.
+  Issue #748 then ran one authorized pre-corpus smoke against clean runtime
+  source `git:e152a2b1c1f2aba150cb28cbf577780d699b0011`, artifact
+  `sha256:80a4bc792f727b75ab1259c4c6d9fdc4e93dad333d112f2f75bab143c7ea9cdd`,
+  and `codex-relay/default/codex-responses/gpt-5.5` at the fixed adapter
+  endpoint. It failed closed with HTTP 404 and bounded `model_not_found`
+  diagnostics; baseline and candidate remained 0/36 and absent, with no
+  verdict. No retry or substitution occurred, v4 remains unexecuted, and
+  Task 8.2/Phase 9 remain locked. This diagnostic applies only to #748's
+  response and does not establish its producing layer or explain #742.
+  Issue #751 completed one successful post-deploy no-tool/no-file smoke after
+  fresh exact-identity authorization and provider-free admission passed. The
+  `codex-relay/default/codex-responses/gpt-5.6-sol` smoke used one turn with no
+  retry, fallback, substitution, or workspace mutation. This is connectivity-
+  only evidence; 4xx correlation was not exercised, v4 remains unexecuted, and
+  Task 8.2/Phase 9 remain locked. Issue #756 is retained as an immutable harness-
+  contract failure rather than qualification evidence; v4 remains 0/36. A
+  complete valid held-out baseline unlocks Phase 9 measurement, while adoption
+  or release still requires a changed-build candidate with `qualified: true`.
+  Detailed evidence and the next-campaign authorization boundary are in
+  [Native Fixture Contracts](docs/NATIVE_FIXTURE_CONTRACTS.md).
+  A
   bounded DeepSeek baseline for
   the exact
   `anthropic/default/deepseek-v4-flash` pin completed 36/36 runs with
@@ -511,7 +545,7 @@ normal/low-capability full-frame p95 budgets of `<16.7/<33 ms`.
 `npm run test:coverage` measures all production code under `src/**` with V8 and
 enforces global floors of 79% statements, 70% branches, 85% functions, and 81% lines,
 and rejects any production runtime module with zero covered statements (while allowing
-type-only modules). `npm run test:fixtures` executes the 76-behavior native contract; 68 behaviors
+type-only modules). `npm run test:fixtures` executes the 77-behavior native contract; 69 behaviors
 are qualified and 8 are explicitly excluded. Schema-v2 risk tiers and executable evidence dimensions
 are enforced fail-closed. `npm run verify:fixture-contracts` performs the structural check and is part
 of `npm run check`.

package/dist/build-identity.json

@@ -1 +1 @@
-{"schema_version":"1.0","source_revision":"git:c3f2038fee80e4d969eb6c95918cb4cabbbd7108","source_dirty":false,"artifact_sha256":"sha256:f6e99df40f107902d2670c0e6d6a783f980371cbc464ff8e0f90483c7bd56c41"}
+{"schema_version":"1.0","source_revision":"git:4fd3c4ef9402e26c4358e8192333ef9b23468fb0","source_dirty":false,"artifact_sha256":"sha256:c047ab2ccddb9756f5c594724d1b37186d6ed8788e60b82621f189c4d3c19c8e"}

