Merge branch 'master' of https://git.d-popov.com/popov/neuron-tai

Co-authored-by: Cursor <cursoragent@cursor.com>

.claude/memory/alpha-hardening-navigation.md

@@ -30,3 +30,7 @@ Both are already migrated into `.scratch/alpha-hardening/prd.json` (AH-021 updat
 
 **Why:** three audits agreed the alpha blockers are unauthenticated gossip (anyone can inject billing events), the free-credit faucet, and ephemeral bans.
 **How to apply:** work test-first per issue acceptance criteria; use `.venv`; `cryptography` belongs in node deps (wallet.py imports it — causes many of the 24 "failures" in a fresh env). See [[project-status]] and [[autonomous-work-style]].
+
+## Routing telemetry resume (2026-07-07)
+
+`.scratch/alpha-hardening/issues/24-routing-telemetry-resume.md` / AH-024 captures the interrupted Claude handoff. Learned routing is already committed at `518c259`; the dirty tree contains live-progress/current-request heartbeat/dashboard telemetry. First known blocker: `packages/tracker/meshnet_tracker/server.py:1490` uses `threading.Lock | None`, which crashes import because `threading.Lock` is a factory function at runtime. Fix that before running the targeted telemetry tests. Keep `.claude/settings.local.json` uncommitted unless explicitly approved.

.claude/memory/project-status.md

@@ -42,7 +42,8 @@ Historical handoff note: `/mnt/c/Users/popov/Downloads/neuron-tai-alpha-handoff-
 - Verification: downloader/startup targeted subset passes (`pytest tests/test_node_startup.py -k "download_shard or same_shard"`). Full `tests/test_node_startup.py` has 46 passed and 4 unrelated Windows chmod/path separator failures.
 - Live Windows confirmation: `meshnet-node start --tracker http://192.168.0.179:8080 --model Qwen3.6-35B-A3B` reuses `F:\_STORAGE\models\qwen3.6-35b-a3b`, prints `Cached at`, registers, and reaches ready as node `5gMLrmyB-26b1f8a4204a`.
 - Follow-up fix: preset-model startup now starts the heartbeat thread after registration; without this, the node appeared briefly on the dashboard and was purged on first inference/route after heartbeat expiry. Tracker dashboard now has a "Console output" panel backed by `/v1/console` for node register/expiry, routing failures, and proxy events.
-- Qwen3.6-35B-A3B reserve-based split is expected: an 79 GB CPU node may be assigned layers 0-36, and a second node fills 37-39. Do not "fix" this by bypassing the 20% assignment reserve unless the shard-planning policy changes.
+- Qwen3.6-35B-A3B CPU runtime cap (2026-07-08): the old reserve-based split could assign an 79 GB CPU node layers 0-36, but real partial loading can exceed that budget and die without a Python traceback. Node startup now clips oversized CPU auto-assignments before loading, and tracker CPU assignment uses a stricter runtime headroom factor; do not revert this to the old 20% reserve-only policy.
 - Route hardening: tracker chat proxy and `/v1/route` diagnostics now use alias-aware preset node matching for split Qwen3.6 routes; dashboard derives grouped inference history from proxy route/complete console events and shows observed TPS after completion.
 - Live proxy hardening: model lookup trims outer whitespace before alias matching (`qwen3.6-35b-a3b ` resolves), and tracker route logs/dashboard queue depth combine heartbeat queue with tracker-local proxy in-flight counts so Postman-style bursts no longer show every selected route as queue `0`.
 - Split-shard streaming hardening: Qwen3.6-style distributed generation now emits SSE chunks token-by-token from the head node instead of buffering all generated text until completion. Tracker direct/relay stream proxy logs `proxy progress` with live tokens/TPS, dashboard Inference history shows currently processing requests with live TPS/tokens/queue, and relay stream completion no longer references an undefined `session_id`.
+- Native Windows Qwen3.6-MoE import fix: `flash-linear-attention` imports `triton`; without `triton-windows`, startup fails with misleading `Could not import module 'Qwen3_5MoeForCausalLM'`. Installed `triton-windows` in `C:\Users\popov\miniforge3` and added it as a Windows-only node dependency.

.gitattributes

@@ -0,0 +1,28 @@
+# Normalize line endings across Windows/Linux checkouts.
+# All text files are stored as LF in the repo and checked out as LF
+# on every OS. Git auto-detects text vs binary.
+* text=auto eol=lf
+
+# Explicitly binary — never touch these bytes.
+*.png binary
+*.jpg binary
+*.jpeg binary
+*.gif binary
+*.ico binary
+*.pdf binary
+*.zip binary
+*.gz binary
+*.tar binary
+*.wasm binary
+*.sqlite binary
+*.sqlite3 binary
+*.safetensors binary
+*.gguf binary
+
+# Scripts that must stay LF even if someone forces CRLF locally.
+*.sh text eol=lf
+*.py text eol=lf
+
+# Windows batch files genuinely need CRLF.
+*.bat text eol=crlf
+*.cmd text eol=crlf

.gitignore

@@ -18,5 +18,11 @@ dist/
 !.env.example
 !.env.testnet
 .rocm-local/*
-billing.sqlite
+.pytest-tmp/*
-.pytest-tmp/*
+
+# Local tracker/node sqlite databases (never commit runtime state)
+*.sqlite
+*.sqlite3
+logs/tracker/error.log
+logs/tracker/info.log
+logs/tracker/warning.log

.scratch/alpha-hardening/README.md

@@ -9,6 +9,8 @@ Pre-release alpha audit + grilling (2026-07-04). Bucket 1 trust-boundary blocker
 
 Locked scope: one settlement tracker, open node join, devnet mock-USDT, reputation carries forward → fraud must be bounded. See [ADR-0016](../../docs/adr/0016-alpha-scope-and-known-limitations.md).
 
+**Resume task (2026-07-07):** [24 - Routing telemetry resume](./issues/24-routing-telemetry-resume.md) is `ready-for-agent`. Learned-routing commit `518c259` is already present; dirty tree contains current-request heartbeat/dashboard telemetry and a known import-time annotation crash in `server.py:1490`.
+
 ## Artifacts
 
 | Path | Status |

.scratch/alpha-hardening/issues/24-routing-telemetry-resume.md

@@ -0,0 +1,92 @@
+Status: ready-for-agent
+
+Scoped 2026-07-07 from an interrupted Claude session. This is a resume/cleanup task for routing and live-progress work that is partly committed and partly left dirty in the working tree.
+
+# 24 - Finish learned-routing telemetry and live-progress cleanup
+
+## Current state
+
+The main dynamic routing feature is already committed at `518c259` (`routing improvements - dynamic (wip)`):
+
+- `packages/tracker/meshnet_tracker/routing_stats.py` - decayed-EWMA route stats store, epsilon-greedy route selection, diagnostics.
+- `packages/tracker/meshnet_tracker/server.py` - route enumeration per head, bandit selection in the chat proxy, epoch bumps on node join/leave, `/v1/routing`, route sample recording with 8-token hygiene.
+- `packages/tracker/meshnet_tracker/cli.py` - `--route-explore-share`, `--route-weight-alpha`, `--route-stats-half-life` and env vars.
+- `packages/tracker/meshnet_tracker/dashboard.html` - "Routing (learned)" panel.
+- `docs/adr/0021-dynamic-statistical-routing.md` - design record.
+- `tests/test_dynamic_routing.py` - includes the exact GPU(0-21)+CPU(0-39) topology, hybrid downstream `start_layer=22`, 0.6/0.4 traffic split for a 1.5 TPS ratio, and scout-rate behavior.
+
+The current working tree still has uncommitted follow-up work:
+
+- `packages/node/meshnet_node/torch_server.py` - tracks in-flight chat requests, exposes `TorchNodeServer.current_requests`, prints generation progress with TPS.
+- `packages/node/meshnet_node/startup.py` - sends `current_requests` in heartbeat payloads and increases heartbeat cadence while busy.
+- `packages/tracker/meshnet_tracker/server.py` - accepts heartbeat `current_requests`, includes them in `/v1/network/map`, and logs `proxy connecting` before upstream connection.
+- `packages/tracker/meshnet_tracker/dashboard.html` - enriches the call wall from heartbeat `current_requests` so active requests remain visible even before terminal proxy events.
+- `tests/test_real_model_backend.py` and `tests/test_tracker_routing.py` - targeted coverage for current-request snapshots, heartbeat sanitization/storage, and TPS progress logging.
+- `QUICKSTART.md` - documents optional linear-attention fast-path packages for Qwen3.5/3.6 GPU nodes.
+
+There is also an untracked local file, `.claude/settings.local.json`, which should not be included unless the owner explicitly wants local Claude settings committed.
+
+## Known blocker found during resume
+
+Targeted pytest currently fails during import before reaching the new tests:
+
+```text
+TypeError: unsupported operand type(s) for |: 'builtin_function_or_method' and 'NoneType'
+```
+
+Immediate cause: `packages/tracker/meshnet_tracker/server.py:1490` annotates `ws_lock: threading.Lock | None = None`. `threading.Lock` is a factory function at runtime, not a type, so `| None` evaluates eagerly and crashes. This exists on `HEAD` too, not just in the dirty telemetry changes.
+
+Fix options:
+
+- Add `from __future__ import annotations` at the top of `server.py`, then run enough tests to catch any annotation side effects.
+- Or change that annotation to a safe runtime type such as `Any | None` / remove the union annotation. Keep the change minimal.
+
+## What to do next
+
+1. Fix the import-time `threading.Lock | None` crash.
+2. Re-run the targeted tests:
+
+   ```bash
+   .\.venv\Scripts\python.exe -m pytest tests/test_tracker_routing.py::test_tracker_heartbeat_stores_current_requests tests/test_tracker_routing.py::test_normalize_current_requests_sanitizes_payload tests/test_real_model_backend.py::test_current_requests_snapshot_while_generating tests/test_real_model_backend.py::test_distributed_generating_log_includes_tps -q
+   ```
+
+3. Run the relevant routing regression tests:
+
+   ```bash
+   .\.venv\Scripts\python.exe -m pytest tests/test_dynamic_routing.py tests/test_tracker_routing.py -q
+   ```
+
+4. If practical, run the non-integration suite:
+
+   ```bash
+   .\.venv\Scripts\python.exe -m pytest tests/ -q -m "not integration"
+   ```
+
+5. Confirm or document the pre-existing failure from the interrupted session: `test_proxy_chat_splits_payout_by_tracker_assigned_route_span` reportedly failed on `HEAD` too and was unrelated.
+6. Commit the intentional work in two commits if it remains naturally split:
+   - learned routing is already committed in `518c259`; leave it alone unless fixing regressions there.
+   - commit the live-progress/current-request telemetry cleanup separately after tests pass.
+
+## Acceptance criteria
+
+- [ ] Importing `meshnet_tracker.server` no longer crashes on the lock annotation.
+- [ ] Current-request heartbeat payloads are sanitized and surfaced in `/v1/network/map`.
+- [ ] Node-side in-flight chat snapshots report request id, model, token count, elapsed seconds, tokens/sec, and routing completion.
+- [ ] Dashboard call wall can show active requests from heartbeat data, not only tracker console terminal events.
+- [ ] Targeted telemetry tests pass.
+- [ ] Dynamic routing tests still pass, including GPU(0-21)+CPU(0-39) hybrid-route enumeration and traffic split behavior.
+- [ ] Full or non-integration suite result is recorded; unrelated pre-existing failures are named explicitly.
+- [ ] `.claude/settings.local.json` remains uncommitted unless intentionally approved.
+
+## ADR links
+
+- [ADR-0020](../../docs/adr/0020-chat-streaming-live-progress-and-mixed-topology-routing.md)
+- [ADR-0021](../../docs/adr/0021-dynamic-statistical-routing.md)
+
+## Blocked by
+
+None. The import-time annotation crash is the first fix.
+
+## Blocks
+
+Clean handoff/commit of the interrupted live routing progress work.

