Merge pull request 'feat(neuron): server-measured prefill/decode timing on Finish (#85)' (#100) from feat/85-prefill-decode-timing into main

The TP streaming producer builds its Finish event after the 'work
labelled block exits (inside `if failure.is_none()`), but prefill_elapsed
and decode_start were declared inside that block — so the CUDA type-check
failed with E0425 (the CPU build doesn't compile this cfg(cuda) path).

Hoist `prefill_ms_measured: u32` and `decode_start: Option<Instant>`
above the block; populate them at the prefill→decode boundary inside;
read them at the terminal Finish. The worker and local producers were
unaffected (their timers already share the Finish scope).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VrJ4i3pfLRSTM76o3ofnVq

.gitea/workflows/build-prerelease.yml

@@ -66,6 +66,7 @@ jobs:
       build_cortex: ${{ steps.changes.outputs.build_cortex }}
       build_neuron: ${{ steps.changes.outputs.build_neuron }}
       build_bench: ${{ steps.changes.outputs.build_bench }}
+      build_upstream: ${{ steps.changes.outputs.build_upstream }}
       check_rust: ${{ steps.changes.outputs.check_rust }}
     steps:
       - uses: actions/checkout@v4
@@ -104,6 +105,7 @@ jobs:
           BUILD_CORTEX=true
           BUILD_NEURON=true
           BUILD_BENCH=true
+          BUILD_UPSTREAM=true
           CHECK_RUST=true
 
           if [ "${GITHUB_EVENT_NAME}" = "push" ]; then
@@ -149,6 +151,7 @@ jobs:
               NEURON_RE='^crates/neuron/|^crates/cortex-core/|^Cargo\.toml$|^Cargo\.lock$|^rpm/helexa-neuron-prerelease\.spec$|^data/neuron|^neuron\.example\.toml$|^\.gitea/workflows/build-prerelease\.yml$'
               CORTEX_RE='^crates/cortex-gateway/|^crates/cortex-cli/|^crates/cortex-core/|^Cargo\.toml$|^Cargo\.lock$|^rpm/cortex-prerelease\.spec$|^data/cortex|^cortex\.example\.toml$|^models\.example\.toml$|^\.gitea/workflows/build-prerelease\.yml$'
               BENCH_RE='^crates/helexa-bench/|^crates/cortex-core/|^Cargo\.toml$|^Cargo\.lock$|^rpm/helexa-bench-prerelease\.spec$|^data/helexa-bench|^helexa-bench\.example\.toml$|^\.gitea/workflows/build-prerelease\.yml$'
+              UPSTREAM_RE='^crates/helexa-upstream/|^crates/cortex-core/|^Cargo\.toml$|^Cargo\.lock$|^rpm/helexa-upstream-prerelease\.spec$|^data/helexa-upstream|^helexa-upstream\.example\.toml$|^\.gitea/workflows/build-prerelease\.yml$'
               # Any Rust change (incl. crates not packaged here, e.g.
               # helexa-acp) still needs lint+test on main.
               RUST_RE='\.rs$|^crates/|Cargo\.toml$|^Cargo\.lock$'
@@ -156,10 +159,12 @@ jobs:
               CORTEX_BASE=$(base_for cortex)
               NEURON_BASE=$(base_for helexa-neuron-blackwell)
               BENCH_BASE=$(base_for helexa-bench)
+              UPSTREAM_BASE=$(base_for helexa-upstream)
               BUILD_CORTEX=$(decide "$CORTEX_BASE" "$CORTEX_RE")
               BUILD_NEURON=$(decide "$NEURON_BASE" "$NEURON_RE")
               BUILD_BENCH=$(decide "$BENCH_BASE" "$BENCH_RE")
-              if [ "$BUILD_CORTEX" = "true" ] || [ "$BUILD_NEURON" = "true" ] || [ "$BUILD_BENCH" = "true" ]; then
+              BUILD_UPSTREAM=$(decide "$UPSTREAM_BASE" "$UPSTREAM_RE")
+              if [ "$BUILD_CORTEX" = "true" ] || [ "$BUILD_NEURON" = "true" ] || [ "$BUILD_BENCH" = "true" ] || [ "$BUILD_UPSTREAM" = "true" ]; then
                 CHECK_RUST=true
               else
                 CHECK_RUST=$(decide "$CORTEX_BASE" "$RUST_RE")
@@ -170,8 +175,9 @@ jobs:
           echo "build_cortex=${BUILD_CORTEX}" >> "$GITHUB_OUTPUT"
           echo "build_neuron=${BUILD_NEURON}" >> "$GITHUB_OUTPUT"
           echo "build_bench=${BUILD_BENCH}" >> "$GITHUB_OUTPUT"
+          echo "build_upstream=${BUILD_UPSTREAM}" >> "$GITHUB_OUTPUT"
           echo "check_rust=${CHECK_RUST}" >> "$GITHUB_OUTPUT"
-          echo "### change detection: build_cortex=${BUILD_CORTEX} build_neuron=${BUILD_NEURON} build_bench=${BUILD_BENCH} check_rust=${CHECK_RUST}"
+          echo "### change detection: build_cortex=${BUILD_CORTEX} build_neuron=${BUILD_NEURON} build_bench=${BUILD_BENCH} build_upstream=${BUILD_UPSTREAM} check_rust=${CHECK_RUST}"
 
   # fmt + clippy + test moved here from ci.yml for main pushes so the
   # two workflows stop queueing against each other (ci.yml's checks
@@ -303,6 +309,45 @@ jobs:
           path: artifacts/helexa-bench
           retention-days: 1
 
+  build-upstream:
+    name: Build helexa-upstream binary
+    timeout-minutes: 25
+    needs: prepare
+    if: needs.prepare.outputs.build_upstream == 'true'
+    # Pure-Rust, non-CUDA binary — same runner as cortex/bench.
+    runs-on: rust
+    env:
+      RUSTC_WRAPPER: sccache
+      SCCACHE_BUCKET: sccache
+      SCCACHE_ENDPOINT: http://caveman.kosherinata.internal:9000
+      SCCACHE_REGION: auto
+      SCCACHE_S3_USE_SSL: "false"
+      AWS_ACCESS_KEY_ID: ${{ secrets.SCCACHE_S3_ACCESS_KEY }}
+      AWS_SECRET_ACCESS_KEY: ${{ secrets.SCCACHE_S3_SECRET_KEY }}
+      # helexa-upstream uses the sqlx runtime query API (no compile-time
+      # query macros), so it builds without a database or a .sqlx cache.
+      # Set OFFLINE defensively so a stray macro can never reach for a DB.
+      SQLX_OFFLINE: "true"
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref }}
+
+      - name: Build helexa-upstream (release, sccache escalation)
+        run: script/ci-cargo-escalate.sh cargo build --release -p helexa-upstream
+
+      - name: Stage binary
+        run: |
+          mkdir --parents artifacts
+          cp target/release/helexa-upstream artifacts/helexa-upstream
+          ./artifacts/helexa-upstream --version || true
+
+      - uses: actions/upload-artifact@v3
+        with:
+          name: upstream-fc43
+          path: artifacts/helexa-upstream
+          retention-days: 1
+
   build-neuron:
     name: Build neuron-${{ matrix.flavour }}
     timeout-minutes: 35
@@ -459,6 +504,44 @@ jobs:
           path: ~/rpmbuild/RPMS/x86_64/*.rpm
           retention-days: 7
 
+  package-upstream:
+    name: Package helexa-upstream RPM
+    timeout-minutes: 20
+    needs: [prepare, build-upstream]
+    runs-on: rpm
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref }}
+
+      - uses: actions/download-artifact@v3
+        with:
+          name: upstream-fc43
+          path: artifacts/
+
+      - name: Build RPM
+        run: |
+          set -eux
+          rm -f ~/.rpmmacros
+          rpmdev-setuptree
+          cp artifacts/helexa-upstream ~/rpmbuild/SOURCES/
+          cp data/helexa-upstream.service ~/rpmbuild/SOURCES/
+          cp data/helexa-upstream-sysusers.conf ~/rpmbuild/SOURCES/
+          cp data/helexa-upstream-firewalld.xml ~/rpmbuild/SOURCES/
+          cp helexa-upstream.example.toml ~/rpmbuild/SOURCES/
+          cp LICENSE ~/rpmbuild/SOURCES/
+          rpmbuild -bb rpm/helexa-upstream-prerelease.spec \
+            --define "upstream_version ${{ needs.prepare.outputs.version }}" \
+            --define "upstream_prerelease ${{ needs.prepare.outputs.release }}" \
+            --undefine dist \
+            --define "dist .fc43"
+
+      - uses: actions/upload-artifact@v3
+        with:
+          name: rpm-upstream-fc43
+          path: ~/rpmbuild/RPMS/x86_64/*.rpm
+          retention-days: 7
+
   package-neuron:
     name: Package helexa-neuron-${{ matrix.flavour }} RPM
     timeout-minutes: 20
@@ -508,7 +591,7 @@ jobs:
   publish:
     name: Publish to rpm.lair.cafe (unstable)
     timeout-minutes: 25
-    needs: [lint, test, package-cortex, package-neuron, package-bench]
+    needs: [lint, test, package-cortex, package-neuron, package-bench, package-upstream]
     # Runs when at least one package was built and nothing failed.
     # lint/test may be skipped (docs-only refs never get here because
     # no packages build), but a real failure in any blocks the
@@ -518,10 +601,11 @@ jobs:
         !cancelled()
         && (needs.lint.result == 'success' || needs.lint.result == 'skipped')
         && (needs.test.result == 'success' || needs.test.result == 'skipped')
-        && (needs.package-cortex.result == 'success' || needs.package-neuron.result == 'success' || needs.package-bench.result == 'success')
+        && (needs.package-cortex.result == 'success' || needs.package-neuron.result == 'success' || needs.package-bench.result == 'success' || needs.package-upstream.result == 'success')
         && needs.package-cortex.result != 'failure'
         && needs.package-neuron.result != 'failure'
         && needs.package-bench.result != 'failure'
+        && needs.package-upstream.result != 'failure'
       }}
     runs-on: rpm
     concurrency:

Cargo.toml

@@ -9,6 +9,7 @@ members = [
     "crates/helexa-bench",
     "crates/helexa-router",
     "crates/helexa-stream",
+    "crates/helexa-upstream",
 ]
 
 [workspace.package]

cortex.example.toml

@@ -90,3 +90,20 @@ account_id = "operator"
 key_id = "infra"
 # No hard_cap → uncapped operator infra key (own fleet, own use). Still
 # metered for visibility.
+
+# -- Upstream (helexa mesh) entitlements client (#57) --------------------
+# When enabled, a bearer key NOT found in [[entitlements.keys]] above is
+# validated against the helexa-upstream authority (mesh accounts), and its
+# budget is reserved/settled there. Operator-local keys (incl. the infra
+# key) never leave this process. Fail-closed: if upstream is unreachable a
+# request is refused (503 + Retry-After), never served un-authorized.
+# Disabled by default — a standalone operator runs purely local.
+[upstream]
+enabled = false
+# url = "https://upstream.helexa.ai"
+# Shared client bearer this cortex presents (maps to an operator_id
+# upstream). Override via CORTEX_UPSTREAM__BEARER in prod.
+# bearer = "replace-with-operator-client-secret"
+# timeout_secs = 5
+# How often to flush served-usage counters to upstream for reconciliation (#58).
+# served_usage_report_interval_secs = 60

crates/cortex-core/src/config.rs

@@ -22,6 +22,43 @@ pub struct GatewayConfig {
     /// setups keep working until keys are configured.
     #[serde(default)]
     pub entitlements: EntitlementsConfig,
+    /// helexa-upstream client (#57). When enabled, keys not found in the
+    /// local `[entitlements]` config are validated against the mesh
+    /// authority, and budget is reserved/settled there. Disabled by default
+    /// — a single operator runs purely local.
+    #[serde(default)]
+    pub upstream: UpstreamClientConfig,
+}
+
+/// `[upstream]` — the helexa-upstream authority client (#57). Locally
+/// unrecognised bearer keys are resolved against `url`'s `/authz/v1` surface
+/// (mesh accounts); local keys (operator + infra) never leave the process.
+#[derive(Debug, Clone, Serialize, Deserialize, Default)]
+pub struct UpstreamClientConfig {
+    /// Enable the upstream fallthrough. Off → purely local entitlements.
+    #[serde(default)]
+    pub enabled: bool,
+    /// Base URL of helexa-upstream (e.g. "https://upstream.helexa.ai").
+    #[serde(default)]
+    pub url: String,
+    /// Shared client bearer this cortex presents to `/authz/v1` (maps to an
+    /// operator_id upstream). Sent as `Authorization: Bearer <bearer>`.
+    #[serde(default)]
+    pub bearer: String,
+    /// Per-call timeout (seconds) to upstream.
+    #[serde(default = "default_upstream_timeout")]
+    pub timeout_secs: u64,
+    /// How often (seconds) to flush served-usage counters to upstream for
+    /// reconciliation (#58).
+    #[serde(default = "default_served_usage_interval")]
+    pub served_usage_report_interval_secs: u64,
+}
+
+fn default_upstream_timeout() -> u64 {
+    5
+}
+fn default_served_usage_interval() -> u64 {
+    60
 }
 
 /// `[entitlements]` — the local/static [`crate::entitlements::EntitlementProvider`]
@@ -129,6 +166,7 @@ impl Default for GatewayConfig {
             neurons: vec![],
             models_config: default_models_path(),
             entitlements: EntitlementsConfig::default(),
+            upstream: UpstreamClientConfig::default(),
         }
     }
 }

crates/cortex-core/src/entitlements.rs

@@ -81,12 +81,19 @@ pub struct BudgetSnapshot {
     pub reserved: u64,
 }
 
-/// Authentication failure — the bearer key could not be resolved. Maps to
-/// `401 invalid_api_key` (#49/#63).
+/// Authentication failure — the bearer key could not be resolved.
 #[derive(Debug, thiserror::Error)]
 pub enum AuthError {
+    /// The key is genuinely unknown → `401 invalid_api_key` (#49/#63).
     #[error("invalid or unknown API key")]
     InvalidKey,
+    /// The authority that could resolve the key is unreachable (e.g. the
+    /// helexa-upstream client failed, #57). Fail **closed** but distinctly:
+    /// a transient outage must surface as `503 service_unavailable` +
+    /// `Retry-After`, never `401` — a real key must not be rejected as
+    /// invalid during an upstream blip.
+    #[error("entitlement authority unavailable; retry in {retry_after_secs}s")]
+    Unavailable { retry_after_secs: u64 },
 }
 
 /// Why a reservation was refused. Carries enough for the caller to build the

crates/cortex-core/src/openai.rs

@@ -116,6 +116,23 @@ pub struct Usage {
     /// prompt caching lands (#11); `None` until then.
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub prompt_tokens_details: Option<PromptTokensDetails>,
+    /// helexa extension (non-OpenAI): server-measured prefill/decode
+    /// timing, so the bench harness can compute true prefill vs decode
+    /// tok/s instead of inferring both from client-side SSE arrival
+    /// (#85). Additive and optional — standard OpenAI clients ignore
+    /// it; cortex forwards usage verbatim so it survives proxying.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub helexa_timing: Option<HelexaTiming>,
+}
+
+/// helexa extension carried on [`Usage::helexa_timing`]. Mirrors
+/// neuron's internal `FinishTiming`. All fields are server-measured;
+/// `prefill_tokens` is the prefill-rate denominator.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct HelexaTiming {
+    pub prefill_ms: u64,
+    pub decode_ms: u64,
+    pub prefill_tokens: u64,
 }
 
 /// Sub-counts of `Usage::completion_tokens`.

crates/cortex-core/src/responses.rs

@@ -66,14 +66,48 @@ pub struct ResponsesRequest {
     pub extra: Value,
 }
 
-/// `input` is either a single string or an array of typed items.
+/// `input` is either a single string or an array of items.
 /// `#[serde(untagged)]` so the wire shape `"input": "hi"` and
 /// `"input": [{...}]` both deserialize.
 #[derive(Debug, Clone, Serialize, Deserialize)]
 #[serde(untagged)]
 pub enum ResponsesInput {
     Text(String),
-    Items(Vec<ResponsesInputItem>),
+    Items(Vec<ResponsesInputElement>),
+}
+
+/// One element of an `input` array.
+///
+/// OpenAI's Responses API accepts three shapes here, and real clients
+/// use all of them — most notably agent-zero (via litellm), which
+/// sends the bare "easy message" form. We must tolerate every shape,
+/// because `input` is an `#[serde(untagged)]` array: a single element
+/// that matches no variant fails the *entire* request with a 422
+/// (`did not match any variant of untagged enum ResponsesInput`).
+///
+/// 1. [`Self::Typed`] — an item carrying an explicit `"type"`
+///    discriminant (`message`, `function_call`, `function_call_output`,
+///    `reasoning`).
+/// 2. [`Self::EasyMessage`] — a bare `{role, content}` with **no**
+///    `type` field. This is OpenAI's `EasyInputMessage` and what
+///    litellm emits for every turn. `content` is optional so an
+///    assistant turn carrying only tool calls (`content: null`) still
+///    parses.
+/// 3. [`Self::Other`] — anything else, captured as raw JSON and
+///    dropped during translation. This is the forward-compat escape
+///    hatch that mirrors [`ResponsesRequest::extra`] at the item
+///    level: an unmodeled item type can never again reject the whole
+///    request.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+#[serde(untagged)]
+pub enum ResponsesInputElement {
+    Typed(ResponsesInputItem),
+    EasyMessage {
+        role: String,
+        #[serde(default, skip_serializing_if = "Option::is_none")]
+        content: Option<ResponsesMessageContent>,
+    },
+    Other(Value),
 }
 
 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -91,8 +125,11 @@ pub enum ResponsesInputItem {
         name: String,
         arguments: String,
     },
-    /// User is feeding a tool result back into the model.
-    FunctionCallOutput { call_id: String, output: String },
+    /// User is feeding a tool result back into the model. `output`
+    /// is a `Value` because OpenAI allows it to be either a plain
+    /// string or an array of content parts; the translator renders
+    /// either form to text rather than losing the tool result.
+    FunctionCallOutput { call_id: String, output: Value },
     /// Reasoning items emitted by o-series models. Accepted but
     /// not forwarded to the model — neuron's candle path doesn't
     /// surface reasoning separately yet.
@@ -132,6 +169,11 @@ pub enum ResponsesContentPart {
         #[serde(default, skip_serializing_if = "Vec::is_empty")]
         annotations: Vec<Value>,
     },
+    /// Any content-part type we don't model (e.g. `refusal`, audio).
+    /// Captured as a unit so an unknown part can't reject the whole
+    /// request; dropped during translation.
+    #[serde(other)]
+    Unknown,
 }
 
 // ── Response (non-streaming) ─────────────────────────────────────────
@@ -277,20 +319,116 @@ mod tests {
             ResponsesInput::Items(items) => {
                 assert_eq!(items.len(), 1);
                 match &items[0] {
-                    ResponsesInputItem::Message { role, content } => {
+                    ResponsesInputElement::Typed(ResponsesInputItem::Message { role, content }) => {
                         assert_eq!(role, "user");
                         match content {
                             ResponsesMessageContent::Text(t) => assert_eq!(t, "hi"),
                             other => panic!("expected Text content, got {other:?}"),
                         }
                     }
-                    other => panic!("expected Message item, got {other:?}"),
+                    other => panic!("expected typed Message item, got {other:?}"),
                 }
             }
             other => panic!("expected Items, got {other:?}"),
         }
     }
 
+    #[test]
+    fn deserialises_bare_easy_message_without_type() {
+        // The shape agent-zero (via litellm) actually sends: `input`
+        // items are bare `{role, content}` with NO `type` field. This
+        // is the exact payload that was returning 422.
+        let raw = r#"{
+            "model": "Qwen/Qwen3.6-27B",
+            "store": true,
+            "tools": [{"type": "function", "name": "x", "description": "d", "parameters": {}}],
+            "input": [
+                {"role": "system", "content": "you are helpful"},
+                {"role": "assistant", "content": "{\"tool_name\":\"response\"}"},
+                {"role": "user", "content": "hi"}
+            ]
+        }"#;
+        let req: ResponsesRequest = serde_json::from_str(raw).unwrap();
+        let items = match req.input {
+            ResponsesInput::Items(i) => i,
+            other => panic!("expected Items, got {other:?}"),
+        };
+        assert_eq!(items.len(), 3);
+        for el in &items {
+            assert!(
+                matches!(el, ResponsesInputElement::EasyMessage { .. }),
+                "expected EasyMessage, got {el:?}"
+            );
+        }
+        // `tools` / `store` ride through `extra`, not `input`.
+        assert!(req.extra.get("tools").is_some());
+        assert_eq!(req.extra.get("store"), Some(&Value::Bool(true)));
+    }
+
+    #[test]
+    fn tolerates_null_content_and_unknown_item_types() {
+        // An assistant turn carrying only tool calls has `content: null`;
+        // and a future/unmodeled item type must not 422 the request.
+        let raw = r#"{
+            "model": "m",
+            "input": [
+                {"role": "assistant", "content": null},
+                {"type": "item_reference", "id": "abc"},
+                {"type": "function_call_output", "call_id": "c1",
+                 "output": [{"type": "output_text", "text": "result"}]},
+                {"role": "user", "content": "go"}
+            ]
+        }"#;
+        let req: ResponsesRequest = serde_json::from_str(raw).unwrap();
+        let items = match req.input {
+            ResponsesInput::Items(i) => i,
+            other => panic!("expected Items, got {other:?}"),
+        };
+        assert_eq!(items.len(), 4);
+        assert!(matches!(
+            &items[0],
+            ResponsesInputElement::EasyMessage { content: None, .. }
+        ));
+        assert!(matches!(&items[1], ResponsesInputElement::Other(_)));
+        assert!(matches!(
+            &items[2],
+            ResponsesInputElement::Typed(ResponsesInputItem::FunctionCallOutput { .. })
+        ));
+        assert!(matches!(
+            &items[3],
+            ResponsesInputElement::EasyMessage { .. }
+        ));
+    }
+
+    #[test]
+    fn tolerates_unknown_content_part_type() {
+        // A `refusal` (or any unmodeled) content part must parse, not 422.
+        let raw = r#"{
+            "model": "m",
+            "input": [
+                {"role": "assistant", "content": [
+                    {"type": "refusal", "refusal": "no"},
+                    {"type": "output_text", "text": "ok"}
+                ]}
+            ]
+        }"#;
+        let req: ResponsesRequest = serde_json::from_str(raw).unwrap();
+        let items = match req.input {
+            ResponsesInput::Items(i) => i,
+            other => panic!("expected Items, got {other:?}"),
+        };
+        let parts = match &items[0] {
+            ResponsesInputElement::EasyMessage {
+                content: Some(ResponsesMessageContent::Parts(p)),
+                ..
+            } => p,
+            other => panic!("expected EasyMessage with Parts, got {other:?}"),
+        };
+        assert_eq!(parts.len(), 2);
+        assert!(matches!(&parts[0], ResponsesContentPart::Unknown));
+        assert!(matches!(&parts[1], ResponsesContentPart::OutputText { .. }));
+    }
+
     #[test]
     fn deserialises_input_with_image() {
         let raw = r#"{
@@ -308,10 +446,10 @@ mod tests {
             other => panic!("expected Items, got {other:?}"),
         };
         let parts = match &items[0] {
-            ResponsesInputItem::Message {
+            ResponsesInputElement::Typed(ResponsesInputItem::Message {
                 content: ResponsesMessageContent::Parts(p),
                 ..
-            } => p,
+            }) => p,
             other => panic!("expected Parts, got {other:?}"),
         };
         assert_eq!(parts.len(), 2);

crates/cortex-core/src/translate.rs

@@ -400,6 +400,7 @@ pub fn openai_to_anthropic(resp: ChatCompletionResponse) -> MessagesResponse {
         total_tokens: 0,
         completion_tokens_details: None,
         prompt_tokens_details: None,
+        helexa_timing: None,
     });
 
     MessagesResponse {
@@ -772,6 +773,7 @@ mod stream_tests {
             total_tokens: 267,
             completion_tokens_details: None,
             prompt_tokens_details: None,
+            helexa_timing: None,
         });
         t.on_chunk(&usage_chunk);
         let fin = t.finish();

crates/cortex-gateway/src/auth.rs

@@ -22,7 +22,7 @@ use axum::http::header::AUTHORIZATION;
 use axum::http::{HeaderMap, HeaderValue};
 use axum::middleware::Next;
 use axum::response::Response;
-use cortex_core::entitlements::{HEADER_ACCOUNT_ID, HEADER_KEY_ID};
+use cortex_core::entitlements::{AuthError, HEADER_ACCOUNT_ID, HEADER_KEY_ID};
 use cortex_core::error_envelope::OpenAiError;
 use std::sync::Arc;
 
@@ -83,14 +83,25 @@ pub async fn require_principal(
                 req.extensions_mut().insert(principal);
                 next.run(req).await
             }
-            // An unrecognized key only hard-fails when auth is *required*.
-            // In allow-anonymous mode (the default) we must IGNORE it and
-            // serve the request unauthenticated — otherwise the placeholder
-            // keys that OpenAI-compatible clients send by default (opencode,
-            // Open WebUI, Agent Zero, litellm) would all break, even though
-            // the operator never opted into auth. Pre-#49 the bearer was
-            // never inspected at all; this preserves that for require_auth=false.
-            Err(_) => {
+            // The entitlement authority is unreachable (upstream client
+            // blip, #57). Fail **closed but distinct**: a transient outage
+            // must not reject a real key as `401 invalid_api_key` — it's a
+            // retryable `503`. This holds regardless of require_auth: we
+            // can't safely serve a key we couldn't authorize.
+            Err(AuthError::Unavailable { retry_after_secs }) => {
+                envelope_response(OpenAiError::service_unavailable(
+                    "entitlement authority temporarily unavailable",
+                    Some(retry_after_secs),
+                ))
+            }
+            // A genuinely unrecognized key only hard-fails when auth is
+            // *required*. In allow-anonymous mode (the default) we IGNORE it
+            // and serve unauthenticated — otherwise the placeholder keys that
+            // OpenAI-compatible clients send by default (opencode, Open WebUI,
+            // Agent Zero, litellm) would all break though the operator never
+            // opted into auth. Pre-#49 the bearer was never inspected; this
+            // preserves that for require_auth=false.
+            Err(AuthError::InvalidKey) => {
                 if fleet.require_auth {
                     unauthorized("invalid API key")
                 } else {

crates/cortex-gateway/src/entitlements_chain.rs

@@ -0,0 +1,112 @@
+//! Chained entitlement provider (#57): operator-local keys first, mesh
+//! upstream for everything else.
+//!
+//! `resolve` tries the [`LocalEntitlementProvider`] (operator + infra keys —
+//! never a network hop); only a locally-unknown key falls through to
+//! [`UpstreamEntitlementProvider`]. Because the local provider treats an
+//! unconfigured principal as uncapped, reserve/settle/release/snapshot must
+//! **not** blindly hit local — they dispatch to whichever backend resolved
+//! that account, remembered in a map keyed by `account_id` (populated at
+//! resolve time).
+
+use crate::entitlements_local::LocalEntitlementProvider;
+use crate::entitlements_upstream::UpstreamEntitlementProvider;
+use async_trait::async_trait;
+use cortex_core::entitlements::{
+    AuthError, BudgetError, BudgetSnapshot, EntitlementProvider, Principal, Reservation,
+};
+use std::collections::HashMap;
+use tokio::sync::RwLock;
+
+#[derive(Clone, Copy, Debug, PartialEq, Eq)]
+enum Backend {
+    Local,
+    Upstream,
+}
+
+pub struct ChainedEntitlementProvider {
+    local: LocalEntitlementProvider,
+    upstream: UpstreamEntitlementProvider,
+    /// account_id → which backend owns it, learned at resolve time.
+    backends: RwLock<HashMap<String, Backend>>,
+}
+
+impl ChainedEntitlementProvider {
+    pub fn new(local: LocalEntitlementProvider, upstream: UpstreamEntitlementProvider) -> Self {
+        Self {
+            local,
+            upstream,
+            backends: RwLock::new(HashMap::new()),
+        }
+    }
+
+    async fn record(&self, account_id: &str, backend: Backend) {
+        self.backends
+            .write()
+            .await
+            .insert(account_id.to_string(), backend);
+    }
+
+    /// The backend that owns `account_id`. Defaults to `Upstream` for an
+    /// account never resolved this process-lifetime (a resolve always
+    /// precedes reserve in a request, so this is just a safe fallback —
+    /// upstream fails closed if the account is bogus).
+    async fn backend_for(&self, account_id: &str) -> Backend {
+        self.backends
+            .read()
+            .await
+            .get(account_id)
+            .copied()
+            .unwrap_or(Backend::Upstream)
+    }
+}
+
+#[async_trait]
+impl EntitlementProvider for ChainedEntitlementProvider {
+    async fn resolve(&self, api_key: &str) -> Result<Principal, AuthError> {
+        match self.local.resolve(api_key).await {
+            Ok(p) => {
+                self.record(&p.account_id, Backend::Local).await;
+                Ok(p)
+            }
+            Err(AuthError::InvalidKey) => {
+                let p = self.upstream.resolve(api_key).await?;
+                self.record(&p.account_id, Backend::Upstream).await;
+                Ok(p)
+            }
+            Err(e) => Err(e),
+        }
+    }
+
+    async fn reserve(
+        &self,
+        principal: &Principal,
+        max_tokens: u64,
+    ) -> Result<Reservation, BudgetError> {
+        match self.backend_for(&principal.account_id).await {
+            Backend::Local => self.local.reserve(principal, max_tokens).await,
+            Backend::Upstream => self.upstream.reserve(principal, max_tokens).await,
+        }
+    }
+
+    async fn settle(&self, reservation: Reservation, actual_tokens: u64) {
+        match self.backend_for(&reservation.principal.account_id).await {
+            Backend::Local => self.local.settle(reservation, actual_tokens).await,
+            Backend::Upstream => self.upstream.settle(reservation, actual_tokens).await,
+        }
+    }
+
+    async fn release(&self, reservation: Reservation) {
+        match self.backend_for(&reservation.principal.account_id).await {
+            Backend::Local => self.local.release(reservation).await,
+            Backend::Upstream => self.upstream.release(reservation).await,
+        }
+    }
+
+    async fn snapshot(&self, principal: &Principal) -> Option<BudgetSnapshot> {
+        match self.backend_for(&principal.account_id).await {
+            Backend::Local => self.local.snapshot(principal).await,
+            Backend::Upstream => self.upstream.snapshot(principal).await,
+        }
+    }
+}

crates/cortex-gateway/src/entitlements_upstream.rs

@@ -0,0 +1,246 @@
+//! helexa-upstream client (#57): an [`EntitlementProvider`] that resolves
+//! keys and reserves/settles budget against the mesh authority's
+//! `/authz/v1` surface (B2). It is "just another impl of the trait" — cortex
+//! enforcement (`auth.rs`, `metering.rs`) is unchanged.
+//!
+//! **Fail closed.** When upstream is unreachable, `resolve` returns
+//! [`AuthError::Unavailable`] (→ `503`, never `401`) and `reserve` refuses
+//! with a retryable [`BudgetError::RateLimited`] — a request is never served
+//! on an un-authorized key, and a real key is never rejected as invalid
+//! during a blip.
+
+use async_trait::async_trait;
+use cortex_core::config::UpstreamClientConfig;
+use cortex_core::entitlements::{
+    AuthError, BudgetError, BudgetSnapshot, EntitlementProvider, Principal, Reservation,
+};
+use serde::Deserialize;
+use std::time::Duration;
+
+/// Retry-After (seconds) advertised when we fail closed on an upstream
+/// outage.
+const FAIL_CLOSED_RETRY_SECS: u64 = 5;
+
+pub struct UpstreamEntitlementProvider {
+    client: reqwest::Client,
+    base_url: String,
+    bearer: String,
+}
+
+#[derive(Deserialize)]
+struct PrincipalDto {
+    account_id: String,
+    key_id: String,
+}
+#[derive(Deserialize)]
+struct SnapshotDto {
+    hard_cap: Option<u64>,
+    spent: u64,
+    reserved: u64,
+}
+#[derive(Deserialize)]
+struct ResolveResp {
+    principal: PrincipalDto,
+    #[allow(dead_code)]
+    snapshot: Option<SnapshotDto>,
+}
+#[derive(Deserialize)]
+struct ReserveResp {
+    reservation_id: Option<i64>,
+    rejected: Option<Rejection>,
+}
+#[derive(Deserialize)]
+#[serde(tag = "kind", rename_all = "snake_case")]
+enum Rejection {
+    InsufficientQuota {
+        requested: u64,
+        available: u64,
+    },
+    RateLimited {
+        requested: u64,
+        available: u64,
+        retry_after_secs: u64,
+    },
+}
+
+impl UpstreamEntitlementProvider {
+    pub fn new(cfg: &UpstreamClientConfig) -> Self {
+        let client = reqwest::Client::builder()
+            .timeout(Duration::from_secs(cfg.timeout_secs))
+            .build()
+            .expect("failed to build upstream HTTP client");
+        Self {
+            client,
+            base_url: cfg.url.trim_end_matches('/').to_string(),
+            bearer: cfg.bearer.clone(),
+        }
+    }
+
+    fn url(&self, path: &str) -> String {
+        format!("{}{}", self.base_url, path)
+    }
+}
+
+#[async_trait]
+impl EntitlementProvider for UpstreamEntitlementProvider {
+    async fn resolve(&self, api_key: &str) -> Result<Principal, AuthError> {
+        let resp = self
+            .client
+            .post(self.url("/authz/v1/resolve"))
+            .bearer_auth(&self.bearer)
+            .json(&serde_json::json!({ "api_key": api_key }))
+            .send()
+            .await;
+        let resp = match resp {
+            Ok(r) => r,
+            Err(e) => {
+                tracing::warn!(error = %e, "upstream resolve unreachable; failing closed");
+                return Err(AuthError::Unavailable {
+                    retry_after_secs: FAIL_CLOSED_RETRY_SECS,
+                });
+            }
+        };
+        if resp.status().as_u16() == 401 {
+            return Err(AuthError::InvalidKey);
+        }
+        if !resp.status().is_success() {
+            return Err(AuthError::Unavailable {
+                retry_after_secs: FAIL_CLOSED_RETRY_SECS,
+            });
+        }
+        match resp.json::<ResolveResp>().await {
+            Ok(r) => Ok(Principal {
+                account_id: r.principal.account_id,
+                key_id: r.principal.key_id,
+            }),
+            Err(e) => {
+                tracing::warn!(error = %e, "upstream resolve: bad body; failing closed");
+                Err(AuthError::Unavailable {
+                    retry_after_secs: FAIL_CLOSED_RETRY_SECS,
+                })
+            }
+        }
+    }
+
+    async fn reserve(
+        &self,
+        principal: &Principal,
+        max_tokens: u64,
+    ) -> Result<Reservation, BudgetError> {
+        let fail_closed = || BudgetError::RateLimited {
+            requested: max_tokens,
+            available: 0,
+            retry_after_secs: FAIL_CLOSED_RETRY_SECS,
+        };
+        let resp = self
+            .client
+            .post(self.url("/authz/v1/reserve"))
+            .bearer_auth(&self.bearer)
+            .json(&serde_json::json!({
+                "account_id": principal.account_id,
+                "key_id": principal.key_id,
+                "max_tokens": max_tokens,
+            }))
+            .send()
+            .await;
+        let resp = match resp {
+            Ok(r) if r.status().is_success() => r,
+            Ok(r) => {
+                tracing::warn!(status = %r.status(), "upstream reserve non-2xx; failing closed");
+                return Err(fail_closed());
+            }
+            Err(e) => {
+                tracing::warn!(error = %e, "upstream reserve unreachable; failing closed");
+                return Err(fail_closed());
+            }
+        };
+        match resp.json::<ReserveResp>().await {
+            Ok(ReserveResp {
+                reservation_id: Some(id),
+                ..
+            }) => Ok(Reservation {
+                id: id as u64,
+                principal: principal.clone(),
+                reserved: max_tokens,
+            }),
+            Ok(ReserveResp {
+                rejected:
+                    Some(Rejection::InsufficientQuota {
+                        requested,
+                        available,
+                    }),
+                ..
+            }) => Err(BudgetError::InsufficientQuota {
+                requested,
+                available,
+            }),
+            Ok(ReserveResp {
+                rejected:
+                    Some(Rejection::RateLimited {
+                        requested,
+                        available,
+                        retry_after_secs,
+                    }),
+                ..
+            }) => Err(BudgetError::RateLimited {
+                requested,
+                available,
+                retry_after_secs,
+            }),
+            _ => Err(fail_closed()),
+        }
+    }
+
+    async fn settle(&self, reservation: Reservation, actual_tokens: u64) {
+        // Best-effort; a lost settle is reaped by the upstream sweeper (B2).
+        let _ = self
+            .client
+            .post(self.url("/authz/v1/settle"))
+            .bearer_auth(&self.bearer)
+            .json(&serde_json::json!({
+                "reservation_id": reservation.id as i64,
+                "actual_tokens": actual_tokens,
+            }))
+            .send()
+            .await
+            .inspect_err(
+                |e| tracing::warn!(error = %e, "upstream settle failed (sweeper will reap)"),
+            );
+    }
+
+    async fn release(&self, reservation: Reservation) {
+        let _ = self
+            .client
+            .post(self.url("/authz/v1/release"))
+            .bearer_auth(&self.bearer)
+            .json(&serde_json::json!({ "reservation_id": reservation.id as i64 }))
+            .send()
+            .await
+            .inspect_err(
+                |e| tracing::warn!(error = %e, "upstream release failed (sweeper will reap)"),
+            );
+    }
+
+    async fn snapshot(&self, principal: &Principal) -> Option<BudgetSnapshot> {
+        let resp = self
+            .client
+            .post(self.url("/authz/v1/snapshot"))
+            .bearer_auth(&self.bearer)
+            .json(&serde_json::json!({
+                "account_id": principal.account_id,
+                "key_id": principal.key_id,
+            }))
+            .send()
+            .await
+            .ok()?;
+        if !resp.status().is_success() {
+            return None;
+        }
+        let dto = resp.json::<SnapshotDto>().await.ok()?;
+        Some(BudgetSnapshot {
+            hard_cap: dto.hard_cap,
+            spent: dto.spent,
+            reserved: dto.reserved,
+        })
+    }
+}

crates/cortex-gateway/src/handlers.rs

@@ -322,7 +322,11 @@ async fn anthropic_messages(
             )
             .await
             {
-                Ok(guard) => Some(crate::metering::usage_sink(principal, guard)),
+                Ok(guard) => Some(crate::metering::usage_sink(
+                    principal,
+                    guard,
+                    std::sync::Arc::clone(&fleet.served_usage),
+                )),
                 Err(env) => return crate::error::envelope_response(env),
             }
         }
@@ -802,7 +806,11 @@ async fn proxy_with_metrics(
             )
             .await
             {
-                Ok(guard) => Some(crate::metering::usage_sink(principal, guard)),
+                Ok(guard) => Some(crate::metering::usage_sink(
+                    principal,
+                    guard,
+                    std::sync::Arc::clone(&fleet.served_usage),
+                )),
                 Err(env) => return crate::error::envelope_response(env),
             }
         }

crates/cortex-gateway/src/lib.rs

@@ -1,6 +1,8 @@
 pub mod anthropic_sse;
 pub mod auth;
+pub mod entitlements_chain;
 pub mod entitlements_local;
+pub mod entitlements_upstream;
 pub mod error;
 pub mod evictor;
 pub mod handlers;
@@ -9,6 +11,7 @@ pub mod metrics;
 pub mod poller;
 pub mod proxy;
 pub mod router;
+pub mod served_usage;
 pub mod state;
 
 use anyhow::Result;
@@ -55,6 +58,28 @@ pub async fn run(config: GatewayConfig) -> Result<()> {
         evictor::eviction_loop(evictor_fleet).await;
     });
 
+    // Served-usage reporter (#58): when this operator is part of the mesh,
+    // periodically flush absolute per-principal served-token counters to
+    // upstream for reconciliation.
+    if config.upstream.enabled {
+        let su_fleet = Arc::clone(&fleet);
+        let url = config.upstream.url.clone();
+        let bearer = config.upstream.bearer.clone();
+        let interval =
+            std::time::Duration::from_secs(config.upstream.served_usage_report_interval_secs);
+        tokio::spawn(async move {
+            loop {
+                tokio::time::sleep(interval).await;
+                let rows = su_fleet.served_usage.snapshot();
+                if let Err(e) =
+                    served_usage::report(&su_fleet.http_client, &url, &bearer, &rows).await
+                {
+                    tracing::warn!(error = %e, "served-usage report failed (will retry)");
+                }
+            }
+        });
+    }
+
     let app = build_app(Arc::clone(&fleet));
 
     let listen_addr = config.gateway.listen.parse::<std::net::SocketAddr>()?;

crates/cortex-gateway/src/metering.rs

@@ -117,9 +117,21 @@ impl Drop for ReservationGuard {
 /// Build the completion sink for an authenticated request: record spend and
 /// settle the reservation with the observed total. Dropping it unused (no
 /// usage observed) releases the reservation via the guard.
-pub fn usage_sink(principal: Principal, guard: ReservationGuard) -> UsageSink {
+pub fn usage_sink(
+    principal: Principal,
+    guard: ReservationGuard,
+    served_usage: std::sync::Arc<crate::served_usage::ServedUsage>,
+) -> UsageSink {
     Box::new(move |prompt, completion| {
         record_spend(&principal, prompt, completion);
+        // Per-principal served-usage tally for #58 reconciliation. Recorded
+        // for every metered (authenticated) request; the flush task reports
+        // it to upstream when the operator is part of the mesh.
+        served_usage.add(
+            &principal.account_id,
+            &principal.key_id,
+            prompt + completion,
+        );
         guard.settle(prompt + completion);
     })
 }

crates/cortex-gateway/src/served_usage.rs

@@ -0,0 +1,105 @@
+//! Served-usage ledger (#58): cortex meters, per principal and per UTC day,
+//! the tokens it has served on behalf of mesh accounts, and periodically
+//! reports **absolute** cumulative counters to helexa-upstream for
+//! reconciliation (operators are compensated for served tokens).
+//!
+//! Counters are cumulative-since-process-start for the current period;
+//! upstream upserts them monotonically (GREATEST), so re-sending the same
+//! value is idempotent and a flush that races another is harmless. (A
+//! process restart resets the in-memory counter; the monotonic upsert keeps
+//! upstream from regressing — at most it under-counts the restarted window,
+//! acceptable for beta. One cortex per operator token is assumed.)
+
+use serde::Serialize;
+use std::collections::HashMap;
+use std::sync::Mutex;
+
+#[derive(Debug, Clone, Serialize, PartialEq, Eq)]
+pub struct ServedRow {
+    pub account_id: String,
+    pub key_id: String,
+    pub period: String, // YYYY-MM-DD (UTC)
+    pub served_tokens: u64,
+}
+
+#[derive(Default)]
+pub struct ServedUsage {
+    inner: Mutex<HashMap<(String, String, String), u64>>,
+}
+
+impl ServedUsage {
+    pub fn new() -> Self {
+        Self::default()
+    }
+
+    /// Add served tokens for a principal in today's (UTC) period.
+    pub fn add(&self, account_id: &str, key_id: &str, tokens: u64) {
+        if tokens == 0 {
+            return;
+        }
+        let period = chrono::Utc::now().format("%Y-%m-%d").to_string();
+        let mut m = self.inner.lock().expect("served-usage lock");
+        *m.entry((account_id.to_string(), key_id.to_string(), period))
+            .or_insert(0) += tokens;
+    }
+
+    /// Absolute cumulative counters, for a flush to upstream.
+    pub fn snapshot(&self) -> Vec<ServedRow> {
+        let m = self.inner.lock().expect("served-usage lock");
+        m.iter()
+            .map(|((account_id, key_id, period), &served_tokens)| ServedRow {
+                account_id: account_id.clone(),
+                key_id: key_id.clone(),
+                period: period.clone(),
+                served_tokens,
+            })
+            .collect()
+    }
+}
+
+/// POST the absolute counters to upstream's `/authz/v1/served-usage`.
+pub async fn report(
+    client: &reqwest::Client,
+    base_url: &str,
+    bearer: &str,
+    rows: &[ServedRow],
+) -> Result<(), reqwest::Error> {
+    if rows.is_empty() {
+        return Ok(());
+    }
+    let url = format!("{}/authz/v1/served-usage", base_url.trim_end_matches('/'));
+    client
+        .post(url)
+        .bearer_auth(bearer)
+        .json(&serde_json::json!({ "rows": rows }))
+        .send()
+        .await?
+        .error_for_status()?;
+    Ok(())
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn accumulates_per_principal_and_period() {
+        let su = ServedUsage::new();
+        su.add("acct", "key", 10);
+        su.add("acct", "key", 5);
+        su.add("acct", "other", 7);
+        su.add("acct", "key", 0); // no-op
+        let mut rows = su.snapshot();
+        rows.sort_by(|a, b| a.key_id.cmp(&b.key_id));
+        assert_eq!(rows.len(), 2);
+        let key_row = rows.iter().find(|r| r.key_id == "key").unwrap();
+        assert_eq!(key_row.served_tokens, 15);
+        assert_eq!(
+            rows.iter()
+                .find(|r| r.key_id == "other")
+                .unwrap()
+                .served_tokens,
+            7
+        );
+    }
+}

crates/cortex-gateway/src/state.rs

@@ -1,4 +1,6 @@
+use crate::entitlements_chain::ChainedEntitlementProvider;
 use crate::entitlements_local::LocalEntitlementProvider;
+use crate::entitlements_upstream::UpstreamEntitlementProvider;
 use cortex_core::catalogue::ModelCatalogue;
 use cortex_core::config::{EvictionSettings, GatewayConfig, NeuronEndpoint};
 use cortex_core::entitlements::EntitlementProvider;
@@ -20,6 +22,9 @@ pub struct CortexState {
     /// Whether to reject unauthenticated requests (#49). Read by the auth
     /// middleware once it lands.
     pub require_auth: bool,
+    /// Per-principal served-token tally (#58), reported to upstream for
+    /// operator reconciliation by the flush task when upstream is enabled.
+    pub served_usage: Arc<crate::served_usage::ServedUsage>,
 }
 
 impl CortexState {
@@ -45,8 +50,20 @@ impl CortexState {
 
         let catalogue = ModelCatalogue::load(&config.models_config);
 