package/dist/providers/codex-responses.js

@@ -6,20 +6,132 @@ function failure(kind, retryable, status) {
         ? 'Codex Responses provider request failed'
         : `Codex Responses provider request failed with HTTP ${status}`, { kind, retryable, ...(status === undefined ? {} : { status }) });
 }
-function statusFailure(status) {
+function statusFailure(status, diagnostics) {
+    let result;
     if (status === 401 || status === 403)
-        return failure('authentication_failed', false, status);
-    if (status === 402)
-        return failure('billing_error', false, status);
-    if (status === 408)
-        return failure('timeout', true, status);
-    if (status === 429)
-        return failure('rate_limit', true, status);
-    if (status === 529)
-        return failure('overloaded', true, status);
-    if (status >= 500)
-        return failure('server_error', true, status);
-    return failure('invalid_request', false, status);
+        result = failure('authentication_failed', false, status);
+    else if (status === 402)
+        result = failure('billing_error', false, status);
+    else if (status === 408)
+        result = failure('timeout', true, status);
+    else if (status === 429)
+        result = failure('rate_limit', true, status);
+    else if (status === 529)
+        result = failure('overloaded', true, status);
+    else if (status >= 500)
+        result = failure('server_error', true, status);
+    else
+        result = failure('invalid_request', false, status);
+    if (diagnostics !== undefined)
+        return new ModelProviderError(`${result.message} (${diagnostics})`, {
+            retryable: result.retryable,
+            ...(result.kind === undefined ? {} : { kind: result.kind }),
+            ...(result.status === undefined ? {} : { status: result.status }),
+        });
+    return result;
+}
+const safeDiagnostic = /^[A-Za-z0-9][A-Za-z0-9._-]*$/u;
+function safeValue(value) {
+    return (typeof value === 'string' &&
+        value.length >= 1 &&
+        value.length <= 128 &&
+        safeDiagnostic.test(value));
+}
+function parseErrorDiagnostics(body, headers) {
+    let parsed;
+    if (body !== undefined) {
+        try {
+            parsed = JSON.parse(body);
+        }
+        catch {
+            parsed = undefined;
+        }
+    }
+    const object = typeof parsed === 'object' && parsed !== null && !Array.isArray(parsed)
+        ? parsed
+        : undefined;
+    const nested = object?.error !== null &&
+        typeof object?.error === 'object' &&
+        !Array.isArray(object?.error)
+        ? object?.error
+        : undefined;
+    const values = [
+        ['type', nested === undefined ? object?.type : nested.type],
+        ['code', nested === undefined ? object?.code : nested.code],
+        ['relay_request_id', headers.get('x-relay-request-id')],
+        ['request_id', headers.get('x-request-id')],
+        ['cf_ray', headers.get('cf-ray')],
+    ];
+    const seen = new Set();
+    const admitted = [];
+    for (const [key, raw] of values) {
+        if (!safeValue(raw) || seen.has(raw))
+            continue;
+        seen.add(raw);
+        admitted.push(`${key}=${raw}`);
+    }
+    return admitted.length === 0 ? undefined : admitted.join(', ');
+}
+async function readErrorBody(response, maxBytes, onChunk) {
+    const reader = response.body?.getReader();
+    if (reader === undefined)
+        return undefined;
+    const chunks = [];
+    let total = 0;
+    let ended = false;
+    let failed = false;
+    try {
+        while (true) {
+            const next = await reader.read();
+            if (next.done) {
+                ended = true;
+                break;
+            }
+            if (next.value.byteLength > 0)
+                onChunk();
+            if (total + next.value.byteLength > maxBytes) {
+                if (total < maxBytes)
+                    chunks.push(next.value.slice(0, maxBytes - total));
+                total = maxBytes;
+                break;
+            }
+            chunks.push(next.value);
+            total += next.value.byteLength;
+        }
+    }
+    catch {
+        failed = true;
+    }
+    finally {
+        if (!ended) {
+            try {
+                await reader.cancel();
+            }
+            catch {
+                failed = true;
+            }
+        }
+        try {
+            reader.releaseLock();
+        }
+        catch {
+            failed = true;
+        }
+    }
+    if (failed || !ended)
+        return undefined;
+    try {
+        const bytes = new Uint8Array(total);
+        let offset = 0;
+        for (const chunk of chunks) {
+            bytes.set(chunk, offset);
+            offset += chunk.byteLength;
+        }
+        return new TextDecoder().decode(bytes);
+    }
+    catch {
+        return undefined;
+    }
 }
 export class CodexResponsesProvider {
     options;
@@ -109,40 +221,8 @@ export class CodexResponsesProvider {
             throw failure('transport_error', true);
         }
         if (!response.ok) {
-            const reader = response.body?.getReader();
-            if (reader) {
-                let total = 0;
-                let ended = false;
-                try {
-                    while (true) {
-                        const next = await reader.read();
-                        if (next.done) {
-                            ended = true;
-                            break;
-                        }
-                        if (next.value.byteLength > 0)
-                            reportProviderTransportActivity(request, 'response-chunk');
-                        total += next.value.byteLength;
-                        if (total > this.maxErrorBodyBytes)
-                            break;
-                    }
-                }
-                catch {
-                    /* preserve the redacted HTTP status classification */
-                }
-                finally {
-                    if (!ended) {
-                        try {
-                            await reader.cancel();
-                        }
-                        catch {
-                            /* preserve the redacted HTTP status classification */
-                        }
-                    }
-                    reader.releaseLock();
-                }
-            }
-            throw statusFailure(response.status);
+            const body = await readErrorBody(response, this.maxErrorBodyBytes, () => reportProviderTransportActivity(request, 'response-chunk'));
+            throw statusFailure(response.status, parseErrorDiagnostics(body, response.headers));
         }
         if (!response.body)
             throw failure('transport_error', true);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "praxis-agent",
-  "version": "0.70.1",
+  "version": "0.70.3",
   "description": "Local-first, single-user general agent for the command line.",
   "license": "MIT",
   "author": "wuqisen",
@@ -63,7 +63,7 @@
     "verify:fixture-contracts": "node scripts/verify-fixture-contracts.mjs",
     "test:fixtures": "node scripts/run-fixture-contracts.mjs",
     "test:eval:baseline": "vitest run src/evals/coding-baseline.test.ts src/evals/project-eval-comparison.test.ts src/evals/apply-patch-admission.test.ts src/evals/lsp-diagnostics-admission.test.ts src/evals/glob-ripgrep-admission.test.ts",
-    "test:eval:held-out-contract": "vitest run src/evals/held-out-corpus.test.ts src/evals/held-out-corpus-v3.test.ts",
+    "test:eval:held-out-contract": "vitest run src/evals/held-out-corpus.test.ts src/evals/held-out-corpus-v3.test.ts src/evals/held-out-corpus-v4.test.ts",
     "test:eval:held-out-qualification": "vitest run src/evals/held-out-qualification.test.ts"
   },
   "engines": {