.scratch/alpha-hardening/prd.json

@@ -483,9 +483,29 @@
       "notes": "Source issue: .scratch/alpha-hardening/issues/23-dynamic-hf-pricing.md. High priority, ship-soon for launch, NOT an alpha-release blocker (unlike AH-021).",
       "dependsOn": [],
       "completionNotes": "Completed by agent"
+    },
+    {
+      "id": "AH-024",
+      "title": "24 - Finish learned-routing telemetry and live-progress cleanup",
+      "description": "Status: ready-for-agent\n\nScoped 2026-07-07 from an interrupted Claude session. The learned-routing feature is already committed at 518c259 (`routing improvements - dynamic (wip)`): routing_stats.py, tracker route enumeration and bandit selection, CLI routing flags, `/v1/routing`, dashboard Routing (learned), ADR-0021, and tests/test_dynamic_routing.py including the GPU(0-21)+CPU(0-39) hybrid topology. The dirty working tree contains follow-up live-progress/current-request telemetry in torch_server.py, startup.py, tracker server/dashboard, tests, and QUICKSTART. Known blocker found during resume: importing meshnet_tracker.server currently crashes at `server.py:1490` because `ws_lock: threading.Lock | None = None` evaluates `threading.Lock` as a factory function, not a type. Fix that first, then verify and commit the telemetry cleanup separately from the already-committed dynamic-routing work. Leave `.claude/settings.local.json` uncommitted unless explicitly approved.\n\nSource issue has exact file list, commands, and the reported pre-existing unrelated failure (`test_proxy_chat_splits_payout_by_tracker_assigned_route_span`).",
+      "acceptanceCriteria": [
+        "Importing `meshnet_tracker.server` no longer crashes on the lock annotation",
+        "Current-request heartbeat payloads are sanitized and surfaced in `/v1/network/map`",
+        "Node-side in-flight chat snapshots report request id, model, token count, elapsed seconds, tokens/sec, and routing completion",
+        "Dashboard call wall can show active requests from heartbeat data, not only tracker console terminal events",
+        "Targeted telemetry tests pass",
+        "Dynamic routing tests still pass, including GPU(0-21)+CPU(0-39) hybrid-route enumeration and traffic split behavior",
+        "Full or non-integration suite result is recorded; unrelated pre-existing failures are named explicitly",
+        "`.claude/settings.local.json` remains uncommitted unless intentionally approved"
+      ],
+      "priority": 24,
+      "passes": true,
+      "notes": "Source issue: .scratch/alpha-hardening/issues/24-routing-telemetry-resume.md. Resume task for interrupted 2026-07-07 Claude session; first known fix is server.py:1490 annotation crash.",
+      "dependsOn": [],
+      "completionNotes": ""
     }
   ],
   "metadata": {
-    "updatedAt": "2026-07-06T06:01:25.474Z"
+    "updatedAt": "2026-07-07T21:30:00.000Z"
   }
-}
+}

CONTEXT.md

@@ -1,23 +1,23 @@
-# Distributed Inference Network
+# Distributed Inference Network
-
+
-A volunteer GPU network where nodes independently load model shards, a tracker routes inference through optimal node chains, and contributors earn tokens for serving compute.
+A volunteer GPU network where nodes independently load model shards, a tracker routes inference through optimal node chains, and contributors earn tokens for serving compute.
-
+
-## Language
+## Language
-
+
-### Nodes & compute
+### Nodes & compute
-
+
-**Node**:
+**Node**:
-A volunteer machine that runs the node client, holds one or more shards on disk, and serves inference requests for those shards.
+A volunteer machine that runs the node client, holds one or more shards on disk, and serves inference requests for those shards.
-_Avoid_: worker, peer, miner, server
+_Avoid_: worker, peer, miner, server
-
+
-**Shard**:
+**Shard**:
-A contiguous range of transformer layers from a model that a node loads and serves. Shards are the unit of storage, assignment, and reward.
+A contiguous range of transformer layers from a model that a node loads and serves. Shards are the unit of storage, assignment, and reward.
-_Avoid_: partition, slice, chunk, segment
+_Avoid_: partition, slice, chunk, segment
-
+
-**Shard Swarm**:
+**Shard Swarm**:
-The P2P group of nodes that collectively seed and download a specific shard. One swarm exists per shard.
+The P2P group of nodes that collectively seed and download a specific shard. One swarm exists per shard.
-_Avoid_: torrent, cluster, pool
+_Avoid_: torrent, cluster, pool
-
+
 **Inference Route**:
 An ordered sequence of nodes whose shards together cover all layers of a model. The tracker selects the optimal route per request.
 _Avoid_: pipeline, chain, path
@@ -55,115 +55,115 @@ Realtime progress information for an active Route Session, including phase, gene
 _Avoid_: logs, debug output
 