-        let entitlements: Arc<dyn EntitlementProvider> =
-            Arc::new(LocalEntitlementProvider::from_config(&config.entitlements));
+        // Local provider always handles operator + infra keys. When the
+        // upstream client is enabled (#57), wrap it in the chain so locally
+        // unknown keys fall through to the mesh authority; otherwise stay
+        // purely local.
+        let local = LocalEntitlementProvider::from_config(&config.entitlements);
+        let entitlements: Arc<dyn EntitlementProvider> = if config.upstream.enabled {
+            tracing::info!(url = %config.upstream.url, "upstream entitlement client enabled");
+            Arc::new(ChainedEntitlementProvider::new(
+                local,
+                UpstreamEntitlementProvider::new(&config.upstream),
+            ))
+        } else {
+            Arc::new(local)
+        };
 
         Self {
             nodes: RwLock::new(nodes),
@@ -59,6 +76,7 @@ impl CortexState {
                 .expect("failed to build HTTP client"),
             entitlements,
             require_auth: config.entitlements.require_auth,
+            served_usage: Arc::new(crate::served_usage::ServedUsage::new()),
         }
     }
 }

crates/cortex-gateway/tests/aliases.rs

@@ -57,6 +57,7 @@ async fn test_alias_resolves_in_chat_completions() {
         }],
         models_config: models_path.to_string_lossy().to_string(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
 
     let fleet = Arc::new(CortexState::from_config(&config));
@@ -143,6 +144,7 @@ async fn test_aliases_surface_in_v1_models() {
         }],
         models_config: models_path.to_string_lossy().to_string(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
 
     let fleet = Arc::new(CortexState::from_config(&config));
@@ -232,6 +234,7 @@ async fn test_alias_falls_through_for_unmapped_model() {
         }],
         models_config: models_path.to_string_lossy().to_string(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
 
     let fleet = Arc::new(CortexState::from_config(&config));

crates/cortex-gateway/tests/auth.rs

@@ -105,6 +105,7 @@ async fn spawn_gateway(neuron_url: &str, entitlements: EntitlementsConfig) -> St
         }],
         models_config: "/dev/null".into(),
         entitlements,
+        upstream: Default::default(),
     };
 
     let fleet = Arc::new(CortexState::from_config(&config));

crates/cortex-gateway/tests/budget_enforcement.rs

@@ -81,6 +81,7 @@ async fn spawn_gateway(neuron_url: &str, key: ApiKeyConfig) -> (Arc<CortexState>
             require_auth: true,
             keys: vec![key],
         },
+        upstream: Default::default(),
     };
     let fleet = Arc::new(CortexState::from_config(&config));
     {

crates/cortex-gateway/tests/common/mod.rs

@@ -430,6 +430,7 @@ pub async fn spawn_gateway_with_state(mock_url: &str) -> (Arc<CortexState>, Stri
         }],
         models_config: "/dev/null".into(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
 
     let fleet = Arc::new(CortexState::from_config(&config));

crates/cortex-gateway/tests/error_envelope.rs

@@ -89,6 +89,7 @@ async fn error_response_no_healthy_nodes() {
         }],
         models_config: "/dev/null".into(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
 
     let fleet = Arc::new(cortex_gateway::state::CortexState::from_config(&config));

crates/cortex-gateway/tests/eviction.rs

@@ -72,6 +72,7 @@ fn make_fleet(endpoint: &str, defrag_after: u32) -> Arc<CortexState> {
         }],
         models_config: "/dev/null".into(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
     Arc::new(CortexState::from_config(&config))
 }

crates/cortex-gateway/tests/feasibility_routing.rs

@@ -74,6 +74,7 @@ async fn fleet_with(big_healthy: bool, big_devices: usize) -> Arc<CortexState> {
         ],
         models_config: cat.to_string_lossy().into_owned(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
     let fleet = Arc::new(CortexState::from_config(&config));
     {

crates/cortex-gateway/tests/load_routing.rs

@@ -72,6 +72,7 @@ async fn two_neuron_fleet(endpoint_a: &str, endpoint_b: &str) -> Arc<CortexState
         ],
         models_config: "/dev/null".into(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
     Arc::new(CortexState::from_config(&config))
 }

crates/cortex-gateway/tests/metering.rs

@@ -53,6 +53,7 @@ async fn spawn_metered_gateway(neuron_url: &str) -> (Arc<CortexState>, String) {
                 window: CapWindow::Balance,
             }],
         },
+        upstream: Default::default(),
     };
 
     let fleet = Arc::new(CortexState::from_config(&config));
@@ -158,6 +159,7 @@ async fn anonymous_request_records_no_spend() {
         }],
         models_config: "/dev/null".into(),
         entitlements: EntitlementsConfig::default(),
+        upstream: Default::default(),
     };
     let fleet = Arc::new(CortexState::from_config(&config));
     {

crates/cortex-gateway/tests/model_cost.rs

@@ -66,6 +66,7 @@ harness = "candle"
         }],
         models_config: cat_path.to_string_lossy().into_owned(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
 
     let fleet = Arc::new(CortexState::from_config(&config));

crates/cortex-gateway/tests/model_limits.rs

@@ -55,6 +55,7 @@ capabilities = ["text"]
         }],
         models_config: cat_path.to_string_lossy().into_owned(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
 
     let fleet = Arc::new(CortexState::from_config(&config));

crates/cortex-gateway/tests/poller.rs

@@ -32,6 +32,7 @@ async fn test_poller_discovers_models() {
         }],
         models_config: "/dev/null".into(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
 
     let fleet = Arc::new(CortexState::from_config(&config));
@@ -84,6 +85,7 @@ async fn test_poller_updates_gateway_models_endpoint() {
         }],
         models_config: "/dev/null".into(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
 
     let fleet = Arc::new(CortexState::from_config(&config));
@@ -156,6 +158,7 @@ async fn test_models_endpoint_unions_capabilities_across_nodes() {
         ],
         models_config: "/dev/null".into(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
 
     let fleet = Arc::new(CortexState::from_config(&config));
@@ -219,6 +222,7 @@ async fn test_poller_marks_unreachable_node_unhealthy() {
         }],
         models_config: "/dev/null".into(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
 
     let fleet = Arc::new(CortexState::from_config(&config));
@@ -273,6 +277,7 @@ async fn test_poller_removes_stale_models() {
         }],
         models_config: "/dev/null".into(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
 
     let fleet = Arc::new(CortexState::from_config(&config));
@@ -304,6 +309,7 @@ async fn test_poller_removes_stale_models() {
         }],
         models_config: "/dev/null".into(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
 
     let fleet2 = Arc::new(CortexState::from_config(&config2));
@@ -386,6 +392,7 @@ async fn test_poller_captures_activation_from_health() {
         }],
         models_config: "/dev/null".into(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
 
     let fleet = Arc::new(CortexState::from_config(&config));
@@ -431,6 +438,7 @@ async fn test_poller_parses_recovering_status() {
         }],
         models_config: "/dev/null".into(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
 
     let fleet = Arc::new(CortexState::from_config(&config));

crates/cortex-gateway/tests/prompt_prevalidation.rs

@@ -75,6 +75,7 @@ async fn spawn_gateway(neuron: &str, context: usize) -> String {
         }],
         models_config: "/dev/null".into(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
     let fleet = Arc::new(CortexState::from_config(&config));
     {

crates/cortex-gateway/tests/proxy_basic.rs

@@ -118,6 +118,7 @@ async fn test_no_healthy_nodes() {
         }],
         models_config: "/dev/null".into(),
         entitlements: Default::default(),
+        upstream: Default::default(),
     };
     let fleet = std::sync::Arc::new(cortex_gateway::state::CortexState::from_config(&config));
 

crates/cortex-gateway/tests/upstream_chain.rs

@@ -0,0 +1,106 @@
+//! B3: the chained entitlement provider (local → upstream) and fail-closed
+//! semantics, exercised against a mock helexa-upstream `/authz/v1`.
+
+use axum::{Json, Router, routing::post};
+use cortex_core::config::{ApiKeyConfig, EntitlementsConfig, UpstreamClientConfig};
+use cortex_core::entitlements::{AuthError, EntitlementProvider};
+use cortex_gateway::entitlements_chain::ChainedEntitlementProvider;
+use cortex_gateway::entitlements_local::LocalEntitlementProvider;
+use cortex_gateway::entitlements_upstream::UpstreamEntitlementProvider;
+use serde_json::{Value, json};
+use tokio::net::TcpListener;
+
+/// Mock upstream: `mesh-key` resolves to a mesh account; anything else 401.
+/// reserve always grants reservation 1.
+async fn spawn_mock_upstream() -> String {
+    async fn resolve(Json(body): Json<Value>) -> axum::response::Response {
+        use axum::response::IntoResponse;
+        if body["api_key"] == "mesh-key" {
+            Json(json!({"principal": {"account_id": "mesh-acct", "key_id": "mesh-key-1"}}))
+                .into_response()
+        } else {
+            (
+                axum::http::StatusCode::UNAUTHORIZED,
+                Json(json!({"error": {"code": "invalid_api_key"}})),
+            )
+                .into_response()
+        }
+    }
+    async fn reserve() -> Json<Value> {
+        Json(json!({ "reservation_id": 1 }))
+    }
+    let app = Router::new()
+        .route("/authz/v1/resolve", post(resolve))
+        .route("/authz/v1/reserve", post(reserve));
+    let listener = TcpListener::bind("127.0.0.1:0").await.unwrap();
+    let addr = listener.local_addr().unwrap();
+    tokio::spawn(async move {
+        axum::serve(listener, app).await.unwrap();
+    });
+    format!("http://{addr}")
+}
+
+fn local_with_key() -> LocalEntitlementProvider {
+    let cfg = EntitlementsConfig {
+        require_auth: false,
+        keys: vec![ApiKeyConfig {
+            key: "local-key".into(),
+            account_id: "op".into(),
+            key_id: None,
+            hard_cap: None,
+            window: Default::default(),
+        }],
+    };
+    LocalEntitlementProvider::from_config(&cfg)
+}
+
+fn chain(local: LocalEntitlementProvider, url: &str) -> ChainedEntitlementProvider {
+    let upstream = UpstreamEntitlementProvider::new(&UpstreamClientConfig {
+        enabled: true,
+        url: url.to_string(),
+        bearer: "client-secret".into(),
+        timeout_secs: 5,
+        served_usage_report_interval_secs: 60,
+    });
+    ChainedEntitlementProvider::new(local, upstream)
+}
+
+#[tokio::test]
+async fn local_key_resolves_locally() {
+    let url = spawn_mock_upstream().await;
+    let c = chain(local_with_key(), &url);
+    let p = c.resolve("local-key").await.expect("local resolves");
+    assert_eq!(p.account_id, "op");
+}
+
+#[tokio::test]
+async fn unknown_key_falls_through_to_upstream() {
+    let url = spawn_mock_upstream().await;
+    let c = chain(local_with_key(), &url);
+    let p = c.resolve("mesh-key").await.expect("upstream resolves");
+    assert_eq!(p.account_id, "mesh-acct");
+    assert_eq!(p.key_id, "mesh-key-1");
+}
+
+#[tokio::test]
+async fn unknown_everywhere_is_invalid_key() {
+    let url = spawn_mock_upstream().await;
+    let c = chain(local_with_key(), &url);
+    match c.resolve("nope").await {
+        Err(AuthError::InvalidKey) => {}
+        other => panic!("expected InvalidKey, got {other:?}"),
+    }
+}
+
+#[tokio::test]
+async fn upstream_unreachable_fails_closed_as_unavailable() {
+    // No mock — point at a dead port. A locally-unknown key must surface
+    // Unavailable (→ 503), never InvalidKey (→ 401).
+    let c = chain(local_with_key(), "http://127.0.0.1:1");
+    match c.resolve("some-mesh-key").await {
+        Err(AuthError::Unavailable { retry_after_secs }) => assert!(retry_after_secs > 0),
+        other => panic!("expected Unavailable, got {other:?}"),
+    }
+    // A local key still resolves without touching upstream.
+    assert_eq!(c.resolve("local-key").await.unwrap().account_id, "op");
+}

crates/helexa-upstream/Cargo.toml

@@ -0,0 +1,63 @@
+[package]
+name = "helexa-upstream"
+version.workspace = true
+edition.workspace = true
+license.workspace = true
+repository.workspace = true
+
+[[bin]]
+name = "helexa-upstream"
+path = "src/main.rs"
+
+[lib]
+name = "helexa_upstream"
+path = "src/lib.rs"
+
+[dependencies]
+tokio = { workspace = true }
+axum = { workspace = true }
+tower-http = { workspace = true }
+serde = { workspace = true }
+serde_json = { workspace = true }
+figment = { workspace = true }
+anyhow = { workspace = true }
+thiserror = { workspace = true }
+clap = { workspace = true }
+tracing = { workspace = true }
+tracing-subscriber = { workspace = true }
+chrono = { workspace = true }
+
+# PostgreSQL — the mesh authority's system of record. Runtime query API
+# (not the compile-time `query!` macros) so the crate builds in CI without a
+# live database or a committed `.sqlx` offline cache; correctness is covered
+# by the gated integration tests. (Macro adoption is a later refinement once
+# a dev DB + offline cache exist.)
+sqlx = { version = "0.8", default-features = false, features = [
+    "runtime-tokio",
+    "tls-rustls",
+    "postgres",
+    "macros",
+    "migrate",
+    "chrono",
+    "uuid",
+] }
+uuid = { version = "1", features = ["v4", "serde"] }
+sha2 = "0.10"
+subtle = "2.6"
+# Web auth (B4): argon2id password hashing, JWT sessions, CSPRNG secrets,
+# transactional email.
+argon2 = "0.5"
+jsonwebtoken = "9"
+rand = "0.8"
+lettre = { version = "0.11", default-features = false, features = [
+    "tokio1-rustls-tls",
+    "smtp-transport",
+    "builder",
+] }
+
+# cortex-core for the shared #63 OpenAiError envelope on the authz surface.
+cortex-core = { workspace = true }
+
+[dev-dependencies]
+figment = { workspace = true, features = ["test"] }
+reqwest = { workspace = true }

crates/helexa-upstream/migrations/0001_init.sql

@@ -0,0 +1,137 @@
+-- helexa-upstream initial schema (#59): accounts, keys, ledger, top-up
+-- codes, served-usage. The mesh-level authority's system of record.
+--
+-- Token amounts are BIGINT (i64) throughout; the cortex EntitlementProvider
+-- carries u64 but mesh allocations sit comfortably inside i64 and Postgres
+-- has no unsigned type.
+
+CREATE EXTENSION IF NOT EXISTS citext;
+CREATE EXTENSION IF NOT EXISTS pgcrypto;
+
+-- ── Users (web auth: email + password) ──────────────────────────────
+CREATE TABLE users (
+    id                       UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+    email                    CITEXT NOT NULL UNIQUE,
+    password_hash            TEXT NOT NULL,                 -- argon2id PHC string
+    email_verified           BOOLEAN NOT NULL DEFAULT FALSE,
+    -- Browser fingerprint captured at registration (#abuse). Best-effort,
+    -- client-supplied; the primary signal for silent multi-account
+    -- detection. NULL when the client could not produce one.
+    registration_fingerprint TEXT,
+    created_at               TIMESTAMPTZ NOT NULL DEFAULT now()
+);
+CREATE INDEX users_registration_fingerprint_idx
+    ON users (registration_fingerprint)
+    WHERE registration_fingerprint IS NOT NULL;
+
+-- Single-use email tokens for verification and password reset. Only the
+-- sha256 of the emailed secret is stored.
+CREATE TABLE email_tokens (
+    token_hash BYTEA PRIMARY KEY,
+    user_id    UUID NOT NULL REFERENCES users(id) ON DELETE CASCADE,
+    kind       TEXT NOT NULL CHECK (kind IN ('verify', 'reset')),
+    expires_at TIMESTAMPTZ NOT NULL,
+    consumed_at TIMESTAMPTZ
+);
+CREATE INDEX email_tokens_user_idx ON email_tokens (user_id);
+
+-- ── Accounts (the billable allocation ledger) ───────────────────────
+CREATE TABLE accounts (
+    id                 UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+    owner_user_id      UUID NOT NULL REFERENCES users(id) ON DELETE CASCADE,
+    allocation_total   BIGINT NOT NULL DEFAULT 0,
+    allocation_spent   BIGINT NOT NULL DEFAULT 0,
+    allocation_reserved BIGINT NOT NULL DEFAULT 0,
+    -- 'deactivated' is the SILENT abuse flag: keys stop authorizing but no
+    -- surface ever tells the user why (see resolve → 401).
+    status             TEXT NOT NULL DEFAULT 'active'
+                       CHECK (status IN ('active', 'deactivated')),
+    -- This account shares a registration fingerprint with >= 1 other.
+    fingerprint_flagged BOOLEAN NOT NULL DEFAULT FALSE,
+    created_at         TIMESTAMPTZ NOT NULL DEFAULT now(),
+    -- The no-overshoot backstop to the atomic reserve UPDATE.
+    CONSTRAINT accounts_no_overshoot
+        CHECK (allocation_spent + allocation_reserved <= allocation_total),
+    CONSTRAINT accounts_nonneg
+        CHECK (allocation_spent >= 0 AND allocation_reserved >= 0)
+);
+CREATE INDEX accounts_owner_idx ON accounts (owner_user_id);
+
+-- ── API keys (Principal.key_id = api_keys.id) ───────────────────────
+CREATE TABLE api_keys (
+    id          UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+    account_id  UUID NOT NULL REFERENCES accounts(id) ON DELETE CASCADE,
+    key_hash    BYTEA NOT NULL,                 -- sha256(raw key)
+    key_prefix  TEXT NOT NULL,                  -- non-secret display prefix
+    label       TEXT NOT NULL DEFAULT '',
+    status      TEXT NOT NULL DEFAULT 'active'
+                CHECK (status IN ('active', 'archived')),
+    -- Per-key sub-cap: 'hardcap' = absolute tokens; 'percent' = % of the
+    -- account's allocation_total (resolved to an absolute at reserve time).
+    limit_kind  TEXT NOT NULL DEFAULT 'percent'
+                CHECK (limit_kind IN ('percent', 'hardcap')),
+    limit_value BIGINT NOT NULL DEFAULT 100,
+    -- serde of cortex_core::entitlements::CapWindow (Balance | Rolling).
+    cap_window  JSONB NOT NULL DEFAULT '{"kind":"balance"}'::jsonb,
+    -- Per-key running ledger (mirrors the account ledger; Balance semantics
+    -- in this migration — rolling-window reset lands with the authz API).
+    key_spent    BIGINT NOT NULL DEFAULT 0,
+    key_reserved BIGINT NOT NULL DEFAULT 0,
+    created_at  TIMESTAMPTZ NOT NULL DEFAULT now(),
+    CONSTRAINT api_keys_key_nonneg
+        CHECK (key_spent >= 0 AND key_reserved >= 0)
+);
+-- A raw key resolves only while active; the hash is unique among active keys.
+CREATE UNIQUE INDEX api_keys_active_hash_idx
+    ON api_keys (key_hash) WHERE status = 'active';
+CREATE INDEX api_keys_account_idx ON api_keys (account_id);
+
+-- ── Reservations (reserve → settle/release) ─────────────────────────
+-- id is BIGSERIAL so it maps to the cortex Reservation.id (u64) verbatim,
+-- with the Postgres sequence as the sole global authority.
+CREATE TABLE reservations (
+    id          BIGSERIAL PRIMARY KEY,
+    account_id  UUID NOT NULL REFERENCES accounts(id) ON DELETE CASCADE,
+    key_id      UUID NOT NULL REFERENCES api_keys(id) ON DELETE CASCADE,
+    reserved    BIGINT NOT NULL,
+    actual      BIGINT,
+    state       TEXT NOT NULL DEFAULT 'open'
+                CHECK (state IN ('open', 'settled', 'released')),
+    created_at  TIMESTAMPTZ NOT NULL DEFAULT now(),
+    settled_at  TIMESTAMPTZ
+);
+-- The sweeper scans open reservations by age.
+CREATE INDEX reservations_open_idx
+    ON reservations (created_at) WHERE state = 'open';
+
+-- ── Top-up codes (hybrid allocation) ────────────────────────────────
+CREATE TABLE top_up_codes (
+    code_hash   BYTEA PRIMARY KEY,             -- sha256(raw code)
+    value       BIGINT NOT NULL,              -- tokens this code grants
+    denomination TEXT,                         -- human label (e.g. "small")
+    created_at  TIMESTAMPTZ NOT NULL DEFAULT now(),
+    redeemed_by UUID REFERENCES accounts(id) ON DELETE SET NULL,
+    redeemed_at TIMESTAMPTZ
+);
+
+-- ── Served-usage ledger (#58 reconciliation) ────────────────────────
+-- Absolute per-(operator, account, key, period) served tokens, upserted by
+-- each cortex; reconciliation rolls these up for operator compensation.
+CREATE TABLE served_usage (
+    operator_id   TEXT NOT NULL,
+    account_id    UUID NOT NULL,
+    key_id        UUID NOT NULL,
+    period        DATE NOT NULL,
+    served_tokens BIGINT NOT NULL DEFAULT 0,
+    reconciled_at TIMESTAMPTZ,
+    PRIMARY KEY (operator_id, account_id, key_id, period)
+);
+
+-- ── Web sessions (DB-backed; alt/complement to stateless JWT) ───────
+CREATE TABLE sessions (
+    token_hash BYTEA PRIMARY KEY,             -- sha256(session token)
+    user_id    UUID NOT NULL REFERENCES users(id) ON DELETE CASCADE,
+    expires_at TIMESTAMPTZ NOT NULL,
+    created_at TIMESTAMPTZ NOT NULL DEFAULT now()
+);
+CREATE INDEX sessions_user_idx ON sessions (user_id);

crates/helexa-upstream/src/authz.rs

@@ -0,0 +1,340 @@
+//! `/authz/v1` — the machine surface cortex's `UpstreamEntitlementProvider`
+//! (#57) consumes. It mirrors the `cortex_core::entitlements::EntitlementProvider`
+//! trait 1:1 (resolve / reserve / settle / release / snapshot) over the B1
+//! ledger.
+//!
+//! Contract notes for the cortex client:
+//! - A **non-2xx** response means the authority could not give an
+//!   authoritative answer (bad caller auth, malformed request, server
+//!   error) → the client should **fail closed**.
+//! - `reserve` returns **200** whether granted or budget-refused: the body
+//!   carries either `reservation_id` or a `rejected` discriminant. A budget
+//!   refusal is an authoritative answer, not a transport failure.
+//! - Rejections that are genuinely auth failures use the #63 `OpenAiError`
+//!   envelope so they can be surfaced verbatim.
+
+use crate::crypto::sha256;
+use crate::error::envelope_response;
+use crate::ledger::{self, LedgerError};
+use crate::state::AppState;
+use axum::extract::{Request, State};
+use axum::http::{StatusCode, header};
+use axum::middleware::Next;
+use axum::response::{IntoResponse, Response};
+use axum::routing::post;
+use axum::{Extension, Json, Router};
+use cortex_core::error_envelope::OpenAiError;
+use serde::{Deserialize, Serialize};
+use subtle::ConstantTimeEq;
+use uuid::Uuid;
+
+/// The operator a validated client bearer identifies (served-usage
+/// attribution, #58). Inserted into request extensions by [`client_auth`].
+#[derive(Debug, Clone)]
+pub struct OperatorId(pub String);
+
+/// Build the `/authz/v1` router with the client-auth layer applied.
+pub fn router(state: &AppState) -> Router<AppState> {
+    Router::new()
+        .route("/authz/v1/resolve", post(resolve))
+        .route("/authz/v1/reserve", post(reserve))
+        .route("/authz/v1/settle", post(settle))
+        .route("/authz/v1/release", post(release))
+        .route("/authz/v1/snapshot", post(snapshot))
+        .route("/authz/v1/served-usage", post(served_usage))
+        .layer(axum::middleware::from_fn_with_state(
+            state.clone(),
+            client_auth,
+        ))
+}
+
+// ── client auth (shared bearer → operator_id) ───────────────────────
+
+/// Validate the caller's `Authorization: Bearer` against the configured
+/// client tokens (constant-time) and stamp the `operator_id`. When no tokens
+/// are configured the surface is open (dev) and a synthetic operator is
+/// used.
+async fn client_auth(State(state): State<AppState>, mut req: Request, next: Next) -> Response {
+    let tokens = &state.config.client_auth.tokens;
+    if tokens.is_empty() {
+        req.extensions_mut().insert(OperatorId("dev".into()));
+        return next.run(req).await;
+    }
+    let presented = req
+        .headers()
+        .get(header::AUTHORIZATION)
+        .and_then(|v| v.to_str().ok())
+        .and_then(|v| v.strip_prefix("Bearer "))
+        .map(str::trim)
+        .unwrap_or("");
+    let matched = tokens
+        .iter()
+        .find(|t| t.token.as_bytes().ct_eq(presented.as_bytes()).into());
+    match matched {
+        Some(t) => {
+            req.extensions_mut()
+                .insert(OperatorId(t.operator_id.clone()));
+            next.run(req).await
+        }
+        None => envelope_response(OpenAiError::invalid_api_key(
+            "missing or invalid client credentials",
+        )),
+    }
+}
+
+// ── DTOs ────────────────────────────────────────────────────────────
+
+#[derive(Deserialize)]
+struct ResolveReq {
+    api_key: String,
+}
+
+#[derive(Serialize)]
+struct PrincipalDto {
+    account_id: String,
+    key_id: String,
+}
+
+#[derive(Serialize)]
+struct SnapshotDto {
+    hard_cap: Option<i64>,
+    spent: i64,
+    reserved: i64,
+}
+
+#[derive(Serialize)]
+struct ResolveResp {
+    principal: PrincipalDto,
+    snapshot: SnapshotDto,
+}
+
+#[derive(Deserialize)]
+struct ReserveReq {
+    account_id: String,
+    key_id: String,
+    max_tokens: i64,
+}
+
+#[derive(Serialize, Default)]
+struct ReserveResp {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    reservation_id: Option<i64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    rejected: Option<Rejection>,
+}
+
+#[derive(Serialize)]
+#[serde(tag = "kind", rename_all = "snake_case")]
+enum Rejection {
+    InsufficientQuota {
+        requested: i64,
+        available: i64,
+    },
+    // Part of the frozen wire contract so the cortex client (#57) can map it
+    // without a later breaking change. Not yet constructed: the B1 ledger
+    // implements Balance caps only; rolling-window key sub-caps (which yield
+    // this) land in a follow-up.
+    #[allow(dead_code)]
+    RateLimited {
+        requested: i64,
+        available: i64,
+        retry_after_secs: u64,
+    },
+}
+
+#[derive(Deserialize)]
+struct SettleReq {
+    reservation_id: i64,
+    actual_tokens: i64,
+}
+
+#[derive(Deserialize)]
+struct ReservationRef {
+    reservation_id: i64,
+}
+
+#[derive(Deserialize)]
+struct SnapshotReq {
+    account_id: String,
+    key_id: String,
+}
+
+// ── handlers ────────────────────────────────────────────────────────
+
+/// `POST /authz/v1/resolve` — bearer key → principal + snapshot, or
+/// `401 invalid_api_key` (also for a deactivated account: no clue).
+async fn resolve(State(state): State<AppState>, Json(req): Json<ResolveReq>) -> Response {
+    match ledger::resolve_key(&state.pool, &sha256(&req.api_key)).await {
+        Ok(Some(p)) => Json(ResolveResp {
+            principal: PrincipalDto {
+                account_id: p.account_id.to_string(),
+                key_id: p.key_id.to_string(),
+            },
+            snapshot: SnapshotDto {
+                hard_cap: Some(p.hard_cap),
+                spent: p.key_spent,
+                reserved: p.key_reserved,
+            },
+        })
+        .into_response(),
+        Ok(None) => envelope_response(OpenAiError::invalid_api_key("invalid or unknown API key")),
+        Err(e) => {
+            tracing::error!(error = %e, "resolve query failed");
+            envelope_response(OpenAiError::service_unavailable("authority error", Some(5)))
+        }
+    }
+}
+
+/// `POST /authz/v1/reserve` — 200 with `reservation_id` (granted) or
+/// `rejected` (budget). Non-2xx only for bad input / server error.
+async fn reserve(State(state): State<AppState>, Json(req): Json<ReserveReq>) -> Response {
+    let (Ok(account_id), Ok(key_id)) = (
+        Uuid::parse_str(&req.account_id),
+        Uuid::parse_str(&req.key_id),
+    ) else {
+        return bad_request("account_id and key_id must be UUIDs");
+    };
+    match ledger::reserve(&state.pool, account_id, key_id, req.max_tokens).await {
+        Ok(reservation_id) => Json(ReserveResp {
+            reservation_id: Some(reservation_id),
+            rejected: None,
+        })
+        .into_response(),
+        Err(LedgerError::InsufficientQuota {
+            requested,
+            available,
+        }) => Json(ReserveResp {
+            reservation_id: None,
+            rejected: Some(Rejection::InsufficientQuota {
+                requested,
+                available,
+            }),
+        })
+        .into_response(),
+        Err(LedgerError::AccountNotFound | LedgerError::KeyNotFound) => {
+            // Resolve succeeded earlier; the principal vanished (archived /
+            // deactivated). Treat as no budget — fail closed at the client.
+            Json(ReserveResp {
+                reservation_id: None,
+                rejected: Some(Rejection::InsufficientQuota {
+                    requested: req.max_tokens,
+                    available: 0,
+                }),
+            })
+            .into_response()
+        }
+        Err(LedgerError::Db(e)) => {
+            tracing::error!(error = %e, "reserve failed");
+            envelope_response(OpenAiError::service_unavailable("authority error", Some(5)))
+        }
+    }
+}
+
+/// `POST /authz/v1/settle` — idempotent; `204`.
+async fn settle(State(state): State<AppState>, Json(req): Json<SettleReq>) -> Response {
+    match ledger::settle(&state.pool, req.reservation_id, req.actual_tokens).await {
+        Ok(()) => StatusCode::NO_CONTENT.into_response(),
+        Err(e) => {
+            tracing::error!(error = %e, "settle failed");
+            envelope_response(OpenAiError::service_unavailable("authority error", Some(5)))
+        }
+    }
+}
+
+/// `POST /authz/v1/release` — idempotent; `204`.
+async fn release(State(state): State<AppState>, Json(req): Json<ReservationRef>) -> Response {
+    match ledger::release(&state.pool, req.reservation_id).await {
+        Ok(()) => StatusCode::NO_CONTENT.into_response(),
+        Err(e) => {
+            tracing::error!(error = %e, "release failed");
+            envelope_response(OpenAiError::service_unavailable("authority error", Some(5)))
+        }
+    }
+}
+
+/// `POST /authz/v1/snapshot` — `{hard_cap, spent, reserved}` or `404`.
+async fn snapshot(State(state): State<AppState>, Json(req): Json<SnapshotReq>) -> Response {
+    let (Ok(account_id), Ok(key_id)) = (
+        Uuid::parse_str(&req.account_id),
+        Uuid::parse_str(&req.key_id),
+    ) else {
+        return bad_request("account_id and key_id must be UUIDs");
+    };
+    match ledger::snapshot(&state.pool, account_id, key_id).await {
+        Ok(Some((hard_cap, spent, reserved))) => Json(SnapshotDto {
+            hard_cap: Some(hard_cap),
+            spent,
+            reserved,
+        })
+        .into_response(),
+        Ok(None) => StatusCode::NOT_FOUND.into_response(),
+        Err(e) => {
+            tracing::error!(error = %e, "snapshot failed");
+            envelope_response(OpenAiError::service_unavailable("authority error", Some(5)))
+        }
+    }
+}
+
+// ── served-usage report (#58) ───────────────────────────────────────
+
+#[derive(Deserialize)]
+struct ServedUsageReport {
+    rows: Vec<ServedUsageRow>,
+}
+
+#[derive(Deserialize)]
+struct ServedUsageRow {
+    account_id: String,
+    key_id: String,
+    period: String, // YYYY-MM-DD
+    served_tokens: i64,
+}
+
+/// `POST /authz/v1/served-usage` — a cortex reports the absolute served-token
+/// counters it has accrued for the current period. Upsert is monotonic
+/// (`GREATEST`) so re-sends and races are idempotent and never regress.
+/// `operator_id` comes from the validated client bearer (request extension).
+async fn served_usage(
+    State(state): State<AppState>,
+    Extension(operator): Extension<OperatorId>,
+    Json(req): Json<ServedUsageReport>,
+) -> Response {
+    for row in &req.rows {
+        let (Ok(account_id), Ok(key_id)) = (
+            Uuid::parse_str(&row.account_id),
+            Uuid::parse_str(&row.key_id),
+        ) else {
+            continue; // skip malformed ids rather than fail the whole batch
+        };
+        let Ok(period) = chrono::NaiveDate::parse_from_str(&row.period, "%Y-%m-%d") else {
+            continue;
+        };
+        let res = sqlx::query(
+            "INSERT INTO served_usage (operator_id, account_id, key_id, period, served_tokens) \
+             VALUES ($1, $2, $3, $4, $5) \
+             ON CONFLICT (operator_id, account_id, key_id, period) \
+             DO UPDATE SET served_tokens = GREATEST(served_usage.served_tokens, EXCLUDED.served_tokens)",
+        )
+        .bind(&operator.0)
+        .bind(account_id)
+        .bind(key_id)
+        .bind(period)
+        .bind(row.served_tokens.max(0))
+        .execute(&state.pool)
+        .await;
+        if let Err(e) = res {
+            tracing::error!(error = %e, "served-usage upsert failed");
+            return envelope_response(OpenAiError::service_unavailable("authority error", Some(5)));
+        }
+    }
+    StatusCode::NO_CONTENT.into_response()
+}
+
+fn bad_request(msg: &str) -> Response {
+    envelope_response(OpenAiError::new(
+        400,
+        "invalid_request_error",
+        "invalid_request",
+        msg,
+    ))
+}

crates/helexa-upstream/src/config.rs

@@ -0,0 +1,261 @@
+//! helexa-upstream configuration: loaded from `helexa-upstream.toml` with
+//! figment, `UPSTREAM_`-prefixed env overrides (mirrors the cortex/router
+//! convention, e.g. `UPSTREAM_SERVER__LISTEN`, `UPSTREAM_DB__URL`).
+
+use figment::{
+    Figment,
+    providers::{Env, Format, Toml},
+};
+use serde::{Deserialize, Serialize};
+use std::path::Path;
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct UpstreamConfig {
+    #[serde(default)]
+    pub server: ServerSettings,
+    pub db: DbSettings,
+    #[serde(default)]
+    pub grant: GrantSettings,
+    #[serde(default)]
+    pub abuse: AbuseSettings,
+    #[serde(default)]
+    pub client_auth: ClientAuthSettings,
+    #[serde(default)]
+    pub authz: AuthzSettings,
+    #[serde(default)]
+    pub auth: AuthSettings,
+    #[serde(default)]
+    pub email: EmailSettings,
+}
+
+/// `[auth]` — web-session signing + token lifetimes (B4). Web sessions are
+/// JWTs, distinct from inference API keys.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct AuthSettings {
+    /// HMAC secret for signing session JWTs. MUST be overridden in prod
+    /// (env `UPSTREAM_AUTH__JWT_SECRET`); the default is dev-only.
+    #[serde(default = "default_jwt_secret")]
+    pub jwt_secret: String,
+    /// Session token lifetime (seconds).
+    #[serde(default = "default_session_ttl")]
+    pub session_ttl_secs: u64,
+    /// Email verification / password-reset token lifetime (seconds).
+    #[serde(default = "default_email_token_ttl")]
+    pub email_token_ttl_secs: u64,
+    /// Public base URL of the frontend, used to build verify/reset links.
+    #[serde(default = "default_app_base_url")]
+    pub app_base_url: String,
+}
+
+impl Default for AuthSettings {
+    fn default() -> Self {
+        Self {
+            jwt_secret: default_jwt_secret(),
+            session_ttl_secs: default_session_ttl(),
+            email_token_ttl_secs: default_email_token_ttl(),
+            app_base_url: default_app_base_url(),
+        }
+    }
+}
+
+/// `[email]` — transactional email transport for verify/reset.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct EmailSettings {
+    /// `"log"` (dev — logs the link) or `"smtp"`.
+    #[serde(default = "default_email_provider")]
+    pub provider: String,
+    /// SMTP relay URL (e.g. "smtp://user:pass@host:587") when provider=smtp.
+    #[serde(default)]
+    pub smtp_url: Option<String>,
+    /// `From:` address.
+    #[serde(default = "default_from_addr")]
+    pub from_addr: String,
+}
+
+impl Default for EmailSettings {
+    fn default() -> Self {
+        Self {
+            provider: default_email_provider(),
+            smtp_url: None,
+            from_addr: default_from_addr(),
+        }
+    }
+}
+
+/// `[client_auth]` — credentials operators' cortexes present to `/authz/v1`.
+/// Each token maps to an `operator_id` (served-usage attribution, #58). This
+/// transport credential is distinct from end-user API keys (which ride in
+/// the `resolve` body). v2 adds mTLS.
+#[derive(Debug, Clone, Serialize, Deserialize, Default)]
+pub struct ClientAuthSettings {
+    /// When empty the authz surface is **open** (dev only; logged at warn).
+    #[serde(default)]
+    pub tokens: Vec<ClientToken>,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ClientToken {
+    /// Shared bearer a cortex presents.
+    pub token: String,
+    /// Operator this token identifies.
+    pub operator_id: String,
+}
+
+/// `[authz]` — reservation lifecycle knobs.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct AuthzSettings {
+    /// Open reservations older than this are swept (released), self-healing
+    /// a reservation whose settle/release from cortex was lost.
+    #[serde(default = "default_reservation_ttl")]
+    pub reservation_ttl_secs: u64,
+    /// How often the sweeper runs.
+    #[serde(default = "default_sweep_interval")]
+    pub sweep_interval_secs: u64,
+}
+
+impl Default for AuthzSettings {
+    fn default() -> Self {
+        Self {
+            reservation_ttl_secs: default_reservation_ttl(),
+            sweep_interval_secs: default_sweep_interval(),
+        }
+    }
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ServerSettings {
+    /// Address to listen on (e.g. "0.0.0.0:8090"). Plaintext — edge nginx
+    /// terminates TLS, consistent with the rest of the stack.
+    #[serde(default = "default_listen")]
+    pub listen: String,
+}
+
+impl Default for ServerSettings {
+    fn default() -> Self {
+        Self {
+            listen: default_listen(),
+        }
+    }
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct DbSettings {
+    /// PostgreSQL connection URL (e.g. "postgres://user:pass@host/helexa").
+    pub url: String,
+    /// Max pool connections.
+    #[serde(default = "default_max_connections")]
+    pub max_connections: u32,
+}
+
+/// `[grant]` — the flat free token grant every email-verified account
+/// receives (the floor of the hybrid allocation model; top-up codes extend
+/// it).
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct GrantSettings {
+    #[serde(default = "default_free_grant")]
+    pub free_token_grant: i64,
+}
+
+impl Default for GrantSettings {
+    fn default() -> Self {
+        Self {
+            free_token_grant: default_free_grant(),
+        }
+    }
+}
+
+/// `[abuse]` — silent multi-account abuse detection. When at least
+/// `fingerprint_account_threshold` accounts share one registration
+/// fingerprint, all of them are silently deactivated (no notice to the
+/// user; deactivation only surfaces as ordinary inference rejections).
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct AbuseSettings {
+    #[serde(default = "default_fingerprint_threshold")]
+    pub fingerprint_account_threshold: i64,
+}
+
+impl Default for AbuseSettings {
+    fn default() -> Self {
+        Self {
+            fingerprint_account_threshold: default_fingerprint_threshold(),
+        }
+    }
+}
+
+fn default_listen() -> String {
+    "0.0.0.0:8090".into()
+}
+fn default_max_connections() -> u32 {
+    16
+}
+fn default_free_grant() -> i64 {
+    1_000_000
+}
+fn default_fingerprint_threshold() -> i64 {
+    5
+}
+fn default_reservation_ttl() -> u64 {
+    120
+}
+fn default_sweep_interval() -> u64 {
+    60
+}
+fn default_jwt_secret() -> String {
+    "dev-insecure-change-me".into()
+}
+fn default_session_ttl() -> u64 {
+    7 * 24 * 3600
+}
+fn default_email_token_ttl() -> u64 {
+    24 * 3600
+}
+fn default_app_base_url() -> String {
+    "http://localhost:5173".into()
+}
+fn default_email_provider() -> String {
+    "log".into()
+}
+fn default_from_addr() -> String {
+    "helexa <no-reply@helexa.ai>".into()
+}
+
+impl UpstreamConfig {
+    /// Load from a TOML file with `UPSTREAM_`-prefixed env overrides
+    /// (`__` nesting separator).
+    pub fn load(path: impl AsRef<Path>) -> Result<Self, Box<figment::Error>> {
+        Figment::new()
+            .merge(Toml::file(path))
+            .merge(Env::prefixed("UPSTREAM_").split("__"))
+            .extract()
+            .map_err(Box::new)
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    #[allow(clippy::result_large_err)]
+    fn loads_toml_with_env_override_and_defaults() {
+        figment::Jail::expect_with(|jail| {
+            jail.create_file(
+                "helexa-upstream.toml",
+                r#"
+[db]
+url = "postgres://localhost/helexa"
+"#,
+            )?;
+            jail.set_env("UPSTREAM_SERVER__LISTEN", "127.0.0.1:9099");
+
+            let cfg = UpstreamConfig::load("helexa-upstream.toml").expect("load");
+            assert_eq!(cfg.server.listen, "127.0.0.1:9099");
+            assert_eq!(cfg.db.url, "postgres://localhost/helexa");
+            // Defaults applied when sections omitted.
+            assert_eq!(cfg.grant.free_token_grant, 1_000_000);
+            assert_eq!(cfg.abuse.fingerprint_account_threshold, 5);
+            assert_eq!(cfg.db.max_connections, 16);
+            Ok(())
+        });
+    }
+}