 ### Tracker
-
+
-**Tracker**:
+**Tracker**:
-The coordinator service that maintains the node registry, scores nodes by throughput/latency, and assigns inference routes. Runs as a centralized service with a P2P gossip fallback.
+The coordinator service that maintains the node registry, scores nodes by throughput/latency, and assigns inference routes. Runs as a centralized service with a P2P gossip fallback.
-_Avoid_: coordinator, scheduler, director
+_Avoid_: coordinator, scheduler, director
-
+
 **Tracker Node**:
 A node that serves at least the first-layer shard (`layers[0..k]`) for a model and acts as the inference entry point for that model. Tracker nodes own the tokenizer and `embed_tokens`, receive client requests directly, select the onward route from the coverage map, and stream results and progress when possible. Any node advertising a new model to the network becomes its tracker node.
 _Avoid_: primary node, master node, gateway node
-
+
-**Coverage Map**:
+**Coverage Map**:
-The tracker's per-model mapping of layer ranges to node counts: `[(start_layer, end_layer, node_count), ...]`. A layer range with `node_count=0` is a coverage gap — the model is unroutable until the gap is filled. Coverage-first bin-packing fills all gaps before adding redundancy.
+The tracker's per-model mapping of layer ranges to node counts: `[(start_layer, end_layer, node_count), ...]`. A layer range with `node_count=0` is a coverage gap — the model is unroutable until the gap is filled. Coverage-first bin-packing fills all gaps before adding redundancy.
-_Avoid_: shard map, assignment table, coverage report
+_Avoid_: shard map, assignment table, coverage report
-
+
-**Rebalance Directive**:
+**Rebalance Directive**:
-A `LOAD_SHARD` or `DROP_SHARD` instruction the tracker issues to a node when the coverage map changes (node joins, node leaves, or load-balance reoptimization). Delivered as part of the node's heartbeat response.
+A `LOAD_SHARD` or `DROP_SHARD` instruction the tracker issues to a node when the coverage map changes (node joins, node leaves, or load-balance reoptimization). Delivered as part of the node's heartbeat response.
-_Avoid_: rebalance command, shard instruction, migration order
+_Avoid_: rebalance command, shard instruction, migration order
-
+
-**Node Score**:
+**Node Score**:
-A throughput/latency rating the tracker maintains per node, used for route selection. Updated continuously from inference telemetry.
+A throughput/latency rating the tracker maintains per node, used for route selection. Updated continuously from inference telemetry.
-_Avoid_: reputation, rating, rank
+_Avoid_: reputation, rating, rank
-
+
-### Payments & fraud
+### Payments & fraud
-
+
-**Stake**:
+**Stake**:
-Collateral a node stands to lose for fraud. In the current design the node's Pending Balance serves as stake — no upfront deposit is required. An optional USDT/TAI deposit may return later for routing priority.
+Collateral a node stands to lose for fraud. In the current design the node's Pending Balance serves as stake — no upfront deposit is required. An optional USDT/TAI deposit may return later for routing priority.
-_Avoid_: deposit, bond, escrow
+_Avoid_: deposit, bond, escrow
-
+
-**Treasury**:
+**Treasury**:
-The single project-owned Solana wallet that custodially holds client deposits, pays node payouts, and accumulates the Protocol Cut. Its keypair is loaded only on settlement-capable trackers.
+The single project-owned Solana wallet that custodially holds client deposits, pays node payouts, and accumulates the Protocol Cut. Its keypair is loaded only on settlement-capable trackers.
-_Avoid_: escrow, vault, hot wallet
+_Avoid_: escrow, vault, hot wallet
-
+
-**Pending Balance**:
+**Pending Balance**:
-A node's accrued, not-yet-paid USDT earnings on the tracker ledger. Doubles as the node's fraud collateral: it is forfeited in full when a validator catches a divergent output.
+A node's accrued, not-yet-paid USDT earnings on the tracker ledger. Doubles as the node's fraud collateral: it is forfeited in full when a validator catches a divergent output.
-_Avoid_: unpaid rewards, accrual, balance due
+_Avoid_: unpaid rewards, accrual, balance due
-
+
-**Settlement Period**:
+**Settlement Period**:
-The dynamic interval driving on-chain payouts: a node is paid when its Pending Balance exceeds the Payout Threshold or the period elapses, whichever comes first. Short in development (seconds), long in production (daily), configurable to grow with volume.
+The dynamic interval driving on-chain payouts: a node is paid when its Pending Balance exceeds the Payout Threshold or the period elapses, whichever comes first. Short in development (seconds), long in production (daily), configurable to grow with volume.
-_Avoid_: epoch, payout cycle, billing cycle
+_Avoid_: epoch, payout cycle, billing cycle
-
+
-**Payout Threshold**:
+**Payout Threshold**:
-The minimum Pending Balance that triggers an immediate payout before the Settlement Period elapses. Includes a dust floor so payouts are never smaller than they are worth.
+The minimum Pending Balance that triggers an immediate payout before the Settlement Period elapses. Includes a dust floor so payouts are never smaller than they are worth.
-_Avoid_: minimum payout, dust limit
+_Avoid_: minimum payout, dust limit
-
+
-**Protocol Cut**:
+**Protocol Cut**:
-The 10% of inference fees retained by the project for infrastructure; the remaining 90% goes to the nodes that served the request. Accumulates in the Treasury as the future TAI liquidity reserve.
+The 10% of inference fees retained by the project for infrastructure; the remaining 90% goes to the nodes that served the request. Accumulates in the Treasury as the future TAI liquidity reserve.
-_Avoid_: spread, commission, house fee
+_Avoid_: spread, commission, house fee
-
+
-**Deposit Watcher**:
+**Deposit Watcher**:
-The tracker component that observes the Treasury's on-chain USDT deposits and credits the sending client's API-key ledger balance.
+The tracker component that observes the Treasury's on-chain USDT deposits and credits the sending client's API-key ledger balance.
-_Avoid_: payment listener, chain scanner
+_Avoid_: payment listener, chain scanner
-
+
-**Mock USDT**:
+**Mock USDT**:
-The self-created 6-decimal SPL mint that stands in for USDT on devnet, where real USDT does not exist. The mint address is configuration, so mainnet cutover is a config change.
+The self-created 6-decimal SPL mint that stands in for USDT on devnet, where real USDT does not exist. The mint address is configuration, so mainnet cutover is a config change.
-_Avoid_: test token, fake USDT, devnet dollar
+_Avoid_: test token, fake USDT, devnet dollar
-
+
-**Tax**:
+**Tax**:
-The share of caller payments distributed to compute nodes as rewards. Taxes are weighted by completed work and historical node speed so faster, larger nodes earn proportionally more.
+The share of caller payments distributed to compute nodes as rewards. Taxes are weighted by completed work and historical node speed so faster, larger nodes earn proportionally more.
-_Avoid_: fee, toll, commission
+_Avoid_: fee, toll, commission
-
+
-**Caller Credit**:
+**Caller Credit**:
-Free starting balance granted to a new caller/API key so they can try the network before topping up.
+Free starting balance granted to a new caller/API key so they can try the network before topping up.
-_Avoid_: signup bonus, faucet, airdrop
+_Avoid_: signup bonus, faucet, airdrop
-
+
-**Free Compute Job**:
+**Free Compute Job**:
-Work a compute node performs without earning immediate rewards, usually during probation or bootstrap phases.
+Work a compute node performs without earning immediate rewards, usually during probation or bootstrap phases.
-_Avoid_: unpaid labor, warmup request
+_Avoid_: unpaid labor, warmup request
-
+
-**Slash**:
+**Slash**:
-The penalty for a proven fraud incident: the node's entire Pending Balance is forfeited to the Treasury and a Strike is recorded.
+The penalty for a proven fraud incident: the node's entire Pending Balance is forfeited to the Treasury and a Strike is recorded.
-_Avoid_: penalize, burn, fine, forfeit
+_Avoid_: penalize, burn, fine, forfeit
-
+
-**Strike**:
+**Strike**:
-A fraud incident recorded on-chain against a node. Enough strikes result in a ban.
+A fraud incident recorded on-chain against a node. Enough strikes result in a ban.
-_Avoid_: infraction, violation, flag
+_Avoid_: infraction, violation, flag
-
+
-**Ban**:
+**Ban**:
-Permanent exclusion of a wallet from the network after exceeding the strike threshold. Recorded on-chain.
+Permanent exclusion of a wallet from the network after exceeding the strike threshold. Recorded on-chain.
-_Avoid_: blacklist, block, suspension
+_Avoid_: blacklist, block, suspension
-
+
-**Probationary Period**:
+**Probationary Period**:
-The first N jobs a new wallet must complete without earning, to raise the cost of re-entering after a ban.
+The first N jobs a new wallet must complete without earning, to raise the cost of re-entering after a ban.
-_Avoid_: trial period, warmup, grace period
+_Avoid_: trial period, warmup, grace period
-
+
-**Token**:
+**Token**:
-TAI, our native Solana SPL token. Deferred (ADR-0015): nodes are currently paid directly in USDT; TAI returns as the reward/upside layer once volume exists, funded by the accumulated Protocol Cut. Clients never need to hold it.
+TAI, our native Solana SPL token. Deferred (ADR-0015): nodes are currently paid directly in USDT; TAI returns as the reward/upside layer once volume exists, funded by the accumulated Protocol Cut. Clients never need to hold it.
-_Avoid_: coin, reward token, native token
+_Avoid_: coin, reward token, native token
-
+
-**Contract Boundary**:
+**Contract Boundary**:
-The Python interface in `packages/contracts` that represents registry, payment, and settlement behavior. During the prototype it is implemented by deterministic local wrappers; later the same boundary is backed by real Solana programs.
+The Python interface in `packages/contracts` that represents registry, payment, and settlement behavior. During the prototype it is implemented by deterministic local wrappers; later the same boundary is backed by real Solana programs.
-_Avoid_: mock contract, fake chain, temporary hack
+_Avoid_: mock contract, fake chain, temporary hack
-
+
-**Validator**:
+**Validator**:
-A trusted node (or the tracker itself) that re-runs a sample of inference requests to detect fraud.
+A trusted node (or the tracker itself) that re-runs a sample of inference requests to detect fraud.
-_Avoid_: auditor, checker, referee
+_Avoid_: auditor, checker, referee
-
+
-**Validation Event**:
+**Validation Event**:
-A completed inference record that contains enough information for a validator to decide whether to sample and re-run the request: session id, model preset, messages, inference route, node wallets, and observed output.
+A completed inference record that contains enough information for a validator to decide whether to sample and re-run the request: session id, model preset, messages, inference route, node wallets, and observed output.
-_Avoid_: audit log, trace, receipt
+_Avoid_: audit log, trace, receipt
-
+
-**Slash Proof**:
+**Slash Proof**:
-The record submitted by a validator when a sampled re-run diverges from the observed output beyond tolerance. In the prototype this is deterministic local contract state; later it maps to an on-chain proof transaction.
+The record submitted by a validator when a sampled re-run diverges from the observed output beyond tolerance. In the prototype this is deterministic local contract state; later it maps to an on-chain proof transaction.
-_Avoid_: accusation, report, claim
+_Avoid_: accusation, report, claim
-
+
-### Client-facing
+### Client-facing
-
+
-**Client**:
+**Client**:
-Any application or user that sends inference requests to the gateway. Prepays USDT into the Treasury; each request is metered against the resulting ledger balance at a per-1K-tokens price set per model.
+Any application or user that sends inference requests to the gateway. Prepays USDT into the Treasury; each request is metered against the resulting ledger balance at a per-1K-tokens price set per model.
-_Avoid_: user, caller, consumer
+_Avoid_: user, caller, consumer
-
+
-**Model Preset**:
+**Model Preset**:
-A named, versioned model available on the network (e.g. `llama-3-70b`). The tracker knows which nodes hold which shards for each preset.
+A named, versioned model available on the network (e.g. `llama-3-70b`). The tracker knows which nodes hold which shards for each preset.
-_Avoid_: model, checkpoint, version
+_Avoid_: model, checkpoint, version

docs/INSTALL_WINDOWS.md

@@ -103,8 +103,26 @@ Verify the install:
 
 ```bash
 meshnet-node --help
+python -c "import transformers; print(transformers.__version__)"
 ```
 
+`transformers` must be **≥ 5.12** for Qwen3.5/3.6-MoE models (older versions fail
+with `'Qwen3_5MoeConfig' object has no attribute 'vocab_size'`). If you install
+into an existing conda/miniforge env instead of a fresh venv, run
+`pip install -U transformers` there. The startup warning about
+`flash-linear-attention` / `causal-conv1d` ("fast path is not available") is
+harmless on CPU — those are optional CUDA-only kernels.
+
+If you run the node from native Windows instead of WSL2, install the Triton shim
+in the same environment:
+
+```powershell
+python -m pip install triton-windows
+```
+
+Without it, Qwen3.5/3.6-MoE startup can fail with the misleading message
+`Could not import module 'Qwen3_5MoeForCausalLM'`.
+
 ---
 
 ## Step 6 — Pre-download the model shard

docs/adr/0020-chat-streaming-live-progress-and-mixed-topology-routing.md

@@ -0,0 +1,127 @@
+# ADR-0020: Dashboard chat streaming, live request progress, and the mixed-topology routing flaw
+
+## Status: Accepted (chat/streaming/styles implemented); routing flaw documented, fix pending
+
+## Context
+
+Live alpha testing (2026-07-07) with `Qwen3.6-35B-A3B` split across two LAN nodes surfaced
+three UX gaps and one routing correctness flaw:
+
+1. **No visibility while a request is processing.** The Call wall showed
+   "no in-flight requests" during a 52-second generation. Cause: the dashboard chat sent
+   `stream: false`, and the tracker only emits `proxy progress` console events (the Call
+   wall's live-status source, `_tracker_log_proxy_progress`, `server.py` ~2199) for
+   **streamed** requests. Non-streamed proxying produces only
+   `route selected → connected → complete`, and short requests complete inside the
+   dashboard's 4-second poll window.
+2. **Chat did not stream.** The nodes support SSE token-by-token generation
+   (`generate_text_streaming`, hardened earlier for split shards), and the tracker proxy
+   passes `text/event-stream` through (`server.py` ~3256), but the chat panel blocked on
+   full JSON and showed nothing until completion.
+3. **Chat panel styles drifted.** The "new chat layout" redesign left hardcoded one-off
+   colors (`#1f4788`, `#2563b8`, `#10151d`, `#1a1012`, `#5c2020`, `#ffb4b4`) mixed with
+   the CSS custom-property palette.
+
+## Decisions
+
+### 1. Chat streams by default (SSE)
+
+`dashboard.html` `sendChat()` now sends `stream: true` and consumes the SSE body with a
+`ReadableStream` reader:
+
+- Assistant tokens render incrementally into the last bubble (direct DOM update, full
+  re-render only at boundaries), with a blinking `▍` cursor while streaming.
+- Chat status shows live progress: `generating… N tokens · X tok/s`.
+- The send button becomes a stop button (`■`) during generation, backed by an
+  `AbortController`; a stopped generation keeps the partial text.
+- Non-SSE responses (JSON fallback, errors) are still handled; `data: {"error": ...}`
+  stream events surface as error bubbles.
+- `streaming` flags are stripped when loading persisted sessions so an interrupted
+  generation never leaves a stuck cursor.
+
+### 2. Live in-flight visibility rides on streaming
+
+No tracker change was needed: because chat now streams, the tracker emits `proxy progress`
+events (throttled to stdout, updated in place in the console ring via
+`update_console_key`), and the existing Call wall state machine
+(`buildCallWallStates`) renders processing rows with live tokens/TPS/queue.
+
+**Known limitation (accepted):** non-streamed API requests still show no progress between
+`proxy connected` and `proxy complete` — there is nothing to report until the node
+returns. Callers wanting live visibility should use `stream: true`.
+
+### 3. Chat style tokens
+
+All chat colors route through `:root` custom properties (`--hover-bg`, `--chat-user-bg`
+`#1f6feb`, `--chat-user-border`, `--chat-error-bg/border/fg`). No hardcoded hex values
+remain in chat rules, so future palette changes are single-line edits.
+
+## Documented flaw: mixed-topology routing (partial GPU head + full CPU node)
+
+### Observed (2026-07-07, tracker 192.168.0.179:8080)
+
+Two nodes registered for `qwen3.6-35b-a3b`:
+
+| node | hardware | shard | benchmark |
+|---|---|---|---|
+| `5gMLrmyB-ec3afe6f1a03` (192.168.0.20) | RTX 4060, CUDA | 0–21 (partial, fast) | 11,164 |
+| `7j77FsPY-55249b0583e5` (192.168.0.179) | CPU | 0–39 (full, slow) | 425 |
+
+When the tracker selected the GPU node as head, it injected:
+
+```
+downstream=[{"endpoint": "http://192.168.0.179:7000", "start_layer": 0}]
+```
+
+`start_layer: 0` — not 22. The downstream full node re-ran **all 40 layers from layer 0
+on hidden states that had already passed through the head's layers 0–21**, producing
+garbage logits. Evidence from the logs:
+
+- GPU-headed requests: `generation complete tokens=1` and billed `out=0`/`out=1`/`out=3`
+  — near-instant EOS from corrupt activations.
+- The same prompt routed directly to the CPU full node: 209 tokens over 52 s (healthy).
+- Observed TPS for GPU-headed requests was meaningless (2.5–19.0 "tok/s" on 0–3 token
+  outputs), and those samples now pollute the rolling per-`(node, model)` throughput
+  stats used for routing preference.
+- Clients were **billed** for these broken 1-token responses.
+
+### Root cause
+
+The route planner treats the full-coverage node as a standalone complete route
+(`route=7j77FsPY…[0-39]`) but still injects it as the head's downstream with the
+downstream node's own `shard_start` (0) instead of `head.shard_end + 1` (22). A partial
+head + full-model downstream is a topology the planner never had to handle before —
+prior split tests used disjoint shards (0–11 + 12–23) where `shard_start` happened to
+equal the correct continuation layer.
+
+### Required fix (not yet implemented)
+
+1. **Correct continuation layer:** when hop N ends at layer `e`, hop N+1 must execute
+   from `start_layer = e + 1` regardless of the downstream node's own `shard_start`
+   (the `X-Meshnet-Start-Layer` overlapping-shard mechanism from ADR-0012 exists for
+   exactly this; the planner must set it for full-model downstream nodes too).
+2. **Route preference sanity:** with a healthy single-node full route available, prefer
+   it over a multi-hop route unless the pipeline is estimated faster; a fast head that
+   forces a slow full-model tail wins nothing (every token still crosses the CPU node).
+3. **Stat hygiene:** exclude or flag throughput samples from responses with ≤ a few
+   output tokens, so broken routes don't skew routing preference.
+4. **Billing guard (consider):** suspiciously short completions from multi-hop routes
+   during this window were billed; a minimum-viability check (or refund path) may be
+   warranted once audits land.
+
+### Verification for the fix
+
+Reproduce with a partial GPU head (0–21) + full CPU node (0–39): a chat request routed
+through the GPU head must produce output equivalent to the direct CPU route, with
+`downstream start_layer=22` visible in `proxy route selected`, and multi-token streamed
+output on the Call wall.
+
+## Verification of this ADR's implemented changes
+
+- `pytest tests/test_dashboard.py` — 5 passed (stale "Chat / inference" panel assertion
+  updated to the tabbed layout).
+- Embedded dashboard JS parses (`new Function(script)` under Node 22).
+- Live check: open `/dashboard` → Chat, send a prompt to `qwen3.6-35b-a3b` — tokens
+  must appear incrementally with live tok/s in the status line, the Call wall must show
+  the request as `processing` with live TPS, and the send button must stop generation
+  mid-stream keeping partial text.

docs/adr/0021-dynamic-statistical-routing.md

@@ -0,0 +1,119 @@
+# ADR-0021: Dynamic statistical routing (bandit-style route selection)
+
+## Status: Accepted, implemented
+
+## Context
+
+ADR-0020 documented the mixed-topology flaw: with a fast GPU node serving layers 0–21 and
+a slow CPU node serving 0–39 of `Qwen3.6-35B-A3B`, the tracker picked the GPU node as
+proxy head *independently* of route planning, injecting a downstream hop with the wrong
+`start_layer` (0 instead of 22) and corrupting generation.
+
+Beyond the bug, the deeper issue is that the tracker **cannot know a priori** which route
+is faster. Is one CPU node running all 40 layers faster than a GPU running 0–21 plus a
+CPU hop for 22–39? Benchmarks don't answer that — network hops, MoE expert loading, and
+queue dynamics only show up in real end-to-end requests. The router must *measure*.
+
+## Decision
+
+Route selection is a **multi-armed bandit** over enumerated candidate routes, implemented
+in `packages/tracker/meshnet_tracker/routing_stats.py` and wired into the chat proxy in
+`server.py`.
+
+### Arms: route signatures
+
+A route's identity is `model_key | node_id[shard] -> node_id[shard] -> …`. Node ids embed
+wallet + shard, so a node re-registering with a different shard produces a new arm
+automatically. The proxy target is **always the route's own head** (`route_nodes[0]`),
+and each hop's `start_layer` is `previous_hop.shard_end + 1` — this fixes ADR-0020's flaw
+structurally: head choice and route planning can no longer disagree.
+
+### Candidate enumeration (`_enumerate_routes`)
+
+One candidate per distinct head (a node whose `shard_start` equals the model's first
+layer — it must tokenize/embed), greedily completed with longest-advancing hops. Each
+candidate carries a `prior_tps`: its bottleneck hop's queue-adjusted effective throughput
+× reputation. Capped at 8 candidates ranked by prior.
+
+### Statistics: decayed EWMA + topology epochs
+
+Per (model, signature), `RouteStatsStore` keeps an EWMA of observed end-to-end tokens/sec
+with **time-decayed sample mass** (half-life default 600 s). Two staleness mechanisms
+handle the morphing network:
+
+- **Continuous**: sample mass decays; a route unproven for a while (mass < 0.5) drops out
+  of the exploit pool and gets re-scouted.
+- **Abrupt**: any node join/leave/shard-change bumps the model's *topology epoch*. Stats
+  from an older epoch keep their EWMA as a display prior but are demoted to the scout
+  pool ("stale") until re-measured under the new topology.
+
+Sample hygiene: completions below `min_sample_tokens` (default 8) are rejected — the
+1-token garbage responses from the ADR-0020 bug would otherwise poison arms with
+meaningless tps values. Routes with no samples for 24 h are pruned.
+
+### Selection policy (`choose_route`)
+
+1. **Scout** (probability `explore_share`, default 0.3): if any candidate is unproven /
+   stale / decayed, route the request there — least-measured first, tiebreak on prior.
+   These are the user's "discovery/scout routes". With *no* proven arms at all, selection
+   is deterministic best-prior (matches the old benchmark-based behavior, keeps cold
+   start sane and tests deterministic).
+2. **Exploit** (otherwise): weighted random among proven arms with
+   `P(route) ∝ tps^alpha`, `alpha` default 1.0 — a 1.5×-faster route gets 1.5× the
+   traffic. `alpha` is a config knob: >1 shifts toward winner-takes-most as the network
+   matures, without redesign. (Proportional split is not throughput-optimal in queueing
+   terms, but it keeps every arm warm with fresh samples; tune alpha up when traffic
+   justifies it.)
+
+Pinned routes (`"route": [...]` in the request body) bypass the bandit but still record
+samples.
+
+### Configuration
+
+| CLI flag | env var | default |
+|---|---|---|
+| `--route-explore-share` | `MESHNET_ROUTE_EXPLORE_SHARE` | 0.3 |
+| `--route-weight-alpha` | `MESHNET_ROUTE_WEIGHT_ALPHA` | 1.0 |
+| `--route-stats-half-life` | `MESHNET_ROUTE_STATS_HALF_LIFE` | 600 |
+| — | `MESHNET_ROUTE_MIN_SAMPLE_TOKENS` | 8 |
+
+High explore share now (development, few requests); drop toward 0.05–0.1 once real
+traffic provides passive coverage.
+
+### Visibility
+
+- **`GET /v1/routing`** (optionally `?model=`): per model — topology epoch and the full
+  candidate table: hops, learned tps, **coefficient** (tps ÷ best proven route's tps),
+  **expected traffic share**, sample count, decayed weight, status
+  (proven / unsampled / stale / decayed).
+- **Dashboard → Overview → "Routing (learned)"**: renders that table live (4 s poll),
+  with the active config in the header line.
+- **Console/`proxy route selected`** events now include the routing decision
+  (`{"mode": "scout"|"exploit"|"pinned"|"greedy-fallback", "signature": …}`), so the Call
+  wall history shows which arm served each request.
+
+## Storage considerations
+
+Stats are **in-memory per tracker** for alpha: they are cheap to relearn (a few requests
+per route), and gossiping them would import ADR-0019's consistency questions for data
+that is intentionally ephemeral. If multi-tracker route learning is needed later, ship
+route samples over the existing stats gossip and merge EWMAs by decayed weight — the
+store's (value, mass, timestamp) representation merges cleanly.
+
+## Consequences
+
+- The GPU(0–21)+CPU(0–39) topology now works: both routes get measured, the coefficient
+  is visible on the dashboard, and traffic shifts to whichever is actually faster.
+- Routing is no longer deterministic once samples exist. Tests needing determinism seed
+  `server.route_rng` or rely on the cold-start deterministic path.
+- The billing-relevant fix: heads are always part of the planned route, so per-hop
+  `start_layer` and work-unit spans are consistent.
+
+## Verification
+
+`tests/test_dynamic_routing.py` (11 tests): EWMA/decay/epoch semantics, near-empty sample
+rejection, traffic split ≈ tps ratio at alpha=1 (0.6/0.4 over 4000 seeded draws), scout
+rate ≈ explore share, mixed-topology enumeration (both routes, hybrid prior = bottleneck),
+head-is-route-head regression with `start_layer=22` on the hybrid route, and `/v1/routing`
+table shape. Live: start both nodes, run several chats, open the dashboard "Routing
+(learned)" panel and watch coefficients converge.