crates/helexa-upstream/src/crypto.rs

@@ -0,0 +1,113 @@
+//! Hashing + secret-generation helpers.
+//!
+//! - **Passwords** (low-entropy) → argon2id PHC strings.
+//! - **API keys / top-up codes / email + session tokens** (high-entropy
+//!   secrets minted here) → stored only as their sha256; sha256 is the fast,
+//!   sufficient choice for high-entropy material.
+
+use argon2::Argon2;
+use argon2::password_hash::rand_core::OsRng as ArgonOsRng;
+use argon2::password_hash::{PasswordHash, PasswordHasher, PasswordVerifier, SaltString};
+use rand::RngCore;
+use sha2::{Digest, Sha256};
+
+/// sha256 of `input`, as raw bytes (matches the `BYTEA` columns).
+pub fn sha256(input: &str) -> Vec<u8> {
+    let mut h = Sha256::new();
+    h.update(input.as_bytes());
+    h.finalize().to_vec()
+}
+
+/// Hash a password with argon2id, returning a PHC string for storage.
+pub fn hash_password(password: &str) -> Result<String, argon2::password_hash::Error> {
+    let salt = SaltString::generate(&mut ArgonOsRng);
+    Ok(Argon2::default()
+        .hash_password(password.as_bytes(), &salt)?
+        .to_string())
+}
+
+/// Verify a password against a stored PHC hash. `false` on any mismatch or
+/// malformed hash (never panics).
+pub fn verify_password(password: &str, phc: &str) -> bool {
+    match PasswordHash::new(phc) {
+        Ok(parsed) => Argon2::default()
+            .verify_password(password.as_bytes(), &parsed)
+            .is_ok(),
+        Err(_) => false,
+    }
+}
+
+/// A fresh URL-safe high-entropy secret (256 bits) for email/session/reset
+/// tokens. The caller stores only `sha256` of this and emails/returns the
+/// raw value.
+pub fn random_token() -> String {
+    let mut bytes = [0u8; 32];
+    rand::rngs::OsRng.fill_bytes(&mut bytes);
+    base62(&bytes)
+}
+
+/// Mint a new API key: `(raw, prefix)`. `raw` is shown to the user once;
+/// only `sha256(raw)` is stored. The prefix is a non-secret display tag.
+pub fn generate_api_key() -> (String, String) {
+    let mut bytes = [0u8; 32];
+    rand::rngs::OsRng.fill_bytes(&mut bytes);
+    let raw = format!("sk-helexa-{}", base62(&bytes));
+    // Non-secret prefix for the dashboard list (scheme + first few chars).
+    let prefix: String = raw.chars().take(14).collect();
+    (raw, prefix)
+}
+
+/// base62 encode (0-9A-Za-z) — URL/clipboard friendly, no padding.
+fn base62(bytes: &[u8]) -> String {
+    const ALPHABET: &[u8] = b"0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz";
+    // Treat the bytes as a big-endian integer and base62 it. 32 bytes → ~43
+    // chars. Simple repeated-division over a big-uint built from the bytes.
+    let mut digits: Vec<u8> = vec![0];
+    for &byte in bytes {
+        let mut carry = byte as u32;
+        for d in digits.iter_mut() {
+            let v = (*d as u32) * 256 + carry;
+            *d = (v % 62) as u8;
+            carry = v / 62;
+        }
+        while carry > 0 {
+            digits.push((carry % 62) as u8);
+            carry /= 62;
+        }
+    }
+    digits
+        .iter()
+        .rev()
+        .map(|&d| ALPHABET[d as usize] as char)
+        .collect()
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn password_round_trips_and_rejects_wrong() {
+        let phc = hash_password("correct horse").unwrap();
+        assert!(verify_password("correct horse", &phc));
+        assert!(!verify_password("wrong", &phc));
+        assert!(!verify_password("correct horse", "not-a-phc-string"));
+    }
+
+    #[test]
+    fn api_key_has_scheme_prefix_and_unique_body() {
+        let (raw, prefix) = generate_api_key();
+        assert!(raw.starts_with("sk-helexa-"));
+        assert!(prefix.starts_with("sk-helexa-"));
+        let (raw2, _) = generate_api_key();
+        assert_ne!(raw, raw2, "keys are unique");
+    }
+
+    #[test]
+    fn random_tokens_are_unique_and_nonempty() {
+        let a = random_token();
+        let b = random_token();
+        assert!(!a.is_empty());
+        assert_ne!(a, b);
+    }
+}

crates/helexa-upstream/src/db.rs

@@ -0,0 +1,20 @@
+//! PostgreSQL pool + embedded migrations.
+
+use anyhow::{Context, Result};
+use sqlx::postgres::{PgPool, PgPoolOptions};
+
+/// Connect to Postgres and run embedded migrations (`./migrations`).
+pub async fn connect_and_migrate(url: &str, max_connections: u32) -> Result<PgPool> {
+    let pool = PgPoolOptions::new()
+        .max_connections(max_connections)
+        .connect(url)
+        .await
+        .with_context(|| "connecting to PostgreSQL")?;
+
+    sqlx::migrate!("./migrations")
+        .run(&pool)
+        .await
+        .with_context(|| "running migrations")?;
+
+    Ok(pool)
+}

crates/helexa-upstream/src/email.rs

@@ -0,0 +1,64 @@
+//! Transactional email for verification + password-reset links.
+//!
+//! Two transports: `Log` (dev — writes the link to the log so flows are
+//! testable without a relay) and `Smtp` (lettre over rustls). Built from
+//! `[email]` config.
+
+use crate::config::EmailSettings;
+use anyhow::{Context, Result};
+use lettre::message::Mailbox;
+use lettre::{AsyncSmtpTransport, AsyncTransport, Message, Tokio1Executor};
+
+#[derive(Clone)]
+pub enum EmailSender {
+    /// Dev: log the message instead of sending.
+    Log { from: String },
+    Smtp {
+        from: String,
+        transport: AsyncSmtpTransport<Tokio1Executor>,
+    },
+}
+
+impl EmailSender {
+    pub fn from_config(cfg: &EmailSettings) -> Result<Self> {
+        match cfg.provider.as_str() {
+            "smtp" => {
+                let url = cfg
+                    .smtp_url
+                    .as_deref()
+                    .context("[email].smtp_url required when provider = \"smtp\"")?;
+                let transport = AsyncSmtpTransport::<Tokio1Executor>::from_url(url)
+                    .context("parsing [email].smtp_url")?
+                    .build();
+                Ok(EmailSender::Smtp {
+                    from: cfg.from_addr.clone(),
+                    transport,
+                })
+            }
+            _ => Ok(EmailSender::Log {
+                from: cfg.from_addr.clone(),
+            }),
+        }
+    }
+
+    /// Send a plaintext email. Errors are returned but the caller treats
+    /// send failures as non-fatal to the request (the user can re-request).
+    pub async fn send(&self, to: &str, subject: &str, body: &str) -> Result<()> {
+        match self {
+            EmailSender::Log { from } => {
+                tracing::info!(%from, %to, %subject, body, "EMAIL (log transport)");
+                Ok(())
+            }
+            EmailSender::Smtp { from, transport } => {
+                let msg = Message::builder()
+                    .from(from.parse::<Mailbox>().context("parsing from_addr")?)
+                    .to(to.parse::<Mailbox>().context("parsing recipient")?)
+                    .subject(subject)
+                    .body(body.to_string())
+                    .context("building message")?;
+                transport.send(msg).await.context("sending email")?;
+                Ok(())
+            }
+        }
+    }
+}

crates/helexa-upstream/src/error.rs

@@ -0,0 +1,21 @@
+//! Adapter from the shared, axum-agnostic
+//! [`cortex_core::error_envelope::OpenAiError`] (#60/#63) to an axum
+//! response, with `Retry-After`. The `/authz/v1` surface speaks the #63
+//! envelope so cortex (an OpenAI-compatible proxy) can forward rejections
+//! verbatim. (The future `/web/v1` surface uses a plain JSON error shape.)
+
+use axum::http::{HeaderValue, StatusCode, header};
+use axum::response::{IntoResponse, Json, Response};
+use cortex_core::error_envelope::OpenAiError;
+
+pub fn envelope_response(err: OpenAiError) -> Response {
+    let status = StatusCode::from_u16(err.status).unwrap_or(StatusCode::INTERNAL_SERVER_ERROR);
+    let retry_after = err.retry_after_secs;
+    let mut response = (status, Json(err.body())).into_response();
+    if let Some(secs) = retry_after
+        && let Ok(value) = HeaderValue::from_str(&secs.to_string())
+    {
+        response.headers_mut().insert(header::RETRY_AFTER, value);
+    }
+    response
+}

crates/helexa-upstream/src/handlers.rs

@@ -0,0 +1,21 @@
+//! HTTP handlers. B1 ships `/health`; the authz (`/authz/v1`) and web
+//! (`/web/v1`) surfaces land in later phases.
+
+use crate::state::AppState;
+use axum::{Json, Router, extract::State, routing::get};
+use serde_json::{Value, json};
+
+pub fn routes() -> Router<AppState> {
+    Router::new()
+        .route("/health", get(health))
+        .route("/", get(health))
+}
+
+/// `GET /health` — liveness + a database round-trip (`SELECT 1`).
+async fn health(State(state): State<AppState>) -> Json<Value> {
+    let db_ok = sqlx::query("SELECT 1").execute(&state.pool).await.is_ok();
+    Json(json!({
+        "status": if db_ok { "ok" } else { "degraded" },
+        "db": if db_ok { "ok" } else { "unreachable" },
+    }))
+}

crates/helexa-upstream/src/ledger.rs

@@ -0,0 +1,338 @@
+//! The allocation ledger: reserve → settle/release with the no-overshoot
+//! guarantee enforced by a row-locked transaction.
+//!
+//! Each reserve takes `SELECT … FOR UPDATE` on the account (and key) row, so
+//! concurrent reserves from many cortexes serialize and `spent + reserved`
+//! can never exceed the effective cap. The `accounts_no_overshoot` CHECK is
+//! the DB-level backstop. Settle/release are idempotent (they only act on a
+//! reservation still in `open`).
+//!
+//! Per-key effective cap = `min(resolved key cap, remaining account
+//! allocation)`. The key cap is resolved from its `limit_kind`:
+//! `hardcap` → the value verbatim; `percent` → that % of the account's
+//! `allocation_total`.
+//!
+//! Cap-window semantics: this module implements **Balance** (non-resetting)
+//! caps. Rolling-window key sub-caps (and the `RateLimited` rejection that
+//! rides them) land with the authz API (B2); today an over-cap is always
+//! `InsufficientQuota`.
+
+use sqlx::postgres::PgPool;
+use uuid::Uuid;
+
+/// A bearer key resolved to its principal + a budget snapshot.
+#[derive(Debug, Clone)]
+pub struct ResolvedPrincipal {
+    pub account_id: Uuid,
+    pub key_id: Uuid,
+    /// Effective per-key absolute cap (the key sub-cap; the account cap
+    /// still binds at reserve time).
+    pub hard_cap: i64,
+    pub key_spent: i64,
+    pub key_reserved: i64,
+}
+
+/// Resolve a key by its `sha256` hash to its principal, or `None` when the
+/// key is unknown/archived **or its account is deactivated** (the silent
+/// abuse flag — indistinguishable from an unknown key, by design: no clue).
+pub async fn resolve_key(
+    pool: &PgPool,
+    key_hash: &[u8],
+) -> Result<Option<ResolvedPrincipal>, sqlx::Error> {
+    let row = sqlx::query(
+        "SELECT k.id AS key_id, k.account_id, k.limit_kind, k.limit_value, \
+                k.key_spent, k.key_reserved, a.allocation_total \
+         FROM api_keys k JOIN accounts a ON a.id = k.account_id \
+         WHERE k.key_hash = $1 AND k.status = 'active' AND a.status = 'active'",
+    )
+    .bind(key_hash)
+    .fetch_optional(pool)
+    .await?;
+    Ok(row.map(|r| {
+        let total: i64 = sqlx::Row::get(&r, "allocation_total");
+        let limit_kind: String = sqlx::Row::get(&r, "limit_kind");
+        let limit_value: i64 = sqlx::Row::get(&r, "limit_value");
+        ResolvedPrincipal {
+            account_id: sqlx::Row::get(&r, "account_id"),
+            key_id: sqlx::Row::get(&r, "key_id"),
+            hard_cap: resolve_abs_cap(&limit_kind, limit_value, total),
+            key_spent: sqlx::Row::get(&r, "key_spent"),
+            key_reserved: sqlx::Row::get(&r, "key_reserved"),
+        }
+    }))
+}
+
+/// Per-key budget snapshot `(hard_cap, spent, reserved)`, or `None` if the
+/// key/account isn't an active pair.
+pub async fn snapshot(
+    pool: &PgPool,
+    account_id: Uuid,
+    key_id: Uuid,
+) -> Result<Option<(i64, i64, i64)>, sqlx::Error> {
+    let row = sqlx::query(
+        "SELECT k.limit_kind, k.limit_value, k.key_spent, k.key_reserved, a.allocation_total \
+         FROM api_keys k JOIN accounts a ON a.id = k.account_id \
+         WHERE k.id = $1 AND k.account_id = $2 AND k.status = 'active' AND a.status = 'active'",
+    )
+    .bind(key_id)
+    .bind(account_id)
+    .fetch_optional(pool)
+    .await?;
+    Ok(row.map(|r| {
+        let total: i64 = sqlx::Row::get(&r, "allocation_total");
+        let limit_kind: String = sqlx::Row::get(&r, "limit_kind");
+        let limit_value: i64 = sqlx::Row::get(&r, "limit_value");
+        let cap = resolve_abs_cap(&limit_kind, limit_value, total);
+        (
+            cap,
+            sqlx::Row::get::<i64, _>(&r, "key_spent"),
+            sqlx::Row::get::<i64, _>(&r, "key_reserved"),
+        )
+    }))
+}
+
+/// Release every `open` reservation older than `max_age_secs`, returning
+/// each one's reserved tokens to its account and key in a single statement.
+/// The lost-settle self-heal. Returns the number swept.
+pub async fn sweep_stale(pool: &PgPool, max_age_secs: i64) -> Result<u64, sqlx::Error> {
+    // Data-modifying CTEs: release stale rows, then fold their reserved sums
+    // back into accounts and api_keys. All in one atomic statement.
+    let result = sqlx::query(
+        "WITH stale AS ( \
+             UPDATE reservations SET state = 'released', settled_at = now() \
+             WHERE state = 'open' AND created_at < now() - make_interval(secs => $1) \
+             RETURNING account_id, key_id, reserved \
+         ), acct AS ( \
+             UPDATE accounts a SET allocation_reserved = allocation_reserved - s.total \
+             FROM (SELECT account_id, SUM(reserved) AS total FROM stale GROUP BY account_id) s \
+             WHERE a.id = s.account_id \
+         ) \
+         UPDATE api_keys k SET key_reserved = key_reserved - s.total \
+         FROM (SELECT key_id, SUM(reserved) AS total FROM stale GROUP BY key_id) s \
+         WHERE k.id = s.key_id",
+    )
+    .bind(max_age_secs as f64)
+    .execute(pool)
+    .await?;
+    Ok(result.rows_affected())
+}
+
+/// Resolve a key's per-key cap to an absolute token count.
+///
+/// `percent` is `floor(allocation_total * limit_value / 100)`; `hardcap` is
+/// `limit_value` verbatim. Computed in i128 to avoid overflow, floored at 0.
+pub fn resolve_abs_cap(limit_kind: &str, limit_value: i64, allocation_total: i64) -> i64 {
+    let cap = match limit_kind {
+        "percent" => (allocation_total as i128 * limit_value as i128) / 100,
+        _ => limit_value as i128, // "hardcap" (and any unknown → treat as absolute)
+    };
+    cap.clamp(0, i64::MAX as i128) as i64
+}
+
+#[derive(Debug, thiserror::Error)]
+pub enum LedgerError {
+    #[error("account not found")]
+    AccountNotFound,
+    #[error("api key not found or not active")]
+    KeyNotFound,
+    /// Account balance or a Balance-window key sub-cap is exhausted.
+    #[error("insufficient quota: requested {requested}, available {available}")]
+    InsufficientQuota { requested: i64, available: i64 },
+    #[error(transparent)]
+    Db(#[from] sqlx::Error),
+}
+
+/// Reserve `max_tokens` against `account_id`/`key_id`. Returns the
+/// reservation id (the `BIGSERIAL`, mapped to the cortex `Reservation.id`).
+pub async fn reserve(
+    pool: &PgPool,
+    account_id: Uuid,
+    key_id: Uuid,
+    max_tokens: i64,
+) -> Result<i64, LedgerError> {
+    let mut tx = pool.begin().await?;
+
+    // Lock the account row — serializes concurrent reserves on this account.
+    let acct = sqlx::query(
+        "SELECT allocation_total, allocation_spent, allocation_reserved \
+         FROM accounts WHERE id = $1 AND status = 'active' FOR UPDATE",
+    )
+    .bind(account_id)
+    .fetch_optional(&mut *tx)
+    .await?;
+    let Some(acct) = acct else {
+        return Err(LedgerError::AccountNotFound);
+    };
+    let total: i64 = sqlx::Row::get(&acct, "allocation_total");
+    let spent: i64 = sqlx::Row::get(&acct, "allocation_spent");
+    let reserved: i64 = sqlx::Row::get(&acct, "allocation_reserved");
+    let account_avail = total - spent - reserved;
+
+    // Lock the key row and resolve its absolute sub-cap.
+    let key = sqlx::query(
+        "SELECT limit_kind, limit_value, key_spent, key_reserved \
+         FROM api_keys WHERE id = $1 AND account_id = $2 AND status = 'active' FOR UPDATE",
+    )
+    .bind(key_id)
+    .bind(account_id)
+    .fetch_optional(&mut *tx)
+    .await?;
+    let Some(key) = key else {
+        return Err(LedgerError::KeyNotFound);
+    };
+    let limit_kind: String = sqlx::Row::get(&key, "limit_kind");
+    let limit_value: i64 = sqlx::Row::get(&key, "limit_value");
+    let key_spent: i64 = sqlx::Row::get(&key, "key_spent");
+    let key_reserved: i64 = sqlx::Row::get(&key, "key_reserved");
+    let key_cap = resolve_abs_cap(&limit_kind, limit_value, total);
+    let key_avail = key_cap - key_spent - key_reserved;
+
+    let available = account_avail.min(key_avail).max(0);
+    if max_tokens > available {
+        // tx rolls back on drop
+        return Err(LedgerError::InsufficientQuota {
+            requested: max_tokens,
+            available,
+        });
+    }
+
+    let id: i64 = sqlx::Row::get(
+        &sqlx::query(
+            "INSERT INTO reservations (account_id, key_id, reserved, state) \
+             VALUES ($1, $2, $3, 'open') RETURNING id",
+        )
+        .bind(account_id)
+        .bind(key_id)
+        .bind(max_tokens)
+        .fetch_one(&mut *tx)
+        .await?,
+        "id",
+    );
+    sqlx::query("UPDATE accounts SET allocation_reserved = allocation_reserved + $1 WHERE id = $2")
+        .bind(max_tokens)
+        .bind(account_id)
+        .execute(&mut *tx)
+        .await?;
+    sqlx::query("UPDATE api_keys SET key_reserved = key_reserved + $1 WHERE id = $2")
+        .bind(max_tokens)
+        .bind(key_id)
+        .execute(&mut *tx)
+        .await?;
+
+    tx.commit().await?;
+    Ok(id)
+}
+
+/// Settle a reservation with the actual tokens used (clamped to
+/// `[0, reserved]`). Idempotent: a second settle (or settle after release)
+/// is a no-op.
+pub async fn settle(
+    pool: &PgPool,
+    reservation_id: i64,
+    actual_tokens: i64,
+) -> Result<(), LedgerError> {
+    let mut tx = pool.begin().await?;
+    let row = sqlx::query(
+        "UPDATE reservations SET state = 'settled', settled_at = now(), \
+         actual = LEAST(GREATEST($2, 0), reserved) \
+         WHERE id = $1 AND state = 'open' \
+         RETURNING reserved, account_id, key_id, actual",
+    )
+    .bind(reservation_id)
+    .bind(actual_tokens)
+    .fetch_optional(&mut *tx)
+    .await?;
+    let Some(row) = row else {
+        return Ok(()); // already settled/released, or unknown → idempotent no-op
+    };
+    let reserved: i64 = sqlx::Row::get(&row, "reserved");
+    let actual: i64 = sqlx::Row::get(&row, "actual");
+    let account_id: Uuid = sqlx::Row::get(&row, "account_id");
+    let key_id: Uuid = sqlx::Row::get(&row, "key_id");
+
+    sqlx::query(
+        "UPDATE accounts SET allocation_reserved = allocation_reserved - $1, \
+         allocation_spent = allocation_spent + $2 WHERE id = $3",
+    )
+    .bind(reserved)
+    .bind(actual)
+    .bind(account_id)
+    .execute(&mut *tx)
+    .await?;
+    sqlx::query(
+        "UPDATE api_keys SET key_reserved = key_reserved - $1, key_spent = key_spent + $2 WHERE id = $3",
+    )
+    .bind(reserved)
+    .bind(actual)
+    .bind(key_id)
+    .execute(&mut *tx)
+    .await?;
+
+    tx.commit().await?;
+    Ok(())
+}
+
+/// Release a reservation, returning its full reserved amount to the
+/// allocation. Idempotent.
+pub async fn release(pool: &PgPool, reservation_id: i64) -> Result<(), LedgerError> {
+    let mut tx = pool.begin().await?;
+    let row = sqlx::query(
+        "UPDATE reservations SET state = 'released', settled_at = now() \
+         WHERE id = $1 AND state = 'open' \
+         RETURNING reserved, account_id, key_id",
+    )
+    .bind(reservation_id)
+    .fetch_optional(&mut *tx)
+    .await?;
+    let Some(row) = row else {
+        return Ok(());
+    };
+    let reserved: i64 = sqlx::Row::get(&row, "reserved");
+    let account_id: Uuid = sqlx::Row::get(&row, "account_id");
+    let key_id: Uuid = sqlx::Row::get(&row, "key_id");
+
+    sqlx::query("UPDATE accounts SET allocation_reserved = allocation_reserved - $1 WHERE id = $2")
+        .bind(reserved)
+        .bind(account_id)
+        .execute(&mut *tx)
+        .await?;
+    sqlx::query("UPDATE api_keys SET key_reserved = key_reserved - $1 WHERE id = $2")
+        .bind(reserved)
+        .bind(key_id)
+        .execute(&mut *tx)
+        .await?;
+
+    tx.commit().await?;
+    Ok(())
+}
+
+#[cfg(test)]
+mod tests {
+    use super::resolve_abs_cap;
+
+    #[test]
+    fn hardcap_is_verbatim() {
+        assert_eq!(resolve_abs_cap("hardcap", 50_000, 1_000_000), 50_000);
+    }
+
+    #[test]
+    fn percent_is_fraction_of_allocation() {
+        assert_eq!(resolve_abs_cap("percent", 25, 1_000_000), 250_000);
+        assert_eq!(resolve_abs_cap("percent", 100, 1_000_000), 1_000_000);
+        // floor
+        assert_eq!(resolve_abs_cap("percent", 33, 10), 3);
+    }
+
+    #[test]
+    fn percent_does_not_overflow_on_large_allocation() {
+        // total * value would overflow i64 if not widened to i128.
+        let cap = resolve_abs_cap("percent", 100, i64::MAX);
+        assert_eq!(cap, i64::MAX);
+    }
+
+    #[test]
+    fn negative_or_zero_clamps_to_zero() {
+        assert_eq!(resolve_abs_cap("hardcap", -5, 100), 0);
+        assert_eq!(resolve_abs_cap("percent", 0, 1_000_000), 0);
+    }
+}

crates/helexa-upstream/src/lib.rs

@@ -0,0 +1,90 @@
+//! helexa-upstream — the mesh-level account/authorization authority (#59).
+//!
+//! The clearing house above cortex: it issues accounts and API keys, holds
+//! the real token-allocation ledger, authorizes inference in real time
+//! (reserve → settle, fail-closed), and tracks served usage for operator
+//! reconciliation. cortex's `UpstreamEntitlementProvider` (#57) is a client
+//! of the `/authz/v1` surface; the helexa.ai frontend is a client of the
+//! `/web/v1` surface.
+//!
+//! Landed so far: B1 — schema + reserve→settle [`ledger`] (no-overshoot) +
+//! `/health`. B2 — the `/authz/v1` [`authz`] surface (resolve/reserve/
+//! settle/release/snapshot) with shared-bearer client auth and a
+//! stale-reservation sweeper.
+
+pub mod authz;
+pub mod config;
+pub mod crypto;
+pub mod db;
+pub mod email;
+pub mod error;
+pub mod handlers;
+pub mod ledger;
+pub mod reconcile;
+pub mod state;
+pub mod topup;
+pub mod web;
+
+use anyhow::Result;
+use config::UpstreamConfig;
+use email::EmailSender;
+use state::AppState;
+use std::time::Duration;
+use tower_http::cors::CorsLayer;
+use tower_http::trace::TraceLayer;
+
+/// Build the axum application.
+pub fn build_app(state: AppState) -> axum::Router {
+    axum::Router::new()
+        .merge(handlers::routes())
+        .merge(authz::router(&state))
+        .merge(web::router(&state))
+        // The /web/v1 surface is called cross-origin by the browser SPA in
+        // dev; same-origin behind nginx in prod. Permissive is fine — these
+        // endpoints authenticate via bearer/JWT, not cookies.
+        .layer(CorsLayer::permissive())
+        .layer(TraceLayer::new_for_http())
+        .with_state(state)
+}
+
+/// Start the service: connect Postgres, run migrations, spawn the
+/// reservation sweeper, bind the listener.
+pub async fn run(config: UpstreamConfig) -> Result<()> {
+    let pool = db::connect_and_migrate(&config.db.url, config.db.max_connections).await?;
+    let email = EmailSender::from_config(&config.email)?;
+    let listen = config.server.listen.clone();
+    let state = AppState::new(pool, config, email);
+
+    if state.config.client_auth.tokens.is_empty() {
+        tracing::warn!(
+            "no [client_auth] tokens configured — the /authz/v1 surface is OPEN (dev only)"
+        );
+    }
+
+    // Stale-reservation sweeper: releases open reservations whose
+    // settle/release from cortex was lost, self-healing allocation_reserved.
+    spawn_sweeper(&state);
+
+    let addr = listen.parse::<std::net::SocketAddr>()?;
+    tracing::info!("helexa-upstream listening on {addr}");
+
+    let listener = tokio::net::TcpListener::bind(addr).await?;
+    axum::serve(listener, build_app(state)).await?;
+    Ok(())
+}
+
+fn spawn_sweeper(state: &AppState) {
+    let pool = state.pool.clone();
+    let ttl = state.config.authz.reservation_ttl_secs as i64;
+    let interval = Duration::from_secs(state.config.authz.sweep_interval_secs);
+    tokio::spawn(async move {
+        loop {
+            tokio::time::sleep(interval).await;
+            match ledger::sweep_stale(&pool, ttl).await {
+                Ok(n) if n > 0 => tracing::info!(swept = n, "released stale reservations"),
+                Ok(_) => {}
+                Err(e) => tracing::warn!(error = %e, "reservation sweep failed"),
+            }
+        }
+    });
+}

crates/helexa-upstream/src/main.rs

@@ -0,0 +1,99 @@
+use anyhow::Result;
+use clap::{Parser, Subcommand};
+use helexa_upstream::config::UpstreamConfig;
+use tracing_subscriber::EnvFilter;
+
+#[derive(Parser)]
+#[command(name = "helexa-upstream")]
+#[command(about = "Mesh-level account & authorization authority for helexa")]
+#[command(version)]
+struct Cli {
+    #[command(subcommand)]
+    command: Commands,
+}
+
+#[derive(Subcommand)]
+enum Commands {
+    /// Start the upstream server.
+    Serve {
+        /// Path to the config file.
+        #[arg(short, long, default_value = "helexa-upstream.toml")]
+        config: String,
+    },
+    /// Mint single-use top-up codes and print them (one per line). The raw
+    /// codes are shown only here — only their hash is stored. (The future
+    /// faucet bot calls the same path.)
+    Mint {
+        #[arg(short, long, default_value = "helexa-upstream.toml")]
+        config: String,
+        /// Tokens each code grants.
+        #[arg(long)]
+        value: i64,
+        /// How many codes to mint.
+        #[arg(long, default_value_t = 1)]
+        count: u32,
+        /// Optional human label (e.g. "small", "beta-launch").
+        #[arg(long)]
+        denomination: Option<String>,
+    },
+    /// Roll up not-yet-reconciled served usage per operator/period (#58),
+    /// stamp it reconciled, and print the totals. Payout is out of scope.
+    Reconcile {
+        #[arg(short, long, default_value = "helexa-upstream.toml")]
+        config: String,
+    },
+}
+
+#[tokio::main]
+async fn main() -> Result<()> {
+    tracing_subscriber::fmt()
+        .with_env_filter(
+            EnvFilter::try_from_default_env()
+                .unwrap_or_else(|_| EnvFilter::new("info,helexa_upstream=debug")),
+        )
+        .init();
+
+    let cli = Cli::parse();
+
+    match cli.command {
+        Commands::Serve { config } => {
+            let cfg = UpstreamConfig::load(&config)
+                .map_err(|e| anyhow::anyhow!("failed to load config from '{config}': {e}"))?;
+            tracing::info!(listen = %cfg.server.listen, "starting helexa-upstream");
+            helexa_upstream::run(cfg).await?;
+        }
+        Commands::Mint {
+            config,
+            value,
+            count,
+            denomination,
+        } => {
+            let cfg = UpstreamConfig::load(&config)
+                .map_err(|e| anyhow::anyhow!("failed to load config from '{config}': {e}"))?;
+            let pool =
+                helexa_upstream::db::connect_and_migrate(&cfg.db.url, cfg.db.max_connections)
+                    .await?;
+            let codes =
+                helexa_upstream::topup::mint(&pool, value, count, denomination.as_deref()).await?;
+            // Raw codes to stdout (one per line) for the operator to distribute;
+            // logs/diagnostics go to stderr via tracing.
+            for code in codes {
+                println!("{code}");
+            }
+        }
+        Commands::Reconcile { config } => {
+            let cfg = UpstreamConfig::load(&config)
+                .map_err(|e| anyhow::anyhow!("failed to load config from '{config}': {e}"))?;
+            let pool =
+                helexa_upstream::db::connect_and_migrate(&cfg.db.url, cfg.db.max_connections)
+                    .await?;
+            let rollup = helexa_upstream::reconcile::reconcile(&pool).await?;
+            for r in &rollup {
+                println!("{}\t{}\t{}", r.operator_id, r.period, r.total_served_tokens);
+            }
+            tracing::info!(operators_periods = rollup.len(), "reconciliation complete");
+        }
+    }
+
+    Ok(())
+}

crates/helexa-upstream/src/reconcile.rs

@@ -0,0 +1,43 @@
+//! Reconciliation rollup (#58): aggregate the served-usage ledger per
+//! operator and period for operator compensation, stamping rows
+//! `reconciled_at` so each window is settled once. The payout mechanism
+//! itself is out of scope — this produces the authoritative per-operator
+//! totals a settlement process consumes.
+
+use sqlx::Row;
+use sqlx::postgres::PgPool;
+
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct RollupRow {
+    pub operator_id: String,
+    pub period: chrono::NaiveDate,
+    pub total_served_tokens: i64,
+}
+
+/// Roll up all not-yet-reconciled served-usage into per-(operator, period)
+/// totals, then stamp those rows `reconciled_at`. Returns the rollup.
+/// Idempotent: a second run finds nothing unreconciled and returns empty.
+pub async fn reconcile(pool: &PgPool) -> Result<Vec<RollupRow>, sqlx::Error> {
+    let mut tx = pool.begin().await?;
+    let rows = sqlx::query(
+        // SUM(bigint) is numeric in Postgres — cast back to bigint for i64.
+        "SELECT operator_id, period, SUM(served_tokens)::bigint AS total \
+         FROM served_usage WHERE reconciled_at IS NULL \
+         GROUP BY operator_id, period ORDER BY operator_id, period",
+    )
+    .fetch_all(&mut *tx)
+    .await?;
+    let rollup: Vec<RollupRow> = rows
+        .iter()
+        .map(|r| RollupRow {
+            operator_id: r.get("operator_id"),
+            period: r.get("period"),
+            total_served_tokens: r.get::<i64, _>("total"),
+        })
+        .collect();
+    sqlx::query("UPDATE served_usage SET reconciled_at = now() WHERE reconciled_at IS NULL")
+        .execute(&mut *tx)
+        .await?;
+    tx.commit().await?;
+    Ok(rollup)
+}

crates/helexa-upstream/src/state.rs

@@ -0,0 +1,23 @@
+//! Shared application state.
+
+use crate::config::UpstreamConfig;
+use crate::email::EmailSender;
+use sqlx::postgres::PgPool;
+use std::sync::Arc;
+
+#[derive(Clone)]
+pub struct AppState {
+    pub pool: PgPool,
+    pub config: Arc<UpstreamConfig>,
+    pub email: EmailSender,
+}
+
+impl AppState {
+    pub fn new(pool: PgPool, config: UpstreamConfig, email: EmailSender) -> Self {
+        Self {
+            pool,
+            config: Arc::new(config),
+            email,
+        }
+    }
+}

crates/helexa-upstream/src/topup.rs

@@ -0,0 +1,82 @@
+//! Single-use top-up codes (#B5) — the second half of the hybrid allocation
+//! model. Each code grants `value` tokens to the account that redeems it,
+//! raising `accounts.allocation_total`. Minting codes is operator/CLI side
+//! (the future faucet bot calls the same `mint` path); redemption is a
+//! `/web/v1` action.
+//!
+//! Security: only `sha256(code)` is stored. Redemption is **timing-safe and
+//! single-use** — a conditional `UPDATE … WHERE redeemed_by IS NULL` does
+//! the claim atomically (concurrent double-redeem → exactly one winner), and
+//! a not-found code and an already-redeemed code return the **same** generic
+//! failure with the same code path (no oracle for "valid but spent").
+
+use crate::crypto::{random_token, sha256};
+use sqlx::Row;
+use sqlx::postgres::PgPool;
+use uuid::Uuid;
+
+#[derive(Debug, thiserror::Error)]
+pub enum TopUpError {
+    /// Code unknown OR already redeemed — deliberately indistinguishable.
+    #[error("invalid or already-redeemed code")]
+    Invalid,
+    #[error(transparent)]
+    Db(#[from] sqlx::Error),
+}
+
+/// Redeem `raw_code` for `account_id`, raising the account's
+/// `allocation_total` by the code's value. Returns the new total.
+pub async fn redeem(pool: &PgPool, account_id: Uuid, raw_code: &str) -> Result<i64, TopUpError> {
+    let mut tx = pool.begin().await?;
+    // Atomic single-use claim. `redeemed_by IS NULL` is the guarantee: under
+    // concurrent redemption exactly one UPDATE touches the row.
+    let claimed = sqlx::query(
+        "UPDATE top_up_codes SET redeemed_by = $1, redeemed_at = now() \
+         WHERE code_hash = $2 AND redeemed_by IS NULL RETURNING value",
+    )
+    .bind(account_id)
+    .bind(sha256(raw_code))
+    .fetch_optional(&mut *tx)
+    .await?;
+    let Some(row) = claimed else {
+        // Not found or already redeemed — same path, same error.
+        return Err(TopUpError::Invalid);
+    };
+    let value: i64 = row.get("value");
+    let new_total: i64 = sqlx::query(
+        "UPDATE accounts SET allocation_total = allocation_total + $1 WHERE id = $2 \
+         RETURNING allocation_total",
+    )
+    .bind(value)
+    .bind(account_id)
+    .fetch_one(&mut *tx)
+    .await?
+    .get("allocation_total");
+    tx.commit().await?;
+    Ok(new_total)
+}
+
+/// Mint `count` codes each worth `value` tokens, optionally tagged with a
+/// `denomination` label. Returns the raw codes (shown once — only their
+/// hash is stored). The CLI prints these; the future faucet bot calls this.
+pub async fn mint(
+    pool: &PgPool,
+    value: i64,
+    count: u32,
+    denomination: Option<&str>,
+) -> Result<Vec<String>, sqlx::Error> {
+    let mut codes = Vec::with_capacity(count as usize);
+    for _ in 0..count {
+        let raw = format!("helexa-topup-{}", random_token());
+        sqlx::query(
+            "INSERT INTO top_up_codes (code_hash, value, denomination) VALUES ($1, $2, $3)",
+        )
+        .bind(sha256(&raw))
+        .bind(value)
+        .bind(denomination)
+        .execute(pool)
+        .await?;
+        codes.push(raw);
+    }
+    Ok(codes)
+}