docs/issues/30-manual-route-and-hop-benchmark.md

@@ -1,48 +1,48 @@
-# US-020 — Manual route selection + hop-penalty benchmarking
+# US-020 — Manual route selection + hop-penalty benchmarking
-
+
-## Context
+## Context
-
+
-The tracker auto-selects inference routes based on synthetic benchmark scores. To measure
+The tracker auto-selects inference routes based on synthetic benchmark scores. To measure
-the real cost of adding hops (latency per node boundary), we need:
+the real cost of adding hops (latency per node boundary), we need:
-
+
-1. A way to pin a request to a specific route so we control the variable.
+1. A way to pin a request to a specific route so we control the variable.
-2. A benchmark endpoint that runs the same prompt through 1-node, 2-node, and 3-node
+2. A benchmark endpoint that runs the same prompt through 1-node, 2-node, and 3-node
-   routes and records per-hop latency.
+   routes and records per-hop latency.
-
+
-Results are stored to disk. Routing algorithm is **not** changed in this story — this is
+Results are stored to disk. Routing algorithm is **not** changed in this story — this is
-data collection only. The data will inform a future routing optimisation story.
+data collection only. The data will inform a future routing optimisation story.
-
+
-## Design decisions (grilled 2026-07-01)
+## Design decisions (grilled 2026-07-01)
-
+
-| Decision | Choice |
+| Decision | Choice |
-|---|---|
+|---|---|
-| Route spec | Optional `route` field in JSON request body (list of node IDs) |
+| Route spec | Optional `route` field in JSON request body (list of node IDs) |
-| Trigger | Explicit only — `POST /v1/benchmark/hop-penalty` endpoint |
+| Trigger | Explicit only — `POST /v1/benchmark/hop-penalty` endpoint |
-| Auth | Header-presence stub (`Authorization` must be non-empty); real auth in future story |
+| Auth | Header-presence stub (`Authorization` must be non-empty); real auth in future story |
-| Routing integration | Store data only; routing algorithm unchanged |
+| Routing integration | Store data only; routing algorithm unchanged |
-| Persistence | Append to `benchmark_results.json` in tracker working dir; in-memory queryable |
+| Persistence | Append to `benchmark_results.json` in tracker working dir; in-memory queryable |
-
+
-## Acceptance criteria
+## Acceptance criteria
-
+
-- `POST /v1/chat/completions` accepts optional `"route": ["<node_id>", ...]` in the
+- `POST /v1/chat/completions` accepts optional `"route": ["<node_id>", ...]` in the
-  request body. If present, the tracker uses those nodes in order instead of auto-selecting.
+  request body. If present, the tracker uses those nodes in order instead of auto-selecting.
-  If absent, existing routing is unchanged (no breaking change for unaware clients).
+  If absent, existing routing is unchanged (no breaking change for unaware clients).
-- Missing or invalid node IDs in `route` return HTTP 400 with a descriptive error.
+- Missing or invalid node IDs in `route` return HTTP 400 with a descriptive error.
-- `POST /v1/benchmark/hop-penalty` is auth-gated: requests without a non-empty
+- `POST /v1/benchmark/hop-penalty` is auth-gated: requests without a non-empty
-  `Authorization` header return HTTP 401. Body: `{"model": "...", "prompt": "...",
+  `Authorization` header return HTTP 401. Body: `{"model": "...", "prompt": "...",
-  "max_new_tokens": 64}`.
+  "max_new_tokens": 64}`.
-- Benchmark fans out to up to three routes: 1-node (single node covering all layers),
+- Benchmark fans out to up to three routes: 1-node (single node covering all layers),
-  2-node (two consecutive shard nodes), 3-node (three nodes) — using whatever is
+  2-node (two consecutive shard nodes), 3-node (three nodes) — using whatever is
-  currently registered. Routes with insufficient coverage are skipped, not errored.
+  currently registered. Routes with insufficient coverage are skipped, not errored.
-- Response includes per-route breakdown: `total_ms`, `per_hop_ms: [...]`,
+- Response includes per-route breakdown: `total_ms`, `per_hop_ms: [...]`,
-  `tokens_generated`, `route: [node_id, ...]`.
+  `tokens_generated`, `route: [node_id, ...]`.
-- Results are appended to `<tracker_working_dir>/benchmark_results.json` (created if
+- Results are appended to `<tracker_working_dir>/benchmark_results.json` (created if
-  absent) as a JSON array. Each entry includes timestamp, model, prompt hash, and the
+  absent) as a JSON array. Each entry includes timestamp, model, prompt hash, and the
-  per-route breakdown.
+  per-route breakdown.
-- `GET /v1/benchmark/results` returns the stored results array. Also auth-gated.
+- `GET /v1/benchmark/results` returns the stored results array. Also auth-gated.
-- Clients that never send `route` or call `/v1/benchmark/*` are completely unaffected.
+- Clients that never send `route` or call `/v1/benchmark/*` are completely unaffected.
-- Integration test: send the same prompt via a pinned 1-node route and a pinned 2-node
+- Integration test: send the same prompt via a pinned 1-node route and a pinned 2-node
-  route; assert 2-node result has 2 entries in `per_hop_ms`; assert both records appear
+  route; assert 2-node result has 2 entries in `per_hop_ms`; assert both records appear
-  in `benchmark_results.json`.
+  in `benchmark_results.json`.
-- `python -m pytest` passes from repo root.
+- `python -m pytest` passes from repo root.
-- Commit only this story's changes.
+- Commit only this story's changes.

packages/gateway/meshnet_gateway/server.py

@@ -286,7 +286,7 @@ class _GatewayHandler(http.server.BaseHTTPRequestHandler):
             self._send_json(200, completion)
 
     def _proxy_to_head_worker(self, url: str, body_bytes: bytes) -> None:
-        """Forward a raw request body to a head worker and stream the response back."""
+        """Forward a raw request body to a head worker and relay SSE without buffering."""
         target_url = f"{url}/v1/chat/completions"
         req = urllib.request.Request(
             target_url,
@@ -297,6 +297,19 @@ class _GatewayHandler(http.server.BaseHTTPRequestHandler):
         try:
             with urllib.request.urlopen(req, timeout=30.0) as r:
                 content_type = r.headers.get("Content-Type", "application/json")
+                if "text/event-stream" in content_type:
+                    self.send_response(r.status)
+                    self.send_header("Content-Type", content_type)
+                    self.send_header("Cache-Control", "no-cache")
+                    self.send_header("X-Accel-Buffering", "no")
+                    self.end_headers()
+                    while True:
+                        line = r.readline()
+                        if not line:
+                            break
+                        self.wfile.write(line)
+                        self.wfile.flush()
+                    return
                 resp_body = r.read()
                 status = r.status
         except urllib.error.HTTPError as exc:

packages/node/meshnet_node/model_backend.py

@@ -134,8 +134,9 @@ class TorchModelShard:
                     self.model.to(self.device)
         except Exception as exc:
             if _looks_like_oom(exc):
+                memory_kind = "VRAM" if self.device.type == "cuda" else "RAM"
                 raise InsufficientVRAMError(
-                    f"insufficient VRAM to load {model_id} layers {shard_start}:{shard_end} "
+                    f"insufficient {memory_kind} to load {model_id} layers {shard_start}:{shard_end} "
                     f"with {quantization} quantization; choose a smaller shard or lower quantization"
                 ) from exc
             raise
@@ -215,7 +216,7 @@ class TorchModelShard:
     def generate_text(
         self,
         messages: list[dict],
-        max_new_tokens: int = 256,
+        max_new_tokens: int = 5120,
         temperature: float = 1.0,
         top_p: float = 1.0,
     ) -> str:
@@ -245,7 +246,7 @@ class TorchModelShard:
     def generate_text_streaming(
         self,
         messages: list[dict],
-        max_new_tokens: int = 256,
+        max_new_tokens: int = 5000,
         temperature: float = 1.0,
         top_p: float = 1.0,
     ):
@@ -411,7 +412,7 @@ def _should_partial_materialize_shard(
         return False
     if total_layers_hint is None:
         return False
-    return not (shard_start == 0 and shard_end >= total_layers_hint - 1)
+    return True
 
 
 def _load_partial_model_from_snapshot(
@@ -476,17 +477,41 @@ def _load_partial_model_from_snapshot(
         )
 
     with init_empty_weights_fn():
-        model = auto_model_for_causal_lm.from_config(cfg, torch_dtype=dtype)
+        model = auto_model_for_causal_lm.from_config(_causal_lm_config(cfg), torch_dtype=dtype)
     tie_weights = getattr(model, "tie_weights", None)
     if callable(tie_weights):
         tie_weights()
 
+    # Multimodal/MTP checkpoints (e.g. Qwen3.5/3.6-MoE) carry vision and
+    # multi-token-prediction tensors the text-only CausalLM never builds;
+    # transformers' from_pretrained drops them via _keys_to_ignore_on_load_unexpected,
+    # so the manual loader must skip them too.
+    expected_keys = _model_state_dict_keys(model)
     tensors_by_file: dict[str, list[str]] = {}
+    skipped: list[str] = []
     for tensor_name in sorted(tensor_names):
         rel_file = weight_map.get(tensor_name)
         if not isinstance(rel_file, str):
             continue
+        if (
+            expected_keys is not None
+            and _checkpoint_tensor_name_for_model(model, tensor_name) not in expected_keys
+        ):
+            skipped.append(tensor_name)
+            continue
         tensors_by_file.setdefault(rel_file, []).append(tensor_name)
+    if skipped:
+        preview = ", ".join(skipped[:3])
+        print(
+            f"  Skipping {len(skipped)} checkpoint tensors absent from the causal LM "
+            f"(e.g. {preview})",
+            flush=True,
+        )
+    if not tensors_by_file:
+        raise PartialModelLoadUnsupported(
+            f"no checkpoint tensors for layers {shard_start}-{shard_end} match the "
+            f"causal LM built from {snapshot_dir}"
+        )
 
     for rel_file, names in tensors_by_file.items():
         checkpoint_file = snapshot_dir / rel_file
@@ -498,7 +523,7 @@ def _load_partial_model_from_snapshot(
             for tensor_name in names:
                 set_tensor_fn(
                     model,
-                    tensor_name,
+                    _checkpoint_tensor_name_for_model(model, tensor_name),
                     device,
                     value=handle.get_tensor(tensor_name),
                     dtype=dtype,
@@ -569,38 +594,85 @@ def _native_torch_dtype(cfg: Any, torch: Any) -> Any:
     return torch.bfloat16
 
 
+def _causal_lm_config(cfg: Any) -> Any:
+    """Use the text decoder config for composite VLM/MoE presets."""
+    get_text_config = getattr(cfg, "get_text_config", None)
+    if callable(get_text_config):
+        try:
+            return get_text_config()
+        except Exception:
+            pass
+    text_config = getattr(cfg, "text_config", None)
+    if text_config is not None:
+        return text_config
+    return cfg
+
+
+def _model_state_dict_keys(model: Any) -> set[str] | None:
+    """Expected parameter/buffer names, or None when the model can't report them."""
+    state_dict = getattr(model, "state_dict", None)
+    if not callable(state_dict):
+        return None
+    try:
+        return set(state_dict().keys())
+    except Exception:
+        return None
+
+
+def _checkpoint_tensor_name_for_model(model: Any, tensor_name: str) -> str:
+    """Map multimodal checkpoint keys onto text-only CausalLM modules when needed."""
+    inner = getattr(model, "model", None)
+    if inner is not None and hasattr(inner, "language_model"):
+        return tensor_name
+    if ".language_model." in tensor_name:
+        return tensor_name.replace(".language_model.", ".")
+    return tensor_name
+
+
+def _transformer_backbone(model: Any) -> Any:
+    if hasattr(model, "model"):
+        inner = model.model
+        language_model = getattr(inner, "language_model", None)
+        if language_model is not None:
+            return language_model
+        return inner
+    if hasattr(model, "transformer"):
+        return model.transformer
+    raise ModelBackendError(
+        "unsupported HuggingFace model architecture: no transformer backbone found"
+    )
+
+
 def _model_layers(model: Any) -> Any:
-    if hasattr(model, "model") and hasattr(model.model, "layers"):
+    backbone = _transformer_backbone(model)
-        return model.model.layers
+    for attr in ("layers", "h", "blocks"):
-    if hasattr(model, "transformer") and hasattr(model.transformer, "h"):
+        layers = getattr(backbone, attr, None)
-        return model.transformer.h
+        if layers is not None:
+            return layers
     raise ModelBackendError(
         "unsupported HuggingFace model architecture: no transformer layers found"
     )
 
 
 def _embed_tokens(model: Any) -> Any:
-    if hasattr(model, "model") and hasattr(model.model, "embed_tokens"):
+    backbone = _transformer_backbone(model)
-        return model.model.embed_tokens
+    for attr in ("embed_tokens", "wte"):
-    if hasattr(model, "transformer") and hasattr(model.transformer, "wte"):
+        embed = getattr(backbone, attr, None)
-        return model.transformer.wte
+        if embed is not None:
+            return embed
     raise ModelBackendError(
         "unsupported HuggingFace model architecture: no token embeddings found"
     )
 
 
 def _position_embeddings(model: Any) -> Any | None:
-    if hasattr(model, "transformer") and hasattr(model.transformer, "wpe"):
+    backbone = _transformer_backbone(model)
-        return model.transformer.wpe
+    return getattr(backbone, "wpe", None)
-    return None
 
 
 def _rotary_embedding_module(model: Any) -> Any | None:
-    if hasattr(model, "model") and hasattr(model.model, "rotary_emb"):
+    backbone = _transformer_backbone(model)
-        return model.model.rotary_emb
+    return getattr(backbone, "rotary_emb", None)
-    if hasattr(model, "transformer") and hasattr(model.transformer, "rotary_emb"):
-        return model.transformer.rotary_emb
-    return None
 
 
 def _active_modules_for_shard(model: Any, shard_start: int, shard_end: int) -> list[Any]:
@@ -627,10 +699,11 @@ def _active_modules_for_shard(model: Any, shard_start: int, shard_end: int) -> l
 
 
 def _final_norm(model: Any) -> Any | None:
-    if hasattr(model, "model") and hasattr(model.model, "norm"):
+    backbone = _transformer_backbone(model)
-        return model.model.norm
+    for attr in ("norm", "ln_f", "final_layer_norm"):
-    if hasattr(model, "transformer") and hasattr(model.transformer, "ln_f"):
+        norm = getattr(backbone, attr, None)
-        return model.transformer.ln_f
+        if norm is not None:
+            return norm
     return None
 
 
@@ -743,7 +816,12 @@ def _looks_like_oom(exc: BaseException) -> bool:
     current: BaseException | None = exc
     while current is not None:
         text = str(current).lower()
-        if "out of memory" in text or "cuda error: out of memory" in text:
+        if (
+            "out of memory" in text
+            or "cuda error: out of memory" in text
+            or "paging file is too small" in text
+            or "os error 1455" in text
+        ):
             return True
         current = current.__cause__ or current.__context__
     return False

packages/node/meshnet_node/relay_bridge.py

@@ -164,6 +164,9 @@ class RelayHttpBridge:
         path = str(payload.get("path") or "/")
         headers = payload.get("headers") if isinstance(payload.get("headers"), dict) else {}
 
+        req_suffix = f" request_id={request_id}" if request_id else ""
+        print(f"  [node] relay {method} {path}{req_suffix}", flush=True)
+
         # body_base64 carries binary data (e.g. bfloat16 activation tensors) safely.
         # Fallback to text "body" for backward-compat with non-binary requests.
         body_b64 = payload.get("body_base64")

packages/node/meshnet_node/startup.py

@@ -197,12 +197,58 @@ def _max_assignable_layers(
     memory_mb: int,
     total_layers: int | None,
     bytes_per_layer: int | None = None,
+    *,
+    safety_fraction: float = 0.8,
 ) -> int:
     if total_layers is None or total_layers <= 0 or memory_mb <= 0:
         return 0
     budget_bytes = memory_mb * 1024 * 1024
     layer_bytes = bytes_per_layer or _DEFAULT_BYTES_PER_LAYER
-    return min(total_layers, int((budget_bytes * 0.8) // layer_bytes))
+    return min(total_layers, int((budget_bytes * safety_fraction) // layer_bytes))
+
+
+def _runtime_shard_safety_fraction(device: str) -> float:
+    """CPU partial loads need room for model skeletons, tokenizer, and allocator peaks."""
+    return 0.55 if device != "cuda" else 0.8
+
+
+def _cap_auto_assigned_shard(
+    shard_start: int,
+    shard_end: int,
+    total_layers: int | None,
+    memory_mb: int,
+    bytes_per_layer: int | None,
+    device: str,
+) -> tuple[int, bool, int]:
+    if bytes_per_layer is None or total_layers is None:
+        return shard_end, False, 0
+    max_layers = _max_assignable_layers(
+        memory_mb,
+        total_layers,
+        bytes_per_layer=bytes_per_layer,
+        safety_fraction=_runtime_shard_safety_fraction(device),
+    )
+    if max_layers <= 0:
+        return shard_end, False, max_layers
+    assigned_layers = shard_end - shard_start + 1
+    if assigned_layers <= max_layers:
+        return shard_end, False, max_layers
+    return min(total_layers - 1, shard_start + max_layers - 1), True, max_layers
+
+
+def _format_shard_label(
+    shard_start: int,
+    shard_end: int,
+    total_layers: int | None = None,
+    *,
+    model_name: str | None = None,
+) -> str:
+    layer_count = shard_end - shard_start + 1
+    if isinstance(total_layers, int) and total_layers > 0:
+        return f"layers {shard_start}–{shard_end} ({layer_count} of {total_layers})"
+    if model_name:
+        return f"layers {shard_start}–{shard_end} ({model_name})"
+    return f"layers {shard_start}–{shard_end}"
 
 
 def _shard_budget_line(
@@ -211,13 +257,19 @@ def _shard_budget_line(
     total_layers: int | None,
     quantization: str,
     bytes_per_layer: int | None = None,
+    safety_fraction: float = 0.8,
 ) -> str:
     memory_gb = memory_mb / 1024
     gb_str = f"{memory_gb:.1f} GB"
     budget_quantization = "bfloat16" if quantization == "auto" else quantization
     if total_layers is None or total_layers <= 0:
         return f"Memory budget: {gb_str} {memory_source}; shard budget: unknown model layer count"
-    max_layers = _max_assignable_layers(memory_mb, total_layers, bytes_per_layer=bytes_per_layer)
+    max_layers = _max_assignable_layers(
+        memory_mb,
+        total_layers,
+        bytes_per_layer=bytes_per_layer,
+        safety_fraction=safety_fraction,
+    )
     # Remaining capacity after one full model load (rough estimate)
     shard_bytes = max_layers * (bytes_per_layer or _DEFAULT_BYTES_PER_LAYER)
     remaining_gb = (memory_mb * 1024 * 1024 - shard_bytes) / (1024 ** 3)
@@ -334,25 +386,38 @@ def _attach_relay_bridge(node: StubNodeServer | TorchNodeServer, bridge: RelayHt
 _PENDING_NODE_ID = "pending"
 
 
+_HEARTBEAT_INTERVAL_IDLE = 20.0
+_HEARTBEAT_INTERVAL_BUSY = 3.0
+
+
 def _start_heartbeat(
     tracker_url: str,
     node_id: str,
     register_payload: dict,
-    interval: float = 20.0,
+    interval: float = _HEARTBEAT_INTERVAL_IDLE,
     node_ref: Any | None = None,
     start_time: float | None = None,
 ) -> threading.Thread:
     """Daemon thread: sends heartbeats and re-registers automatically after tracker restarts.
 
     Heartbeat body carries cumulative stats (total_requests, failed_requests,
-    queue_depth, uptime_seconds, status). Stats are buffered locally during
+    queue_depth, current_requests, uptime_seconds, status). Stats are buffered
-    outage and flushed on next successful heartbeat.
+    locally during outage and flushed on next successful heartbeat.
 
     Heartbeat response may include new_assignment: {model, shard_start, shard_end}
     which is logged for now (hot-reload implemented in US-026).
     """
     _start_time = start_time or time.monotonic()
 
+    def _current_requests_snapshot() -> list[dict]:
+        if node_ref is None:
+            return []
+        getter = getattr(node_ref, "current_requests", None)
+        if getter is None:
+            return []
+        current = getter() if callable(getter) else getter
+        return list(current) if isinstance(current, list) else []
+
     def _get_stats() -> dict:
         uptime = time.monotonic() - _start_time
         stats: dict = {"uptime_seconds": round(uptime, 1), "status": "ready"}
@@ -364,8 +429,16 @@ def _start_heartbeat(
             )
             stats["failed_requests"] = getattr(node_ref, "failed_requests", 0)
             stats["queue_depth"] = getattr(node_ref, "queue_depth", 0)
+        current_requests = _current_requests_snapshot()
+        if current_requests:
+            stats["current_requests"] = current_requests
         return stats
 
+    def _sleep_interval() -> float:
+        if _current_requests_snapshot() or (node_ref is not None and getattr(node_ref, "queue_depth", 0) > 0):
+            return _HEARTBEAT_INTERVAL_BUSY
+        return interval
+
     def _reregister() -> bool:
         nonlocal node_id
         try:
@@ -427,7 +500,7 @@ def _start_heartbeat(
         outage_streak = 1 if node_id == _PENDING_NODE_ID else 0
 
         while True:
-            time.sleep(interval)
+            time.sleep(_sleep_interval())
 