crates/helexa-upstream/src/web.rs

@@ -0,0 +1,594 @@
+//! `/web/v1` — the human-facing account API the helexa.ai frontend (#F4)
+//! consumes: email+password auth (register / verify / login / reset),
+//! API-key CRUD with per-key limits, and the account balance. Web sessions
+//! are JWTs, **distinct** from inference API keys.
+//!
+//! Errors use a plain JSON shape `{ "error": { "message", "code" } }` (web
+//! clients, not OpenAI clients — the #63 envelope is the authz surface).
+//!
+//! Silent fingerprint abuse (no clue to the abuser): registration captures
+//! the browser fingerprint and always succeeds; when ≥ threshold accounts
+//! share one fingerprint, all are silently `deactivated` (keys then resolve
+//! as ordinary `401`s at the authz surface — never a "banned" signal).
+
+use crate::crypto::{generate_api_key, hash_password, random_token, sha256, verify_password};
+use crate::state::AppState;
+use axum::extract::{Path, Request, State};
+use axum::http::{StatusCode, header};
+use axum::middleware::Next;
+use axum::response::{IntoResponse, Json, Response};
+use axum::routing::{get, post};
+use axum::{Extension, Router};
+use chrono::{DateTime, Duration, Utc};
+use jsonwebtoken::{DecodingKey, EncodingKey, Header, Validation, decode, encode};
+use serde::{Deserialize, Serialize};
+use serde_json::json;
+use sqlx::Row;
+use uuid::Uuid;
+
+pub fn router(state: &AppState) -> Router<AppState> {
+    let protected = Router::new()
+        .route("/web/v1/account", get(account))
+        .route("/web/v1/keys", get(list_keys).post(create_key))
+        .route("/web/v1/keys/{id}/archive", post(archive_key))
+        .route(
+            "/web/v1/keys/{id}/limit",
+            axum::routing::patch(update_key_limit),
+        )
+        .route("/web/v1/redeem", post(redeem))
+        .layer(axum::middleware::from_fn_with_state(
+            state.clone(),
+            require_session,
+        ));
+
+    Router::new()
+        .route("/web/v1/register", post(register))
+        .route("/web/v1/verify", post(verify))
+        .route("/web/v1/login", post(login))
+        .route("/web/v1/password-reset/request", post(reset_request))
+        .route("/web/v1/password-reset/confirm", post(reset_confirm))
+        .merge(protected)
+}
+
+// ── errors ──────────────────────────────────────────────────────────
+
+enum WebError {
+    BadRequest(&'static str),
+    Unauthorized,
+    Internal,
+}
+
+impl IntoResponse for WebError {
+    fn into_response(self) -> Response {
+        let (status, code, message) = match self {
+            WebError::BadRequest(m) => (StatusCode::BAD_REQUEST, "bad_request", m),
+            WebError::Unauthorized => (StatusCode::UNAUTHORIZED, "unauthorized", "unauthorized"),
+            WebError::Internal => (
+                StatusCode::INTERNAL_SERVER_ERROR,
+                "internal_error",
+                "internal error",
+            ),
+        };
+        (
+            status,
+            Json(json!({"error": {"message": message, "code": code}})),
+        )
+            .into_response()
+    }
+}
+
+impl From<sqlx::Error> for WebError {
+    fn from(e: sqlx::Error) -> Self {
+        tracing::error!(error = %e, "web db error");
+        WebError::Internal
+    }
+}
+
+type WebResult<T> = Result<T, WebError>;
+
+// ── sessions (JWT) ──────────────────────────────────────────────────
+
+#[derive(Serialize, Deserialize)]
+struct Claims {
+    sub: String, // user id
+    exp: usize,
+}
+
+fn mint_session(state: &AppState, user_id: Uuid) -> WebResult<String> {
+    let exp = (Utc::now() + Duration::seconds(state.config.auth.session_ttl_secs as i64))
+        .timestamp() as usize;
+    let claims = Claims {
+        sub: user_id.to_string(),
+        exp,
+    };
+    encode(
+        &Header::default(),
+        &claims,
+        &EncodingKey::from_secret(state.config.auth.jwt_secret.as_bytes()),
+    )
+    .map_err(|_| WebError::Internal)
+}
+
+/// Authenticated user id, injected by [`require_session`].
+#[derive(Clone)]
+struct AuthUser(Uuid);
+
+async fn require_session(State(state): State<AppState>, mut req: Request, next: Next) -> Response {
+    let token = req
+        .headers()
+        .get(header::AUTHORIZATION)
+        .and_then(|v| v.to_str().ok())
+        .and_then(|v| v.strip_prefix("Bearer "))
+        .map(str::trim);
+    let Some(token) = token else {
+        return WebError::Unauthorized.into_response();
+    };
+    let decoded = decode::<Claims>(
+        token,
+        &DecodingKey::from_secret(state.config.auth.jwt_secret.as_bytes()),
+        &Validation::default(),
+    );
+    match decoded
+        .ok()
+        .and_then(|d| Uuid::parse_str(&d.claims.sub).ok())
+    {
+        Some(uid) => {
+            req.extensions_mut().insert(AuthUser(uid));
+            next.run(req).await
+        }
+        None => WebError::Unauthorized.into_response(),
+    }
+}
+
+/// The caller's single account id.
+async fn account_id_for(state: &AppState, user_id: Uuid) -> WebResult<Uuid> {
+    let row = sqlx::query("SELECT id FROM accounts WHERE owner_user_id = $1")
+        .bind(user_id)
+        .fetch_optional(&state.pool)
+        .await?;
+    row.map(|r| r.get::<Uuid, _>("id"))
+        .ok_or(WebError::Internal)
+}
+
+// ── auth lifecycle ──────────────────────────────────────────────────
+
+#[derive(Deserialize)]
+struct RegisterReq {
+    email: String,
+    password: String,
+    #[serde(default)]
+    fingerprint: Option<String>,
+}
+
+/// `POST /web/v1/register` — always returns `202`, regardless of whether the
+/// email was new, already taken, or fingerprint-flagged (no enumeration, no
+/// abuse clue).
+async fn register(State(state): State<AppState>, Json(req): Json<RegisterReq>) -> Response {
+    match register_inner(&state, req).await {
+        Ok(()) | Err(WebError::BadRequest(_)) => {}
+        Err(e) => return e.into_response(),
+    }
+    // Generic 202 whatever happened above (except hard server errors).
+    StatusCode::ACCEPTED.into_response()
+}
+
+async fn register_inner(state: &AppState, req: RegisterReq) -> WebResult<()> {
+    if !req.email.contains('@') {
+        return Err(WebError::BadRequest("invalid email"));
+    }
+    if req.password.len() < 8 {
+        return Err(WebError::BadRequest("password too short (min 8)"));
+    }
+    let phc = hash_password(&req.password).map_err(|_| WebError::Internal)?;
+
+    // Insert the user; a duplicate email silently no-ops (no enumeration).
+    let user_id: Option<Uuid> = sqlx::query(
+        "INSERT INTO users (email, password_hash, registration_fingerprint) \
+         VALUES ($1, $2, $3) ON CONFLICT (email) DO NOTHING RETURNING id",
+    )
+    .bind(&req.email)
+    .bind(&phc)
+    .bind(&req.fingerprint)
+    .fetch_optional(&state.pool)
+    .await?
+    .map(|r| r.get("id"));
+
+    let Some(user_id) = user_id else {
+        return Ok(()); // email already registered — say nothing
+    };
+
+    // Account with the flat free grant.
+    sqlx::query("INSERT INTO accounts (owner_user_id, allocation_total) VALUES ($1, $2)")
+        .bind(user_id)
+        .bind(state.config.grant.free_token_grant)
+        .execute(&state.pool)
+        .await?;
+
+    // Silent fingerprint abuse handling.
+    if let Some(fp) = req.fingerprint.as_deref().filter(|f| !f.is_empty()) {
+        apply_fingerprint_policy(state, fp).await?;
+    }
+
+    // Email verification link.
+    let token = random_token();
+    let expires: DateTime<Utc> =
+        Utc::now() + Duration::seconds(state.config.auth.email_token_ttl_secs as i64);
+    sqlx::query(
+        "INSERT INTO email_tokens (token_hash, user_id, kind, expires_at) \
+         VALUES ($1, $2, 'verify', $3)",
+    )
+    .bind(sha256(&token))
+    .bind(user_id)
+    .bind(expires)
+    .execute(&state.pool)
+    .await?;
+
+    let link = format!("{}/verify?token={token}", state.config.auth.app_base_url);
+    let _ = state
+        .email
+        .send(
+            &req.email,
+            "Verify your helexa account",
+            &format!("Welcome to helexa. Verify your email:\n\n{link}\n"),
+        )
+        .await;
+    Ok(())
+}
+
+/// Count accounts sharing `fp`; flag them, and silently deactivate all once
+/// the count reaches the configured threshold. No response difference — the
+/// abuser gets no signal.
+async fn apply_fingerprint_policy(state: &AppState, fp: &str) -> WebResult<()> {
+    let count: i64 =
+        sqlx::query_scalar("SELECT count(*) FROM users WHERE registration_fingerprint = $1")
+            .bind(fp)
+            .fetch_one(&state.pool)
+            .await?;
+    if count > 1 {
+        sqlx::query(
+            "UPDATE accounts SET fingerprint_flagged = true \
+             WHERE owner_user_id IN (SELECT id FROM users WHERE registration_fingerprint = $1)",
+        )
+        .bind(fp)
+        .execute(&state.pool)
+        .await?;
+    }
+    if count >= state.config.abuse.fingerprint_account_threshold {
+        let res = sqlx::query(
+            "UPDATE accounts SET status = 'deactivated' \
+             WHERE owner_user_id IN (SELECT id FROM users WHERE registration_fingerprint = $1)",
+        )
+        .bind(fp)
+        .execute(&state.pool)
+        .await?;
+        tracing::warn!(
+            fingerprint = fp,
+            accounts = res.rows_affected(),
+            "silently deactivated fingerprint-abusing accounts"
+        );
+    }
+    Ok(())
+}
+
+#[derive(Deserialize)]
+struct TokenReq {
+    token: String,
+}
+
+/// `POST /web/v1/verify` — consume a verification token, mark verified.
+async fn verify(State(state): State<AppState>, Json(req): Json<TokenReq>) -> WebResult<Response> {
+    let row = sqlx::query(
+        "UPDATE email_tokens SET consumed_at = now() \
+         WHERE token_hash = $1 AND kind = 'verify' AND consumed_at IS NULL AND expires_at > now() \
+         RETURNING user_id",
+    )
+    .bind(sha256(&req.token))
+    .fetch_optional(&state.pool)
+    .await?;
+    let Some(row) = row else {
+        return Err(WebError::BadRequest("invalid or expired token"));
+    };
+    let user_id: Uuid = row.get("user_id");
+    sqlx::query("UPDATE users SET email_verified = true WHERE id = $1")
+        .bind(user_id)
+        .execute(&state.pool)
+        .await?;
+    Ok(StatusCode::OK.into_response())
+}
+
+#[derive(Deserialize)]
+struct LoginReq {
+    email: String,
+    password: String,
+}
+
+/// `POST /web/v1/login` — verify password + email-verified → session JWT.
+async fn login(State(state): State<AppState>, Json(req): Json<LoginReq>) -> WebResult<Response> {
+    let row = sqlx::query("SELECT id, password_hash, email_verified FROM users WHERE email = $1")
+        .bind(&req.email)
+        .fetch_optional(&state.pool)
+        .await?;
+    // Generic 401 for every failure mode (no enumeration).
+    let Some(row) = row else {
+        return Err(WebError::Unauthorized);
+    };
+    let phc: String = row.get("password_hash");
+    let verified: bool = row.get("email_verified");
+    if !verify_password(&req.password, &phc) || !verified {
+        return Err(WebError::Unauthorized);
+    }
+    let user_id: Uuid = row.get("id");
+    let token = mint_session(&state, user_id)?;
+    Ok(Json(json!({
+        "token": token,
+        "expires_in": state.config.auth.session_ttl_secs,
+    }))
+    .into_response())
+}
+
+#[derive(Deserialize)]
+struct EmailReq {
+    email: String,
+}
+
+/// `POST /web/v1/password-reset/request` — always `202` (no enumeration);
+/// mints + emails a reset token only if the account exists.
+async fn reset_request(State(state): State<AppState>, Json(req): Json<EmailReq>) -> Response {
+    // The inner only ever yields `Internal` (DB failure); a missing email is
+    // Ok(()) so there's no enumeration. Surface 500 on a real error, else 202.
+    match reset_request_inner(&state, &req.email).await {
+        Ok(()) => StatusCode::ACCEPTED.into_response(),
+        Err(e) => e.into_response(),
+    }
+}
+
+async fn reset_request_inner(state: &AppState, email: &str) -> WebResult<()> {
+    let row = sqlx::query("SELECT id FROM users WHERE email = $1")
+        .bind(email)
+        .fetch_optional(&state.pool)
+        .await?;
+    let Some(row) = row else { return Ok(()) };
+    let user_id: Uuid = row.get("id");
+    let token = random_token();
+    let expires: DateTime<Utc> =
+        Utc::now() + Duration::seconds(state.config.auth.email_token_ttl_secs as i64);
+    sqlx::query(
+        "INSERT INTO email_tokens (token_hash, user_id, kind, expires_at) \
+         VALUES ($1, $2, 'reset', $3)",
+    )
+    .bind(sha256(&token))
+    .bind(user_id)
+    .bind(expires)
+    .execute(&state.pool)
+    .await?;
+    let link = format!("{}/reset?token={token}", state.config.auth.app_base_url);
+    let _ = state
+        .email
+        .send(
+            email,
+            "Reset your helexa password",
+            &format!("Reset your password:\n\n{link}\n"),
+        )
+        .await;
+    Ok(())
+}
+
+#[derive(Deserialize)]
+struct ResetConfirmReq {
+    token: String,
+    new_password: String,
+}
+
+/// `POST /web/v1/password-reset/confirm` — consume reset token, rotate hash.
+async fn reset_confirm(
+    State(state): State<AppState>,
+    Json(req): Json<ResetConfirmReq>,
+) -> WebResult<Response> {
+    if req.new_password.len() < 8 {
+        return Err(WebError::BadRequest("password too short (min 8)"));
+    }
+    let row = sqlx::query(
+        "UPDATE email_tokens SET consumed_at = now() \
+         WHERE token_hash = $1 AND kind = 'reset' AND consumed_at IS NULL AND expires_at > now() \
+         RETURNING user_id",
+    )
+    .bind(sha256(&req.token))
+    .fetch_optional(&state.pool)
+    .await?;
+    let Some(row) = row else {
+        return Err(WebError::BadRequest("invalid or expired token"));
+    };
+    let user_id: Uuid = row.get("user_id");
+    let phc = hash_password(&req.new_password).map_err(|_| WebError::Internal)?;
+    sqlx::query("UPDATE users SET password_hash = $1 WHERE id = $2")
+        .bind(phc)
+        .bind(user_id)
+        .execute(&state.pool)
+        .await?;
+    Ok(StatusCode::OK.into_response())
+}
+
+// ── account + keys (protected) ──────────────────────────────────────
+
+async fn account(
+    State(state): State<AppState>,
+    Extension(user): Extension<AuthUser>,
+) -> WebResult<Response> {
+    let acct = account_id_for(&state, user.0).await?;
+    let row = sqlx::query(
+        "SELECT allocation_total, allocation_spent, allocation_reserved FROM accounts WHERE id = $1",
+    )
+    .bind(acct)
+    .fetch_one(&state.pool)
+    .await?;
+    Ok(Json(json!({
+        "account_id": acct.to_string(),
+        "allocation_total": row.get::<i64, _>("allocation_total"),
+        "allocation_spent": row.get::<i64, _>("allocation_spent"),
+        "allocation_reserved": row.get::<i64, _>("allocation_reserved"),
+    }))
+    .into_response())
+}
+
+async fn list_keys(
+    State(state): State<AppState>,
+    Extension(user): Extension<AuthUser>,
+) -> WebResult<Response> {
+    let acct = account_id_for(&state, user.0).await?;
+    let rows = sqlx::query(
+        "SELECT id, key_prefix, label, status, limit_kind, limit_value, key_spent, key_reserved, \
+                created_at \
+         FROM api_keys WHERE account_id = $1 ORDER BY created_at DESC",
+    )
+    .bind(acct)
+    .fetch_all(&state.pool)
+    .await?;
+    let keys: Vec<_> = rows
+        .iter()
+        .map(|r| {
+            json!({
+                "id": r.get::<Uuid, _>("id").to_string(),
+                "prefix": r.get::<String, _>("key_prefix"),
+                "label": r.get::<String, _>("label"),
+                "status": r.get::<String, _>("status"),
+                "limit_kind": r.get::<String, _>("limit_kind"),
+                "limit_value": r.get::<i64, _>("limit_value"),
+                "spent": r.get::<i64, _>("key_spent"),
+                "reserved": r.get::<i64, _>("key_reserved"),
+                "created_at": r.get::<DateTime<Utc>, _>("created_at").to_rfc3339(),
+            })
+        })
+        .collect();
+    Ok(Json(json!({ "keys": keys })).into_response())
+}
+
+#[derive(Deserialize)]
+struct CreateKeyReq {
+    #[serde(default)]
+    label: String,
+    /// "percent" | "hardcap" (default percent=100 → full allocation).
+    #[serde(default)]
+    limit_kind: Option<String>,
+    #[serde(default)]
+    limit_value: Option<i64>,
+}
+
+async fn create_key(
+    State(state): State<AppState>,
+    Extension(user): Extension<AuthUser>,
+    Json(req): Json<CreateKeyReq>,
+) -> WebResult<Response> {
+    let acct = account_id_for(&state, user.0).await?;
+    let limit_kind = match req.limit_kind.as_deref() {
+        Some("hardcap") => "hardcap",
+        _ => "percent",
+    };
+    let limit_value = req.limit_value.unwrap_or(100).max(0);
+    let (raw, prefix) = generate_api_key();
+    let id: Uuid = sqlx::query(
+        "INSERT INTO api_keys (account_id, key_hash, key_prefix, label, limit_kind, limit_value) \
+         VALUES ($1, $2, $3, $4, $5, $6) RETURNING id",
+    )
+    .bind(acct)
+    .bind(sha256(&raw))
+    .bind(&prefix)
+    .bind(&req.label)
+    .bind(limit_kind)
+    .bind(limit_value)
+    .fetch_one(&state.pool)
+    .await?
+    .get("id");
+    // The raw key is shown exactly once.
+    Ok((
+        StatusCode::CREATED,
+        Json(json!({
+            "id": id.to_string(),
+            "key": raw,
+            "prefix": prefix,
+            "limit_kind": limit_kind,
+            "limit_value": limit_value,
+        })),
+    )
+        .into_response())
+}
+
+async fn archive_key(
+    State(state): State<AppState>,
+    Extension(user): Extension<AuthUser>,
+    Path(id): Path<Uuid>,
+) -> WebResult<Response> {
+    let acct = account_id_for(&state, user.0).await?;
+    let res = sqlx::query(
+        "UPDATE api_keys SET status = 'archived' WHERE id = $1 AND account_id = $2 AND status = 'active'",
+    )
+    .bind(id)
+    .bind(acct)
+    .execute(&state.pool)
+    .await?;
+    if res.rows_affected() == 0 {
+        return Err(WebError::BadRequest("no such active key"));
+    }
+    Ok(StatusCode::NO_CONTENT.into_response())
+}
+
+#[derive(Deserialize)]
+struct UpdateLimitReq {
+    limit_kind: String,
+    limit_value: i64,
+}
+
+async fn update_key_limit(
+    State(state): State<AppState>,
+    Extension(user): Extension<AuthUser>,
+    Path(id): Path<Uuid>,
+    Json(req): Json<UpdateLimitReq>,
+) -> WebResult<Response> {
+    if req.limit_kind != "percent" && req.limit_kind != "hardcap" {
+        return Err(WebError::BadRequest(
+            "limit_kind must be percent or hardcap",
+        ));
+    }
+    if req.limit_value < 0 {
+        return Err(WebError::BadRequest("limit_value must be >= 0"));
+    }
+    let acct = account_id_for(&state, user.0).await?;
+    let res = sqlx::query(
+        "UPDATE api_keys SET limit_kind = $1, limit_value = $2 WHERE id = $3 AND account_id = $4",
+    )
+    .bind(&req.limit_kind)
+    .bind(req.limit_value)
+    .bind(id)
+    .bind(acct)
+    .execute(&state.pool)
+    .await?;
+    if res.rows_affected() == 0 {
+        return Err(WebError::BadRequest("no such key"));
+    }
+    Ok(StatusCode::NO_CONTENT.into_response())
+}
+
+#[derive(Deserialize)]
+struct RedeemReq {
+    code: String,
+}
+
+/// `POST /web/v1/redeem` — redeem a single-use top-up code, raising the
+/// account's allocation. Returns the new total. Generic 400 for an invalid
+/// or already-redeemed code (no oracle).
+async fn redeem(
+    State(state): State<AppState>,
+    Extension(user): Extension<AuthUser>,
+    Json(req): Json<RedeemReq>,
+) -> WebResult<Response> {
+    let acct = account_id_for(&state, user.0).await?;
+    match crate::topup::redeem(&state.pool, acct, &req.code).await {
+        Ok(new_total) => Ok(Json(json!({ "allocation_total": new_total })).into_response()),
+        Err(crate::topup::TopUpError::Invalid) => {
+            Err(WebError::BadRequest("invalid or already-redeemed code"))
+        }
+        Err(crate::topup::TopUpError::Db(e)) => {
+            tracing::error!(error = %e, "redeem db error");
+            Err(WebError::Internal)
+        }
+    }
+}

crates/helexa-upstream/tests/authz_pg.rs

@@ -0,0 +1,243 @@
+//! Integration tests for the `/authz/v1` surface against a real Postgres,
+//! driving the built axum app over HTTP. Gated on `UPSTREAM_TEST_DATABASE_URL`
+//! (skips cleanly when unset, so CI stays green without a DB):
+//!
+//!   UPSTREAM_TEST_DATABASE_URL=postgres://helexa:helexa@localhost/helexa_test \
+//!     cargo test -p helexa-upstream --test authz_pg
+
+use helexa_upstream::config::{ClientToken, UpstreamConfig};
+use helexa_upstream::crypto::sha256;
+use helexa_upstream::db::connect_and_migrate;
+use helexa_upstream::state::AppState;
+use serde_json::{Value, json};
+use sqlx::Executor;
+use sqlx::Row;
+use sqlx::postgres::PgPool;
+use uuid::Uuid;
+
+const CLIENT_TOKEN: &str = "test-operator-token";
+
+async fn spawn_or_skip(test: &str) -> Option<(String, PgPool)> {
+    let Ok(url) = std::env::var("UPSTREAM_TEST_DATABASE_URL") else {
+        eprintln!("skipping {test}: UPSTREAM_TEST_DATABASE_URL not set");
+        return None;
+    };
+    let pool = connect_and_migrate(&url, 16).await.expect("migrate");
+
+    let mut config = UpstreamConfig {
+        server: Default::default(),
+        db: helexa_upstream::config::DbSettings {
+            url,
+            max_connections: 16,
+        },
+        grant: Default::default(),
+        abuse: Default::default(),
+        client_auth: Default::default(),
+        authz: Default::default(),
+        auth: Default::default(),
+        email: Default::default(),
+    };
+    config.client_auth.tokens.push(ClientToken {
+        token: CLIENT_TOKEN.into(),
+        operator_id: "op-test".into(),
+    });
+
+    let email = helexa_upstream::email::EmailSender::from_config(&config.email).unwrap();
+    let state = AppState::new(pool.clone(), config, email);
+    let app = helexa_upstream::build_app(state);
+    let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
+    let addr = listener.local_addr().unwrap();
+    tokio::spawn(async move {
+        axum::serve(listener, app).await.unwrap();
+    });
+    Some((format!("http://{addr}"), pool))
+}
+
+/// Seed an account with `total` allocation and an active key with raw value
+/// `raw` (percent=100). Optionally deactivate the account. Returns
+/// (account_id, key_id).
+async fn seed_key(pool: &PgPool, total: i64, raw: &str, deactivated: bool) -> (Uuid, Uuid) {
+    let user_id: Uuid = pool
+        .fetch_one(
+            sqlx::query(
+                "INSERT INTO users (email, password_hash, email_verified) VALUES ($1,'x',true) RETURNING id",
+            )
+            .bind(format!("u-{}@t.local", Uuid::new_v4())),
+        )
+        .await
+        .unwrap()
+        .get("id");
+    let status = if deactivated { "deactivated" } else { "active" };
+    let account_id: Uuid = pool
+        .fetch_one(
+            sqlx::query(
+                "INSERT INTO accounts (owner_user_id, allocation_total, status) VALUES ($1,$2,$3) RETURNING id",
+            )
+            .bind(user_id)
+            .bind(total)
+            .bind(status),
+        )
+        .await
+        .unwrap()
+        .get("id");
+    let key_id: Uuid = pool
+        .fetch_one(
+            sqlx::query(
+                "INSERT INTO api_keys (account_id, key_hash, key_prefix, limit_kind, limit_value) \
+                 VALUES ($1,$2,'sk-test','percent',100) RETURNING id",
+            )
+            .bind(account_id)
+            .bind(sha256(raw)),
+        )
+        .await
+        .unwrap()
+        .get("id");
+    (account_id, key_id)
+}
+
+fn client() -> reqwest::Client {
+    reqwest::Client::new()
+}
+
+async fn post(
+    c: &reqwest::Client,
+    url: String,
+    body: Value,
+    bearer: Option<&str>,
+) -> reqwest::Response {
+    let mut req = c.post(url).json(&body);
+    if let Some(b) = bearer {
+        req = req.bearer_auth(b);
+    }
+    req.send().await.unwrap()
+}
+
+#[tokio::test]
+async fn resolve_reserve_settle_round_trip() {
+    let Some((base, pool)) = spawn_or_skip("resolve_reserve_settle_round_trip").await else {
+        return;
+    };
+    let raw = format!("sk-{}", Uuid::new_v4());
+    let (account_id, key_id) = seed_key(&pool, 1000, &raw, false).await;
+    let c = client();
+
+    // resolve
+    let r = post(
+        &c,
+        format!("{base}/authz/v1/resolve"),
+        json!({"api_key": raw}),
+        Some(CLIENT_TOKEN),
+    )
+    .await;
+    assert_eq!(r.status(), 200);
+    let body: Value = r.json().await.unwrap();
+    assert_eq!(body["principal"]["account_id"], account_id.to_string());
+    assert_eq!(body["principal"]["key_id"], key_id.to_string());
+    assert_eq!(body["snapshot"]["hard_cap"], 1000);
+
+    // reserve 400
+    let r = post(
+        &c,
+        format!("{base}/authz/v1/reserve"),
+        json!({"account_id": account_id, "key_id": key_id, "max_tokens": 400}),
+        Some(CLIENT_TOKEN),
+    )
+    .await;
+    assert_eq!(r.status(), 200);
+    let body: Value = r.json().await.unwrap();
+    let rid = body["reservation_id"].as_i64().expect("granted");
+
+    // settle 150
+    let r = post(
+        &c,
+        format!("{base}/authz/v1/settle"),
+        json!({"reservation_id": rid, "actual_tokens": 150}),
+        Some(CLIENT_TOKEN),
+    )
+    .await;
+    assert_eq!(r.status(), 204);
+
+    // snapshot reflects spend
+    let r = post(
+        &c,
+        format!("{base}/authz/v1/snapshot"),
+        json!({"account_id": account_id, "key_id": key_id}),
+        Some(CLIENT_TOKEN),
+    )
+    .await;
+    let body: Value = r.json().await.unwrap();
+    assert_eq!(body["spent"], 150);
+    assert_eq!(body["reserved"], 0);
+}
+
+#[tokio::test]
+async fn over_cap_reserve_is_rejected_not_errored() {
+    let Some((base, pool)) = spawn_or_skip("over_cap_reserve_is_rejected_not_errored").await else {
+        return;
+    };
+    let raw = format!("sk-{}", Uuid::new_v4());
+    let (account_id, key_id) = seed_key(&pool, 100, &raw, false).await;
+    let c = client();
+    let r = post(
+        &c,
+        format!("{base}/authz/v1/reserve"),
+        json!({"account_id": account_id, "key_id": key_id, "max_tokens": 999}),
+        Some(CLIENT_TOKEN),
+    )
+    .await;
+    assert_eq!(r.status(), 200, "budget refusal is an authoritative 200");
+    let body: Value = r.json().await.unwrap();
+    assert!(body["reservation_id"].is_null());
+    assert_eq!(body["rejected"]["kind"], "insufficient_quota");
+    assert_eq!(body["rejected"]["available"], 100);
+}
+
+#[tokio::test]
+async fn deactivated_account_resolves_as_invalid_no_clue() {
+    let Some((base, pool)) = spawn_or_skip("deactivated_account_resolves_as_invalid_no_clue").await
+    else {
+        return;
+    };
+    let raw = format!("sk-{}", Uuid::new_v4());
+    seed_key(&pool, 1000, &raw, true).await; // deactivated
+    let c = client();
+    let r = post(
+        &c,
+        format!("{base}/authz/v1/resolve"),
+        json!({"api_key": raw}),
+        Some(CLIENT_TOKEN),
+    )
+    .await;
+    // Indistinguishable from an unknown key.
+    assert_eq!(r.status(), 401);
+    let body: Value = r.json().await.unwrap();
+    assert_eq!(body["error"]["code"], "invalid_api_key");
+}
+
+#[tokio::test]
+async fn missing_client_auth_is_401_before_db() {
+    let Some((base, pool)) = spawn_or_skip("missing_client_auth_is_401_before_db").await else {
+        return;
+    };
+    let raw = format!("sk-{}", Uuid::new_v4());
+    seed_key(&pool, 1000, &raw, false).await;
+    let c = client();
+    // No bearer → rejected by client_auth.
+    let r = post(
+        &c,
+        format!("{base}/authz/v1/resolve"),
+        json!({"api_key": raw}),
+        None,
+    )
+    .await;
+    assert_eq!(r.status(), 401);
+    // Wrong bearer → also rejected.
+    let r = post(
+        &c,
+        format!("{base}/authz/v1/resolve"),
+        json!({"api_key": raw}),
+        Some("wrong"),
+    )
+    .await;
+    assert_eq!(r.status(), 401);
+}

crates/helexa-upstream/tests/ledger_pg.rs

@@ -0,0 +1,204 @@
+//! Integration tests for the allocation ledger against a real PostgreSQL.
+//!
+//! Gated on `UPSTREAM_TEST_DATABASE_URL` — when unset (CI's generic runner,
+//! local builds without a DB), every test logs a skip and returns, so
+//! `cargo test --workspace` stays green without Postgres. Point the env var
+//! at a throwaway database to exercise the no-overshoot guarantee and
+//! settle/release idempotency:
+//!
+//!   UPSTREAM_TEST_DATABASE_URL=postgres://helexa:helexa@localhost/helexa_test \
+//!     cargo test -p helexa-upstream --test ledger_pg
+
+use helexa_upstream::db::connect_and_migrate;
+use helexa_upstream::ledger::{self, LedgerError};
+use sqlx::Executor;
+use sqlx::Row;
+use sqlx::postgres::PgPool;
+use uuid::Uuid;
+
+/// Returns a migrated pool, or `None` (with a skip log) when the env var is
+/// unset.
+async fn pool_or_skip(test: &str) -> Option<PgPool> {
+    let Ok(url) = std::env::var("UPSTREAM_TEST_DATABASE_URL") else {
+        eprintln!("skipping {test}: UPSTREAM_TEST_DATABASE_URL not set");
+        return None;
+    };
+    Some(
+        connect_and_migrate(&url, 16)
+            .await
+            .expect("connect + migrate"),
+    )
+}
+
+/// Seed a verified user + account (with `total` allocation) + an active key
+/// (percent=100 so the account cap binds). Returns (account_id, key_id).
+async fn seed(pool: &PgPool, total: i64) -> (Uuid, Uuid) {
+    let user_id: Uuid = pool
+        .fetch_one(
+            sqlx::query(
+                "INSERT INTO users (email, password_hash, email_verified) \
+                 VALUES ($1, 'x', true) RETURNING id",
+            )
+            .bind(format!("u-{}@test.local", Uuid::new_v4())),
+        )
+        .await
+        .unwrap()
+        .get("id");
+    let account_id: Uuid = pool
+        .fetch_one(
+            sqlx::query(
+                "INSERT INTO accounts (owner_user_id, allocation_total) \
+                 VALUES ($1, $2) RETURNING id",
+            )
+            .bind(user_id)
+            .bind(total),
+        )
+        .await
+        .unwrap()
+        .get("id");
+    let key_id: Uuid = pool
+        .fetch_one(
+            sqlx::query(
+                "INSERT INTO api_keys (account_id, key_hash, key_prefix, limit_kind, limit_value) \
+                 VALUES ($1, $2, 'sk-test', 'percent', 100) RETURNING id",
+            )
+            .bind(account_id)
+            .bind(Uuid::new_v4().as_bytes().to_vec()),
+        )
+        .await
+        .unwrap()
+        .get("id");
+    (account_id, key_id)
+}
+
+async fn account_cols(pool: &PgPool, account_id: Uuid) -> (i64, i64) {
+    let row = pool
+        .fetch_one(
+            sqlx::query("SELECT allocation_spent, allocation_reserved FROM accounts WHERE id = $1")
+                .bind(account_id),
+        )
+        .await
+        .unwrap();
+    (row.get("allocation_spent"), row.get("allocation_reserved"))
+}
+
+#[tokio::test]
+async fn concurrent_reserves_never_overshoot() {
+    let Some(pool) = pool_or_skip("concurrent_reserves_never_overshoot").await else {
+        return;
+    };
+    // Allocation admits exactly 5 reservations of 100 (cap 500).
+    let (account_id, key_id) = seed(&pool, 500).await;
+
+    let mut handles = Vec::new();
+    for _ in 0..20 {
+        let pool = pool.clone();
+        handles.push(tokio::spawn(async move {
+            ledger::reserve(&pool, account_id, key_id, 100).await
+        }));
+    }
+    let mut ok = 0;
+    let mut quota = 0;
+    for h in handles {
+        match h.await.unwrap() {
+            Ok(_) => ok += 1,
+            Err(LedgerError::InsufficientQuota { .. }) => quota += 1,
+            Err(e) => panic!("unexpected error: {e}"),
+        }
+    }
+    assert_eq!(ok, 5, "exactly 5 reserves of 100 fit in a 500 allocation");
+    assert_eq!(quota, 15);
+
+    let (spent, reserved) = account_cols(&pool, account_id).await;
+    assert_eq!(spent, 0);
+    assert_eq!(reserved, 500, "reserved exactly the cap, never over");
+}
+
+#[tokio::test]
+async fn settle_is_idempotent_and_reconciles_spend() {
+    let Some(pool) = pool_or_skip("settle_is_idempotent_and_reconciles_spend").await else {
+        return;
+    };
+    let (account_id, key_id) = seed(&pool, 1000).await;
+    let rid = ledger::reserve(&pool, account_id, key_id, 400)
+        .await
+        .unwrap();
+
+    // Settle actual=150 (< reserved 400): spent=150, reserved back to 0.
+    ledger::settle(&pool, rid, 150).await.unwrap();
+    let (spent, reserved) = account_cols(&pool, account_id).await;
+    assert_eq!((spent, reserved), (150, 0));
+
+    // Second settle is a no-op.
+    ledger::settle(&pool, rid, 999).await.unwrap();
+    let (spent2, reserved2) = account_cols(&pool, account_id).await;
+    assert_eq!((spent2, reserved2), (150, 0), "settle is idempotent");
+}
+
+#[tokio::test]
+async fn release_returns_reservation_and_is_idempotent() {
+    let Some(pool) = pool_or_skip("release_returns_reservation_and_is_idempotent").await else {
+        return;
+    };
+    let (account_id, key_id) = seed(&pool, 1000).await;
+    let rid = ledger::reserve(&pool, account_id, key_id, 300)
+        .await
+        .unwrap();
+    assert_eq!(account_cols(&pool, account_id).await, (0, 300));
+
+    ledger::release(&pool, rid).await.unwrap();
+    assert_eq!(account_cols(&pool, account_id).await, (0, 0));
+    // Idempotent; settle-after-release also a no-op.
+    ledger::release(&pool, rid).await.unwrap();
+    ledger::settle(&pool, rid, 100).await.unwrap();
+    assert_eq!(account_cols(&pool, account_id).await, (0, 0));
+}
+
+#[tokio::test]
+async fn hardcap_key_subcap_binds_below_account() {
+    let Some(pool) = pool_or_skip("hardcap_key_subcap_binds_below_account").await else {
+        return;
+    };
+    // Account has 1000 but the key is hard-capped at 200.
+    let user_id: Uuid = pool
+        .fetch_one(
+            sqlx::query(
+                "INSERT INTO users (email, password_hash, email_verified) \
+                 VALUES ($1, 'x', true) RETURNING id",
+            )
+            .bind(format!("u-{}@test.local", Uuid::new_v4())),
+        )
+        .await
+        .unwrap()
+        .get("id");
+    let account_id: Uuid = pool
+        .fetch_one(
+            sqlx::query(
+                "INSERT INTO accounts (owner_user_id, allocation_total) VALUES ($1, 1000) RETURNING id",
+            )
+            .bind(user_id),
+        )
+        .await
+        .unwrap()
+        .get("id");
+    let key_id: Uuid = pool
+        .fetch_one(
+            sqlx::query(
+                "INSERT INTO api_keys (account_id, key_hash, key_prefix, limit_kind, limit_value) \
+                 VALUES ($1, $2, 'sk-test', 'hardcap', 200) RETURNING id",
+            )
+            .bind(account_id)
+            .bind(Uuid::new_v4().as_bytes().to_vec()),
+        )
+        .await
+        .unwrap()
+        .get("id");
+
+    ledger::reserve(&pool, account_id, key_id, 200)
+        .await
+        .unwrap();
+    match ledger::reserve(&pool, account_id, key_id, 1).await {
+        Err(LedgerError::InsufficientQuota { available, .. }) => assert_eq!(available, 0),
+        other => panic!("expected InsufficientQuota, got {other:?}"),
+    }
+}

crates/helexa-upstream/tests/served_usage_pg.rs

@@ -0,0 +1,116 @@
+//! Integration test for the served-usage report (#58): the idempotent,
+//! monotonic upsert and the reconcile rollup. Gated on
+//! UPSTREAM_TEST_DATABASE_URL (skips cleanly when unset).
+
+use helexa_upstream::config::{ClientToken, UpstreamConfig};
+use helexa_upstream::db::connect_and_migrate;
+use helexa_upstream::email::EmailSender;
+use helexa_upstream::reconcile::reconcile;
+use helexa_upstream::state::AppState;
+use serde_json::{Value, json};
+use sqlx::Row;
+use sqlx::postgres::PgPool;
+use uuid::Uuid;
+
+const CLIENT_TOKEN: &str = "su-test-token";
+const OPERATOR: &str = "op-su-test";
+
+async fn spawn_or_skip(test: &str) -> Option<(String, PgPool)> {
+    let Ok(url) = std::env::var("UPSTREAM_TEST_DATABASE_URL") else {
+        eprintln!("skipping {test}: UPSTREAM_TEST_DATABASE_URL not set");
+        return None;
+    };
+    let pool = connect_and_migrate(&url, 16).await.expect("migrate");
+    let mut config = UpstreamConfig {
+        server: Default::default(),
+        db: helexa_upstream::config::DbSettings {
+            url,
+            max_connections: 16,
+        },
+        grant: Default::default(),
+        abuse: Default::default(),
+        client_auth: Default::default(),
+        authz: Default::default(),
+        auth: Default::default(),
+        email: Default::default(),
+    };
+    config.client_auth.tokens.push(ClientToken {
+        token: CLIENT_TOKEN.into(),
+        operator_id: OPERATOR.into(),
+    });
+    let email = EmailSender::from_config(&config.email).unwrap();
+    let state = AppState::new(pool.clone(), config, email);
+    let app = helexa_upstream::build_app(state);
+    let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
+    let addr = listener.local_addr().unwrap();
+    tokio::spawn(async move {
+        axum::serve(listener, app).await.unwrap();
+    });
+    Some((format!("http://{addr}"), pool))
+}
+
+async fn report(base: &str, rows: Value) -> u16 {
+    reqwest::Client::new()
+        .post(format!("{base}/authz/v1/served-usage"))
+        .bearer_auth(CLIENT_TOKEN)
+        .json(&json!({ "rows": rows }))
+        .send()
+        .await
+        .unwrap()
+        .status()
+        .as_u16()
+}
+
+async fn stored(pool: &PgPool, account: Uuid, key: Uuid) -> i64 {
+    sqlx::query(
+        "SELECT served_tokens FROM served_usage WHERE operator_id = $1 AND account_id = $2 AND key_id = $3",
+    )
+    .bind(OPERATOR)
+    .bind(account)
+    .bind(key)
+    .fetch_one(pool)
+    .await
+    .unwrap()
+    .get("served_tokens")
+}
+
+#[tokio::test]
+async fn served_usage_upsert_is_monotonic_and_reconciles() {
+    let Some((base, pool)) = spawn_or_skip("served_usage_upsert_is_monotonic_and_reconciles").await
+    else {
+        return;
+    };
+    let account = Uuid::new_v4();
+    let key = Uuid::new_v4();
+    let period = "2026-06-23";
+    let row = |n: i64| json!([{"account_id": account, "key_id": key, "period": period, "served_tokens": n}]);
+
+    // First report.
+    assert_eq!(report(&base, row(100)).await, 204);
+    assert_eq!(stored(&pool, account, key).await, 100);
+
+    // Re-send a higher absolute value → advances.
+    assert_eq!(report(&base, row(250)).await, 204);
+    assert_eq!(stored(&pool, account, key).await, 250);
+
+    // A lower value (e.g. a restarted cortex) must NOT regress (GREATEST).
+    assert_eq!(report(&base, row(50)).await, 204);
+    assert_eq!(stored(&pool, account, key).await, 250);
+
+    // Re-sending the same value is idempotent.
+    assert_eq!(report(&base, row(250)).await, 204);
+    assert_eq!(stored(&pool, account, key).await, 250);
+
+    // Reconcile rolls it up and stamps reconciled_at; a second run is empty.
+    let rollup = reconcile(&pool).await.unwrap();
+    let mine = rollup
+        .iter()
+        .find(|r| r.operator_id == OPERATOR)
+        .expect("operator in rollup");
+    assert!(mine.total_served_tokens >= 250);
+    let again = reconcile(&pool).await.unwrap();
+    assert!(
+        again.iter().all(|r| r.operator_id != OPERATOR),
+        "already reconciled"
+    );
+}

crates/helexa-upstream/tests/web_pg.rs

@@ -0,0 +1,425 @@
+//! Integration tests for the `/web/v1` account API + the silent fingerprint
+//! abuse policy, driving the built app over HTTP against a real Postgres.
+//! Gated on `UPSTREAM_TEST_DATABASE_URL` (skips cleanly when unset).
+
+use helexa_upstream::config::{ClientToken, UpstreamConfig};
+use helexa_upstream::crypto::sha256;
+use helexa_upstream::db::connect_and_migrate;
+use helexa_upstream::email::EmailSender;
+use helexa_upstream::state::AppState;
+use serde_json::{Value, json};
+use sqlx::Executor;
+use sqlx::Row;
+use sqlx::postgres::PgPool;
+
+const CLIENT_TOKEN: &str = "web-test-operator-token";
+
+async fn spawn_or_skip(test: &str) -> Option<(String, PgPool)> {
+    let Ok(url) = std::env::var("UPSTREAM_TEST_DATABASE_URL") else {
+        eprintln!("skipping {test}: UPSTREAM_TEST_DATABASE_URL not set");
+        return None;
+    };
+    let pool = connect_and_migrate(&url, 16).await.expect("migrate");
+    let mut config = UpstreamConfig {
+        server: Default::default(),
+        db: helexa_upstream::config::DbSettings {
+            url,
+            max_connections: 16,
+        },
+        grant: Default::default(),
+        abuse: Default::default(),
+        client_auth: Default::default(),
+        authz: Default::default(),
+        auth: Default::default(),
+        email: Default::default(), // Log transport
+    };
+    config.client_auth.tokens.push(ClientToken {
+        token: CLIENT_TOKEN.into(),
+        operator_id: "op-web".into(),
+    });
+    let email = EmailSender::from_config(&config.email).unwrap();
+    let state = AppState::new(pool.clone(), config, email);
+    let app = helexa_upstream::build_app(state);
+    let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
+    let addr = listener.local_addr().unwrap();
+    tokio::spawn(async move {
+        axum::serve(listener, app).await.unwrap();
+    });
+    Some((format!("http://{addr}"), pool))
+}
+
+fn unique_email() -> String {
+    format!("u-{}@test.local", uuid::Uuid::new_v4())
+}
+
+async fn post(url: String, body: Value, bearer: Option<&str>) -> reqwest::Response {
+    let c = reqwest::Client::new();
+    let mut req = c.post(url).json(&body);
+    if let Some(b) = bearer {
+        req = req.bearer_auth(b);
+    }
+    req.send().await.unwrap()
+}
+
+#[tokio::test]
+async fn verify_endpoint_consumes_token_once() {
+    let Some((base, pool)) = spawn_or_skip("verify_endpoint_consumes_token_once").await else {
+        return;
+    };
+    let email = unique_email();
+    // Register, then mint a verify token directly (the raw token is only in
+    // the email; here we insert a known one to drive the endpoint).
+    assert_eq!(
+        post(
+            format!("{base}/web/v1/register"),
+            json!({"email": email, "password": "password123"}),
+            None
+        )
+        .await
+        .status(),
+        202
+    );
+    let user_id: uuid::Uuid = pool
+        .fetch_one(sqlx::query("SELECT id FROM users WHERE email = $1").bind(&email))
+        .await
+        .unwrap()
+        .get("id");
+    let raw = "verify-raw-token-xyz";
+    pool.execute(
+        sqlx::query(
+            "INSERT INTO email_tokens (token_hash, user_id, kind, expires_at) \
+             VALUES ($1, $2, 'verify', now() + interval '1 hour')",
+        )
+        .bind(sha256(raw))
+        .bind(user_id),
+    )
+    .await
+    .unwrap();
+
+    assert_eq!(
+        post(format!("{base}/web/v1/verify"), json!({"token": raw}), None)
+            .await
+            .status(),
+        200
+    );
+    // Consumed → second attempt fails.
+    assert_eq!(
+        post(format!("{base}/web/v1/verify"), json!({"token": raw}), None)
+            .await
+            .status(),
+        400
+    );
+
+    let verified: bool = pool
+        .fetch_one(sqlx::query("SELECT email_verified FROM users WHERE id = $1").bind(user_id))
+        .await
+        .unwrap()
+        .get("email_verified");
+    assert!(verified);
+}
+
+#[tokio::test]
+async fn account_lifecycle_and_key_resolves_then_archives() {
+    let Some((base, pool)) =
+        spawn_or_skip("account_lifecycle_and_key_resolves_then_archives").await
+    else {
+        return;
+    };
+    let email = unique_email();
+    post(
+        format!("{base}/web/v1/register"),
+        json!({"email": email, "password": "password123"}),
+        None,
+    )
+    .await;
+    // Bypass the email step for the login/key portion.
+    pool.execute(
+        sqlx::query("UPDATE users SET email_verified = true WHERE email = $1").bind(&email),
+    )
+    .await
+    .unwrap();
+
+    // login → session JWT
+    let r = post(
+        format!("{base}/web/v1/login"),
+        json!({"email": email, "password": "password123"}),
+        None,
+    )
+    .await;
+    assert_eq!(r.status(), 200);
+    let token = r.json::<Value>().await.unwrap()["token"]
+        .as_str()
+        .unwrap()
+        .to_string();
+
+    // create key (raw shown once)
+    let r = post(
+        format!("{base}/web/v1/keys"),
+        json!({"label": "laptop"}),
+        Some(&token),
+    )
+    .await;
+    assert_eq!(r.status(), 201);
+    let body: Value = r.json().await.unwrap();
+    let raw_key = body["key"].as_str().unwrap().to_string();
+    let key_id = body["id"].as_str().unwrap().to_string();
+    assert!(raw_key.starts_with("sk-helexa-"));
+
+    // account balance reflects the free grant
+    let r = reqwest::Client::new()
+        .get(format!("{base}/web/v1/account"))
+        .bearer_auth(&token)
+        .send()
+        .await
+        .unwrap();
+    assert_eq!(
+        r.json::<Value>().await.unwrap()["allocation_total"],
+        1_000_000
+    );
+
+    // list keys shows the prefix, never the raw secret
+    let r = reqwest::Client::new()
+        .get(format!("{base}/web/v1/keys"))
+        .bearer_auth(&token)
+        .send()
+        .await
+        .unwrap();
+    let listed = r.json::<Value>().await.unwrap();
+    let k = &listed["keys"][0];
+    assert_eq!(k["id"], key_id);
+    assert!(k.get("key").is_none(), "raw secret never listed");
+    assert!(k["prefix"].as_str().unwrap().starts_with("sk-helexa-"));
+
+    // the key authorizes at the authz surface
+    let r = post(
+        format!("{base}/authz/v1/resolve"),
+        json!({"api_key": raw_key}),
+        Some(CLIENT_TOKEN),
+    )
+    .await;
+    assert_eq!(r.status(), 200);
+
+    // archive → the key no longer resolves
+    let r = post(
+        format!("{base}/web/v1/keys/{key_id}/archive"),
+        json!({}),
+        Some(&token),
+    )
+    .await;
+    assert_eq!(r.status(), 204);
+    let r = post(
+        format!("{base}/authz/v1/resolve"),
+        json!({"api_key": raw_key}),
+        Some(CLIENT_TOKEN),
+    )
+    .await;
+    assert_eq!(r.status(), 401);
+}
+
+#[tokio::test]
+async fn fingerprint_abuse_silently_deactivates_all_no_clue() {
+    let Some((base, pool)) =
+        spawn_or_skip("fingerprint_abuse_silently_deactivates_all_no_clue").await
+    else {
+        return;
+    };
+    let fp = format!("fp-{}", uuid::Uuid::new_v4());
+
+    // 5 registrations sharing one fingerprint — every one returns a normal 202.
+    let mut emails = Vec::new();
+    for _ in 0..5 {
+        let email = unique_email();
+        let r = post(
+            format!("{base}/web/v1/register"),
+            json!({"email": email, "password": "password123", "fingerprint": fp}),
+            None,
+        )
+        .await;
+        assert_eq!(r.status(), 202, "registration always looks successful");
+        emails.push(email);
+    }
+
+    // Silent effect: all 5 accounts are deactivated + flagged.
+    let (deactivated, flagged): (i64, i64) = {
+        let row = pool
+            .fetch_one(
+                sqlx::query(
+                    "SELECT \
+                   count(*) FILTER (WHERE a.status = 'deactivated') AS d, \
+                   count(*) FILTER (WHERE a.fingerprint_flagged) AS f \
+                 FROM accounts a JOIN users u ON u.id = a.owner_user_id \
+                 WHERE u.registration_fingerprint = $1",
+                )
+                .bind(&fp),
+            )
+            .await
+            .unwrap();
+        (row.get("d"), row.get("f"))
+    };
+    assert_eq!(deactivated, 5, "all sharing accounts silently deactivated");
+    assert_eq!(flagged, 5);
+
+    // No clue at the authz surface: a key on a deactivated account resolves
+    // as an ordinary 401, indistinguishable from an unknown key.
+    let acct: uuid::Uuid = pool
+        .fetch_one(
+            sqlx::query(
+                "SELECT a.id FROM accounts a JOIN users u ON u.id = a.owner_user_id \
+                 WHERE u.registration_fingerprint = $1 LIMIT 1",
+            )
+            .bind(&fp),
+        )
+        .await
+        .unwrap()
+        .get("id");
+    let raw = "sk-helexa-deactivated-probe";
+    pool.execute(
+        sqlx::query(
+            "INSERT INTO api_keys (account_id, key_hash, key_prefix) VALUES ($1, $2, 'sk-helexa-')",
+        )
+        .bind(acct)
+        .bind(sha256(raw)),
+    )
+    .await
+    .unwrap();
+    let r = post(
+        format!("{base}/authz/v1/resolve"),
+        json!({"api_key": raw}),
+        Some(CLIENT_TOKEN),
+    )
+    .await;
+    assert_eq!(
+        r.status(),
+        401,
+        "deactivated account's key looks like any invalid key"
+    );
+}
+
+#[tokio::test]
+async fn topup_redeem_raises_allocation_single_use() {
+    let Some((base, pool)) = spawn_or_skip("topup_redeem_raises_allocation_single_use").await
+    else {
+        return;
+    };
+    let email = unique_email();
+    post(
+        format!("{base}/web/v1/register"),
+        json!({"email": email, "password": "password123"}),
+        None,
+    )
+    .await;
+    pool.execute(
+        sqlx::query("UPDATE users SET email_verified = true WHERE email = $1").bind(&email),
+    )
+    .await
+    .unwrap();
+    let token = post(
+        format!("{base}/web/v1/login"),
+        json!({"email": email, "password": "password123"}),
+        None,
+    )
+    .await
+    .json::<Value>()
+    .await
+    .unwrap()["token"]
+        .as_str()
+        .unwrap()
+        .to_string();
+
+    // Mint a code worth 500_000 (mint path used by the CLI/faucet).
+    let codes = helexa_upstream::topup::mint(&pool, 500_000, 1, Some("test"))
+        .await
+        .unwrap();
+    let code = &codes[0];
+
+    // Redeem → allocation_total rises from the 1_000_000 free grant.
+    let r = post(
+        format!("{base}/web/v1/redeem"),
+        json!({"code": code}),
+        Some(&token),
+    )
+    .await;
+    assert_eq!(r.status(), 200);
+    assert_eq!(
+        r.json::<Value>().await.unwrap()["allocation_total"],
+        1_500_000
+    );
+
+    // Single-use: a second redemption fails generically (no oracle).
+    let r = post(
+        format!("{base}/web/v1/redeem"),
+        json!({"code": code}),
+        Some(&token),
+    )
+    .await;
+    assert_eq!(r.status(), 400);
+
+    // Unknown code: same generic 400.
+    let r = post(
+        format!("{base}/web/v1/redeem"),
+        json!({"code": "helexa-topup-does-not-exist"}),
+        Some(&token),
+    )
+    .await;
+    assert_eq!(r.status(), 400);
+}
+
+#[tokio::test]
+async fn topup_concurrent_double_redeem_one_winner() {
+    let Some((base, pool)) = spawn_or_skip("topup_concurrent_double_redeem_one_winner").await
+    else {
+        return;
+    };
+    // Two verified accounts.
+    let mut tokens = Vec::new();
+    for _ in 0..2 {
+        let email = unique_email();
+        post(
+            format!("{base}/web/v1/register"),
+            json!({"email": email, "password": "password123"}),
+            None,
+        )
+        .await;
+        pool.execute(
+            sqlx::query("UPDATE users SET email_verified = true WHERE email = $1").bind(&email),
+        )
+        .await
+        .unwrap();
+        let t = post(
+            format!("{base}/web/v1/login"),
+            json!({"email": email, "password": "password123"}),
+            None,
+        )
+        .await
+        .json::<Value>()
+        .await
+        .unwrap()["token"]
+            .as_str()
+            .unwrap()
+            .to_string();
+        tokens.push(t);
+    }
+    let code = helexa_upstream::topup::mint(&pool, 100, 1, None)
+        .await
+        .unwrap()
+        .remove(0);
+
+    // Both accounts race to redeem the same code; exactly one wins.
+    let (a, b) = tokio::join!(
+        post(
+            format!("{base}/web/v1/redeem"),
+            json!({"code": code}),
+            Some(&tokens[0])
+        ),
+        post(
+            format!("{base}/web/v1/redeem"),
+            json!({"code": code}),
+            Some(&tokens[1])
+        ),
+    );
+    let wins = [a.status(), b.status()]
+        .iter()
+        .filter(|s| s.as_u16() == 200)
+        .count();
+    assert_eq!(wins, 1, "exactly one redemption wins the single-use code");
+}