             if outage_streak > 0:
                 # Tracker was down — attempt re-registration first (it may have restarted
@@ -693,6 +766,25 @@ def run_startup(
                     if net_asgn.get("hf_repo") == model_id and net_asgn.get("gap_found"):
                         shard_start = net_asgn["shard_start"]
                         shard_end = net_asgn["shard_end"]
+                        asgn_total_layers = int(net_asgn.get("num_layers") or detected)
+                        asgn_bytes_per_layer = _assignment_bytes_per_layer(net_asgn, quantization)
+                        capped_shard_end, was_capped, max_runtime_layers = _cap_auto_assigned_shard(
+                            shard_start,
+                            shard_end,
+                            asgn_total_layers,
+                            memory_budget_mb,
+                            asgn_bytes_per_layer,
+                            device,
+                        )
+                        if was_capped:
+                            original_end = shard_end
+                            shard_end = capped_shard_end
+                            print(
+                                f"  WARNING: tracker assigned layers {shard_start}-{original_end}, "
+                                f"but CPU-safe runtime budget fits {max_runtime_layers}/{asgn_total_layers} layers; "
+                                f"loading layers {shard_start}-{shard_end} instead.",
+                                flush=True,
+                            )
                         full_sources = (
                             [] if tracker_source_disabled
                             else _full_model_sources(net_asgn.get("model_sources", []))
@@ -708,7 +800,7 @@ def run_startup(
                             )
                         print(
                             f"  Tracker found uncovered shard: "
-                            f"layers {shard_start}–{shard_end} (of {detected})",
+                            f"layers {shard_start}-{shard_end} (of {detected})",
                             flush=True,
                         )
                 except Exception:
@@ -734,13 +826,10 @@ def run_startup(
         _node_start_time = time.monotonic()
         actual_port = node.start()
         total_layers = getattr(getattr(node, "backend", None), "total_layers", None)
-        if isinstance(total_layers, int) and total_layers > 0:
+        shard_label = _format_shard_label(shard_start, shard_end, total_layers)
-            layer_count = shard_end - shard_start + 1
-            shard_label = f"layers {shard_start}–{shard_end}; {layer_count} of {total_layers}"
-        else:
-            shard_label = f"layers {shard_start}–{shard_end}"
         public_host = advertise_host or (socket.getfqdn() if host == "0.0.0.0" else host)
         endpoint = f"http://{public_host}:{actual_port}"
+        node.set_advertised_endpoint(endpoint)
         local_base_url = f"http://127.0.0.1:{actual_port}"
         relay_bridge, relay_fields = _start_relay_bridge_if_available(
             tracker_url,
@@ -827,18 +916,36 @@ def run_startup(
         assigned_shard_start: int = net_assignment["shard_start"]
         assigned_shard_end: int = net_assignment["shard_end"]
         assigned_num_layers: int = net_assignment["num_layers"]
+        assigned_bytes_per_layer = _assignment_bytes_per_layer(net_assignment, quantization)
+        capped_shard_end, was_capped, max_runtime_layers = _cap_auto_assigned_shard(
+            assigned_shard_start,
+            assigned_shard_end,
+            assigned_num_layers,
+            memory_budget_mb,
+            assigned_bytes_per_layer,
+            device,
+        )
+        if was_capped:
+            original_end = assigned_shard_end
+            assigned_shard_end = capped_shard_end
+            print(
+                f"  WARNING: tracker assigned layers {assigned_shard_start}-{original_end}, "
+                f"but CPU-safe runtime budget fits {max_runtime_layers}/{assigned_num_layers} layers; "
+                f"loading layers {assigned_shard_start}-{assigned_shard_end} instead.",
+                flush=True,
+            )
         assigned_model_sources: list[dict] = net_assignment.get("model_sources", [])
         if _gap_found:
             print(
                 f"  Assigned gap: {assigned_hf_repo} "
-                f"layers {assigned_shard_start}–{assigned_shard_end} "
+                f"layers {assigned_shard_start}-{assigned_shard_end} "
                 f"(of {assigned_num_layers})",
                 flush=True,
             )
         else:
             print(
                 f"  Assigned redundant copy: {assigned_hf_repo} "
-                f"layers {assigned_shard_start}–{assigned_shard_end} "
+                f"layers {assigned_shard_start}-{assigned_shard_end} "
                 f"(of {assigned_num_layers})",
                 flush=True,
             )
@@ -871,6 +978,7 @@ def run_startup(
         actual_port = node.start()
         public_host = advertise_host or (socket.getfqdn() if host == "0.0.0.0" else host)
         endpoint = f"http://{public_host}:{actual_port}"
+        node.set_advertised_endpoint(endpoint)
         local_base_url = f"http://127.0.0.1:{actual_port}"
         relay_bridge, relay_fields = _start_relay_bridge_if_available(
             tracker_url,
@@ -913,15 +1021,18 @@ def run_startup(
         tracker_node_id = _register_with_tracker(
             tracker_url, auto_reg_payload, node, _node_start_time,
         )
-        shard_count = assigned_shard_end - assigned_shard_start + 1
+        shard_label = _format_shard_label(
+            assigned_shard_start,
+            assigned_shard_end,
+            assigned_num_layers,
+        )
         print(
             f"\n{'=' * 32}\n"
             f"meshnet-node ready (auto-joined)\n"
             f"  Wallet:       {address}\n"
             f"  Model ID:     {assigned_hf_repo}\n"
-            f"  Shard:        layers {assigned_shard_start}–{assigned_shard_end} "
+            f"  Shard:        {shard_label}\n"
-            f"({shard_count} of {assigned_num_layers})\n"
+            f"  {_shard_budget_line(memory_budget_mb, memory_budget_source, assigned_num_layers, quantization, bytes_per_layer=assigned_bytes_per_layer, safety_fraction=_runtime_shard_safety_fraction(device))}\n"
-            f"  {_shard_budget_line(memory_budget_mb, memory_budget_source, assigned_num_layers, quantization)}\n"
             f"  Quantization: {quantization}\n"
             f"  Endpoint:     {endpoint}\n"
             f"  Node ID:      {tracker_node_id or 'unregistered'}\n"
@@ -967,13 +1078,36 @@ def run_startup(
     peers: list[dict] = assignment.get("peers", [])
     model_sources: list[dict] = [] if tracker_source_disabled else assignment.get("model_sources", [])
     assignment_bytes_per_layer = _assignment_bytes_per_layer(assignment, quantization)
+    model_layers_end = assignment.get("model_layers_end")
+    assigned_total_layers = (
+        int(model_layers_end) + 1
+        if model_layers_end is not None
+        else None
+    )
+    shard_label = _format_shard_label(
+        shard_start,
+        shard_end,
+        assigned_total_layers,
+        model_name=assigned_model,
+    )
     if user_pinned_shard:
-        print(
+        shard_label = f"{shard_label} (pinned)"
-            f"  Shard: layers {shard_start}-{shard_end} of {assigned_model} (pinned)",
+    if user_pinned_shard and assigned_total_layers and assignment_bytes_per_layer:
-            flush=True,
+        pinned_layers = shard_end - shard_start + 1
+        max_layers = _max_assignable_layers(
+            memory_budget_mb,
+            assigned_total_layers,
+            assignment_bytes_per_layer,
+            safety_fraction=_runtime_shard_safety_fraction(device),
         )
-    else:
+        if pinned_layers > max_layers:
-        print(f"  Shard: layers {shard_start}-{shard_end} of {assigned_model}", flush=True)
+            raise ValueError(
+                f"Pinned shard layers {shard_start}–{shard_end} ({pinned_layers} layers) exceed "
+                f"the {memory_budget_mb / 1024:.1f} GB {memory_budget_source} budget "
+                f"(fits up to {max_layers}/{assigned_total_layers} layers at bfloat16). "
+                "Drop --shard-start/--shard-end to let the tracker auto-assign, or pin a smaller range."
+            )
+    print(f"  Shard: {shard_label}", flush=True)
 
     # 4. Download shard
     print("Downloading shard...", flush=True)
@@ -998,7 +1132,78 @@ def run_startup(
     )
     print(f"  Cached at: {shard_path}", flush=True)
 
-    # 5. Start HTTP server
+    # 5. Start HTTP server — real HF weights use TorchNodeServer; stub-model stays stub.
+    _node_start_time = time.monotonic()
+    if hf_repo and assigned_model != "stub-model":
+        print("Loading real PyTorch model shard...", flush=True)
+        node = TorchNodeServer(
+            host=host,
+            port=port,
+            model_id=hf_repo,
+            shard_start=shard_start,
+            shard_end=shard_end,
+            quantization=quantization,
+            tracker_url=tracker_url,
+            route_timeout=route_timeout,
+            cache_dir=shard_path,
+            debug=debug,
+            max_loaded_shards=max_loaded_shards,
+        )
+        actual_port = node.start()
+        total_layers = getattr(getattr(node, "backend", None), "total_layers", None) or assigned_total_layers
+        shard_label = _format_shard_label(shard_start, shard_end, total_layers, model_name=assigned_model)
+        if user_pinned_shard:
+            shard_label = f"{shard_label} (pinned)"
+        public_host = advertise_host or (socket.getfqdn() if host == "0.0.0.0" else host)
+        endpoint = f"http://{public_host}:{actual_port}"
+        node.set_advertised_endpoint(endpoint)
+        local_base_url = f"http://127.0.0.1:{actual_port}"
+        relay_bridge, relay_fields = _start_relay_bridge_if_available(
+            tracker_url,
+            address,
+            local_base_url,
+            endpoint,
+            relay_url=relay_url,
+        )
+        _attach_relay_bridge(node, relay_bridge)
+        reg_payload = {
+            "endpoint": endpoint,
+            "model": assigned_model,
+            "hf_repo": hf_repo,
+            "num_layers": total_layers,
+            "shard_start": shard_start,
+            "shard_end": shard_end,
+            "downloaded_models": downloaded_models,
+            "hardware_profile": hw,
+            "wallet_address": address,
+            "quantization": quantization,
+            "score": 1.0,
+            "tracker_mode": (shard_start == 0),
+            "managed_assignment": not user_pinned_shard,
+            "model_metadata": model_metadata_for(hf_repo, total_layers, cache_dir=shard_path),
+            **registration_capabilities,
+            **relay_fields,
+        }
+        tracker_node_id = _register_with_tracker(
+            tracker_url, reg_payload, node, _node_start_time,
+        )
+        print(
+            f"\n{'=' * 32}\n"
+            f"meshnet-node ready\n"
+            f"  Wallet:       {address}\n"
+            f"  Model ID:     {hf_repo}\n"
+            f"  Shard:        {shard_label}\n"
+            f"  {_shard_budget_line(memory_budget_mb, memory_budget_source, total_layers, quantization, bytes_per_layer=assignment_bytes_per_layer, safety_fraction=_runtime_shard_safety_fraction(device))}\n"
+            f"  Quantization: {quantization}\n"
+            f"  Endpoint:     {endpoint}\n"
+            f"  Node ID:      {tracker_node_id or 'unregistered'}\n"
+            f"  Hardware:     {_hardware_label(device, gpu_name)}\n"
+            f"  Benchmark:    {bench_tps:,.0f} (throughput index)\n"
+            f"{'=' * 32}",
+            flush=True,
+        )
+        return node
+
     is_last = shard_end >= assignment.get("model_layers_end", shard_end)
     node = StubNodeServer(
         host=host,
@@ -1009,7 +1214,6 @@ def run_startup(
         model=assigned_model,
         shard_path=shard_path,
     )
-    _node_start_time = time.monotonic()
     actual_port = node.start()
     public_host = advertise_host or (socket.getfqdn() if host == "0.0.0.0" else host)
     endpoint = f"http://{public_host}:{actual_port}"
@@ -1055,12 +1259,18 @@ def run_startup(
     hw_str = device.upper()
     if gpu_name:
         hw_str += f" ({gpu_name}, {vram_mb / 1024:.1f} GB)"
+    shard_label = _format_shard_label(
+        shard_start,
+        shard_end,
+        assigned_total_layers,
+        model_name=assigned_model,
+    )
     print(
         f"\n{'=' * 32}\n"
         f"meshnet-node ready\n"
         f"  Wallet:   {address}\n"
-        f"  Shard:    layers {shard_start}-{shard_end} ({assigned_model})\n"
+        f"  Shard:    {shard_label}\n"
-        f"  {_shard_budget_line(memory_budget_mb, memory_budget_source, assignment.get('model_layers_end', shard_end) + 1, quantization, bytes_per_layer=assignment_bytes_per_layer)}\n"
+        f"  {_shard_budget_line(memory_budget_mb, memory_budget_source, assigned_total_layers, quantization, bytes_per_layer=assignment_bytes_per_layer, safety_fraction=_runtime_shard_safety_fraction(device))}\n"
         f"  Endpoint: {endpoint}\n"
         f"  Node ID:  {node_id}\n"
         f"  Hardware: {hw_str}\n"

packages/node/meshnet_node/torch_server.py

@@ -31,6 +31,69 @@ from .server import (
 )
 