crates/neuron/src/api.rs

@@ -16,7 +16,7 @@ use cortex_core::discovery::{DiscoveryResponse, HealthResponse};
 use cortex_core::entitlements::{HEADER_ACCOUNT_ID, HEADER_KEY_ID};
 use cortex_core::harness::ModelSpec;
 use cortex_core::openai::{ChatCompletionRequest, MessageContent};
-use cortex_core::responses::{ResponsesRequest, ResponsesUsage};
+use cortex_core::responses::{OutputTokensDetails, ResponsesRequest, ResponsesUsage};
 use futures::stream::{self, StreamExt};
 use serde_json::{Value, json};
 use std::convert::Infallible;
@@ -418,8 +418,14 @@ async fn responses(
                     input_tokens: u.prompt_tokens,
                     output_tokens: u.completion_tokens,
                     total_tokens: u.prompt_tokens + u.completion_tokens,
-                    // Non-streaming reasoning accounting deferred (#64).
-                    output_tokens_details: None,
+                    // Carry the reasoning sub-count through from the chat
+                    // usage — the non-streaming path now splits off the
+                    // `<think>` span and counts it (see `split_off_reasoning`).
+                    output_tokens_details: u.completion_tokens_details.as_ref().map(|d| {
+                        OutputTokensDetails {
+                            reasoning_tokens: d.reasoning_tokens,
+                        }
+                    }),
                     input_tokens_details: None,
                 });
                 let meta = openai_responses::ResponseMeta {

crates/neuron/src/harness/candle.rs

@@ -23,11 +23,11 @@ use candle_transformers::models::qwen3_moe as qwen3_moe_dense;
 use cortex_core::harness::{Harness, HarnessHealth, ModelInfo, ModelSpec};
 use cortex_core::openai::{
     ChatCompletionChoice, ChatCompletionChunk, ChatCompletionRequest, ChatCompletionResponse,
-    ChatMessage, MessageContent, Usage,
+    ChatMessage, CompletionTokensDetails, MessageContent, Usage,
 };
 
 use crate::wire::{
-    FinishReason, InferenceEvent, ReasoningTokenPair, ToolCallTokenPair,
+    FinishReason, FinishTiming, InferenceEvent, ReasoningTokenPair, ToolCallTokenPair,
     detect_reasoning_token_pair, detect_tool_call_token_pair, openai_chat as wire_chat,
 };
 use std::collections::HashMap;
@@ -784,6 +784,39 @@ impl ModelArch {
     }
 }
 
+/// Split a non-streaming completion's generated tokens into the
+/// visible answer and the leading reasoning span.
+///
+/// Reasoning models (Qwen3 `<think>`, DeepSeek-R1, …) emit their
+/// chain-of-thought *before* the answer, and the chat template injects
+/// the **opening** marker into the prompt — so the generated tokens look
+/// like `…reasoning… </think> …answer…` with no opening marker present
+/// in the output. The streaming path drops reasoning as
+/// [`InferenceEvent::ReasoningDelta`]; the non-streaming path has to do
+/// the equivalent post-hoc or the chain-of-thought leaks into the
+/// assistant `content` (which broke agent-zero v2.0, whose parser
+/// expected the bare JSON answer, not a `<think>` preamble).
+///
+/// Returns `(content_ids, reasoning_token_count)`. Strategy: if the model
+/// declares a reasoning marker pair and its **close** token appears in
+/// `generated_ids`, everything up to and including the last close token is
+/// reasoning and only the tail is the answer. Otherwise (non-reasoning
+/// model, thinking disabled, or a generation truncated mid-reasoning) the
+/// tokens are returned unchanged. Splitting on the token id — not a
+/// decoded `</think>` string — keeps this robust against tokenizer
+/// byte-fallback and special-token handling.
+fn split_off_reasoning<'a>(
+    generated_ids: &'a [u32],
+    reasoning: Option<&ReasoningTokenPair>,
+) -> (&'a [u32], u64) {
+    if let Some(pair) = reasoning
+        && let Some(idx) = generated_ids.iter().rposition(|&t| t == pair.close_id)
+    {
+        return (&generated_ids[idx + 1..], (idx + 1) as u64);
+    }
+    (generated_ids, 0)
+}
+
 /// Squeeze any leading singleton dims off the logits tensor so the
 /// caller gets a rank-1 `[vocab_size]` slice ready for sampling. Bails
 /// on a non-singleton leading dim (would mean a batched forward, which
@@ -2454,21 +2487,36 @@ impl CandleHarness {
                 )));
             };
 
+            // Strip the leading `<think>` span so the chain-of-thought
+            // doesn't leak into `content` (the streaming path drops it
+            // as ReasoningDelta; this is the non-streaming equivalent).
+            let (content_ids, reasoning_tokens) =
+                split_off_reasoning(&generated_ids, loaded.reasoning_tokens.as_ref());
             let completion_text = loaded
                 .tokenizer
-                .decode(&generated_ids, true)
+                .decode(content_ids, true)
                 .map_err(|e| InferenceError::Other(anyhow::anyhow!("detokenize: {e}")))?;
+            // The first answer token after `</think>` is usually a
+            // newline pair; trim it so `content` starts at the answer.
+            let completion_text = if reasoning_tokens > 0 {
+                completion_text.trim_start().to_string()
+            } else {
+                completion_text
+            };
 
             let usage = Usage {
                 prompt_tokens: prompt_len as u64,
                 completion_tokens: generated_ids.len() as u64,
                 total_tokens: (prompt_len + generated_ids.len()) as u64,
-                // Reasoning accounting is streaming-only: the
-                // non-streaming path doesn't track `in_reasoning`
-                // (would require post-hoc <think> span parsing).
-                // Deferred — see #64.
-                completion_tokens_details: None,
+                // `reasoning_tokens` is an additive sub-count of
+                // `completion_tokens` (which still counts every
+                // generated token, reasoning included).
+                completion_tokens_details: (reasoning_tokens > 0)
+                    .then_some(CompletionTokensDetails { reasoning_tokens }),
                 prompt_tokens_details: None,
+                // Non-streaming path: prefill/decode split is only
+                // surfaced on the streaming Finish event today (#85).
+                helexa_timing: None,
             };
 
             tracing::info!(
@@ -3957,6 +4005,11 @@ impl CandleHarness {
                 // call — promotes the terminal finish_reason to ToolCalls
                 // so Anthropic clients see stop_reason: tool_use.
                 let mut emitted_tool_call = false;
+                // Prefill/decode split timers (#85). Declared outside 'work
+                // so the terminal Finish — built after the block exits — can
+                // read them; populated at the prefill→decode boundary inside.
+                let mut prefill_ms_measured: u32 = 0;
+                let mut decode_start: Option<std::time::Instant> = None;
 
                 'work: {
                     // Prefix-cache decision (#11): vision requests
@@ -4084,14 +4137,16 @@ impl CandleHarness {
                             break 'work;
                         }
                     };
+                    let prefill_elapsed = prefill_start.elapsed();
+                    prefill_ms_measured = prefill_elapsed.as_millis() as u32;
                     tp_for_task
                         .prefill_rate
-                        .record(prompt_len, prefill_start.elapsed());
+                        .record(prompt_len, prefill_elapsed);
                     let (post_prefill_vram_free_mb, _) = tp_for_task.query_vram().await;
                     tracing::info!(
                         model = %model_id,
                         prompt_len,
-                        prefill_ms = prefill_start.elapsed().as_millis(),
+                        prefill_ms = prefill_elapsed.as_millis(),
                         vram_free_mb = post_prefill_vram_free_mb,
                         "TP chat_completion (stream): prefill complete"
                     );
@@ -4116,6 +4171,8 @@ impl CandleHarness {
                                 break 'work;
                             }
                         };
+                    // Decode-phase timer for the Finish prefill/decode split (#85).
+                    decode_start = Some(std::time::Instant::now());
 
                     if Some(next_token) == eos_id {
                         finish_reason = FinishReason::Stop;
@@ -4393,6 +4450,13 @@ impl CandleHarness {
                             prompt_tokens: prompt_len as u32,
                             completion_tokens: all_tokens.len() as u32,
                             reasoning_tokens: reasoning_token_count,
+                            timing: Some(FinishTiming {
+                                prefill_ms: prefill_ms_measured,
+                                decode_ms: decode_start
+                                    .map(|d| d.elapsed().as_millis() as u32)
+                                    .unwrap_or(0),
+                                prefill_tokens: prompt_len as u32,
+                            }),
                         })
                         .await;
                 }
@@ -4722,19 +4786,31 @@ async fn chat_completion_tp_inner(
     }
     drop(pool);
 
+    // Strip the leading `<think>` span (see `split_off_reasoning` and the
+    // single-GPU path) so the chain-of-thought doesn't leak into `content`.
+    let (content_ids, reasoning_tokens) =
+        split_off_reasoning(&generated, tp.reasoning_tokens.as_ref());
     let completion_text = tp
         .tokenizer
-        .decode(&generated, true)
+        .decode(content_ids, true)
         .map_err(|e| InferenceError::Other(anyhow::anyhow!("detokenize: {e}")))?;
+    let completion_text = if reasoning_tokens > 0 {
+        completion_text.trim_start().to_string()
+    } else {
+        completion_text
+    };
 
     let usage = Usage {
         prompt_tokens: prompt_len as u64,
         completion_tokens: generated.len() as u64,
         total_tokens: (prompt_len + generated.len()) as u64,
-        // Reasoning accounting is streaming-only (non-streaming TP path
-        // doesn't track `in_reasoning`). Deferred — see #64.
-        completion_tokens_details: None,
+        // `reasoning_tokens` is an additive sub-count of `completion_tokens`.
+        completion_tokens_details: (reasoning_tokens > 0)
+            .then_some(CompletionTokensDetails { reasoning_tokens }),
         prompt_tokens_details: None,
+        // Non-streaming path: prefill/decode split is only surfaced on
+        // the streaming Finish event today (#85).
+        helexa_timing: None,
     };
 
     tracing::info!(
@@ -6064,7 +6140,8 @@ async fn stream_inference_via_worker(
             }
         }
     };
-    prefill_rate.record(prefill_prompt_len, prefill_start.elapsed());
+    let prefill_elapsed = prefill_start.elapsed();
+    prefill_rate.record(prefill_prompt_len, prefill_elapsed);
     let logits = Tensor::new(logits_vec.as_slice(), &Device::Cpu)?;
     let mut next_token = match sample_with_penalty(&logits, &all_tokens, &mut logits_processor) {
         Ok(t) => t,
@@ -6077,6 +6154,8 @@ async fn stream_inference_via_worker(
             return Err(e);
         }
     };
+    // Decode-phase timer for the Finish prefill/decode split (#85).
+    let decode_start = std::time::Instant::now();
 
     // Per-token routing. `tokenizers::DecodeStream` carries five
     // generic parameters (`M, N, PT, PP, D`) which makes naming
@@ -6221,6 +6300,11 @@ async fn stream_inference_via_worker(
             prompt_tokens: prompt_tokens.len() as u32,
             completion_tokens: all_tokens.len() as u32,
             reasoning_tokens: reasoning_token_count,
+            timing: Some(FinishTiming {
+                prefill_ms: prefill_elapsed.as_millis() as u32,
+                decode_ms: decode_start.elapsed().as_millis() as u32,
+                prefill_tokens: prefill_prompt_len as u32,
+            }),
         })
         .await;
 
@@ -6355,6 +6439,10 @@ fn run_inference_streaming(
     // See `inference_tp_stream`: promotes finish_reason to ToolCalls.
     let mut emitted_tool_call = false;
 
+    // Time prefill and decode separately so the Finish event can carry
+    // a server-measured prefill/decode split (#85) instead of leaving
+    // the client to infer both from SSE chunk arrival.
+    let prefill_start = std::time::Instant::now();
     let reused = restore_or_clear_local(arch, prefix_cache, prompt_tokens)?;
     // Two-stage prefill around the retokenization-stable snapshot
     // boundary — see `run_inference_via_worker`.
@@ -6373,6 +6461,8 @@ fn run_inference_streaming(
         None => chunked_prefill_local(arch, device, prompt_tokens, reused)?,
     };
     let mut next_token = sample_with_penalty(&logits, &all_tokens, &mut logits_processor)?;
+    let prefill_elapsed = prefill_start.elapsed();
+    let decode_start = std::time::Instant::now();
 
     // Per-token routing block, used at both the prefill-sample
     // tail and the decode loop. Macros are ugly but Rust's
@@ -6481,6 +6571,11 @@ fn run_inference_streaming(
         prompt_tokens: prompt_tokens.len() as u32,
         completion_tokens: all_tokens.len() as u32,
         reasoning_tokens: reasoning_token_count,
+        timing: Some(FinishTiming {
+            prefill_ms: prefill_elapsed.as_millis() as u32,
+            decode_ms: decode_start.elapsed().as_millis() as u32,
+            prefill_tokens: prompt_tokens.len() as u32,
+        }),
     });
     Ok(())
 }
@@ -6505,6 +6600,60 @@ mod tests {
 
     const IM_START: u32 = 999;
 
+    fn think_pair() -> ReasoningTokenPair {
+        ReasoningTokenPair {
+            open_id: 100,
+            close_id: 200,
+            open_text: "<think>".into(),
+            close_text: "</think>".into(),
+        }
+    }
+
+    #[test]
+    fn split_off_reasoning_strips_up_to_close_marker() {
+        // [reasoning_a, reasoning_b, </think>, answer_x, answer_y]
+        let ids = [10, 11, 200, 42, 43];
+        let (content, reasoning) = split_off_reasoning(&ids, Some(&think_pair()));
+        assert_eq!(content, &[42, 43]);
+        assert_eq!(reasoning, 3); // two reasoning tokens + the close marker
+    }
+
+    #[test]
+    fn split_off_reasoning_no_close_marker_returns_all() {
+        // Thinking disabled / model never closed the span: return as-is.
+        let ids = [42, 43, 44];
+        let (content, reasoning) = split_off_reasoning(&ids, Some(&think_pair()));
+        assert_eq!(content, &ids);
+        assert_eq!(reasoning, 0);
+    }
+
+    #[test]
+    fn split_off_reasoning_no_marker_pair_is_noop() {
+        let ids = [1, 2, 3];
+        let (content, reasoning) = split_off_reasoning(&ids, None);
+        assert_eq!(content, &ids);
+        assert_eq!(reasoning, 0);
+    }
+
+    #[test]
+    fn split_off_reasoning_close_at_end_yields_empty_content() {
+        // All reasoning, answer truncated to nothing after the marker.
+        let ids = [10, 11, 200];
+        let (content, reasoning) = split_off_reasoning(&ids, Some(&think_pair()));
+        assert!(content.is_empty());
+        assert_eq!(reasoning, 3);
+    }
+
+    #[test]
+    fn split_off_reasoning_splits_on_last_close_marker() {
+        // Defensive: if the model emits its own <think></think> pair plus
+        // the prompt-injected one, split on the LAST close marker.
+        let ids = [200, 10, 200, 42];
+        let (content, reasoning) = split_off_reasoning(&ids, Some(&think_pair()));
+        assert_eq!(content, &[42]);
+        assert_eq!(reasoning, 3);
+    }
+
     #[test]
     fn stable_snapshot_cut_lands_after_last_im_start() {
         // ChatML shape: [im_start, "system", ..., im_start, "user",

crates/neuron/src/wire/event.rs

@@ -84,9 +84,38 @@ pub enum InferenceEvent {
         /// `output_tokens_details.reasoning_tokens` (responses).
         /// Zero for non-reasoning models.
         reasoning_tokens: u32,
+        /// Server-measured prefill/decode timing for the request, or
+        /// `None` on paths that don't measure it (CPU fallback that
+        /// doesn't instrument, tests). Streaming projectors surface
+        /// this as a `helexa_timing` extension on the OpenAI `usage`
+        /// object so the bench harness can compute true prefill vs
+        /// decode tok/s instead of inferring both from client-side
+        /// SSE arrival (#85).
+        timing: Option<FinishTiming>,
     },
 }
 
+/// Server-measured timing for one completed inference, attached to
+/// [`InferenceEvent::Finish`]. The whole point is to separate the two
+/// phases the client cannot tell apart from chunk-arrival timing:
+/// prefill (tokenize + prompt forward pass, ending at the first
+/// sampled token) and decode (every subsequent token through EOS /
+/// `max_tokens`).
+#[derive(Debug, Clone, Copy)]
+pub struct FinishTiming {
+    /// Wall-clock of the prefill phase in milliseconds: from the start
+    /// of the prompt forward pass(es) to the first sampled token.
+    pub prefill_ms: u32,
+    /// Wall-clock of the decode phase in milliseconds: from the first
+    /// sampled token to stream end.
+    pub decode_ms: u32,
+    /// Prompt tokens submitted to the prefill forward pass — the
+    /// denominator for prefill tok/s. With prefix-KV-cache hits (#11)
+    /// the elapsed `prefill_ms` drops while this stays the full prompt
+    /// length, so a high implied rate is itself the cache-hit signal.
+    pub prefill_tokens: u32,
+}
+
 /// Why a stream stopped. Stays small on purpose — anything that
 /// doesn't map cleanly to one of these collapses to [`Stop`].
 ///

crates/neuron/src/wire/mod.rs

@@ -22,6 +22,6 @@ pub mod openai_chat;
 pub mod openai_responses;
 
 pub use event::{
-    FinishReason, InferenceEvent, ReasoningTokenPair, ToolCallTokenPair,
+    FinishReason, FinishTiming, InferenceEvent, ReasoningTokenPair, ToolCallTokenPair,
     detect_reasoning_token_pair, detect_tool_call_token_pair,
 };

crates/neuron/src/wire/openai_chat.rs

@@ -26,11 +26,13 @@
 //! producer blocks on its own send. The bounded channels
 //! propagate without us writing any logic.
 
-use cortex_core::openai::{ChatCompletionChunk, ChunkChoice, CompletionTokensDetails, Usage};
+use cortex_core::openai::{
+    ChatCompletionChunk, ChunkChoice, CompletionTokensDetails, HelexaTiming, Usage,
+};
 use serde_json::json;
 use tokio::sync::mpsc;
 
-use super::event::{FinishReason, InferenceEvent, ReasoningTokenPair};
+use super::event::{FinishReason, FinishTiming, InferenceEvent, ReasoningTokenPair};
 
 /// Output channel buffer size. Mirrors the input side's bound; one
 /// event maps to at most one chunk, so equal capacity keeps the
@@ -193,12 +195,14 @@ pub fn project_chat_stream_with(
                     prompt_tokens,
                     completion_tokens,
                     reasoning_tokens,
+                    timing,
                 } => {
                     // The finish_reason chunk, then an OpenAI-style
                     // usage-only chunk (`choices: []`, `usage` populated).
                     // Clients (opencode) read this to track context size;
                     // cortex's Anthropic translator also picks `usage` up
-                    // for its `message_delta`.
+                    // for its `message_delta`. `timing` rides along as the
+                    // `helexa_timing` usage extension for the bench harness (#85).
                     vec![
                         final_chunk(&id, created, &model_id, reason),
                         usage_chunk(
@@ -208,6 +212,7 @@ pub fn project_chat_stream_with(
                             prompt_tokens,
                             completion_tokens,
                             reasoning_tokens,
+                            timing,
                         ),
                     ]
                 }
@@ -334,6 +339,7 @@ fn usage_chunk(
     prompt_tokens: u32,
     completion_tokens: u32,
     reasoning_tokens: u32,
+    timing: Option<FinishTiming>,
 ) -> ChatCompletionChunk {
     ChatCompletionChunk {
         id: id.into(),
@@ -351,6 +357,14 @@ fn usage_chunk(
                 reasoning_tokens: reasoning_tokens as u64,
             }),
             prompt_tokens_details: None,
+            // helexa extension (#85): server-measured prefill/decode
+            // timing for the bench harness. Omitted on paths that don't
+            // measure it so standard clients see unchanged JSON.
+            helexa_timing: timing.map(|t| HelexaTiming {
+                prefill_ms: t.prefill_ms as u64,
+                decode_ms: t.decode_ms as u64,
+                prefill_tokens: t.prefill_tokens as u64,
+            }),
         }),
         extra: serde_json::Value::Object(Default::default()),
     }
@@ -391,6 +405,7 @@ mod tests {
             prompt_tokens: 0,
             completion_tokens: 0,
             reasoning_tokens: 0,
+            timing: None,
         })
         .await
         .unwrap();
@@ -413,6 +428,45 @@ mod tests {
         }
     }
 
+    #[tokio::test]
+    async fn finish_timing_surfaces_on_usage_chunk() {
+        // O1 (#85) wire contract: a Finish carrying FinishTiming must
+        // surface as `usage.helexa_timing` on the trailing usage chunk,
+        // which is what the bench harness reads to compute true prefill
+        // vs decode tok/s. Absent timing must leave it None.
+        let (tx, rx) = mpsc::channel::<InferenceEvent>(4);
+        let out_rx = project_chat_stream(rx, "id-1".into(), 1700, "m".into());
+
+        tx.send(InferenceEvent::Start).await.unwrap();
+        tx.send(InferenceEvent::Finish {
+            reason: FinishReason::Stop,
+            prompt_tokens: 128,
+            completion_tokens: 64,
+            reasoning_tokens: 0,
+            timing: Some(FinishTiming {
+                prefill_ms: 200,
+                decode_ms: 1500,
+                prefill_tokens: 128,
+            }),
+        })
+        .await
+        .unwrap();
+        drop(tx);
+
+        let out = collect(out_rx).await;
+        let usage = out
+            .iter()
+            .find_map(|c| c.usage.as_ref())
+            .expect("usage chunk present");
+        let timing = usage
+            .helexa_timing
+            .as_ref()
+            .expect("helexa_timing populated when Finish carried timing");
+        assert_eq!(timing.prefill_ms, 200);
+        assert_eq!(timing.decode_ms, 1500);
+        assert_eq!(timing.prefill_tokens, 128);
+    }
+
     #[tokio::test]
     async fn empty_text_delta_is_dropped() {
         let (tx, rx) = mpsc::channel::<InferenceEvent>(4);
@@ -434,6 +488,7 @@ mod tests {
             prompt_tokens: 0,
             completion_tokens: 0,
             reasoning_tokens: 0,
+            timing: None,
         })
         .await
         .unwrap();
@@ -496,6 +551,7 @@ mod tests {
             prompt_tokens: 0,
             completion_tokens: 0,
             reasoning_tokens: 0,
+            timing: None,
         })
         .await
         .unwrap();
@@ -547,6 +603,7 @@ mod tests {
             prompt_tokens: 0,
             completion_tokens: 0,
             reasoning_tokens: 0,
+            timing: None,
         })
         .await
         .unwrap();
@@ -592,6 +649,7 @@ mod tests {
             prompt_tokens: 0,
             completion_tokens: 0,
             reasoning_tokens: 0,
+            timing: None,
         })
         .await
         .unwrap();
@@ -635,6 +693,7 @@ mod tests {
             prompt_tokens: 0,
             completion_tokens: 0,
             reasoning_tokens: 0,
+            timing: None,
         })
         .await
         .unwrap();
@@ -662,6 +721,7 @@ mod tests {
             prompt_tokens: 42,
             completion_tokens: 5,
             reasoning_tokens: 2,
+            timing: None,
         })
         .await
         .unwrap();
@@ -695,6 +755,7 @@ mod tests {
             prompt_tokens: 10,
             completion_tokens: 7,
             reasoning_tokens: 0,
+            timing: None,
         })
         .await
         .unwrap();

crates/neuron/src/wire/openai_responses.rs

@@ -29,9 +29,9 @@
 
 use cortex_core::openai::{ChatCompletionRequest, ChatMessage, MessageContent};
 use cortex_core::responses::{
-    OutputTokensDetails, ResponsesContentPart, ResponsesInput, ResponsesInputItem,
-    ResponsesMessageContent, ResponsesOutputContent, ResponsesOutputItem, ResponsesRequest,
-    ResponsesResponse, ResponsesUsage, events,
+    OutputTokensDetails, ResponsesContentPart, ResponsesInput, ResponsesInputElement,
+    ResponsesInputItem, ResponsesMessageContent, ResponsesOutputContent, ResponsesOutputItem,
+    ResponsesRequest, ResponsesResponse, ResponsesUsage, events,
 };
 use serde_json::{Value, json};
 use tokio::sync::mpsc;
@@ -109,8 +109,26 @@ pub fn request_to_chat(req: ResponsesRequest) -> Result<ChatCompletionRequest, T
             });
         }
         ResponsesInput::Items(items) => {
-            for item in items {
-                if let Some(msg) = input_item_to_chat(item) {
+            for element in items {
+                let msg = match element {
+                    ResponsesInputElement::Typed(item) => input_item_to_chat(item),
+                    // Bare `{role, content}` (OpenAI EasyInputMessage —
+                    // what litellm/agent-zero emit). `content: null`
+                    // (e.g. an assistant turn carrying only tool calls)
+                    // collapses to an empty string so the turn is kept.
+                    ResponsesInputElement::EasyMessage { role, content } => Some(ChatMessage {
+                        role,
+                        content: content
+                            .map(message_content_to_chat)
+                            .unwrap_or_else(|| MessageContent::Text(String::new())),
+                        extra: Value::Object(Default::default()),
+                    }),
+                    // Forward-compat: an item shape we don't model.
+                    // Dropped rather than rejected (see
+                    // `ResponsesInputElement::Other`).
+                    ResponsesInputElement::Other(_) => None,
+                };
+                if let Some(msg) = msg {
                     messages.push(msg);
                 }
             }
@@ -159,11 +177,18 @@ fn input_item_to_chat(item: ResponsesInputItem) -> Option<ChatMessage> {
             })
         }
         ResponsesInputItem::FunctionCallOutput { call_id, output } => {
+            // `output` is either a plain string or an array of content
+            // parts. Render a string as-is; anything else to compact
+            // JSON so the tool result text reaches the model intact.
+            let output_text = match output {
+                Value::String(s) => s,
+                other => other.to_string(),
+            };
             let mut extra = serde_json::Map::new();
             extra.insert("tool_call_id".into(), Value::String(call_id));
             Some(ChatMessage {
                 role: "tool".into(),
-                content: MessageContent::Text(output),
+                content: MessageContent::Text(output_text),
                 extra: Value::Object(extra),
             })
         }
@@ -192,7 +217,9 @@ fn message_content_to_chat(content: ResponsesMessageContent) -> MessageContent {
                     .filter_map(|p| match p {
                         ResponsesContentPart::InputText { text }
                         | ResponsesContentPart::OutputText { text, .. } => Some(text),
-                        ResponsesContentPart::InputImage { .. } => None,
+                        ResponsesContentPart::InputImage { .. } | ResponsesContentPart::Unknown => {
+                            None
+                        }
                     })
                     .collect::<Vec<_>>()
                     .join("\n\n");
@@ -211,6 +238,7 @@ fn message_content_to_chat(content: ResponsesMessageContent) -> MessageContent {
                             "image_url": { "url": image_url },
                         }));
                     }
+                    ResponsesContentPart::Unknown => {}
                 }
             }
             MessageContent::Parts(out)
@@ -309,6 +337,9 @@ async fn run_projection(
                 prompt_tokens,
                 completion_tokens,
                 reasoning_tokens,
+                // Responses-side `helexa_timing` surfacing not wired yet;
+                // the bench harness reads timing off the chat path (#85).
+                timing: _,
             } => {
                 finish = Some(reason);
                 // Surface usage on the streaming `response.completed`
@@ -535,6 +566,18 @@ mod tests {
     use super::*;
     use cortex_core::openai::MessageContent;
 
+    /// Wrap typed items as `input` elements. Most translator tests
+    /// exercise the typed path; the bare easy-message and unknown-item
+    /// paths have dedicated tests below.
+    fn typed_items(items: Vec<ResponsesInputItem>) -> ResponsesInput {
+        ResponsesInput::Items(
+            items
+                .into_iter()
+                .map(ResponsesInputElement::Typed)
+                .collect(),
+        )
+    }
+
     fn meta() -> ResponseMeta {
         ResponseMeta {
             response_id: "resp_1".into(),
@@ -614,7 +657,7 @@ mod tests {
     fn translates_input_items_to_chat_messages() {
         let req = ResponsesRequest {
             model: "m".into(),
-            input: ResponsesInput::Items(vec![
+            input: typed_items(vec![
                 ResponsesInputItem::Message {
                     role: "user".into(),
                     content: ResponsesMessageContent::Text("first".into()),
@@ -646,7 +689,7 @@ mod tests {
     fn image_input_translates_to_chat_parts_array() {
         let req = ResponsesRequest {
             model: "m".into(),
-            input: ResponsesInput::Items(vec![ResponsesInputItem::Message {
+            input: typed_items(vec![ResponsesInputItem::Message {
                 role: "user".into(),
                 content: ResponsesMessageContent::Parts(vec![
                     ResponsesContentPart::InputText {
@@ -687,7 +730,7 @@ mod tests {
         // it's dropped — but it must not break translation.
         let req = ResponsesRequest {
             model: "m".into(),
-            input: ResponsesInput::Items(vec![ResponsesInputItem::Message {
+            input: typed_items(vec![ResponsesInputItem::Message {
                 role: "user".into(),
                 content: ResponsesMessageContent::Parts(vec![
                     ResponsesContentPart::InputText {
@@ -729,7 +772,7 @@ mod tests {
     fn text_only_parts_collapse_to_string() {
         let req = ResponsesRequest {
             model: "m".into(),
-            input: ResponsesInput::Items(vec![ResponsesInputItem::Message {
+            input: typed_items(vec![ResponsesInputItem::Message {
                 role: "user".into(),
                 content: ResponsesMessageContent::Parts(vec![
                     ResponsesContentPart::InputText {
@@ -759,7 +802,7 @@ mod tests {
     fn reasoning_items_are_silently_dropped() {
         let req = ResponsesRequest {
             model: "m".into(),
-            input: ResponsesInput::Items(vec![
+            input: typed_items(vec![
                 ResponsesInputItem::Reasoning { content: vec![] },
                 ResponsesInputItem::Message {
                     role: "user".into(),
@@ -779,6 +822,74 @@ mod tests {
         assert_eq!(chat.messages[0].role, "user");
     }
 
+    #[test]
+    fn bare_easy_messages_translate_like_typed_messages() {
+        // The agent-zero / litellm shape: bare `{role, content}` items
+        // with no `type`. Deserialize from raw JSON (not hand-built)
+        // so this exercises the real parse path end to end.
+        let raw = r#"{
+            "model": "Qwen/Qwen3.6-27B",
+            "store": true,
+            "input": [
+                {"role": "system", "content": "be terse"},
+                {"role": "assistant", "content": "{\"tool_name\":\"response\"}"},
+                {"role": "user", "content": "alpha"}
+            ]
+        }"#;
+        let req: ResponsesRequest = serde_json::from_str(raw).unwrap();
+        let chat = request_to_chat(req).unwrap();
+        let roles: Vec<&str> = chat.messages.iter().map(|m| m.role.as_str()).collect();
+        assert_eq!(roles, vec!["system", "assistant", "user"]);
+        assert!(matches!(
+            &chat.messages[2].content,
+            MessageContent::Text(t) if t == "alpha"
+        ));
+    }
+
+    #[test]
+    fn null_content_and_unknown_items_survive_translation() {
+        // An assistant turn with `content: null` is kept (empty text);
+        // an unmodeled item type is dropped, not rejected.
+        let raw = r#"{
+            "model": "m",
+            "input": [
+                {"role": "assistant", "content": null},
+                {"type": "item_reference", "id": "x"},
+                {"role": "user", "content": "go"}
+            ]
+        }"#;
+        let req: ResponsesRequest = serde_json::from_str(raw).unwrap();
+        let chat = request_to_chat(req).unwrap();
+        // assistant(null) kept, item_reference dropped, user kept.
+        let roles: Vec<&str> = chat.messages.iter().map(|m| m.role.as_str()).collect();
+        assert_eq!(roles, vec!["assistant", "user"]);
+        assert!(matches!(
+            &chat.messages[0].content,
+            MessageContent::Text(t) if t.is_empty()
+        ));
+    }
+
+    #[test]
+    fn function_call_output_array_renders_to_text() {
+        // OpenAI allows `function_call_output.output` to be an array of
+        // content parts; the tool result must reach the model as text.
+        let raw = r#"{
+            "model": "m",
+            "input": [
+                {"type": "function_call_output", "call_id": "c1",
+                 "output": [{"type": "output_text", "text": "42"}]}
+            ]
+        }"#;
+        let req: ResponsesRequest = serde_json::from_str(raw).unwrap();
+        let chat = request_to_chat(req).unwrap();
+        assert_eq!(chat.messages.len(), 1);
+        assert_eq!(chat.messages[0].role, "tool");
+        match &chat.messages[0].content {
+            MessageContent::Text(t) => assert!(t.contains("42"), "got {t:?}"),
+            other => panic!("expected text, got {other:?}"),
+        }
+    }
+
     // ── streaming projector ─────────────────────────────────────────
 
     async fn collect(mut rx: mpsc::Receiver<ResponseStreamFrame>) -> Vec<ResponseStreamFrame> {
@@ -806,6 +917,7 @@ mod tests {
             prompt_tokens: 0,
             completion_tokens: 0,
             reasoning_tokens: 0,
+            timing: None,
         })
         .await
         .unwrap();
@@ -856,6 +968,7 @@ mod tests {
             prompt_tokens: 30,
             completion_tokens: 12,
             reasoning_tokens: 4,
+            timing: None,
         })
         .await
         .unwrap();
@@ -886,6 +999,7 @@ mod tests {
             prompt_tokens: 8,
             completion_tokens: 3,
             reasoning_tokens: 0,
+            timing: None,
         })
         .await
         .unwrap();
@@ -910,6 +1024,7 @@ mod tests {
             prompt_tokens: 0,
             completion_tokens: 0,
             reasoning_tokens: 0,
+            timing: None,
         })
         .await
         .unwrap();
@@ -956,6 +1071,7 @@ mod tests {
             prompt_tokens: 0,
             completion_tokens: 0,
             reasoning_tokens: 0,
+            timing: None,
         })
         .await
         .unwrap();

data/helexa-upstream-firewalld.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="utf-8"?>
+<service>
+  <short>helexa-upstream</short>
+  <description>helexa-upstream — mesh account + budget authority API (/authz/v1 for cortex, /web/v1 for the frontend)</description>
+  <port protocol="tcp" port="8090"/>
+</service>

data/helexa-upstream-sysusers.conf

@@ -0,0 +1,3 @@
+g helexa-upstream - -
+u helexa-upstream - "helexa-upstream authority" /var/lib/helexa-upstream /sbin/nologin
+m helexa-upstream helexa-upstream

data/helexa-upstream.service

@@ -0,0 +1,22 @@
+[Unit]
+Description=helexa-upstream — mesh account + budget authority (accounts, API keys, allocation ledger, top-up codes)
+After=network-online.target
+Wants=network-online.target
+
+[Service]
+Type=simple
+ExecStart=/usr/bin/helexa-upstream serve --config /etc/helexa-upstream/helexa-upstream.toml
+# HTTP authority for cortex (/authz/v1) and the frontend (/web/v1); restart
+# unconditionally if it ever exits. It connects out to PostgreSQL (the
+# system of record) and runs schema migrations on startup.
+Restart=always
+RestartSec=10
+User=helexa-upstream
+Group=helexa-upstream
+# Service user home; no local state (PostgreSQL holds everything), but
+# StateDirectory gives the user a writable, correctly-owned home.
+StateDirectory=helexa-upstream
+StateDirectoryMode=0755
+
+[Install]
+WantedBy=multi-user.target

helexa-upstream.example.toml

@@ -0,0 +1,52 @@
+# helexa-upstream.example.toml — mesh-level account/authorization authority
+#
+# Copy to helexa-upstream.toml and adjust. Env overrides use the UPSTREAM_
+# prefix with __ separators, e.g. UPSTREAM_DB__URL=postgres://...
+
+[server]
+# Plaintext listener; edge nginx terminates TLS (consistent with the stack).
+listen = "0.0.0.0:8090"
+
+[db]
+# PostgreSQL connection URL. Required.
+url = "postgres://helexa:helexa@localhost/helexa_upstream"
+# max_connections = 16
+
+[grant]
+# Flat free token grant every email-verified account receives (the floor of
+# the hybrid allocation; single-use top-up codes extend it).
+# free_token_grant = 1000000
+
+[abuse]
+# When this many accounts share one registration fingerprint, all are
+# silently deactivated (no notice to the user).
+# fingerprint_account_threshold = 5
+
+# -- Client auth: credentials operators' cortexes present to /authz/v1.
+# Each token maps to an operator_id (served-usage attribution). When no
+# tokens are configured the authz surface is OPEN (dev only). Distinct from
+# end-user API keys, which ride inside the resolve request body.
+# [[client_auth.tokens]]
+# token = "replace-with-a-strong-shared-secret"
+# operator_id = "lair-cafe"
+
+[authz]
+# Open reservations older than this are swept (released), self-healing a
+# reservation whose settle/release from a cortex was lost.
+# reservation_ttl_secs = 120
+# sweep_interval_secs = 60
+
+[auth]
+# HMAC secret for signing web-session JWTs. MUST be overridden in prod via
+# UPSTREAM_AUTH__JWT_SECRET; the built-in default is dev-only.
+# jwt_secret = "change-me"
+# session_ttl_secs = 604800        # 7 days
+# email_token_ttl_secs = 86400     # 24 hours
+# Frontend base URL used to build verify/reset links in emails.
+app_base_url = "https://helexa.ai"
+
+[email]
+# "log" (dev: logs the link) or "smtp".
+provider = "log"
+# smtp_url = "smtp://user:pass@smtp.example.com:587"
+from_addr = "helexa <no-reply@helexa.ai>"

helexa.ai/README.md

@@ -32,3 +32,22 @@ F0 scaffold. Theming + i18n (33 languages, usage-ordered selector), the
 `/mission` page, the chat workspace (Dexie + streaming), and the account
 dashboard land in subsequent phases — see
 `~/.claude/plans/we-need-to-plan-modular-graham.md`.
+
+## Deploy (public beta)
+
+Build the SPA and serve it from edge nginx on the **same origin** as the
+two backends — so the browser makes no cross-origin request (no CORS) and
+the user's API key rides as a first-party bearer.
+
+```sh
+npm ci && npm run build          # → dist/
+sudo cp -r dist/* /var/www/helexa.ai/
+sudo cp deploy/nginx.conf /etc/nginx/conf.d/helexa.ai.conf   # adjust upstreams + TLS
+sudo nginx -t && sudo systemctl reload nginx
+```
+
+`deploy/nginx.conf` routes `/` → SPA (history fallback), `/v1` + `/health`
+→ helexa-router, and `/api/` → helexa-upstream `/web/v1/`. Set
+`VITE_PUBLIC_BETA=true` at build time for the beta banner. There is **no
+server-side chat history**: conversations live only in the browser
+(IndexedDB).

helexa.ai/deploy/nginx.conf

@@ -0,0 +1,60 @@
+# helexa.ai — edge nginx for the public beta.
+#
+# Serves the built SPA (helexa.ai/dist) and reverse-proxies the two
+# backends on the SAME ORIGIN, so the browser never makes a cross-origin
+# request: no CORS, and the user's API key rides as a first-party bearer.
+#
+#   /            → static SPA (history fallback to index.html)
+#   /v1, /health → helexa-router (OpenAI-compatible inference data-plane)
+#   /api/        → helexa-upstream /web/v1/ (account control-plane)
+#
+# TLS is terminated here (certs omitted — wire up certbot / your CA). The
+# upstream hosts below are examples; point them at your router/upstream.
+
+upstream helexa_router   { server 127.0.0.1:8088; }
+upstream helexa_upstream { server 127.0.0.1:8090; }
+
+server {
+    listen 443 ssl http2;
+    listen [::]:443 ssl http2;
+    server_name helexa.ai;
+
+    # ssl_certificate     /etc/letsencrypt/live/helexa.ai/fullchain.pem;
+    # ssl_certificate_key /etc/letsencrypt/live/helexa.ai/privkey.pem;
+
+    root /var/www/helexa.ai;
+    index index.html;
+
+    # Long-cache fingerprinted assets; never cache the HTML shell.
+    location /assets/ {
+        expires 1y;
+        add_header Cache-Control "public, immutable";
+    }
+
+    # Inference data-plane → router. Streaming (SSE): disable buffering so
+    # tokens reach the browser as they arrive.
+    location /v1/ {
+        proxy_pass http://helexa_router;
+        proxy_http_version 1.1;
+        proxy_set_header Host $host;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header Connection "";
+        proxy_buffering off;
+        proxy_read_timeout 300s;
+    }
+    location = /health {
+        proxy_pass http://helexa_router;
+    }
+
+    # Account control-plane → upstream /web/v1/ (strip the /api prefix).
+    location /api/ {
+        proxy_pass http://helexa_upstream/web/v1/;
+        proxy_set_header Host $host;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+    }
+
+    # SPA history fallback: anything else serves index.html.
+    location / {
+        try_files $uri $uri/ /index.html;
+    }
+}

helexa.ai/package.json

@@ -8,7 +8,10 @@
     "build": "tsc -b && vite build",
     "preview": "vite preview",
     "lint": "eslint .",
-    "typecheck": "tsc -b"
+    "typecheck": "tsc -b",
+    "i18n:check": "node ./scripts/check-i18n-keys.mjs",
+    "i18n:meta": "node ./scripts/check-i18n-metadata.mjs",
+    "i18n:lang-labels": "node ./scripts/check-i18n-lang-labels.mjs"
   },
   "dependencies": {
     "@fingerprintjs/fingerprintjs": "^4.6.2",

helexa.ai/scripts/check-i18n-keys.mjs

@@ -0,0 +1,332 @@
+#!/usr/bin/env node
+
+/**
+ * Simple i18n key consistency checker.
+ *
+ * Compares translation JSONs for all configured languages against the English
+ * baseline, for each namespace (common, home, chat).
+ *
+ * Exit codes:
+ *  - 0: all good
+ *  - 1: inconsistencies found or unexpected error
+ */
+
+import fs from "fs";
+import path from "path";
+import url from "url";
+
+// Adjust these if your i18n structure changes.
+const ROOT = path.resolve(
+  path.dirname(url.fileURLToPath(import.meta.url)),
+  "..",
+);
+const RESOURCES_DIR = path.join(ROOT, "src", "i18n", "resources");
+
+// Namespaces to validate.
+const NAMESPACES = ["common", "mission", "chat", "account"];
+
+// Languages to validate should track SUPPORTED_LANGUAGES in src/i18n/languages.ts.
+// NOTE: This list is intentionally narrower than SUPPORTED_LANGUAGES and does not
+// enforce that every supported language has wired resources. That enforcement is
+// implemented further below by checking the i18n index.
+const LANGUAGES = [
+  "bg",
+  "de",
+  "el",
+  "en",
+  "es",
+  "et",
+  "fr",
+  "it",
+  "pt",
+  "ro",
+  "ru",
+];
+
+function readJson(filePath) {
+  try {
+    const raw = fs.readFileSync(filePath, "utf8");
+    return JSON.parse(raw);
+  } catch (err) {
+    throw new Error(`Failed to read/parse JSON at ${filePath}: ${err.message}`);
+  }
+}
+
+/**
+ * Recursively walk an object and collect all key paths using dot-notation.
+ * Arrays are traversed structurally but their indexes are not part of the key path
+ * (we only care that the shape exists, not array lengths).
+ */
+function collectKeyPaths(obj, prefix = "") {
+  const keys = new Set();
+
+  if (obj === null || obj === undefined) {
+    return keys;
+  }
+
+  if (typeof obj !== "object") {
+    if (prefix) keys.add(prefix);
+    return keys;
+  }
+
+  // If this is an array, walk its elements but don't add indices to the path.
+  if (Array.isArray(obj)) {
+    obj.forEach((item) => {
+      for (const childKey of collectKeyPaths(item, prefix)) {
+        keys.add(childKey);
+      }
+    });
+    return keys;
+  }
+
+  // Plain object
+  for (const [k, v] of Object.entries(obj)) {
+    const nextPrefix = prefix ? `${prefix}.${k}` : k;
+    if (v !== null && typeof v === "object") {
+      for (const childKey of collectKeyPaths(v, nextPrefix)) {
+        keys.add(childKey);
+      }
+    } else {
+      keys.add(nextPrefix);
+    }
+  }
+
+  return keys;
+}
+
+function diffKeys(baseSet, targetSet) {
+  const missing = [];
+  const extra = [];
+
+  for (const k of baseSet) {
+    if (!targetSet.has(k)) missing.push(k);
+  }
+
+  for (const k of targetSet) {
+    if (!baseSet.has(k)) extra.push(k);
+  }
+
+  missing.sort();
+  extra.sort();
+
+  return { missing, extra };
+}
+
+function logHeader(title) {
+  // Simple console formatting without external deps.
+  console.log("\n" + "=".repeat(title.length));
+  console.log(title);
+  console.log("=".repeat(title.length));
+}
+
+function main() {
+  let hadIssues = false;
+
+  console.log("helexa.ai i18n key consistency check");
+  console.log(`Root: ${ROOT}`);
+  console.log(`Resources dir: ${RESOURCES_DIR}`);
+  console.log(`Languages: ${LANGUAGES.join(", ")}`);
+  console.log(`Namespaces: ${NAMESPACES.join(", ")}`);
+
+  // --- Wiring check: ensure each SUPPORTED_LANGUAGES entry has resources registered ---
+  //
+  // This prevents cases where a language is:
+  //   - present in LanguageCode and SUPPORTED_LANGUAGES
+  //   - has translation JSONs under src/i18n/resources/<code>/
+  // but is *not* wired into the i18n `resources` object (and thus silently
+  // falls back to English at runtime).
+  try {
+    const languagesTs = fs.readFileSync(
+      path.join(ROOT, "src", "i18n", "languages.ts"),
+      "utf8",
+    );
+    const i18nIndexTs = fs.readFileSync(
+      path.join(ROOT, "src", "i18n", "index.ts"),
+      "utf8",
+    );
+
+    // Parse SUPPORTED_LANGUAGES from languages.ts
+    const marker = "export const SUPPORTED_LANGUAGES";
+    const start = languagesTs.indexOf(marker);
+    if (start === -1) {
+      throw new Error("Could not find `SUPPORTED_LANGUAGES` in languages.ts");
+    }
+    const after = languagesTs.slice(start);
+    const bracketIndex = after.indexOf("[");
+    const closingIndex = after.indexOf("];");
+    if (bracketIndex === -1 || closingIndex === -1) {
+      throw new Error("Malformed SUPPORTED_LANGUAGES array");
+    }
+    const arraySlice = after.slice(bracketIndex + 1, closingIndex);
+    const supportedFromTs = new Set();
+    const codeRegex = /"([^"]+)"/g;
+    let m;
+    while ((m = codeRegex.exec(arraySlice)) !== null) {
+      supportedFromTs.add(m[1]);
+    }
+
+    console.log(
+      `SUPPORTED_LANGUAGES from TS for wiring check: ${Array.from(
+        supportedFromTs,
+      )
+        .sort()
+        .join(", ")}`,
+    );
+
+    // Languages that are intentionally "future" and may not yet have
+    // resources wired in. Keep them out of the hard failure path so
+    // CI does not break while their translations are still pending.
+    const FUTURE_LANGUAGES = new Set(["ig", "om", "so", "ti", "wo"]);
+
+    // Parse i18n resources object keys from index.ts.
+    // We look for a block like:
+    //   const resources: Resource = {
+    //     en: { ... },
+    //     fr: { ... },
+    //   };
+    const resourcesMarker = "const resources: Resource = {";
+    const resStart = i18nIndexTs.indexOf(resourcesMarker);
+    if (resStart === -1) {
+      throw new Error("Could not find `const resources: Resource` in index.ts");
+    }
+    const resAfter = i18nIndexTs.slice(resStart + resourcesMarker.length);
+    const resEndIndex = resAfter.indexOf("};");
+    if (resEndIndex === -1) {
+      throw new Error("Malformed resources object in index.ts");
+    }
+    const resourcesBlock = resAfter.slice(0, resEndIndex);
+
+    // Extract top-level language keys: lines starting with two spaces then <code>:
+    // Example: "  en: {" or "  fr: {"
+    const wiredLangs = new Set();
+    const lineRegex = /^\s*([a-z]{2}):\s*{\s*$/gm;
+    let lm;
+    while ((lm = lineRegex.exec(resourcesBlock)) !== null) {
+      wiredLangs.add(lm[1]);
+    }
+
+    console.log(
+      `Languages wired in i18n resources: ${Array.from(wiredLangs)
+        .sort()
+        .join(", ")}`,
+    );
+
+    // Now compare SUPPORTED_LANGUAGES vs wired resources.
+    const missingWiring = [];
+    for (const code of supportedFromTs) {
+      if (FUTURE_LANGUAGES.has(code)) {
+        // These are explicitly allowed to be missing until their
+        // translations and wiring land.
+        continue;
+      }
+      if (!wiredLangs.has(code)) {
+        missingWiring.push(code);
+      }
+    }
+
+    if (missingWiring.length > 0) {
+      hadIssues = true;
+      console.error(
+        "\nERROR: Some SUPPORTED_LANGUAGES codes are not wired into the i18n `resources` object in src/i18n/index.ts:",
+      );
+      for (const code of missingWiring.sort()) {
+        console.error(`  - ${code}`);
+      }
+      console.error(
+        "These languages will silently fall back to English at runtime. Ensure that:",
+      );
+      console.error(
+        "  1) ./resources/<code>/{common,home,chat}.json exist, and",
+      );
+      console.error(
+        "  2) They are imported and registered in the `resources` object.",
+      );
+      console.error("");
+    } else {
+      console.log(
+        "OK: Every SUPPORTED_LANGUAGES entry (excluding future languages) is wired into the i18n resources object.",
+      );
+    }
+  } catch (err) {
+    hadIssues = true;
+    console.error(
+      "ERROR: Failed while checking SUPPORTED_LANGUAGES wiring in i18n index:",
+      err.message,
+    );
+  }
+
+  for (const ns of NAMESPACES) {
+    logHeader(`Namespace: ${ns}`);
+
+    const basePath = path.join(RESOURCES_DIR, "en", `${ns}.json`);
+    let baseJson;
+    try {
+      baseJson = readJson(basePath);
+    } catch (err) {
+      console.error(err.message);
+      hadIssues = true;
+      continue;
+    }
+
+    const baseKeys = collectKeyPaths(baseJson);
+    console.log(`Baseline (en) keys: ${baseKeys.size}`);
+
+    for (const lang of LANGUAGES) {
+      if (lang === "en") continue;
+
+      const langPath = path.join(RESOURCES_DIR, lang, `${ns}.json`);
+      if (!fs.existsSync(langPath)) {
+        console.error(`  [${lang}] MISSING file: ${langPath}`);
+        hadIssues = true;
+        continue;
+      }
+
+      let langJson;
+      try {
+        langJson = readJson(langPath);
+      } catch (err) {
+        console.error(`  [${lang}] ${err.message}`);
+        hadIssues = true;
+        continue;
+      }
+
+      const langKeys = collectKeyPaths(langJson);
+      const { missing, extra } = diffKeys(baseKeys, langKeys);
+
+      if (missing.length === 0 && extra.length === 0) {
+        console.log(`  [${lang}] OK (keys: ${langKeys.size})`);
+      } else {
+        hadIssues = true;
+        console.log(`  [${lang}] Issues found:`);
+        if (missing.length > 0) {
+          console.log("    Missing keys (present in en, absent here):");
+          for (const k of missing) {
+            console.log(`      - ${k}`);
+          }
+        }
+        if (extra.length > 0) {
+          console.log("    Extra keys (present here, absent in en):");
+          for (const k of extra) {
+            console.log(`      + ${k}`);
+          }
+        }
+      }
+    }
+  }
+
+  console.log("");
+  if (hadIssues) {
+    console.error("i18n check completed with inconsistencies.");
+    process.exitCode = 1;
+  } else {
+    console.log("i18n check completed successfully. All keys are consistent.");
+    process.exitCode = 0;
+  }
+}
+
+try {
+  main();
+} catch (err) {
+  console.error("Unexpected error while running i18n check:", err);
+  process.exitCode = 1;
+}

helexa.ai/scripts/check-i18n-lang-labels.mjs

@@ -0,0 +1,249 @@
+#!/usr/bin/env node
+
+/**
+ * helexa.ai i18n language label consistency check
+ *
+ * This script validates that for every supported language code in
+ * `SUPPORTED_LANGUAGES`:
+ *
+ *   1. The English `common.lang` map (`src/i18n/resources/en/common.json`)
+ *      contains a human-readable label at `lang.<code>`.
+ *   2. Optionally (and more leniently), other languages that define a
+ *      `lang` block do not omit supported language codes.
+ *
+ * At minimum, it enforces that the English UI always has labels for all
+ * supported languages, since the header language selector renders
+ * `t("lang.<code>")` using the active language.
+ *
+ * Exit codes:
+ *   - 0: all checks pass
+ *   - 1: one or more inconsistencies found
+ */
+
+import fs from "fs";
+import path from "path";
+import url from "url";
+
+const ROOT = path.resolve(path.dirname(url.fileURLToPath(import.meta.url)), "..");
+const I18N_DIR = path.join(ROOT, "src", "i18n");
+const LANGUAGES_TS = path.join(I18N_DIR, "languages.ts");
+const EN_COMMON_JSON = path.join(I18N_DIR, "resources", "en", "common.json");
+
+/**
+ * Utility: read a file as UTF-8 or throw with a helpful message.
+ */
+function readFileOrDie(filePath) {
+  try {
+    return fs.readFileSync(filePath, "utf8");
+  } catch (err) {
+    throw new Error(`Failed to read ${filePath}: ${err.message}`);
+  }
+}
+
+/**
+ * Parse SUPPORTED_LANGUAGES from languages.ts.
+ *
+ * Expects a definition like:
+ *   export const SUPPORTED_LANGUAGES: LanguageCode[] = [
+ *     "en",
+ *     "bg",
+ *   ];
+ */
+function parseSupportedLanguages(source) {
+  const marker = "export const SUPPORTED_LANGUAGES";
+  const start = source.indexOf(marker);
+  if (start === -1) {
+    throw new Error("Could not find `SUPPORTED_LANGUAGES` in languages.ts");
+  }
+
+  const after = source.slice(start);
+  const bracketIndex = after.indexOf("[");
+  const closingIndex = after.indexOf("];");
+  if (bracketIndex === -1 || closingIndex === -1) {
+    throw new Error("Malformed SUPPORTED_LANGUAGES array");
+  }
+
+  const arraySlice = after.slice(bracketIndex + 1, closingIndex);
+  const codes = new Set();
+  const regex = /"([^"]+)"/g;
+  let m;
+  while ((m = regex.exec(arraySlice)) !== null) {
+    codes.add(m[1]);
+  }
+
+  if (codes.size === 0) {
+    throw new Error("No entries found in SUPPORTED_LANGUAGES");
+  }
+
+  return codes;
+}
+
+/**
+ * Safely read and parse a JSON file.
+ */
+function readJsonOrDie(filePath) {
+  const raw = readFileOrDie(filePath);
+  try {
+    return JSON.parse(raw);
+  } catch (err) {
+    throw new Error(`Failed to parse JSON at ${filePath}: ${err.message}`);
+  }
+}
+
+/**
+ * Compute set difference: a \ b
+ */
+function difference(a, b) {
+  const result = new Set();
+  for (const x of a) {
+    if (!b.has(x)) result.add(x);
+  }
+  return result;
+}
+
+/**
+ * Convenience: sorted array from a Set.
+ */
+function toSortedArray(set) {
+  return [...set].sort();
+}
+
+function main() {
+  console.log("helexa.ai i18n language label check");
+  console.log(`Root: ${ROOT}`);
+  console.log(`Languages file: ${LANGUAGES_TS}`);
+  console.log(`English common.json: ${EN_COMMON_JSON}`);
+  console.log("");
+
+  let hadIssues = false;
+
+  // 1) Load SUPPORTED_LANGUAGES
+  let languagesSource;
+  try {
+    languagesSource = readFileOrDie(LANGUAGES_TS);
+  } catch (err) {
+    console.error(err.message);
+    process.exitCode = 1;
+    return;
+  }
+
+  let supportedLanguages;
+  try {
+    supportedLanguages = parseSupportedLanguages(languagesSource);
+    console.log(
+      `SUPPORTED_LANGUAGES (${supportedLanguages.size}): ${toSortedArray(
+        supportedLanguages,
+      ).join(", ")}`,
+    );
+  } catch (err) {
+    console.error(`ERROR: ${err.message}`);
+    process.exitCode = 1;
+    return;
+  }
+
+  console.log("");
+
+  // 2) Load English common.json and extract lang map
+  let enCommon;
+  try {
+    enCommon = readJsonOrDie(EN_COMMON_JSON);
+  } catch (err) {
+    console.error(`ERROR: ${err.message}`);
+    process.exitCode = 1;
+    return;
+  }
+
+  const enLangMap = enCommon?.lang ?? {};
+  if (!enLangMap || typeof enLangMap !== "object") {
+    console.error("ERROR: `en/common.json` does not contain a `lang` object.");
+    process.exitCode = 1;
+    return;
+  }
+
+  const enLangKeys = new Set(Object.keys(enLangMap));
+  console.log(
+    `English lang map keys (${enLangKeys.size}): ${toSortedArray(
+      enLangKeys,
+    ).join(", ")}`,
+  );
+  console.log("");
+
+  // 3) Ensure every supported language has a corresponding key in en.lang
+  const missingInEnglish = difference(supportedLanguages, enLangKeys);
+  if (missingInEnglish.size > 0) {
+    hadIssues = true;
+    console.error(
+      "ERROR: The following supported languages are missing labels in `en/common.json` under `lang`:",
+    );
+    for (const code of toSortedArray(missingInEnglish)) {
+      console.error(`  - lang.${code}`);
+    }
+  } else {
+    console.log(
+      "OK: Every supported language has a `lang.<code>` entry in `en/common.json`.",
+    );
+  }
+
+  console.log("");
+
+  // 4) Optional: scan other locales for informational consistency
+  //    (non-fatal, just warnings).
+  const resourcesDir = path.join(I18N_DIR, "resources");
+  let otherLocales = [];
+  try {
+    otherLocales = fs
+      .readdirSync(resourcesDir, { withFileTypes: true })
+      .filter((d) => d.isDirectory() && d.name !== "en")
+      .map((d) => d.name);
+  } catch (err) {
+    console.warn(
+      `WARN: Could not list locales in ${resourcesDir}: ${err.message}`,
+    );
+  }
+
+  for (const locale of otherLocales) {
+    const filePath = path.join(resourcesDir, locale, "common.json");
+    if (!fs.existsSync(filePath)) continue;
+
+    let localeJson;
+    try {
+      localeJson = readJsonOrDie(filePath);
+    } catch (err) {
+      console.warn(`WARN: Failed to read ${filePath}: ${err.message}`);
+      continue;
+    }
+
+    const langObj = localeJson?.lang;
+    if (!langObj || typeof langObj !== "object") {
+      // Not all locales need to maintain a full lang map; skip silently.
+      continue;
+    }
+
+    const localeKeys = new Set(Object.keys(langObj));
+    const missingHere = difference(supportedLanguages, localeKeys);
+    if (missingHere.size > 0) {
+      console.warn(
+        `WARN: Locale '${locale}' is missing some supported language labels under "lang":`,
+      );
+      for (const code of toSortedArray(missingHere)) {
+        console.warn(`  - lang.${code}`);
+      }
+      console.warn("");
+    }
+  }
+
+  if (hadIssues) {
+    console.error("Language label check completed with inconsistencies.");
+    process.exitCode = 1;
+  } else {
+    console.log("Language label check completed successfully.");
+    process.exitCode = 0;
+  }
+}
+
+try {
+  main();
+} catch (err) {
+  console.error("Unexpected error while running language label check:", err);
+  process.exitCode = 1;
+}

helexa.ai/scripts/check-i18n-metadata.mjs

@@ -0,0 +1,327 @@
+#!/usr/bin/env node
+
+/**
+ * helexa.ai i18n metadata consistency check
+ *
+ * This script validates that:
+ *  - Every `LanguageCode` used in the project appears in `TRANSLATION_PRIORITY`
+ *  - Every `TRANSLATION_PRIORITY` entry refers to a valid `LanguageCode`
+ *  - `REMAINING_LANGUAGES` is a subset of `LanguageCode`
+ *  - `REMAINING_LANGUAGES` is disjoint from `SUPPORTED_LANGUAGES`
+ *
+ * It is intentionally implemented as a standalone Node script (no TypeScript
+ * build step required) and does a very lightweight parse of the TypeScript
+ * source files to avoid pulling in a full TS compiler.
+ *
+ * Exit codes:
+ *  - 0: all checks pass
+ *  - 1: one or more metadata inconsistencies found
+ */
+
+import fs from "fs";
+import path from "path";
+import url from "url";
+
+/**
+ * Resolve project root as the directory containing this script.
+ */
+const ROOT = path.resolve(path.dirname(url.fileURLToPath(import.meta.url)), "..");
+const I18N_DIR = path.join(ROOT, "src", "i18n");
+const LANGUAGES_TS = path.join(I18N_DIR, "languages.ts");
+const PRIORITY_TS = path.join(I18N_DIR, "translation-priority.ts");
+
+function readFileOrDie(filePath) {
+  try {
+    return fs.readFileSync(filePath, "utf8");
+  } catch (err) {
+    console.error(`Failed to read ${filePath}: ${err.message}`);
+    process.exitCode = 1;
+    return "";
+  }
+}
+
+/**
+ * Extract union members from a definition like:
+ *
+ * export type LanguageCode =
+ *   | "en"
+ *   | "bg"
+ *   | "cs";
+ */
+function parseLanguageCodeUnion(source) {
+  const start = source.indexOf("export type LanguageCode");
+  if (start === -1) {
+    throw new Error("Could not find `export type LanguageCode` in languages.ts");
+  }
+
+  const after = source.slice(start);
+  const eqIndex = after.indexOf("=");
+  if (eqIndex === -1) {
+    throw new Error("Malformed LanguageCode definition (no '=')");
+  }
+
+  const unionBlock = after.slice(eqIndex + 1);
+  const semicolonIndex = unionBlock.indexOf(";");
+  const unionSlice = semicolonIndex === -1 ? unionBlock : unionBlock.slice(0, semicolonIndex);
+
+  const codes = new Set();
+  const regex = /\|\s*"([^"]+)"/g;
+  let m;
+  while ((m = regex.exec(unionSlice)) !== null) {
+    codes.add(m[1]);
+  }
+
+  if (codes.size === 0) {
+    throw new Error("No language codes found in LanguageCode union");
+  }
+
+  return codes;
+}
+
+/**
+ * Parse SUPPORTED_LANGUAGES from languages.ts
+ *
+ * export const SUPPORTED_LANGUAGES: LanguageCode[] = [
+ *   "en",
+ *   "bg",
+ * ];
+ */
+function parseSupportedLanguages(source) {
+  const marker = "export const SUPPORTED_LANGUAGES";
+  const start = source.indexOf(marker);
+  if (start === -1) {
+    throw new Error("Could not find `SUPPORTED_LANGUAGES` in languages.ts");
+  }
+
+  const after = source.slice(start);
+  const bracketIndex = after.indexOf("[");
+  const closingIndex = after.indexOf("];");
+  if (bracketIndex === -1 || closingIndex === -1) {
+    throw new Error("Malformed SUPPORTED_LANGUAGES array");
+  }
+
+  const arraySlice = after.slice(bracketIndex + 1, closingIndex);
+  const codes = new Set();
+  const regex = /"([^"]+)"/g;
+  let m;
+  while ((m = regex.exec(arraySlice)) !== null) {
+    codes.add(m[1]);
+  }
+
+  if (codes.size === 0) {
+    throw new Error("No entries found in SUPPORTED_LANGUAGES");
+  }
+
+  return codes;
+}
+
+/**
+ * Parse REMAINING_LANGUAGES from translation-priority.ts
+ *
+ * export const REMAINING_LANGUAGES: LanguageCode[] = [
+ *   "tr",
+ *   "pl",
+ * ];
+ */
+function parseRemainingLanguages(source) {
+  const marker = "export const REMAINING_LANGUAGES";
+  const start = source.indexOf(marker);
+  if (start === -1) {
+    // It's valid for this list to not exist; treat as empty if missing
+    return new Set();
+  }
+
+  const after = source.slice(start);
+  const bracketIndex = after.indexOf("[");
+  const closingIndex = after.indexOf("];");
+  if (bracketIndex === -1 || closingIndex === -1) {
+    throw new Error("Malformed REMAINING_LANGUAGES array");
+  }
+
+  const arraySlice = after.slice(bracketIndex + 1, closingIndex);
+  const codes = new Set();
+  const regex = /"([^"]+)"/g;
+  let m;
+  while ((m = regex.exec(arraySlice)) !== null) {
+    codes.add(m[1]);
+  }
+
+  return codes;
+}
+
+/**
+ * Parse TRANSLATION_PRIORITY entries from translation-priority.ts
+ *
+ * export const TRANSLATION_PRIORITY: TranslationPriorityEntry[] = [
+ *   {
+ *     code: "tr",
+ *     bucket: "high",
+ *     nativeSpeakers: "70–90M",
+ *   },
+ *   ...
+ * ];
+ */
+function parseTranslationPriority(source) {
+  const marker = "export const TRANSLATION_PRIORITY";
+  const start = source.indexOf(marker);
+  if (start === -1) {
+    throw new Error("Could not find `TRANSLATION_PRIORITY` in translation-priority.ts");
+  }
+
+  const after = source.slice(start);
+  const bracketIndex = after.indexOf("[");
+  const closingIndex = after.indexOf("];");
+  if (bracketIndex === -1 || closingIndex === -1) {
+    throw new Error("Malformed TRANSLATION_PRIORITY array");
+  }
+
+  const arraySlice = after.slice(bracketIndex + 1, closingIndex);
+
+  // Simple heuristic: find code: "<value>" inside objects
+  const codes = new Set();
+  const regex = /code:\s*"([^"]+)"/g;
+  let m;
+  while ((m = regex.exec(arraySlice)) !== null) {
+    codes.add(m[1]);
+  }
+
+  if (codes.size === 0) {
+    throw new Error("No `code` entries found in TRANSLATION_PRIORITY");
+  }
+
+  return codes;
+}
+
+function difference(a, b) {
+  const result = new Set();
+  for (const x of a) {
+    if (!b.has(x)) result.add(x);
+  }
+  return result;
+}
+
+function toSortedArray(set) {
+  return [...set].sort();
+}
+
+function main() {
+  console.log("helexa.ai i18n metadata consistency check");
+  console.log(`Root: ${ROOT}`);
+  console.log(`Languages file: ${LANGUAGES_TS}`);
+  console.log(`Priority file: ${PRIORITY_TS}`);
+  console.log("");
+
+  const languagesSource = readFileOrDie(LANGUAGES_TS);
+  const prioritySource = readFileOrDie(PRIORITY_TS);
+
+  let hadIssues = false;
+
+  let languageCodes;
+  let supportedLanguages;
+  let remainingLanguages;
+  let priorityCodes;
+
+  try {
+    languageCodes = parseLanguageCodeUnion(languagesSource);
+    console.log(`LanguageCode entries: ${languageCodes.size}`);
+  } catch (err) {
+    console.error(`ERROR: ${err.message}`);
+    process.exitCode = 1;
+    return;
+  }
+
+  try {
+    supportedLanguages = parseSupportedLanguages(languagesSource);
+    console.log(`SUPPORTED_LANGUAGES entries: ${supportedLanguages.size}`);
+  } catch (err) {
+    console.error(`ERROR: ${err.message}`);
+    process.exitCode = 1;
+    return;
+  }
+
+  try {
+    remainingLanguages = parseRemainingLanguages(prioritySource);
+    console.log(`REMAINING_LANGUAGES entries: ${remainingLanguages.size}`);
+  } catch (err) {
+    console.error(`ERROR: ${err.message}`);
+    process.exitCode = 1;
+    return;
+  }
+
+  try {
+    priorityCodes = parseTranslationPriority(prioritySource);
+    console.log(`TRANSLATION_PRIORITY entries: ${priorityCodes.size}`);
+  } catch (err) {
+    console.error(`ERROR: ${err.message}`);
+    process.exitCode = 1;
+    return;
+  }
+
+  console.log("");
+
+  // 1) Every LanguageCode should have a TRANSLATION_PRIORITY entry
+  const missingInPriority = difference(languageCodes, priorityCodes);
+  if (missingInPriority.size > 0) {
+    hadIssues = true;
+    console.error("ERROR: The following LanguageCode values are missing from TRANSLATION_PRIORITY:");
+    for (const code of toSortedArray(missingInPriority)) {
+      console.error(`  - ${code}`);
+    }
+  } else {
+    console.log("OK: All LanguageCode values are present in TRANSLATION_PRIORITY.");
+  }
+
+  // 2) Every TRANSLATION_PRIORITY code must be a valid LanguageCode
+  const unknownPriorityCodes = difference(priorityCodes, languageCodes);
+  if (unknownPriorityCodes.size > 0) {
+    hadIssues = true;
+    console.error("ERROR: The following TRANSLATION_PRIORITY codes are not present in LanguageCode:");
+    for (const code of toSortedArray(unknownPriorityCodes)) {
+      console.error(`  - ${code}`);
+    }
+  } else {
+    console.log("OK: All TRANSLATION_PRIORITY codes are valid LanguageCode values.");
+  }
+
+  // 3) REMAINING_LANGUAGES must be subset of LanguageCode
+  const remainingNotInLanguageCode = difference(remainingLanguages, languageCodes);
+  if (remainingNotInLanguageCode.size > 0) {
+    hadIssues = true;
+    console.error("ERROR: The following REMAINING_LANGUAGES entries are not in LanguageCode:");
+    for (const code of toSortedArray(remainingNotInLanguageCode)) {
+      console.error(`  - ${code}`);
+    }
+  } else {
+    console.log("OK: All REMAINING_LANGUAGES are valid LanguageCode values.");
+  }
+
+  // 4) REMAINING_LANGUAGES must be disjoint from SUPPORTED_LANGUAGES
+  const remainingThatAreSupported = difference(remainingLanguages, difference(remainingLanguages, supportedLanguages));
+  // Equivalent to intersection(remainingLanguages, supportedLanguages)
+  if (remainingThatAreSupported.size > 0) {
+    hadIssues = true;
+    console.error("ERROR: The following REMAINING_LANGUAGES are already in SUPPORTED_LANGUAGES:");
+    for (const code of toSortedArray(remainingThatAreSupported)) {
+      console.error(`  - ${code}`);
+    }
+  } else {
+    console.log("OK: REMAINING_LANGUAGES does not include any SUPPORTED_LANGUAGES.");
+  }
+
+  console.log("");
+
+  if (hadIssues) {
+    console.error("i18n metadata check completed with inconsistencies.");
+    process.exitCode = 1;
+  } else {
+    console.log("i18n metadata check completed successfully. All metadata is consistent.");
+    process.exitCode = 0;
+  }
+}
+
+try {
+  main();
+} catch (err) {
+  console.error("Unexpected error while running i18n metadata check:", err);
+  process.exitCode = 1;
+}

helexa.ai/src/App.css

@@ -0,0 +1,423 @@
+:root {
+    --color-bg: #f5f7fb;
+    --color-bg-elevated: #ffffff;
+    --color-bg-subtle: #eef1f7;
+    --color-border-subtle: rgba(15, 23, 42, 0.12);
+    --color-text: #020617;
+    --color-text-muted: #64748b;
+    --color-accent: #22d3ee;
+    --color-accent-hot: #ec4899;
+    --color-accent-soft: rgba(34, 211, 238, 0.12);
+    --color-navbar-bg: rgba(255, 255, 255, 0.85);
+    --color-footer-bg: rgba(255, 255, 255, 0.9);
+    --shadow-soft: 0 18px 45px rgba(15, 23, 42, 0.08);
+    --transition-fast: 150ms ease-out;
+}
+
+/* Dark theme overrides, driven by ThemeProvider via [data-theme] */
+:root[data-theme="dark"] {
+    --color-bg: #000618;
+    --color-bg-elevated: #020617;
+    --color-bg-subtle: #020617;
+    --color-border-subtle: rgba(148, 163, 184, 0.24);
+    --color-text: #e2e8f0;
+    --color-text-muted: #cbd5f5;
+    --color-accent: #22d3ee;
+    --color-accent-soft: rgba(34, 211, 238, 0.18);
+    --color-navbar-bg: rgba(2, 6, 23, 0.92);
+    --color-footer-bg: rgba(2, 6, 23, 0.96);
+    --shadow-soft: 0 22px 55px rgba(15, 23, 42, 0.8);
+}
+
+/* Global base styles */
+
+html,
+body,
+#root {
+    height: 100%;
+}
+
+body {
+    margin: 0;
+    font-family:
+        system-ui,
+        -apple-system,
+        BlinkMacSystemFont,
+        "SF Pro Text",
+        "Segoe UI",
+        sans-serif;
+    background-color: var(--color-bg);
+    color: var(--color-text);
+    -webkit-font-smoothing: antialiased;
+    text-rendering: optimizeLegibility;
+}
+
+/* Basic RTL reset: when the root document is RTL, ensure logical direction */
+html[dir="rtl"] body {
+    direction: rtl;
+}
+
+.app-root {
+    min-height: 100vh;
+    background-color: var(--color-bg);
+    color: var(--color-text);
+    transition:
+        background-color var(--transition-fast),
+        color var(--transition-fast);
+}
+
+/* Typography helpers */
+
+.app-main h1,
+.app-main h2,
+.app-main h3,
+.app-main h4,
+.app-main h5 {
+    letter-spacing: 0.02em;
+}
+
+.app-main p.lead {
+    color: var(--color-text-muted);
+}
+
+/* Hot pink accent utility for occasional emphasis */
+.text-hot-pink {
+    color: var(--color-accent-hot) !important;
+}
+
+/* Header / Navbar */
+
+.app-header {
+    background-color: var(--color-navbar-bg);
+    backdrop-filter: blur(12px);
+    -webkit-backdrop-filter: blur(12px);
+    box-shadow: 0 1px 0 var(--color-border-subtle);
+    transition:
+        background-color var(--transition-fast),
+        box-shadow var(--transition-fast),
+        border-color var(--transition-fast);
+}
+
+.app-header .navbar-brand {
+    font-weight: 700;
+    letter-spacing: 0.08em;
+    text-transform: uppercase;
+    font-size: 0.85rem;
+    color: var(--color-text);
+}
+
+.app-header .navbar-brand:hover {
+    color: var(--color-accent);
+}
+
+.app-header .nav-link {
+    color: var(--color-text-muted);
+    font-weight: 500;
+    font-size: 0.9rem;
+    transition:
+        color var(--transition-fast),
+        background-color var(--transition-fast);
+}
+
+.app-header .nav-link:hover,
+.app-header .nav-link:focus {
+    color: var(--color-accent);
+    background-color: transparent;
+}
+
+.app-header .nav-link.active {
+    color: var(--color-accent);
+}
+
+.app-header .btn.btn-outline-secondary {
+    --bs-btn-color: var(--color-text-muted);
+    --bs-btn-border-color: var(--color-border-subtle);
+    --bs-btn-hover-bg: var(--color-accent-soft);
+    --bs-btn-hover-border-color: var(--color-accent);
+    --bs-btn-hover-color: var(--color-accent);
+    --bs-btn-focus-shadow-rgb: 34, 211, 238;
+    padding-inline: 0.55rem;
+    padding-block: 0.3rem;
+    border-radius: 999px;
+}
+
+/* Language dropdown: theme-aware styling */
+.app-header .dropdown-menu-dark {
+    --bs-dropdown-bg: var(--color-bg-elevated);
+    --bs-dropdown-link-color: var(--color-text);
+    --bs-dropdown-link-hover-bg: var(--color-accent-soft);
+    --bs-dropdown-link-hover-color: var(--color-accent);
+    --bs-dropdown-link-active-bg: var(--color-accent-soft);
+    --bs-dropdown-link-active-color: var(--color-accent);
+    --bs-dropdown-border-color: var(--color-border-subtle);
+    background-color: var(--color-bg-elevated);
+    border-color: var(--color-border-subtle);
+    color: var(--color-text);
+}
+
+/* Prevent language dropdown from overflowing off-screen in RTL */
+html[dir="rtl"] .app-header .dropdown-menu-end {
+    left: auto;
+    right: 0;
+    transform: none;
+}
+
+.app-header .dropdown-menu-dark .dropdown-item.active,
+.app-header .dropdown-menu-dark .dropdown-item:active {
+    background-color: var(--color-accent-soft);
+    color: var(--color-accent);
+}
+
+.app-header .dropdown-menu-dark-context .dropdown-toggle.btn-secondary {
+    --bs-btn-bg: transparent;
+    --bs-btn-border-color: var(--color-border-subtle);
+    --bs-btn-color: var(--color-text-muted);
+    --bs-btn-hover-bg: var(--color-accent-soft);
+    --bs-btn-hover-border-color: var(--color-accent);
+    --bs-btn-hover-color: var(--color-accent);
+    --bs-btn-focus-shadow-rgb: 34, 211, 238;
+}
+
+.app-header .btn.btn-outline-secondary svg {
+    display: block;
+}
+
+/* Generic helper class for mirroring directional icons in RTL.
+   Used by DirectionalIcon when `mirrorInRtl` is enabled. */
+html[dir="rtl"] .diricon-mirror-rtl {
+    transform: scaleX(-1);
+}
+
+/* Provide a visible toggler icon when using default Bootstrap styles */
+.navbar-toggler {
+    border-color: var(--color-border-subtle);
+}
+
+.navbar-toggler-icon {
+    background-image: none;
+    position: relative;
+    width: 1.25rem;
+    height: 1.25rem;
+}
+
+.navbar-toggler-icon::before,
+.navbar-toggler-icon::after,
+.navbar-toggler-icon span {
+    content: "";
+    position: absolute;
+    left: 0;
+    right: 0;
+    height: 2px;
+    border-radius: 999px;
+    background-color: var(--color-text);
+    transition:
+        transform 150ms ease-out,
+        opacity 150ms ease-out;
+}
+
+.navbar-toggler-icon::before {
+    top: 0.25rem;
+}
+
+.navbar-toggler-icon::after {
+    bottom: 0.25rem;
+}
+
+/* Footer */
+
+.app-footer {
+    background-color: var(--color-footer-bg);
+    backdrop-filter: blur(10px);
+    -webkit-backdrop-filter: blur(10px);
+    box-shadow: 0 -1px 0 var(--color-border-subtle);
+    transition:
+        background-color var(--transition-fast),
+        box-shadow var(--transition-fast),
+        border-color var(--transition-fast);
+}
+
+/* Main content layout */
+
+.app-main {
+    max-width: 1120px;
+}
+
+/* When in RTL mode, flip common flex directions and alignment where needed */
+html[dir="rtl"] .app-root {
+    direction: rtl;
+    text-align: right;
+}
+
+html[dir="rtl"] .app-header .navbar-brand {
+    flex-direction: row-reverse;
+}
+
+html[dir="rtl"] .app-header .nav-link {
+    text-align: right;
+}
+
+html[dir="rtl"] .app-header .d-flex.align-items-center.gap-2 {
+    flex-direction: row-reverse;
+}
+
+html[dir="rtl"] .app-main .card-body {
+    text-align: right;
+}
+
+/* Ensure footer content also respects RTL direction */
+html[dir="rtl"] .app-footer {
+    direction: rtl;
+    text-align: right;
+}
+
+.app-main .card,
+.app-main .card-body {
+    background-color: var(--color-bg-elevated);
+    border-color: var(--color-border-subtle);
+}
+
+/* Generic utility styles */
+
+.surface-elevated {
+    background-color: var(--color-bg-elevated);
+    border-radius: 1rem;
+    border: 1px solid var(--color-border-subtle);
+    box-shadow: var(--shadow-soft);
+}
+
+/* Mesh / principle icon containers */
+.mesh-icon,
+.principle-icon {
+    width: 2.25rem;
+    height: 2.25rem;
+    border-radius: 999px;
+    display: inline-flex;
+    align-items: center;
+    justify-content: center;
+    border: 1px solid var(--color-border-subtle);
+    background: radial-gradient(
+        circle,
+        var(--color-accent-soft),
+        transparent 60%
+    );
+    color: var(--color-accent);
+    margin-bottom: 0.35rem;
+    flex-shrink: 0;
+}
+
+.principle-icon {
+    width: 2rem;
+    height: 2rem;
+}
+
+/* CTA background texture */
+.join-mesh-cta {
+    background:
+        radial-gradient(
+            circle at top,
+            rgba(34, 211, 238, 0.18),
+            transparent 60%
+        ),
+        url("/bg-logo-right.png") center/cover no-repeat,
+        var(--color-bg-elevated);
+    background-blend-mode: screen, normal;
+}
+
+.badge-accent {
+    background-color: var(--color-accent-soft);
+    color: var(--color-accent);
+    border-radius: 999px;
+    padding: 0.1rem 0.55rem;
+    font-size: 0.7rem;
+    text-transform: uppercase;
+    letter-spacing: 0.08em;
+}
+
+/* Ensure muted text uses our theme variable instead of Bootstrap defaults */
+.text-muted,
+small {
+    color: var(--color-text-muted) !important;
+}
+
+/* Small cyan dot used inside hero and CTA badges */
+.bg-cyan-500-dot {
+    display: inline-block;
+    width: 0.45rem;
+    height: 0.45rem;
+    border-radius: 999px;
+    background: radial-gradient(
+        circle,
+        var(--color-accent) 0%,
+        transparent 65%
+    );
+}
+
+/* Links */
+
+a {
+    color: var(--color-accent);
+    text-decoration: none;
+}
+
+a:hover {
+    color: var(--color-accent);
+    text-decoration: underline;
+}
+
+/* Scrollbar theming (WebKit) */
+
+*::-webkit-scrollbar {
+    width: 8px;
+    height: 8px;
+}
+
+*::-webkit-scrollbar-thumb {
+    background-color: rgba(148, 163, 184, 0.6);
+    border-radius: 999px;
+}
+
+:root[data-theme="dark"] *::-webkit-scrollbar-thumb {
+    background-color: rgba(148, 163, 184, 0.8);
+}
+
+/* Code blocks / preformatted text placeholders */
+
+pre,
+code {
+    font-family:
+        ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas,
+        "Liberation Mono", "Courier New", monospace;
+}
+
+pre {
+    background-color: var(--color-bg-subtle);
+    border-radius: 0.75rem;
+    padding: 0.75rem 1rem;
+    border: 1px solid var(--color-border-subtle);
+    overflow-x: auto;
+}
+
+/* Small-screen adjustments */
+
+@media (max-width: 576px) {
+    .app-main {
+        padding-left: 1rem !important;
+        padding-right: 1rem !important;
+    }
+
+    .app-header .navbar-brand {
+        font-size: 0.8rem;
+    }
+}
+
+/* Public-beta banner (F6) — slim accent strip above the header. */
+.beta-banner {
+  background: var(--bs-warning-bg-subtle, #fff3cd);
+  color: var(--bs-warning-text-emphasis, #664d03);
+  border-bottom: 1px solid var(--bs-warning-border-subtle, #ffe69c);
+}
+[data-bs-theme="dark"] .beta-banner {
+  background: rgba(255, 193, 7, 0.12);
+  color: #ffda6a;
+  border-bottom-color: rgba(255, 193, 7, 0.25);
+}

helexa.ai/src/App.tsx

@@ -1,12 +1,61 @@
-import { Container } from "react-bootstrap";
+import { BrowserRouter, Routes, Route } from "react-router-dom";
+import ThemeProvider from "./layout/ThemeProvider";
+import AuthProvider from "./auth/AuthProvider";
+import RequireAuth from "./auth/RequireAuth";
+import Header from "./components/Header";
+import Footer from "./components/Footer";
+import BetaBanner from "./components/BetaBanner";
+import Mission from "./pages/Mission";
+import Chat from "./pages/Chat";
+import Login from "./pages/auth/Login";
+import Register from "./pages/auth/Register";
+import VerifyEmail from "./pages/auth/VerifyEmail";
+import RequestReset from "./pages/auth/RequestReset";
+import ResetPassword from "./pages/auth/ResetPassword";
+import Dashboard from "./pages/account/Dashboard";
+import ApiKeys from "./pages/account/ApiKeys";
+import "./App.css";
 
-// F0 scaffold shell. Theming, i18n, routing, the chat workspace, mission
-// page and account dashboard land in the F1+ phases.
+// Composition root: theme → router → auth → layout shell. `/` is the chat
+// workspace (F3); `/mission` the EU-sovereignty narrative (F2); the auth +
+// account routes (F4) follow, with /account guarded.
 export default function App() {
   return (
-    <Container className="py-5">
-      <h1 className="mb-2">helexa.ai</h1>
-      <p className="text-muted">Public beta — coming online.</p>
-    </Container>
+    <ThemeProvider>
+      <BrowserRouter>
+        <AuthProvider>
+          <div className="d-flex flex-column min-vh-100">
+            <BetaBanner />
+            <Header />
+            <Routes>
+              <Route path="/" element={<Chat />} />
+              <Route path="/mission" element={<Mission />} />
+              <Route path="/login" element={<Login />} />
+              <Route path="/register" element={<Register />} />
+              <Route path="/verify" element={<VerifyEmail />} />
+              <Route path="/forgot" element={<RequestReset />} />
+              <Route path="/reset" element={<ResetPassword />} />
+              <Route
+                path="/account"
+                element={
+                  <RequireAuth>
+                    <Dashboard />
+                  </RequireAuth>
+                }
+              />
+              <Route
+                path="/account/keys"
+                element={
+                  <RequireAuth>
+                    <ApiKeys />
+                  </RequireAuth>
+                }
+              />
+            </Routes>
+            <Footer />
+          </div>
+        </AuthProvider>
+      </BrowserRouter>
+    </ThemeProvider>
   );
 }

helexa.ai/src/api/account.ts

@@ -0,0 +1,213 @@
+// Account API client over helexa-upstream's /web/v1 (B4/B5). The browser
+// calls a same-origin `/api` prefix (vite-proxied in dev, nginx-routed in
+// prod). A MockAccountApi behind VITE_USE_MOCK_ACCOUNT_API lets the
+// dashboard be built/demoed before the upstream service is reachable.
+
+import {
+  ApiError,
+  type AccountBalance,
+  type ApiKeySummary,
+  type CreatedKey,
+  type Session,
+} from "./types";
+
+export interface AccountApi {
+  register(email: string, password: string, fingerprint?: string): Promise<void>;
+  verify(token: string): Promise<void>;
+  login(email: string, password: string): Promise<Session>;
+  requestReset(email: string): Promise<void>;
+  confirmReset(token: string, newPassword: string): Promise<void>;
+  account(token: string): Promise<AccountBalance>;
+  listKeys(token: string): Promise<ApiKeySummary[]>;
+  createKey(
+    token: string,
+    label: string,
+    limitKind: "percent" | "hardcap",
+    limitValue: number,
+  ): Promise<CreatedKey>;
+  archiveKey(token: string, id: string): Promise<void>;
+  updateKeyLimit(
+    token: string,
+    id: string,
+    limitKind: "percent" | "hardcap",
+    limitValue: number,
+  ): Promise<void>;
+  redeem(token: string, code: string): Promise<AccountBalance>;
+}
+
+const BASE = (import.meta.env.VITE_ACCOUNT_BASE_URL || "/api").replace(/\/$/, "");
+
+async function call<T>(
+  path: string,
+  init: RequestInit & { token?: string } = {},
+): Promise<T> {
+  const headers: Record<string, string> = { "content-type": "application/json" };
+  if (init.token) headers.authorization = `Bearer ${init.token}`;
+  let resp: Response;
+  try {
+    resp = await fetch(`${BASE}${path}`, { ...init, headers });
+  } catch {
+    throw new ApiError(0, "network_error", "Could not reach the account service.");
+  }
+  if (resp.status === 204) return undefined as T;
+  let body: unknown = null;
+  try {
+    body = await resp.json();
+  } catch {
+    /* empty body */
+  }
+  if (!resp.ok) {
+    const err = (body as { error?: { code?: string; message?: string } })?.error;
+    throw new ApiError(resp.status, err?.code ?? "error", err?.message ?? "Request failed.");
+  }
+  return body as T;
+}
+
+class RealAccountApi implements AccountApi {
+  async register(email: string, password: string, fingerprint?: string) {
+    await call("/register", {
+      method: "POST",
+      body: JSON.stringify({ email, password, fingerprint }),
+    });
+  }
+  async verify(token: string) {
+    await call("/verify", { method: "POST", body: JSON.stringify({ token }) });
+  }
+  login(email: string, password: string) {
+    return call<Session>("/login", {
+      method: "POST",
+      body: JSON.stringify({ email, password }),
+    });
+  }
+  async requestReset(email: string) {
+    await call("/password-reset/request", {
+      method: "POST",
+      body: JSON.stringify({ email }),
+    });
+  }
+  async confirmReset(token: string, newPassword: string) {
+    await call("/password-reset/confirm", {
+      method: "POST",
+      body: JSON.stringify({ token, new_password: newPassword }),
+    });
+  }
+  account(token: string) {
+    return call<AccountBalance>("/account", { token });
+  }
+  listKeys(token: string) {
+    return call<{ keys: ApiKeySummary[] }>("/keys", { token }).then((r) => r.keys);
+  }
+  createKey(token: string, label: string, limit_kind: "percent" | "hardcap", limit_value: number) {
+    return call<CreatedKey>("/keys", {
+      method: "POST",
+      token,
+      body: JSON.stringify({ label, limit_kind, limit_value }),
+    });
+  }
+  async archiveKey(token: string, id: string) {
+    await call(`/keys/${id}/archive`, { method: "POST", token, body: "{}" });
+  }
+  async updateKeyLimit(
+    token: string,
+    id: string,
+    limit_kind: "percent" | "hardcap",
+    limit_value: number,
+  ) {
+    await call(`/keys/${id}/limit`, {
+      method: "PATCH",
+      token,
+      body: JSON.stringify({ limit_kind, limit_value }),
+    });
+  }
+  redeem(token: string, code: string) {
+    return call<AccountBalance>("/redeem", {
+      method: "POST",
+      token,
+      body: JSON.stringify({ code }),
+    });
+  }
+}
+
+// ── Mock (VITE_USE_MOCK_ACCOUNT_API) ────────────────────────────────
+// Minimal in-memory account so the dashboard is fully developable offline.
+
+class MockAccountApi implements AccountApi {
+  private total = 1_000_000;
+  private spent = 0;
+  private reserved = 0;
+  private keys: ApiKeySummary[] = [];
+  private seq = 1;
+
+  async register() {}
+  async verify() {}
+  async login(): Promise<Session> {
+    return { token: "mock-token", expires_in: 604800 };
+  }
+  async requestReset() {}
+  async confirmReset() {}
+  async account(): Promise<AccountBalance> {
+    return {
+      account_id: "mock-account",
+      allocation_total: this.total,
+      allocation_spent: this.spent,
+      allocation_reserved: this.reserved,
+    };
+  }
+  async listKeys(): Promise<ApiKeySummary[]> {
+    return [...this.keys];
+  }
+  async createKey(
+    _t: string,
+    label: string,
+    limit_kind: "percent" | "hardcap",
+    limit_value: number,
+  ): Promise<CreatedKey> {
+    const id = `mock-${this.seq++}`;
+    const prefix = `sk-helexa-mock${this.seq}`;
+    this.keys.push({
+      id,
+      prefix,
+      label,
+      status: "active",
+      limit_kind,
+      limit_value,
+      spent: 0,
+      reserved: 0,
+      created_at: new Date().toISOString(),
+    });
+    return { id, key: `${prefix}-RAWSECRETSHOWNONCE`, prefix, limit_kind, limit_value };
+  }
+  async archiveKey(_t: string, id: string) {
+    const k = this.keys.find((x) => x.id === id);
+    if (k) k.status = "archived";
+  }
+  async updateKeyLimit(
+    _t: string,
+    id: string,
+    limit_kind: "percent" | "hardcap",
+    limit_value: number,
+  ) {
+    const k = this.keys.find((x) => x.id === id);
+    if (k) {
+      k.limit_kind = limit_kind;
+      k.limit_value = limit_value;
+    }
+  }
+  async redeem(_t: string, code: string): Promise<AccountBalance> {
+    if (!code.startsWith("helexa-topup-")) {
+      throw new ApiError(400, "bad_request", "invalid or already-redeemed code");
+    }
+    this.total += 500_000;
+    return this.account();
+  }
+}
+
+let instance: AccountApi | null = null;
+export function accountApi(): AccountApi {
+  if (!instance) {
+    instance = import.meta.env.VITE_USE_MOCK_ACCOUNT_API
+      ? new MockAccountApi()
+      : new RealAccountApi();
+  }
+  return instance;
+}

helexa.ai/src/api/types.ts

@@ -0,0 +1,45 @@
+// Wire types for the helexa-upstream /web/v1 account API (B4/B5).
+
+export interface ApiKeySummary {
+  id: string;
+  prefix: string;
+  label: string;
+  status: "active" | "archived";
+  limit_kind: "percent" | "hardcap";
+  limit_value: number;
+  spent: number;
+  reserved: number;
+  created_at: string;
+}
+
+export interface CreatedKey {
+  id: string;
+  /** Raw secret — shown exactly once at creation. */
+  key: string;
+  prefix: string;
+  limit_kind: "percent" | "hardcap";
+  limit_value: number;
+}
+
+export interface AccountBalance {
+  account_id: string;
+  allocation_total: number;
+  allocation_spent: number;
+  allocation_reserved: number;
+}
+
+export interface Session {
+  token: string;
+  expires_in: number;
+}
+
+/** Typed error carrying the backend's machine-readable code. */
+export class ApiError extends Error {
+  code: string;
+  status: number;
+  constructor(status: number, code: string, message: string) {
+    super(message);
+    this.code = code;
+    this.status = status;
+  }
+}

helexa.ai/src/auth/AuthProvider.tsx

@@ -0,0 +1,76 @@
+import { useEffect, useState, type ReactNode } from "react";
+import { accountApi } from "../api/account";
+import { claimAnonymousData } from "../data/repositories";
+import { getFingerprint } from "../lib/fingerprint";
+import { AuthContext } from "./context";
+
+const TOKEN_KEY = "helexa.token";
+const EMAIL_KEY = "helexa.email";
+
+export default function AuthProvider({ children }: { children: ReactNode }) {
+  const [token, setToken] = useState<string | null>(() =>
+    localStorage.getItem(TOKEN_KEY),
+  );
+  const [email, setEmail] = useState<string | null>(() =>
+    localStorage.getItem(EMAIL_KEY),
+  );
+  const [accountId, setAccountId] = useState<string | null>(null);
+
+  // Resolve the account id for an existing session (page reload) so the chat
+  // workspace can scope its IndexedDB owner without a fresh login.
+  useEffect(() => {
+    if (!token || accountId) return;
+    accountApi()
+      .account(token)
+      .then((a) => setAccountId(a.account_id))
+      .catch(() => {
+        /* token may be stale; chat falls back to anon until re-login */
+      });
+  }, [token, accountId]);
+
+  async function login(em: string, password: string): Promise<void> {
+    const api = accountApi();
+    const session = await api.login(em, password);
+    localStorage.setItem(TOKEN_KEY, session.token);
+    localStorage.setItem(EMAIL_KEY, em);
+    setToken(session.token);
+    setEmail(em);
+    // Claim anonymous local history into the account (stays client-side).
+    try {
+      const acct = await api.account(session.token);
+      setAccountId(acct.account_id);
+      await claimAnonymousData(acct.account_id);
+    } catch {
+      /* non-fatal */
+    }
+  }
+
+  async function register(em: string, password: string): Promise<void> {
+    const fingerprint = await getFingerprint();
+    await accountApi().register(em, password, fingerprint);
+  }
+
+  function logout(): void {
+    localStorage.removeItem(TOKEN_KEY);
+    localStorage.removeItem(EMAIL_KEY);
+    setToken(null);
+    setEmail(null);
+    setAccountId(null);
+  }
+
+  return (
+    <AuthContext.Provider
+      value={{
+        token,
+        email,
+        accountId,
+        status: token ? "authed" : "anon",
+        login,
+        register,
+        logout,
+      }}
+    >
+      {children}
+    </AuthContext.Provider>
+  );
+}

helexa.ai/src/auth/RequireAuth.tsx

@@ -0,0 +1,14 @@
+import { type ReactNode } from "react";
+import { Navigate, useLocation } from "react-router-dom";
+import { useAuth } from "./context";
+
+/** Route guard: redirect unauthenticated users to /login?next=…. */
+export default function RequireAuth({ children }: { children: ReactNode }) {
+  const { status } = useAuth();
+  const location = useLocation();
+  if (status !== "authed") {
+    const next = encodeURIComponent(location.pathname + location.search);
+    return <Navigate to={`/login?next=${next}`} replace />;
+  }
+  return <>{children}</>;
+}

helexa.ai/src/auth/context.ts

@@ -0,0 +1,26 @@
+import { createContext, useContext } from "react";
+
+export interface AuthContextValue {
+  token: string | null;
+  email: string | null;
+  /** The signed-in account id (for the Dexie owner + usage queries). */
+  accountId: string | null;
+  status: "anon" | "authed";
+  login: (email: string, password: string) => Promise<void>;
+  register: (email: string, password: string) => Promise<void>;
+  logout: () => void;
+}
+
+export const AuthContext = createContext<AuthContextValue>({
+  token: null,
+  email: null,
+  accountId: null,
+  status: "anon",
+  login: async () => {},
+  register: async () => {},
+  logout: () => {},
+});
+
+export function useAuth(): AuthContextValue {
+  return useContext(AuthContext);
+}

helexa.ai/src/components/BetaBanner.tsx

@@ -0,0 +1,35 @@
+import { useState } from "react";
+import { useTranslation } from "react-i18next";
+
+/**
+ * Slim public-beta notice shown above the header when VITE_PUBLIC_BETA is
+ * set. Dismissible for the session (sessionStorage) so it doesn't nag, but
+ * returns on the next visit while the beta lasts.
+ */
+const SHOWN = import.meta.env.VITE_PUBLIC_BETA === "true";
+const DISMISS_KEY = "helexa.betaDismissed";
+
+export default function BetaBanner() {
+  const { t } = useTranslation("common");
+  const [hidden, setHidden] = useState(
+    () => sessionStorage.getItem(DISMISS_KEY) === "1",
+  );
+  if (!SHOWN || hidden) return null;
+  return (
+    <div className="beta-banner d-flex align-items-center justify-content-center gap-2 px-3 py-1 small">
+      <span>
+        <strong>{t("beta.tag")}</strong> {t("beta.message")}
+      </span>
+      <button
+        type="button"
+        className="btn-close btn-close-white ms-2"
+        style={{ fontSize: "0.6rem" }}
+        aria-label={t("beta.dismiss")}
+        onClick={() => {
+          sessionStorage.setItem(DISMISS_KEY, "1");
+          setHidden(true);
+        }}
+      />
+    </div>
+  );
+}

helexa.ai/src/components/DirectionalIcon.tsx

@@ -0,0 +1,127 @@
+import React from "react";
+import { useTranslation } from "react-i18next";
+import { isRtlLanguage, type LanguageCode } from "../i18n/languages";
+
+export type Direction = "forward" | "back";
+
+/**
+ * DirectionalIcon
+ *
+ * Small helper component to render direction-aware icons that respect
+ * the current UI writing direction (LTR vs RTL).
+ *
+ * Usage example:
+ *
+ *   <DirectionalIcon
+ *     direction="forward"
+ *     ltrIcon={FaArrowRight}
+ *     rtlIcon={FaArrowLeft}
+ *   />
+ *
+ * - `direction="forward"` means “toward the natural reading direction”
+ *   (right in LTR, left in RTL).
+ * - `direction="back"` means the opposite (left in LTR, right in RTL).
+ *
+ * You can either:
+ *   - pass explicit `ltrIcon` and `rtlIcon` React components, or
+ *   - pass a single `icon` component and set `mirrorInRtl` to flip it
+ *     horizontally when in RTL (via CSS transform).
+ *
+ * In most cases, using explicit LTR / RTL icons is clearer and avoids
+ * surprises with asymmetric icon shapes.
+ */
+export interface DirectionalIconProps {
+  /**
+   * Logical direction relative to reading order.
+   * - "forward": in the direction of the text flow
+   * - "back": opposite the direction of the text flow
+   */
+  direction: Direction;
+
+  /**
+   * Icon component to use for LTR contexts (e.g. FaArrowRight).
+   */
+  ltrIcon?: React.ComponentType<{ size?: number | string; className?: string }>;
+
+  /**
+   * Icon component to use for RTL contexts (e.g. FaArrowLeft).
+   */
+  rtlIcon?: React.ComponentType<{ size?: number | string; className?: string }>;
+
+  /**
+   * Single base icon component. When provided together with
+   * `mirrorInRtl={true}`, it will be mirrored horizontally in RTL.
+   */
+  icon?: React.ComponentType<{ size?: number | string; className?: string }>;
+
+  /**
+   * Whether to flip the `icon` horizontally in RTL.
+   * Ignored if both `ltrIcon` and `rtlIcon` are supplied.
+   */
+  mirrorInRtl?: boolean;
+
+  /**
+   * Optional size forwarded to the rendered icon.
+   */
+  size?: number | string;
+
+  /**
+   * Additional className to apply to the rendered icon.
+   */
+  className?: string;
+}
+
+/**
+ * Determine if current language is RTL based on i18next language code.
+ *
+ * Delegates to the shared `isRtlLanguage` helper from i18n/languages.ts
+ * so that all RTL logic lives in one place.
+ */
+const isRtlLanguageCode = (code: string | undefined | null): boolean => {
+  if (!code) return false;
+  const lang = code.split("-")[0].toLowerCase() as LanguageCode;
+  return isRtlLanguage(lang);
+};
+
+const DirectionalIcon: React.FC<DirectionalIconProps> = ({
+  direction,
+  ltrIcon: LtrIcon,
+  rtlIcon: RtlIcon,
+  icon: BaseIcon,
+  mirrorInRtl = false,
+  size,
+  className,
+}) => {
+  const { i18n } = useTranslation();
+  const isRtl = isRtlLanguageCode(i18n.language);
+
+  // If explicit LTR/RTL icons are provided, prefer those.
+  if (LtrIcon && RtlIcon) {
+    const IconComponent =
+      (direction === "forward" && !isRtl) || (direction === "back" && isRtl)
+        ? LtrIcon
+        : RtlIcon;
+
+    return <IconComponent size={size} className={className} />;
+  }
+
+  // Fallback: single base icon, optionally mirrored in RTL.
+  if (!BaseIcon) {
+    return null;
+  }
+
+  const shouldMirror =
+    mirrorInRtl &&
+    ((direction === "forward" && isRtl) || (direction === "back" && !isRtl));
+
+  const combinedClassName = [
+    className,
+    shouldMirror ? "diricon-mirror-rtl" : null,
+  ]
+    .filter(Boolean)
+    .join(" ");
+
+  return <BaseIcon size={size} className={combinedClassName} />;
+};
+
+export default DirectionalIcon;

helexa.ai/src/components/Footer.tsx

@@ -0,0 +1,23 @@
+import React from "react";
+import { useTranslation } from "react-i18next";
+
+/**
+ * Footer
+ *
+ * Simple application footer used in the main layout.
+ * Renders a subtle, theme-aware bar with copyright text.
+ */
+const Footer: React.FC = () => {
+  const year = new Date().getFullYear();
+  const { t } = useTranslation("common");
+
+  return (
+    <footer className="app-footer border-top py-3 mt-auto">
+      <div className="container-fluid text-center text-muted small">
+        <span>{t("footer.copyright", { year })}</span>
+      </div>
+    </footer>
+  );
+};
+
+export default Footer;

helexa.ai/src/components/Header.tsx

@@ -0,0 +1,160 @@
+import React from "react";
+import { Link, NavLink } from "react-router-dom";
+import { Navbar, Container, Nav, Button, Dropdown } from "react-bootstrap";
+import { FaRegMoon, FaRegSun } from "react-icons/fa6";
+import { useTheme } from "../layout/theme";
+import { useTranslation } from "react-i18next";
+import { AUTONYM_MAP, type LanguageCode, isRtlLanguage } from "../i18n/languages";
+import { getLanguageOptionsByUsage } from "../i18n/translation-priority";
+import { useAuth } from "../auth/context";
+
+/**
+ * Top navigation: brand, primary routes (chat at `/`, `/mission`), an
+ * auth-aware cluster (Account/Sign out when signed in, else Sign in/up),
+ * the theme toggle, and the language selector.
+ *
+ * The language picker is ordered by **estimated usage**
+ * (getLanguageOptionsByUsage), not alphabetically — a deliberate choice that
+ * foregrounds helexa's international grounding. Each item shows the autonym
+ * (language in its own script) plus a secondary label in the current
+ * language; RTL-aware alignment.
+ */
+const Header: React.FC = () => {
+  const { theme, toggleTheme } = useTheme();
+  const { t, i18n } = useTranslation("common");
+  const { status, logout } = useAuth();
+
+  const currentLanguage: LanguageCode = (i18n.language.split("-")[0] ||
+    "en") as LanguageCode;
+  const isRtl = isRtlLanguage(currentLanguage);
+  const languageOptions = getLanguageOptionsByUsage();
+
+  return (
+    <Navbar
+      expand="lg"
+      className="app-header border-bottom"
+      variant={theme === "dark" ? "dark" : "light"}
+    >
+      <Container fluid>
+        <Navbar.Brand
+          as={Link}
+          to="/"
+          className="d-flex align-items-center gap-2"
+        >
+          <img
+            src="/logo.png"
+            alt="helexa logo"
+            width={28}
+            height={28}
+            style={{ borderRadius: "999px" }}
+          />
+          <span className="fw-semibold text-uppercase small tracking-wide">
+            {t("app.name")}
+          </span>
+        </Navbar.Brand>
+
+        <Navbar.Toggle aria-controls="main-navbar" />
+
+        <Navbar.Collapse id="main-navbar">
+          <Nav className="me-auto">
+            <NavLink
+              to="/"
+              end
+              className={({ isActive }): string =>
+                isActive ? "nav-link active" : "nav-link"
+              }
+            >
+              {t("nav.chat")}
+            </NavLink>
+            <NavLink
+              to="/mission"
+              className={({ isActive }): string =>
+                isActive ? "nav-link active" : "nav-link"
+              }
+            >
+              {t("nav.mission")}
+            </NavLink>
+          </Nav>
+
+          <div className="d-flex align-items-center gap-2">
+            {/* Auth-aware cluster. */}
+            {status === "authed" ? (
+              <>
+                <NavLink to="/account" className="nav-link">
+                  {t("nav.account")}
+                </NavLink>
+                <Button
+                  size="sm"
+                  variant="outline-secondary"
+                  onClick={logout}
+                  className="me-1"
+                >
+                  {t("nav.logout")}
+                </Button>
+              </>
+            ) : (
+              <>
+                <NavLink to="/login" className="nav-link">
+                  {t("nav.login")}
+                </NavLink>
+                <NavLink to="/register" className="nav-link">
+                  {t("nav.register")}
+                </NavLink>
+              </>
+            )}
+
+            <Button
+              size="sm"
+              variant="outline-secondary"
+              type="button"
+              onClick={toggleTheme}
+              aria-label={
+                theme === "dark"
+                  ? t("theme.toggle.toLight")
+                  : t("theme.toggle.toDark")
+              }
+              className="d-inline-flex align-items-center justify-content-center"
+            >
+              {theme === "dark" ? <FaRegSun size={16} /> : <FaRegMoon size={16} />}
+            </Button>
+
+            <Dropdown
+              align={isRtl ? "start" : "end"}
+              className={theme === "dark" ? "dropdown-menu-dark-context" : ""}
+            >
+              <Dropdown.Toggle
+                size="sm"
+                variant={theme === "dark" ? "secondary" : "outline-secondary"}
+                id="language-switcher"
+              >
+                <span className="me-1" aria-hidden="true">
+                  文A
+                </span>
+                <span>{AUTONYM_MAP[currentLanguage]}</span>
+              </Dropdown.Toggle>
+              <Dropdown.Menu
+                className={theme === "dark" ? "dropdown-menu-dark" : ""}
+              >
+                {languageOptions.map(({ code, autonym }) => (
+                  <Dropdown.Item
+                    key={code}
+                    active={code === currentLanguage}
+                    onClick={() => void i18n.changeLanguage(code)}
+                    className="d-flex align-items-center gap-2"
+                  >
+                    <span>{autonym}</span>
+                    <span className="text-muted small fw-light">
+                      · {t(`lang.${code}`)}
+                    </span>
+                  </Dropdown.Item>
+                ))}
+              </Dropdown.Menu>
+            </Dropdown>
+          </div>
+        </Navbar.Collapse>
+      </Container>
+    </Navbar>
+  );
+};
+
+export default Header;

helexa.ai/src/data/db.ts

@@ -0,0 +1,72 @@
+// IndexedDB (Dexie) — the ONLY home for chat history and project
+// organisation. Nothing here is ever sent to a server (#69/#F3): the mesh
+// serves inference, but conversations live exclusively in the browser.
+//
+// `owner` namespaces data: `"anon"` for the fingerprinted anonymous visitor,
+// or an account id once signed in. On login, anonymous data can be claimed
+// into the account (F4) — still purely client-side.
+
+import Dexie, { type Table } from "dexie";
+
+export interface Project {
+  id: string;
+  owner: string;
+  name: string;
+  createdAt: number;
+  updatedAt: number;
+  archived: boolean;
+  sortOrder: number;
+}
+
+export interface Conversation {
+  id: string;
+  owner: string;
+  projectId: string | null; // null → "Unsorted"
+  title: string;
+  model: string;
+  createdAt: number;
+  updatedAt: number;
+  pinned: boolean;
+}
+
+export type MessageRole = "system" | "user" | "assistant";
+export type MessageStatus = "complete" | "streaming" | "error";
+
+export interface Message {
+  id: string;
+  conversationId: string;
+  role: MessageRole;
+  content: string;
+  createdAt: number;
+  status: MessageStatus;
+  errorCode?: string;
+  promptTokens?: number;
+  completionTokens?: number;
+}
+
+/** Small key/value store: fingerprint, active conversation, anon usage. */
+export interface Meta {
+  key: string;
+  value: unknown;
+}
+
+class HelexaDB extends Dexie {
+  projects!: Table<Project, string>;
+  conversations!: Table<Conversation, string>;
+  messages!: Table<Message, string>;
+  meta!: Table<Meta, string>;
+
+  constructor() {
+    super("helexa");
+    this.version(1).stores({
+      // Indexes only — Dexie stores the whole object. Compound indexes
+      // drive the common queries (by owner, by conversation in time order).
+      projects: "id, owner, [owner+archived], updatedAt",
+      conversations: "id, owner, projectId, [owner+projectId], updatedAt",
+      messages: "id, conversationId, [conversationId+createdAt]",
+      meta: "key",
+    });
+  }
+}
+
+export const db = new HelexaDB();

helexa.ai/src/data/repositories.ts

@@ -0,0 +1,154 @@
+// Typed CRUD + queries over the Dexie store. UI components use the
+// `useLiveQuery` hook (dexie-react-hooks) with the list helpers here so the
+// sidebar/thread react to writes automatically.
+
+import Dexie from "dexie";
+import {
+  db,
+  type Conversation,
+  type Message,
+  type MessageRole,
+  type Project,
+} from "./db";
+
+function uuid(): string {
+  return crypto.randomUUID();
+}
+function now(): number {
+  return Date.now();
+}
+
+// ── projects ────────────────────────────────────────────────────────
+
+export async function listProjects(owner: string): Promise<Project[]> {
+  const rows = await db.projects.where({ owner }).toArray();
+  return rows
+    .filter((p) => !p.archived)
+    .sort((a, b) => a.sortOrder - b.sortOrder || a.createdAt - b.createdAt);
+}
+
+export async function createProject(owner: string, name: string): Promise<string> {
+  const id = uuid();
+  const ts = now();
+  await db.projects.add({
+    id,
+    owner,
+    name,
+    createdAt: ts,
+    updatedAt: ts,
+    archived: false,
+    sortOrder: ts,
+  });
+  return id;
+}
+
+export async function renameProject(id: string, name: string): Promise<void> {
+  await db.projects.update(id, { name, updatedAt: now() });
+}
+
+export async function archiveProject(id: string): Promise<void> {
+  // Detach its conversations to "Unsorted" so nothing is orphaned.
+  await db.transaction("rw", db.projects, db.conversations, async () => {
+    await db.projects.update(id, { archived: true, updatedAt: now() });
+    const convs = await db.conversations.where({ projectId: id }).toArray();
+    await Promise.all(
+      convs.map((c) => db.conversations.update(c.id, { projectId: null })),
+    );
+  });
+}
+
+// ── conversations ───────────────────────────────────────────────────
+
+export async function listConversations(owner: string): Promise<Conversation[]> {
+  const rows = await db.conversations.where({ owner }).toArray();
+  return rows.sort(
+    (a, b) => Number(b.pinned) - Number(a.pinned) || b.updatedAt - a.updatedAt,
+  );
+}
+
+export async function createConversation(
+  owner: string,
+  model: string,
+  projectId: string | null = null,
+  title = "New chat",
+): Promise<string> {
+  const id = uuid();
+  const ts = now();
+  await db.conversations.add({
+    id,
+    owner,
+    projectId,
+    title,
+    model,
+    createdAt: ts,
+    updatedAt: ts,
+    pinned: false,
+  });
+  return id;
+}
+
+export async function renameConversation(id: string, title: string): Promise<void> {
+  await db.conversations.update(id, { title, updatedAt: now() });
+}
+
+export async function moveConversation(
+  id: string,
+  projectId: string | null,
+): Promise<void> {
+  await db.conversations.update(id, { projectId, updatedAt: now() });
+}
+
+export async function deleteConversation(id: string): Promise<void> {
+  await db.transaction("rw", db.conversations, db.messages, async () => {
+    await db.messages.where({ conversationId: id }).delete();
+    await db.conversations.delete(id);
+  });
+}
+
+// ── messages ────────────────────────────────────────────────────────
+
+export async function listMessages(conversationId: string): Promise<Message[]> {
+  return db.messages
+    .where("[conversationId+createdAt]")
+    .between([conversationId, Dexie.minKey], [conversationId, Dexie.maxKey])
+    .toArray();
+}
+
+export async function addMessage(
+  conversationId: string,
+  role: MessageRole,
+  content: string,
+  status: Message["status"] = "complete",
+): Promise<string> {
+  const id = uuid();
+  await db.messages.add({ id, conversationId, role, content, createdAt: now(), status });
+  await db.conversations.update(conversationId, { updatedAt: now() });
+  return id;
+}
+
+export async function appendToMessage(id: string, delta: string): Promise<void> {
+  const msg = await db.messages.get(id);
+  if (!msg) return;
+  await db.messages.update(id, { content: msg.content + delta });
+}
+
+export async function finalizeMessage(
+  id: string,
+  patch: Partial<Pick<Message, "status" | "errorCode" | "promptTokens" | "completionTokens">>,
+): Promise<void> {
+  await db.messages.update(id, patch);
+}
+
+/** Rewrite all `anon` data to `accountId` on first login (stays local). */
+export async function claimAnonymousData(accountId: string): Promise<void> {
+  await db.transaction("rw", db.projects, db.conversations, async () => {
+    const projects = await db.projects.where({ owner: "anon" }).toArray();
+    await Promise.all(
+      projects.map((p) => db.projects.update(p.id, { owner: accountId })),
+    );
+    const convs = await db.conversations.where({ owner: "anon" }).toArray();
+    await Promise.all(
+      convs.map((c) => db.conversations.update(c.id, { owner: accountId })),
+    );
+  });
+}

helexa.ai/src/i18n/index.ts

@@ -0,0 +1,424 @@
+import i18n, { type Resource } from "i18next";
+import { initReactI18next } from "react-i18next";
+import {
+  SUPPORTED_LANGUAGES,
+  normalizeLocaleToLanguage,
+  isRtlLanguage,
+} from "./languages";
+import type { LanguageCode } from "./languages";
+
+// Core languages
+import enCommon from "./resources/en/common.json";
+import ruCommon from "./resources/ru/common.json";
+import enMission from "./resources/en/mission.json";
+import ruMission from "./resources/ru/mission.json";
+import enChat from "./resources/en/chat.json";
+import enAccount from "./resources/en/account.json";
+import ruChat from "./resources/ru/chat.json";
+import ruAccount from "./resources/ru/account.json";
+
+// Scandinavian & Nordic languages
+import daCommon from "./resources/da/common.json";
+import daMission from "./resources/da/mission.json";
+import daChat from "./resources/da/chat.json";
+import daAccount from "./resources/da/account.json";
+
+import fiCommon from "./resources/fi/common.json";
+import fiMission from "./resources/fi/mission.json";
+import fiChat from "./resources/fi/chat.json";
+import fiAccount from "./resources/fi/account.json";
+
+import noCommon from "./resources/no/common.json";
+import noMission from "./resources/no/mission.json";
+import noChat from "./resources/no/chat.json";
+import noAccount from "./resources/no/account.json";
+
+import svCommon from "./resources/sv/common.json";
+import svMission from "./resources/sv/mission.json";
+import svChat from "./resources/sv/chat.json";
+import svAccount from "./resources/sv/account.json";
+
+import bgCommon from "./resources/bg/common.json";
+import bgMission from "./resources/bg/mission.json";
+import bgChat from "./resources/bg/chat.json";
+import bgAccount from "./resources/bg/account.json";
+
+import etCommon from "./resources/et/common.json";
+import etMission from "./resources/et/mission.json";
+import etChat from "./resources/et/chat.json";
+import etAccount from "./resources/et/account.json";
+
+// African & MENA languages
+import swCommon from "./resources/sw/common.json";
+import swMission from "./resources/sw/mission.json";
+import swChat from "./resources/sw/chat.json";
+import swAccount from "./resources/sw/account.json";
+
+import arCommon from "./resources/ar/common.json";
+import arMission from "./resources/ar/mission.json";
+import arChat from "./resources/ar/chat.json";
+import arAccount from "./resources/ar/account.json";
+
+import faCommon from "./resources/fa/common.json";
+import faMission from "./resources/fa/mission.json";
+import faChat from "./resources/fa/chat.json";
+import faAccount from "./resources/fa/account.json";
+
+import haCommon from "./resources/ha/common.json";
+import haMission from "./resources/ha/mission.json";
+import haChat from "./resources/ha/chat.json";
+import haAccount from "./resources/ha/account.json";
+
+import amCommon from "./resources/am/common.json";
+import amMission from "./resources/am/mission.json";
+import amChat from "./resources/am/chat.json";
+import amAccount from "./resources/am/account.json";
+
+import yoCommon from "./resources/yo/common.json";
+import yoMission from "./resources/yo/mission.json";
+import yoChat from "./resources/yo/chat.json";
+import yoAccount from "./resources/yo/account.json";
+
+import zuCommon from "./resources/zu/common.json";
+import zuMission from "./resources/zu/mission.json";
+import zuChat from "./resources/zu/chat.json";
+import zuAccount from "./resources/zu/account.json";
+
+// Darija (Moroccan Arabic)
+import maCommon from "./resources/ma/common.json";
+import maMission from "./resources/ma/mission.json";
+import maChat from "./resources/ma/chat.json";
+import maAccount from "./resources/ma/account.json";
+
+// European / other languages
+import esCommon from "./resources/es/common.json";
+import esMission from "./resources/es/mission.json";
+import esChat from "./resources/es/chat.json";
+import esAccount from "./resources/es/account.json";
+
+import frCommon from "./resources/fr/common.json";
+import frMission from "./resources/fr/mission.json";
+import frChat from "./resources/fr/chat.json";
+import frAccount from "./resources/fr/account.json";
+
+import deCommon from "./resources/de/common.json";
+import deMission from "./resources/de/mission.json";
+import deChat from "./resources/de/chat.json";
+import deAccount from "./resources/de/account.json";
+
+import elCommon from "./resources/el/common.json";
+import elMission from "./resources/el/mission.json";
+import elChat from "./resources/el/chat.json";
+import elAccount from "./resources/el/account.json";
+
+import itCommon from "./resources/it/common.json";
+import itMission from "./resources/it/mission.json";
+import itChat from "./resources/it/chat.json";
+import itAccount from "./resources/it/account.json";
+
+import heCommon from "./resources/he/common.json";
+import heMission from "./resources/he/mission.json";
+import heChat from "./resources/he/chat.json";
+import heAccount from "./resources/he/account.json";
+
+import ptCommon from "./resources/pt/common.json";
+import ptMission from "./resources/pt/mission.json";
+import ptChat from "./resources/pt/chat.json";
+import ptAccount from "./resources/pt/account.json";
+
+import roCommon from "./resources/ro/common.json";
+import roMission from "./resources/ro/mission.json";
+import roChat from "./resources/ro/chat.json";
+import roAccount from "./resources/ro/account.json";
+
+import kaCommon from "./resources/ka/common.json";
+import kaMission from "./resources/ka/mission.json";
+import kaChat from "./resources/ka/chat.json";
+import kaAccount from "./resources/ka/account.json";
+
+import trCommon from "./resources/tr/common.json";
+import trMission from "./resources/tr/mission.json";
+import trChat from "./resources/tr/chat.json";
+import trAccount from "./resources/tr/account.json";
+
+import plCommon from "./resources/pl/common.json";
+import plMission from "./resources/pl/mission.json";
+import plChat from "./resources/pl/chat.json";
+import plAccount from "./resources/pl/account.json";
+
+import ukCommon from "./resources/uk/common.json";
+import ukMission from "./resources/uk/mission.json";
+import ukChat from "./resources/uk/chat.json";
+import ukAccount from "./resources/uk/account.json";
+
+import nlCommon from "./resources/nl/common.json";
+import nlMission from "./resources/nl/mission.json";
+import nlChat from "./resources/nl/chat.json";
+import nlAccount from "./resources/nl/account.json";
+
+import srCommon from "./resources/sr/common.json";
+import srMission from "./resources/sr/mission.json";
+import srChat from "./resources/sr/chat.json";
+import srAccount from "./resources/sr/account.json";
+
+import kkCommon from "./resources/kk/common.json";
+import kkMission from "./resources/kk/mission.json";
+import kkChat from "./resources/kk/chat.json";
+import kkAccount from "./resources/kk/account.json";
+
+import uzCommon from "./resources/uz/common.json";
+import uzMission from "./resources/uz/mission.json";
+import uzChat from "./resources/uz/chat.json";
+import uzAccount from "./resources/uz/account.json";
+
+/**
+ * Application translation resources, split by language and namespace.
+ *
+ * - `common`: shared UI elements (navigation, theme toggle, etc.)
+ * - `home`:   marketing / narrative copy on the landing page
+ * - `chat`:   copy for the chat workspace
+ */
+const resources: Resource = {
+  en: {
+    common: enCommon,
+    mission: enMission,
+    chat: enChat,
+    account: enAccount,
+  },
+  ru: {
+    common: ruCommon,
+    mission: ruMission,
+    chat: ruChat,
+    account: ruAccount,
+  },
+  bg: {
+    common: bgCommon,
+    mission: bgMission,
+    chat: bgChat,
+    account: bgAccount,
+  },
+  da: {
+    common: daCommon,
+    mission: daMission,
+    chat: daChat,
+    account: daAccount,
+  },
+  et: {
+    common: etCommon,
+    mission: etMission,
+    chat: etChat,
+    account: etAccount,
+  },
+  fi: {
+    common: fiCommon,
+    mission: fiMission,
+    chat: fiChat,
+    account: fiAccount,
+  },
+  kk: {
+    common: kkCommon,
+    mission: kkMission,
+    chat: kkChat,
+    account: kkAccount,
+  },
+  uz: {
+    common: uzCommon,
+    mission: uzMission,
+    chat: uzChat,
+    account: uzAccount,
+  },
+
+  // African & MENA languages (LTR unless marked RTL via isRtlLanguage)
+  sw: {
+    common: swCommon,
+    mission: swMission,
+    chat: swChat,
+    account: swAccount,
+  },
+  ar: {
+    common: arCommon,
+    mission: arMission,
+    chat: arChat,
+    account: arAccount,
+  },
+  fa: {
+    common: faCommon,
+    mission: faMission,
+    chat: faChat,
+    account: faAccount,
+  },
+  ha: {
+    common: haCommon,
+    mission: haMission,
+    chat: haChat,
+    account: haAccount,
+  },
+  am: {
+    common: amCommon,
+    mission: amMission,
+    chat: amChat,
+    account: amAccount,
+  },
+  yo: {
+    common: yoCommon,
+    mission: yoMission,
+    chat: yoChat,
+    account: yoAccount,
+  },
+  zu: {
+    common: zuCommon,
+    mission: zuMission,
+    chat: zuChat,
+    account: zuAccount,
+  },
+  ma: {
+    common: maCommon,
+    mission: maMission,
+    chat: maChat,
+    account: maAccount,
+  },
+
+  // European & other languages
+  es: {
+    common: esCommon,
+    mission: esMission,
+    chat: esChat,
+    account: esAccount,
+  },
+  fr: {
+    common: frCommon,
+    mission: frMission,
+    chat: frChat,
+    account: frAccount,
+  },
+  de: {
+    common: deCommon,
+    mission: deMission,
+    chat: deChat,
+    account: deAccount,
+  },
+  el: {
+    common: elCommon,
+    mission: elMission,
+    chat: elChat,
+    account: elAccount,
+  },
+  it: {
+    common: itCommon,
+    mission: itMission,
+    chat: itChat,
+    account: itAccount,
+  },
+  he: {
+    common: heCommon,
+    mission: heMission,
+    chat: heChat,
+    account: heAccount,
+  },
+  pt: {
+    common: ptCommon,
+    mission: ptMission,
+    chat: ptChat,
+    account: ptAccount,
+  },
+  ro: {
+    common: roCommon,
+    mission: roMission,
+    chat: roChat,
+    account: roAccount,
+  },
+  ka: {
+    common: kaCommon,
+    mission: kaMission,
+    chat: kaChat,
+    account: kaAccount,
+  },
+  tr: {
+    common: trCommon,
+    mission: trMission,
+    chat: trChat,
+    account: trAccount,
+  },
+  pl: {
+    common: plCommon,
+    mission: plMission,
+    chat: plChat,
+    account: plAccount,
+  },
+  uk: {
+    common: ukCommon,
+    mission: ukMission,
+    chat: ukChat,
+    account: ukAccount,
+  },
+  nl: {
+    common: nlCommon,
+    mission: nlMission,
+    chat: nlChat,
+    account: nlAccount,
+  },
+  sr: {
+    common: srCommon,
+    mission: srMission,
+    chat: srChat,
+    account: srAccount,
+  },
+  no: {
+    common: noCommon,
+    mission: noMission,
+    chat: noChat,
+    account: noAccount,
+  },
+  sv: {
+    common: svCommon,
+    mission: svMission,
+    chat: svChat,
+    account: svAccount,
+  },
+};
+
+// Determine initial language from browser, normalised to language-only.
+const browserLang: LanguageCode =
+  typeof navigator !== "undefined"
+    ? normalizeLocaleToLanguage(navigator.language)
+    : "en";
+
+// Keep document direction (ltr/rtl) in sync with the active language.
+if (typeof document !== "undefined") {
+  document.documentElement.dir = isRtlLanguage(browserLang) ? "rtl" : "ltr";
+}
+
+/**
+ * Initialize i18next with React bindings.
+ *
+ * This module is imported once in src/main.tsx before any React
+ * rendering so that `useTranslation` is ready everywhere.
+ */
+i18n.use(initReactI18next).init({
+  resources,
+  lng: browserLang,
+  fallbackLng: "en",
+  supportedLngs: SUPPORTED_LANGUAGES,
+  ns: ["common", "mission", "chat", "account"],
+  defaultNS: "common",
+  // Because we control the keys and interpolate only simple values.
+  interpolation: {
+    escapeValue: false,
+  },
+  // For now we stay language-only; we already normalise the browser locale.
+  load: "languageOnly",
+  // Be explicit about react options for clarity.
+  react: {
+    useSuspense: false,
+  },
+});
+
+// Ensure that when the language changes at runtime, document direction
+// tracks the new language's natural writing direction.
+i18n.on("languageChanged", (lng) => {
+  if (typeof document === "undefined") return;
+  const lang = normalizeLocaleToLanguage(lng);
+  document.documentElement.dir = isRtlLanguage(lang) ? "rtl" : "ltr";
+});
+
+export default i18n;

helexa.ai/src/i18n/languages.ts

@@ -0,0 +1,232 @@
+import type { Resource } from "i18next";
+
+/**
+ * Supported language codes for the application.
+ *
+ * For the foreseeable future we deliberately stay at the language level
+ * (e.g. "en", "ru") rather than full locales (e.g. "en-GB") to keep
+ * translation overhead manageable.
+ *
+ * When you add a new language:
+ * - Add its code to `SUPPORTED_LANGUAGES`
+ * - Add its autonym to `AUTONYM_MAP`
+ * - Add its resources to the i18n configuration
+ */
+export type LanguageCode =
+  | "en"
+  | "bg"
+  | "cs"
+  | "da"
+  | "de"
+  | "el"
+  | "es"
+  | "he"
+  | "et"
+  | "ar"
+  | "fa"
+  | "fi"
+  | "sw"
+  | "ha"
+  | "am"
+  | "yo"
+  | "zu"
+  | "fr"
+  | "ma"
+  | "ga"
+  | "hr"
+  | "hu"
+  | "is"
+  | "it"
+  | "ka"
+  | "lt"
+  | "lv"
+  | "mt"
+  | "nl"
+  | "no"
+  | "pl"
+  | "pt"
+  | "ro"
+  | "ru"
+  | "sk"
+  | "sl"
+  | "sr"
+  | "sv"
+  | "tr"
+  | "uk"
+  | "bs"
+  | "mk"
+  | "kk"
+  | "uz"
+  | "ig"
+  | "om"
+  | "so"
+  | "ti"
+  | "wo";
+
+/**
+ * Ordered list of languages enabled in the UI.
+ *
+ * For now you can keep `SUPPORTED_LANGUAGES` in sync with the
+ * actually configured i18n resources (e.g. ["en", "ru"]) and grow
+ * it as translations land.
+ */
+export const SUPPORTED_LANGUAGES: LanguageCode[] = [
+  "bg",
+  "da",
+  "de",
+  "el",
+  "en",
+  "es",
+  "et",
+  "fi",
+  "fr",
+  "he",
+  "it",
+  "ka",
+  "kk",
+  "nl",
+  "no",
+  "sv",
+  "uz",
+  "ar",
+  "fa",
+  "sw",
+  "ha",
+  "am",
+  "yo",
+  "zu",
+  "ma",
+  "pl",
+  "pt",
+  "ro",
+  "ru",
+  "sr",
+  "tr",
+  "uk",
+  // Future Afro‑European / Eurasian candidates; keep out of SUPPORTED_LANGUAGES until translated:
+  // "ig", // Igbo
+  // "om", // Oromo
+  // "so", // Somali
+  // "ti", // Tigrinya
+  // "wo", // Wolof
+];
+
+/**
+ * Autonym map.
+ *
+ * Each language is named in its own language so that a user only
+ * needs to know their own language to find it in the selector.
+ */
+export const AUTONYM_MAP: Record<LanguageCode, string> = {
+  en: "English",
+  bg: "български",
+  cs: "čeština",
+  da: "dansk",
+  de: "Deutsch",
+  el: "Ελληνικά",
+  es: "español",
+  et: "eesti",
+  he: "עברית",
+  ar: "العربية",
+  fa: "فارسی",
+  sw: "Kiswahili",
+  ha: "Hausa",
+  am: "አማርኛ",
+  yo: "Yorùbá",
+  zu: "isiZulu",
+  ma: "Darija",
+  fi: "suomi",
+  fr: "français",
+  ga: "Gaeilge",
+  hr: "hrvatski",
+  hu: "magyar",
+  is: "íslenska",
+  it: "italiano",
+  lt: "lietuvių",
+  lv: "latviešu",
+  mt: "Malti",
+  nl: "Nederlands",
+  no: "norsk",
+  pl: "polski",
+  pt: "português",
+  ro: "română",
+  ru: "русский",
+  sk: "slovenčina",
+  sl: "slovenščina",
+  sr: "српски",
+  sv: "svenska",
+  tr: "Türkçe",
+  uk: "українська",
+  bs: "bosanski",
+  mk: "македонски",
+  ka: "ქართული", // Georgian
+  kk: "қазақ тілі", // Kazakh
+  uz: "oʻzbekcha", // Uzbek
+  ig: "Igbo", // Igbo
+  om: "Afaan Oromoo", // Oromo
+  so: "Af-Soomaali", // Somali
+  ti: "ትግርኛ", // Tigrinya
+  wo: "Wolof", // Wolof
+};
+
+/**
+ * Normalize a full locale (e.g. "en-GB") down to a `LanguageCode`.
+ *
+ * - Uses the first segment of the locale (before "-")
+ * - Falls back to "en" if the language is unsupported or invalid
+ */
+export const normalizeLocaleToLanguage = (
+  locale: string | null | undefined,
+): LanguageCode => {
+  if (!locale) return "en";
+  const lang = locale.split("-")[0]?.toLowerCase() ?? "en";
+
+  if (SUPPORTED_LANGUAGES.includes(lang as LanguageCode)) {
+    return lang as LanguageCode;
+  }
+
+  return "en";
+};
+
+/**
+ * Build a stable list of language options for UI components
+ * such as dropdowns.
+ */
+export type LanguageOption = {
+  code: LanguageCode;
+  autonym: string;
+};
+
+export const getLanguageOptions = (): LanguageOption[] =>
+  [...SUPPORTED_LANGUAGES]
+    .map((code) => ({
+      code,
+      autonym: AUTONYM_MAP[code],
+    }))
+    .sort((a, b) => a.autonym.localeCompare(b.autonym));
+
+/**
+ * Utility to derive i18next `supportedLngs` from our language codes,
+ * so configuration can import from this module instead of hardcoding
+ * the list in multiple places.
+ */
+export const getSupportedLngsForI18Next = (): Resource["en"] extends never
+  ? string[]
+  : string[] => {
+  // i18next accepts string[], while we keep a stricter LanguageCode[]
+  return [...SUPPORTED_LANGUAGES];
+};
+
+/**
+ * Languages whose natural writing direction is right-to-left.
+ *
+ * This is used by layout code (outside this module) to switch
+ * document direction and RTL-aware styling when needed.
+ */
+export const RTL_LANGUAGES: LanguageCode[] = ["he", "ar", "fa", "ma"];
+
+/**
+ * Utility to check whether a given language code is RTL.
+ */
+export const isRtlLanguage = (code: LanguageCode): boolean =>
+  RTL_LANGUAGES.includes(code);

helexa.ai/src/i18n/resources/am/account.json

@@ -0,0 +1,71 @@
+{
+  "login": {
+    "title": "Sign in",
+    "email": "Email",
+    "password": "Password",
+    "submit": "Sign in",
+    "noAccount": "No account? Sign up"
+  },
+  "register": {
+    "title": "Create your account",
+    "email": "Email",
+    "password": "Password",
+    "submit": "Sign up",
+    "haveAccount": "Already have an account? Sign in",
+    "checkEmail": "Almost there — check your email to verify your account."
+  },
+  "verify": {
+    "verifying": "Verifying…",
+    "ok": "Email verified. You can now sign in.",
+    "failed": "This verification link is invalid or has expired.",
+    "toLogin": "Go to sign in"
+  },
+  "reset": {
+    "requestTitle": "Reset your password",
+    "email": "Email",
+    "requestSubmit": "Send reset link",
+    "requestDone": "If that email has an account, a reset link is on its way.",
+    "confirmTitle": "Choose a new password",
+    "newPassword": "New password",
+    "confirmSubmit": "Set password",
+    "ok": "Password updated. You can now sign in."
+  },
+  "dashboard": {
+    "title": "Account",
+    "balance": "Allocation",
+    "total": "Total",
+    "spent": "Spent",
+    "reserved": "Reserved",
+    "remaining": "Remaining",
+    "manageKeys": "Manage API keys",
+    "redeemTitle": "Redeem a top-up code",
+    "redeemPlaceholder": "helexa-topup-…",
+    "redeem": "Redeem",
+    "redeemed": "Code redeemed.",
+    "logout": "Sign out"
+  },
+  "keys": {
+    "title": "API keys",
+    "create": "Create key",
+    "label": "Label",
+    "limitKind": "Limit",
+    "percent": "% of allocation",
+    "hardcap": "Hard cap (tokens)",
+    "value": "Value",
+    "none": "No keys yet.",
+    "createdTitle": "Your new API key",
+    "createdWarn": "Copy it now — you won't see it again.",
+    "copy": "Copy",
+    "copied": "Copied",
+    "archive": "Archive",
+    "save": "Save",
+    "status": "Status",
+    "usage": "Used",
+    "useForChat": "Use for chat on this device",
+    "usedForChat": "Enabled for chat ✓"
+  },
+  "error": {
+    "generic": "Something went wrong.",
+    "unauthorized": "Please sign in again."
+  }
+}

helexa.ai/src/i18n/resources/am/chat.json

@@ -0,0 +1,21 @@
+{
+  "title": "የውይይት ቦታ",
+  "badge": "ውይይት",
+  "lead": "ይህ የውይይት እይታ ነው። የውይይት ሎጂክዎን እና የተጠቃሚ በስተጀርባ ክፍሎችን ወደዚህ ገፅ ያገናኙ።",
+  "transcriptPlaceholder": "የውይይቱ ሪኮርድ እዚህ ይታያል። የሞዴሉን እና የተጠቃሚውን መልዕክቶች በሚንቀሳቀስ ኮንቴይነር ውስጥ ያቀርቡ፣  приወይም በዙር ዙር በመከፈል ማቅረብ ይችላሉ።",
+  "inputPlaceholder": "ውይይትን ለመጀምር መልዕክት ይፃፉ…",
+  "send": "መላክ",
+  "clear": "ማጽዳት",
+  "newChat": "New chat",
+  "newProject": "New project",
+  "newProjectName": "New project",
+  "unsorted": "Unsorted",
+  "emptyState": "Start a conversation. Your history stays in this browser.",
+  "anonBanner": "You have reached the anonymous limit. Sign up for a free allocation.",
+  "signUp": "Sign up",
+  "stop": "Stop",
+  "topUp": "Top up",
+  "rateLimited": "Rate limited — wait a moment and retry.",
+  "needsKey": "Create an API key and enable it for chat to send as yourself.",
+  "manageKeysLink": "Manage keys"
+}

helexa.ai/src/i18n/resources/am/common.json

@@ -0,0 +1,68 @@
+{
+  "app": {
+    "name": "helexa.ai"
+  },
+  "nav": {
+    "home": "መነሻ ገፅ",
+    "docs": "ሰነዶች",
+    "chat": "ውይይት",
+    "mission": "Mission",
+    "login": "Sign in",
+    "register": "Sign up",
+    "account": "Account",
+    "logout": "Sign out"
+  },
+  "theme": {
+    "toggle": {
+      "toLight": "ወደ ብርሃን ሁኔታ መቀየር",
+      "toDark": "ወደ ጨለማ ሁኔታ መቀየር"
+    }
+  },
+  "lang": {
+    "bg": "ቡልጋሪኛ",
+    "de": "ጀርመንኛ",
+    "el": "ግሪከኛ",
+    "en": "እንግሊዝኛ",
+    "es": "ስፓኒሽኛ",
+    "et": "ኤስቶኒያን",
+    "fr": "ፈረንሳይኛ",
+    "he": "እብራስጥ",
+    "it": "ጣሊያንኛ",
+    "nl": "ደችኛ",
+    "da": "ዴኒሽኛ",
+    "fi": "ፊኒሽኛ",
+    "no": "ኖርዌጂያንኛ",
+    "sv": "ስዊድንኛ",
+    "ar": "ዐርቢኛ",
+    "fa": "ፐርሺያኛ",
+    "sw": "ስዋሂሊኛ",
+    "ha": "ሃውሳኛ",
+    "am": "አማርኛ",
+    "yo": "ዮሩባ",
+    "zu": "ዙሉ",
+    "ma": "ዳሪጃ",
+    "ig": "ኢግቦኛ",
+    "ka": "ጊዮርጂያንኛ",
+    "kk": "ካዛክኛ",
+    "om": "ኦሮሞኛ",
+    "so": "ሶማሊኛ",
+    "ti": "ትግርኛ",
+    "uz": "ኡዝቤክኛ",
+    "wo": "ዎሎፍኛ",
+    "pl": "ፖሊሽኛ",
+    "pt": "ፖርቱጋልኛ",
+    "ro": "ሮማኒያን",
+    "ru": "ራሽኛ",
+    "sr": "ሰርቢኛ",
+    "tr": "ቱርክኛ",
+    "uk": "ዩክሬንኛ"
+  },
+  "footer": {
+    "copyright": "© {{year}} helexa.ai"
+  },
+  "beta": {
+    "tag": "Public beta",
+    "message": "helexa is in open beta — expect rough edges. Your chats stay in your browser.",
+    "dismiss": "Dismiss"
+  }
+}

helexa.ai/src/i18n/resources/am/mission.json

@@ -0,0 +1,103 @@
+{
+  "hero": {
+    "badge": "አዲስ የአእምሮ ቅርጽ",
+    "title": "አዲስ የአእምሮ ቅርጽ",
+    "lead": "Helexa በተገናኙ ነጻ ኦፕሬተሮች የሚነሳ ራሷን የሚያደርግ የኤ.አይ. መረብ ነው። ክፍት ነው። ተበታተነ። በመደጋገም ይቀየራል።",
+    "ctaJoinMesh": "ወደ መረቡ ይቀላቀሉ",
+    "ctaFollowProject": "ፕሮጀክቱን ይከተሉ",
+    "subcopy": "AI ክፍት፣ ጠንካራ እና የሚጋራ መሆን አለበት በሚሉ ለኦፕሬተሮች፣ ለአበልጣጫዎች እና ለማህበረሰቦች ተሠርቷል።",
+    "imageAlt": "የHelexa ሄሊክስ ምስል"
+  },
+
+  "intent": {
+    "title": "Helexa ለምን አለች",
+    "p1": "AI በምድር ላይ በጣም ኃይለኛው መሠረታዊ መዋቅር እየሆነ ነው። ነገር ግን ዛሬ፣ ያ ኃይል በግል ቅድሚያዎች፣ በጂኦግራፊያዊ ገደቦች እና በደካማ ኢኮኖሚዎች የተሳሰበ በጥቂት ኩባንያዎች ውስጥ ተሰብስቧል።",
+    "p2Intro": "Helexa የተለየ ነገር ታስባለች፦",
+    "bullet1": "ከአንድ ቦታ ሳይሆን ከሁሉም ቦታ የሚያድግ አእምሮ።",
+    "bullet2": "ማንኛውም ሰው ሊያስተዋውቅበትና ሊጠቀምበት የሚችለው መረብ።",
+    "bullet3": "በትእዛዝ ሳይሆን በፍላጎት ላይ የሚማር ስርዓት።",
+    "bullet4": "ማህበረሰቦችን ለመተካት ሳይሆን የሚጠናከል ቴክኖሎጂ።",
+    "closing": "Helexa መድረክ አይደለችም። ደመና አይደለችም።\nመረብ ነች — የተወለደ እና የሚሻሻል የነጻ ኦፕሬተሮች መረብ ሆና አዲስ ዓይነት አእምሮ የምታቀና."
+  },
+
+  "whyNow": {
+    "title": "ለAI የሚለው የመቀየር ጊዜ",
+    "problemTitle": "ችግኙ",
+    "problemBullet1": "AI ከቀድሞው ማንኛውም ቴክኖሎጂ የማይተካ ፍጥነት በመሰብሰብ ላይ ነው።",
+    "problemBullet2": "የኮምፒውተር ኃይል መዳረሻ ችሎታን ያወራል፣ ይህም መዳረሻ ግን በቀስታ እየተጠበቀ ነው።",
+    "problemBullet3": "የወጪ መከልከያዎች ምርምር እና የኢንተርፕራይዝ ጀማሪዎችን እና ማህበረሰቦችን እያወጡ ነው።",
+    "problemBullet4": "የጄኦፖለቲካ እና የህግ ግፊት የዓለም አቀፍ መዳረሻን እያቀረበ ነው።",
+    "problemBullet5": "የሞዴሎች ፈጣሪዎችና የሀርድዌር ኦፕሬተሮች ብዙ ጊዜ በራሳቸው የሚፈጥሩትን ዋጋ አያጋሩም።",
+    "opportunityTitle": "እድሉ",
+    "opportunityIntro": "ግን የተሰራጨ ዓለም የሚቻል ነው።",
+    "opportunityBullet1": "ሺዎች የሚቆጠሩ የGPU ካርዶች በዓለም ዙሪያ አሁንም በትንሽ እየተጠቀሙባቸው ነው።",
+    "opportunityBullet2": "ኦፕሬተሮች ለየሚሰጡት ኮምፒውተር ኃይል እውነተኛ እና ፍትሃዊ ክፍያ ይፈልጋሉ።",
+    "opportunityBullet3": "ዲቨሎፐሮች ክፍት እና ከመቆጣጠር የተጠበቀ መሠረታዊ መዋቅር ይፈልጋሉ።",
+    "opportunityBullet4": "ማህበረሰቦች በዲጂታል ስርዓቶቻቸው ውስጥ ስብስብ መንግስታዊነትን እና ጽኑ መሆን ይፈልጋሉ።",
+    "opportunityBullet5": "የAI እድገት ባለመለኪያ ሁኔታ ከባለሙያ ደመናዎች በላይ ቀድሞ ሄዷል — አዳዲስ ቅርጾች ያስፈልጋሉ።",
+    "opportunityClosing": "Helexa እነዚህ ኃይሎች በአንድ ጊዜ የሚገናኙበት ጊዜ ነው።"
+  },
+
+  "howItWorks": {
+    "title": "መረቡ እንዴት እንደሚሰራ",
+    "operators": {
+      "eyebrow": "ኦፕሬተሮች ኖዶችን ይያዙ",
+      "title": "ማንኛውም ሰው የኮምፒውተር ኃይል ሊያቀርብ ይችላል።",
+      "body": "ኦፕሬተሮች የHelexa ኖዶችን ያስኬዳሉ። የማንኛውንም ሞዴል እንዲሰሩ ያስችላሉ። በሀርድዌሩና በኢኮኖሚያዊ ውሳኔዎቻቸው ላይ ቁጥጥር ይጠብቃሉ። ምንም የፈቃድ ሂደት የለም፣ ጠባቂ መከላከያ የለም።"
+    },
+    "routing": {
+      "eyebrow": "መረቡ አእምሮን ይመራል",
+      "title": "ፍላጎት በመረቡ ውስጥ ይፈሳሳል።",
+      "body": "Helexa እየማረከች የቆየበት አቅም ወዴት እንደሚገኝ፣ ፍላጎት የሚጨምርበት ቦታ የት እንደሆነ እና ምን ኖድ ለማቅረብ ተስማሚ እንደሆነ ትማራለች። መረቡ በተፈጥሯዊ መንገድ ይለመዳል — እያደገ ያለ ሄሊክስ እንደሆነ።"
+    },
+    "value": {
+      "eyebrow": "ዋጋው ወደ ኋላ ይመለሳል",
+      "title": "ሥራ ታረጋገጠ። ክፍያ ፍትሃዊ ነው።",
+      "body": "እያንዳንዱ ስራ ክሪፕቶግራፊ የተፈረመ ደረሰኝ ይይዛል። ኦፕሬተሮች በሚሰጡት አእምሮ ላይ ገንዘብ ያገኛሉ። የመድረክ ታክስ የለም። ግልጽ ካልሆነ የክፍያ ሂደት የለም።"
+    }
+  },
+
+  "principles": {
+    "title": "በመድረኮች ላይ ሳይሆን በመርሆዎች ላይ የተገነባ",
+    "distributed": {
+      "title": "በንድፍ የተበታተነ",
+      "body": "አንድ የብቻ የእርምጃ መደበቂያ የለም። ማዕከላዊ ሥልጣን የለም። በእያንዳንዱ አዲስ ኦፕሬተር ጋር የሚጠናከር መረብ ነው።"
+    },
+    "participation": {
+      "title": "ተሳትፎ ለሁሉም ክፍት",
+      "body": "ኮምፒውተር ኃይል ካለህ ልዩ ልዩ ድርሻ ሊያስተዋውቅ ትችላለህ። መረቡ ሁሉንም ይቀበላል — ከኤጀጅ መሣሪያዎች፣ እስከ የቤት አገልጋዮች እና የዳታ ማእከላት ድረስ።"
+    },
+    "fairness": {
+      "title": "ፍትህና ተመልካችነት",
+      "body": "ገቢዎች በእውነተኛ ስራ ላይ ተመስርተዋል፣ በክሪፕቶግራፊ መሠረት ተረጋግጠዋል። ጥቁር ሳጥን የለም። የተደበቀ ክፍያ የለም።"
+    },
+    "evolving": {
+      "title": "የሚያድግ አእምሮ",
+      "body": "መረቡ ከፍላጎት ይማራል። ሞዴሎች የሚፈለጉበት ቦታ ላይ ይጫናሉ። አእምሮ በተባባሪነት ይበተናል።"
+    }
+  },
+
+  "roadAhead": {
+    "title": "Helexa ምን ለመሆን እየተሻሻለች ነው",
+    "p1": "ለሁሉም የሚያገለግል የዓለም አቀፍ የአእምሮ ንብርብር፣ በሄሊክስ ያለ የኖዶችና የማህበረሰቦች መረብ የሚደገፍ።",
+    "p2": "ማቋረጥ፣ ፖለቲካ፣ ነጠላ ባለቤቶች እና ወደፊት ሊከሰት በሚችል እንኳን የሚቋቋም መረብ።",
+    "p3": "ኦፕሬተሮች፣ አበልጣጫዎች እና ተጠቃሚዎች ሁሉም ተዋጊ የሚሆኑበት አዲስ የኢኮኖሚ ሞዴል።",
+    "p4": "ፈጠራ ከጠርዝ የሚያድግ፣ ከማዕከል ሳይሆን፣ የሥራ አካባቢ ኢኮሲስተም።",
+    "card": {
+      "eyebrow": "የራዕይ አጭር እትም",
+      "title": "ወደ የተጋራ የአእምሮ መረብ",
+      "body": "Helexa ገና በቀዳሚ ደረጃ ላይ ይ beታል። ሀሳቦቹ ከአሁን እና ከተፈጠረው ተቀባይነት የበለጠ ትልቅ ናቸው — ይህም በተወሰነ ዓላማ ነው። መረቡ በእያንዳንዱ ደረጃ ይበቃል፣ ኦፕሬተሮችና አበልጣጫዎችም እድገቷን በጋራ ይፀናሉ።"
+    }
+  },
+
+  "joinMesh": {
+    "badge": "የመጀመሪያ ደረጃ",
+    "title": "መረቡ እየተፈጠረ ነው።",
+    "titleHighlight": "እርስዎም ክፍል ሆነው ሊሳተፉበት ይችላሉ።",
+    "lead": "ሀርድዌር ብትከናወኑ፣ ሞዴሎችን ብታበርኩ፣ ወይም በአጠቃላይ AI እንዴት እንደሚመራ ብታስቡ ሆነው፣ በዚህ መረብ ውስጥ ለእርስዎ የተዘጋበ ቦታ አለ።",
+    "ctaRunNode": "ኖድ ያስኬዱ (በቅርቡ)",
+    "ctaJoinAnnouncements": "የቀድሞ ማስታወቂያዎችን ይቀበሉ",
+    "ctaExploreCode": "ኮድን ያስሱ",
+    "footer": "የተጣሉ ፍራንቻዎች የሉም። አንድ ብቻ ባለቤት የለም። የሚመጣውን የአእምሮ ወደፊት በሚያቀና መልኩ በሰዎች፣ በሀርድዌር እና በሀሳቦች የተሠራ መረብ ብቻ ነው።"
+  }
+}

helexa.ai/src/i18n/resources/ar/account.json

@@ -0,0 +1,71 @@
+{
+  "login": {
+    "title": "Sign in",
+    "email": "Email",
+    "password": "Password",
+    "submit": "Sign in",
+    "noAccount": "No account? Sign up"
+  },
+  "register": {
+    "title": "Create your account",
+    "email": "Email",
+    "password": "Password",
+    "submit": "Sign up",
+    "haveAccount": "Already have an account? Sign in",
+    "checkEmail": "Almost there — check your email to verify your account."
+  },
+  "verify": {
+    "verifying": "Verifying…",
+    "ok": "Email verified. You can now sign in.",
+    "failed": "This verification link is invalid or has expired.",
+    "toLogin": "Go to sign in"
+  },
+  "reset": {
+    "requestTitle": "Reset your password",
+    "email": "Email",
+    "requestSubmit": "Send reset link",
+    "requestDone": "If that email has an account, a reset link is on its way.",
+    "confirmTitle": "Choose a new password",
+    "newPassword": "New password",
+    "confirmSubmit": "Set password",
+    "ok": "Password updated. You can now sign in."
+  },
+  "dashboard": {
+    "title": "Account",
+    "balance": "Allocation",
+    "total": "Total",
+    "spent": "Spent",
+    "reserved": "Reserved",
+    "remaining": "Remaining",
+    "manageKeys": "Manage API keys",
+    "redeemTitle": "Redeem a top-up code",
+    "redeemPlaceholder": "helexa-topup-…",
+    "redeem": "Redeem",
+    "redeemed": "Code redeemed.",
+    "logout": "Sign out"
+  },
+  "keys": {
+    "title": "API keys",
+    "create": "Create key",
+    "label": "Label",
+    "limitKind": "Limit",
+    "percent": "% of allocation",
+    "hardcap": "Hard cap (tokens)",
+    "value": "Value",
+    "none": "No keys yet.",
+    "createdTitle": "Your new API key",
+    "createdWarn": "Copy it now — you won't see it again.",
+    "copy": "Copy",
+    "copied": "Copied",
+    "archive": "Archive",
+    "save": "Save",
+    "status": "Status",
+    "usage": "Used",
+    "useForChat": "Use for chat on this device",
+    "usedForChat": "Enabled for chat ✓"
+  },
+  "error": {
+    "generic": "Something went wrong.",
+    "unauthorized": "Please sign in again."
+  }
+}

helexa.ai/src/i18n/resources/ar/chat.json

@@ -0,0 +1,21 @@
+{
+  "title": "مساحة محادثة",
+  "badge": "محادثة",
+  "lead": "هذه هي واجهة المحادثة. قم بتوصيل منطق الحوار الخاص بك ومكوّنات واجهة المستخدم بهذه الصفحة.",
+  "transcriptPlaceholder": "سجل المحادثة سيظهر هنا. اعرض رسائل النموذج والمستخدم في حاوية قابلة للتمرير، ويمكنك تجميعها حسب أدوار الحوار إذا رغبت.",
+  "inputPlaceholder": "اكتب رسالة لبدء المحادثة…",
+  "send": "إرسال",
+  "clear": "مسح",
+  "newChat": "New chat",
+  "newProject": "New project",
+  "newProjectName": "New project",
+  "unsorted": "Unsorted",
+  "emptyState": "Start a conversation. Your history stays in this browser.",
+  "anonBanner": "You have reached the anonymous limit. Sign up for a free allocation.",
+  "signUp": "Sign up",
+  "stop": "Stop",
+  "topUp": "Top up",
+  "rateLimited": "Rate limited — wait a moment and retry.",
+  "needsKey": "Create an API key and enable it for chat to send as yourself.",
+  "manageKeysLink": "Manage keys"
+}

helexa.ai/src/i18n/resources/ar/common.json

@@ -0,0 +1,68 @@
+{
+  "app": {
+    "name": "helexa.ai"
+  },
+  "nav": {
+    "home": "الصفحة الرئيسية",
+    "docs": "التوثيق",
+    "chat": "المحادثة",
+    "mission": "Mission",
+    "login": "Sign in",
+    "register": "Sign up",
+    "account": "Account",
+    "logout": "Sign out"
+  },
+  "theme": {
+    "toggle": {
+      "toLight": "التبديل إلى الوضع الفاتح",
+      "toDark": "التبديل إلى الوضع الداكن"
+    }
+  },
+  "lang": {
+    "bg": "البلغارية",
+    "de": "الألمانية",
+    "el": "اليونانية",
+    "en": "الإنجليزية",
+    "es": "الإسبانية",
+    "et": "الإستونية",
+    "fr": "الفرنسية",
+    "he": "العبرية",
+    "it": "الإيطالية",
+    "nl": "الهولندية",
+    "da": "الدنماركية",
+    "fi": "الفنلندية",
+    "ar": "العربية",
+    "fa": "الفارسية",
+    "sw": "السواحيلية",
+    "ha": "الهوسا",
+    "am": "الأمهرية",
+    "yo": "اليوربا",
+    "zu": "الزولو",
+    "ma": "الدارجة المغربية",
+    "ig": "الإيجبو",
+    "ka": "الجورجية",
+    "kk": "الكازاخية",
+    "no": "النرويجية",
+    "om": "الأورومو",
+    "so": "الصومالية",
+    "sv": "السويدية",
+    "ti": "التيغرينية",
+    "uz": "الأوزبكية",
+    "wo": "الولوف",
+    "pl": "البولندية",
+    "pt": "البرتغالية",
+    "ro": "الرومانية",
+    "ru": "الروسية",
+    "sr": "الصربية",
+    "tr": "التركية",
+    "uk": "الأوكرانية"
+  },
+  "footer": {
+    "copyright": "© {{year}} helexa.ai"
+  },
+  "beta": {
+    "tag": "Public beta",
+    "message": "helexa is in open beta — expect rough edges. Your chats stay in your browser.",
+    "dismiss": "Dismiss"
+  }
+}

helexa.ai/src/i18n/resources/ar/mission.json

@@ -0,0 +1,103 @@
+{
+  "hero": {
+    "badge": "شكل جديد من الذكاء",
+    "title": "شكل جديد من الذكاء",
+    "lead": "هيليكسـا هي شبكة ذكاء اصطناعي ذاتية التنظيم، يشغّلها مشغّلون مستقلون. مفتوحة. موزعة. تتطور باستمرار.",
+    "ctaJoinMesh": "انضم إلى الشبكة",
+    "ctaFollowProject": "تابع المشروع",
+    "subcopy": "صُممت للمشغّلين والبنّائين والمجتمعات التي تؤمن بأن الذكاء الاصطناعي يجب أن يكون مفتوحًا، مرنًا، ومشتركًا.",
+    "imageAlt": "تصور حلزوني لشكل Helexa"
+  },
+
+  "intent": {
+    "title": "لماذا وُجدت Helexa",
+    "p1": "الذكاء الاصطناعي يتحول إلى أقوى بنية تحتية على كوكب الأرض. لكن اليوم، هذه القوة مركّزة في أيدي عدد قليل من الشركات، تشكلها أولويات خاصة، وحدود جغرافية، واقتصادات هشة.",
+    "p2Intro": "هيليكسـا تتخيل شيئًا مختلفًا:",
+    "bullet1": "ذكاء ينمو من كل مكان، لا من نقطة واحدة.",
+    "bullet2": "شبكة يمكن للجميع فيها أن يساهموا ويستفيدوا.",
+    "bullet3": "نظام يتكيّف مع الطلب، لا مع الأوامر الفوقية.",
+    "bullet4": "تكنولوجيا تقوّي المجتمعات بدلًا من أن تستبدلها.",
+    "closing": "هيليكسـا ليست منصة. وليست سحابة.\nإنها شبكة — نسيج حيّ ومتطوّر من مشغّلين مستقلين يشكّلون نوعًا جديدًا من الذكاء."
+  },
+
+  "whyNow": {
+    "title": "نقطة تحوّل للذكاء الاصطناعي",
+    "problemTitle": "المشكلة",
+    "problemBullet1": "الذكاء الاصطناعي يتمركز أسرع من أي تكنولوجيا سبقته.",
+    "problemBullet2": "الوصول إلى القدرة الحاسوبية يحدد الإمكانات، وهذا الوصول يضيق باستمرار.",
+    "problemBullet3": "حواجز التكلفة تستبعد الباحثين والشركات الناشئة والمجتمعات.",
+    "problemBullet4": "الضغوط الجيوسياسية والتنظيمية تهدّد التوافر العالمي.",
+    "problemBullet5": "مُنشئو النماذج ومشغّلو العتاد نادرًا ما يشاركون في القيمة التي ينتجونها.",
+    "opportunityTitle": "الفرصة",
+    "opportunityIntro": "لكن عالمًا موزعًا ممكن.",
+    "opportunityBullet1": "آلاف وحدات الـGPU حول العالم تعمل بأقل من طاقتها.",
+    "opportunityBullet2": "المشغّلون يريدون تعويضًا عادلًا عن الحوسبة التي يقدّمونها.",
+    "opportunityBullet3": "المطورون يريدون بنية تحتية مفتوحة ومقاوِمة للرقابة.",
+    "opportunityBullet4": "المجتمعات تريد سيادة ومرونة في أنظمتها الرقمية.",
+    "opportunityBullet5": "نمو الذكاء الاصطناعي تجاوز البنى السحابية التقليدية — نحن بحاجة إلى أشكال جديدة.",
+    "opportunityClosing": "هيليكسـا هي لحظة تلاقي هذه القوى."
+  },
+
+  "howItWorks": {
+    "title": "كيف تتشكّل الشبكة",
+    "operators": {
+      "eyebrow": "المشغّلون يديرون العقد",
+      "title": "أي شخص يمكنه المساهمة بقوة حاسوبية.",
+      "body": "المشغّلون يشغّلون عُقد Helexa. يقررون أي النماذج يستضيفون. يبقون متحكمين في عتادهم واقتصادهم. لا موافقات، ولا حراس بوابة."
+    },
+    "routing": {
+      "eyebrow": "الشبكة توجّه الذكاء",
+      "title": "الطلب يتدفق عبر الشبكة.",
+      "body": "هيليكسـا تتعلم أين توجد السعة، وأين يرتفع الطلب، وأي العقد أنسب لخدمة الطلبات. الشبكة تتكيّف بشكل عضوي — مثل حلزون ينمو."
+    },
+    "value": {
+      "eyebrow": "القيمة تعود إلى المصدر",
+      "title": "العمل مُثبت. والدفع عادل.",
+      "body": "كل مهمة تحمل إيصالًا تشفيريًا. يكسب المشغّلون مقابل الذكاء الذي يساعدون في توفيره. لا ضرائب منصة. لا فواتير غامضة."
+    }
+  },
+
+  "principles": {
+    "title": "مبنية على مبادئ، لا على منصات",
+    "distributed": {
+      "title": "موزعة بالتصميم",
+      "body": "لا توجد نقطة فشل واحدة. لا توجد سلطة مركزية. شبكة تقوى مع كل مشغّل جديد."
+    },
+    "participation": {
+      "title": "مشاركة مفتوحة",
+      "body": "إذا كان لديك قدرة حاسوبية، يمكنك المساهمة. الشبكة ترحّب بالجميع — من الحافة، إلى الخوادم المنزلية، إلى مراكز البيانات."
+    },
+    "fairness": {
+      "title": "العدالة والشفافية",
+      "body": "الأرباح مبنية على عمل حقيقي، مُثبت تشفيريًا. لا صناديق سوداء. لا رسوم خفية."
+    },
+    "evolving": {
+      "title": "ذكاء يتطور باستمرار",
+      "body": "الشبكة تتعلم من الطلب. تُحمَّل النماذج حيث تكون مطلوبة. الذكاء ينتشر من خلال التعاون."
+    }
+  },
+
+  "roadAhead": {
+    "title": "إلى ماذا تطمح Helexa أن تصبح",
+    "p1": "طبقة ذكاء عالمية تنتمي للجميع، مدفوعة بحلزونة من العقد والمجتمعات.",
+    "p2": "شبكة مقاومة للانقطاعات، والسياسة، والاحتكارات، والإخفاق.",
+    "p3": "نموذج اقتصادي جديد يستفيد منه المشغّلون والبنّاؤون والمستخدمون جميعًا.",
+    "p4": "نظام بيئي تنمو فيه الابتكارات من الأطراف — لا من المركز.",
+    "card": {
+      "eyebrow": "لمحة عن الرؤية",
+      "title": "نحو شبكة ذكاء مشتركة",
+      "body": "هيليكسـا في مرحلة مبكرة. الأفكار أكبر من التنفيذ الحالي — وهذا مقصود. الشبكة ستنمو تدريجيًا، بينما يشكّل المشغّلون والبنّاؤون مسار تطورها."
+    }
+  },
+
+  "joinMesh": {
+    "badge": "مرحلة مبكرة",
+    "title": "الشبكة قيد التشكل.",
+    "titleHighlight": "ويمكنك أن تكون جزءًا منها.",
+    "lead": "سواءً كنت تدير عتادًا، تبني نماذج، أو يهمّك ببساطة كيف يُدار الذكاء الاصطناعي — هناك مكان لك داخل الشبكة.",
+    "ctaRunNode": "تشغيل عقدة (قريبًا)",
+    "ctaJoinAnnouncements": "انضم إلى الإعلانات المبكرة",
+    "ctaExploreCode": "استكشف الشفرة",
+    "footer": "لا حدائق مسوّرة. لا مالك واحد. مجرد شبكة من أشخاص وعتاد وأفكار — تصوغ مستقبلًا مختلفًا للذكاء."
+  }
+}

helexa.ai/src/i18n/resources/bg/account.json

@@ -0,0 +1,71 @@
+{
+  "login": {
+    "title": "Sign in",
+    "email": "Email",
+    "password": "Password",
+    "submit": "Sign in",
+    "noAccount": "No account? Sign up"
+  },
+  "register": {
+    "title": "Create your account",
+    "email": "Email",
+    "password": "Password",
+    "submit": "Sign up",
+    "haveAccount": "Already have an account? Sign in",
+    "checkEmail": "Almost there — check your email to verify your account."
+  },
+  "verify": {
+    "verifying": "Verifying…",
+    "ok": "Email verified. You can now sign in.",
+    "failed": "This verification link is invalid or has expired.",
+    "toLogin": "Go to sign in"
+  },
+  "reset": {
+    "requestTitle": "Reset your password",
+    "email": "Email",
+    "requestSubmit": "Send reset link",
+    "requestDone": "If that email has an account, a reset link is on its way.",
+    "confirmTitle": "Choose a new password",
+    "newPassword": "New password",
+    "confirmSubmit": "Set password",
+    "ok": "Password updated. You can now sign in."
+  },
+  "dashboard": {
+    "title": "Account",
+    "balance": "Allocation",
+    "total": "Total",
+    "spent": "Spent",
+    "reserved": "Reserved",
+    "remaining": "Remaining",
+    "manageKeys": "Manage API keys",
+    "redeemTitle": "Redeem a top-up code",
+    "redeemPlaceholder": "helexa-topup-…",
+    "redeem": "Redeem",
+    "redeemed": "Code redeemed.",
+    "logout": "Sign out"
+  },
+  "keys": {
+    "title": "API keys",
+    "create": "Create key",
+    "label": "Label",
+    "limitKind": "Limit",
+    "percent": "% of allocation",
+    "hardcap": "Hard cap (tokens)",
+    "value": "Value",
+    "none": "No keys yet.",
+    "createdTitle": "Your new API key",
+    "createdWarn": "Copy it now — you won't see it again.",
+    "copy": "Copy",
+    "copied": "Copied",
+    "archive": "Archive",
+    "save": "Save",
+    "status": "Status",
+    "usage": "Used",
+    "useForChat": "Use for chat on this device",
+    "usedForChat": "Enabled for chat ✓"
+  },
+  "error": {
+    "generic": "Something went wrong.",
+    "unauthorized": "Please sign in again."
+  }
+}

helexa.ai/src/i18n/resources/bg/chat.json

@@ -0,0 +1,21 @@
+{
+  "title": "Работно пространство за разговори",
+  "badge": "Чат",
+  "lead": "Това е изгледът за чат. Тук можеш да свържеш своята логика за разговори и потребителски интерфейс.",
+  "transcriptPlaceholder": "Тук ще се показва историята на чата. Визуализирай съобщенията от модела и потребителя в превъртащ се контейнер, по желание групирани по ход.",
+  "inputPlaceholder": "Напиши съобщение, за да започнеш разговора…",
+  "send": "Изпрати",
+  "clear": "Изчисти",
+  "newChat": "New chat",
+  "newProject": "New project",
+  "newProjectName": "New project",
+  "unsorted": "Unsorted",
+  "emptyState": "Start a conversation. Your history stays in this browser.",
+  "anonBanner": "You have reached the anonymous limit. Sign up for a free allocation.",
+  "signUp": "Sign up",
+  "stop": "Stop",
+  "topUp": "Top up",
+  "rateLimited": "Rate limited — wait a moment and retry.",
+  "needsKey": "Create an API key and enable it for chat to send as yourself.",
+  "manageKeysLink": "Manage keys"
+}