 
+def _endpoint_key(url: str) -> str:
+    """Normalize http(s) endpoints for host:port comparison."""
+    parsed = urllib.parse.urlparse(url.rstrip("/"))
+    host = (parsed.hostname or "").lower()
+    if not host:
+        return url.rstrip("/").lower()
+    port = parsed.port
+    if port is None:
+        port = 443 if parsed.scheme == "https" else 80
+    return f"{host}:{port}"
+
+
+def _own_endpoint_key(server: _TorchHTTPServer) -> str:
+    advertised = getattr(server, "advertised_endpoint", None)
+    if advertised:
+        return _endpoint_key(advertised)
+    host, port = server.server_address
+    return _endpoint_key(f"http://{host}:{port}")
+
+
+def _clamp_downstream_hops(
+    hops: list[dict],
+    backend: TorchModelShard | None,
+) -> list[dict]:
+    """Ensure downstream start_layer continues after this shard's layers."""
+    if not hops or backend is None:
+        return hops
+    shard_end = getattr(backend, "shard_end", None)
+    if shard_end is None:
+        return hops
+    min_start = int(shard_end) + 1
+    clamped: list[dict] = []
+    for hop in hops:
+        adjusted = dict(hop)
+        if int(adjusted.get("start_layer", 0)) < min_start:
+            adjusted["start_layer"] = min_start
+        clamped.append(adjusted)
+    return clamped
+
+
+def _format_downstream_route(hops: list[dict]) -> str:
+    return ", ".join(
+        f"{h['endpoint']}@{h.get('start_layer', 0)}" for h in hops
+    )
+
+
+def _write_progress_line(state: list[bool], message: str, *, final: bool = False) -> None:
+    """Rewrite one in-place progress line (\\r) or finish with a newline."""
+    if final:
+        if state[0]:
+            sys.stdout.write("\r" + message + "\n")
+            state[0] = False
+        else:
+            print(message, flush=True)
+        return
+    if state[0]:
+        sys.stdout.write("\r" + message)
+    else:
+        sys.stdout.write(message)
+        state[0] = True
+    sys.stdout.flush()
+
+
 def _relay_hop(
     relay_addr: str,
     path: str,
@@ -87,10 +150,31 @@ class _TorchHTTPServer(http.server.HTTPServer):
         self.route_timeout = route_timeout
         self.debug = debug
         self.max_loaded_shards = max(1, max_loaded_shards)
+        self.advertised_endpoint: str | None = None
         self.total_requests: int = 0
         self.failed_requests: int = 0
         self.queue_depth: int = 0
         self._stats_lock = threading.Lock()
+        self._active_requests: dict[str, dict[str, Any]] = {}
+
+    def snapshot_current_requests(self) -> list[dict[str, Any]]:
+        """In-flight request snapshots for tracker heartbeats."""
+        now = time.monotonic()
+        with self._stats_lock:
+            out: list[dict[str, Any]] = []
+            for rec in self._active_requests.values():
+                elapsed = max(now - float(rec["started"]), 1e-6)
+                tokens = int(rec.get("tokens") or 0)
+                out.append({
+                    "request_id": str(rec["request_id"]),
+                    "model": str(rec.get("model") or ""),
+                    "kind": str(rec.get("kind") or "chat"),
+                    "tokens": tokens,
+                    "elapsed_seconds": round(elapsed, 1),
+                    "tokens_per_sec": round(tokens / elapsed, 2) if tokens > 0 else 0.0,
+                    "routing_complete": bool(rec.get("routing_complete")),
+                })
+            return out
 
     def resolve_backend(self, model_name: str | None) -> TorchModelShard | None:
         if not model_name:
@@ -113,6 +197,53 @@ class _TorchHandler(http.server.BaseHTTPRequestHandler):
     def log_message(self, fmt, *args):  # noqa: suppress request logs in tests
         pass
 
+    def _request_id(self) -> str:
+        return (
+            self.headers.get("X-Meshnet-Request-Id")
+            or self.headers.get("X-Request-Id")
+            or f"local-{time.time_ns():x}"
+        )
+
+    def _request_log_suffix(self) -> str:
+        req_id = self.headers.get("X-Meshnet-Request-Id") or self.headers.get("X-Request-Id")
+        return f" request_id={req_id}" if req_id else ""
+
+    def _track_request_begin(
+        self,
+        server: "_TorchHTTPServer",
+        request_id: str,
+        model: str,
+    ) -> None:
+        with server._stats_lock:
+            server._active_requests[request_id] = {
+                "request_id": request_id,
+                "model": model,
+                "kind": "chat",
+                "started": time.monotonic(),
+                "tokens": 0,
+                "routing_complete": False,
+            }
+
+    def _track_request_progress(
+        self,
+        server: "_TorchHTTPServer",
+        request_id: str,
+        *,
+        tokens: int,
+        routing_complete: bool = False,
+    ) -> None:
+        with server._stats_lock:
+            rec = server._active_requests.get(request_id)
+            if rec is None:
+                return
+            rec["tokens"] = tokens
+            if routing_complete:
+                rec["routing_complete"] = True
+
+    def _track_request_end(self, server: "_TorchHTTPServer", request_id: str) -> None:
+        with server._stats_lock:
+            server._active_requests.pop(request_id, None)
+
     def do_POST(self):
         server: _TorchHTTPServer = self.server  # type: ignore[assignment]
         if self.path == "/forward":
@@ -199,8 +330,18 @@ class _TorchHandler(http.server.BaseHTTPRequestHandler):
             return
 
         server.forward_chunk_count += 1
-        if int(self.headers.get("X-Meshnet-Hop-Index", "0")) > 0:
+        hop_index = int(self.headers.get("X-Meshnet-Hop-Index", "0"))
+        if hop_index > 0:
             server.received_activations = True
+        if chunk_index_value == 0:
+            shard_start = getattr(server.backend, "shard_start", "?")
+            shard_end = getattr(server.backend, "shard_end", "?")
+            print(
+                f"  [node] forward hop={hop_index} "
+                f"layers={shard_start}-{shard_end} "
+                f"session={session[:8]}{self._request_log_suffix()}",
+                flush=True,
+            )
 
         start_layer_header = self.headers.get("X-Meshnet-Start-Layer")
         start_layer = int(start_layer_header) if start_layer_header else None
@@ -280,12 +421,14 @@ class _TorchHandler(http.server.BaseHTTPRequestHandler):
 
     def _handle_chat_completions(self) -> None:
         server: _TorchHTTPServer = self.server  # type: ignore[assignment]
+        request_id = self._request_id()
         with server._stats_lock:
             server.total_requests += 1
             server.queue_depth += 1
         try:
-            self._do_chat_completions(server)
+            self._do_chat_completions(server, request_id)
         finally:
+            self._track_request_end(server, request_id)
             with server._stats_lock:
                 server.queue_depth -= 1
 
@@ -294,7 +437,7 @@ class _TorchHandler(http.server.BaseHTTPRequestHandler):
         with server._stats_lock:
             server.failed_requests += 1
 
-    def _do_chat_completions(self, server: "_TorchHTTPServer") -> None:
+    def _do_chat_completions(self, server: "_TorchHTTPServer", request_id: str) -> None:
         body = self._read_json_body()
         if body is None:
             return
@@ -307,24 +450,65 @@ class _TorchHandler(http.server.BaseHTTPRequestHandler):
         if backend is None or not backend.is_head:
             self._send_json(400, {"error": "model not loaded on this node"})
             return
-        max_tokens = int(body.get("max_tokens") or body.get("max_new_tokens") or 256)
+        max_tokens = int(body.get("max_tokens") or body.get("max_new_tokens") or 5120)
         temperature = float(body.get("temperature") or 1.0)
         top_p = float(body.get("top_p") or 1.0)
 
+        self._track_request_begin(server, request_id, model_name)
+        print(
+            f"  [node] processing chat model={model_name!r} stream={stream} "
+            f"max_tokens={max_tokens}{self._request_log_suffix()}",
+            flush=True,
+        )
+
         # Fast path: this node owns the complete model — use HF generate() with KV cache.
         # Avoids the single-token-per-forward-pass limitation of the distributed path.
         if backend.is_head and backend.is_tail:
+            gen_started = time.monotonic()
+            progress_line = [False]
             try:
                 if stream:
-                    self._stream_openai_response(
+                    token_count = 0
-                        backend.generate_text_streaming(messages, max_tokens, temperature, top_p),
+
-                        model_name,
+                    def _counting_stream():
+                        nonlocal token_count
+                        for token_text in backend.generate_text_streaming(
+                            messages, max_tokens, temperature, top_p,
+                        ):
+                            if token_text:
+                                token_count += 1
+                                self._track_request_progress(
+                                    server, request_id, tokens=token_count, routing_complete=True,
+                                )
+                            yield token_text
+
+                    self._stream_openai_response(_counting_stream(), model_name)
+                    elapsed = time.monotonic() - gen_started
+                    tps = token_count / max(elapsed, 1e-6)
+                    _write_progress_line(
+                        progress_line,
+                        f"  [node] chat complete (stream) tokens={token_count} "
+                        f"elapsed_s={elapsed:.1f} tps={tps:.2f}{self._request_log_suffix()}",
+                        final=True,
                     )
                 else:
                     text = backend.generate_text(messages, max_tokens, temperature, top_p)
+                    completion_tokens = _backend_token_count(
+                        backend, "count_text_tokens", text, fallback=len(text.split()) or 1,
+                    )
+                    print(
+                        f"  [node] chat complete tokens={completion_tokens} "
+                        f"elapsed_s={time.monotonic() - gen_started:.1f}{self._request_log_suffix()}",
+                        flush=True,
+                    )
                     self._send_openai_response(text, model_name, False, messages, backend=backend)
             except Exception as exc:
                 self._record_failed_request()
+                print(
+                    f"  [node] chat failed after {time.monotonic() - gen_started:.1f}s: {exc}"
+                    f"{self._request_log_suffix()}",
+                    flush=True,
+                )
                 self._send_json(500, {"error": f"generation failed: {exc}"})
             return
 
@@ -367,8 +551,14 @@ class _TorchHandler(http.server.BaseHTTPRequestHandler):
         stream_emit = None
         if stream:
             stream_emit = self._start_openai_stream(model_name)
+            self._track_request_progress(server, request_id, tokens=0, routing_complete=True)
 
-        for _ in range(max_tokens):
+        _GENERATION_LOG_INTERVAL = 5.0
+        gen_started = time.monotonic()
+        last_gen_log = gen_started
+        progress_line = [False]
+
+        for step in range(max_tokens):
             try:
                 payload = backend.encode_prompt(current_text)
             except Exception as exc:
@@ -386,6 +576,34 @@ class _TorchHandler(http.server.BaseHTTPRequestHandler):
             if stream_emit is not None:
                 stream_emit(token_str)
             current_text = current_text + token_str
+            self._track_request_progress(
+                server,
+                request_id,
+                tokens=len(generated),
+                routing_complete=True,
+            )
+            now = time.monotonic()
+            if step == 0 or now - last_gen_log >= _GENERATION_LOG_INTERVAL:
+                elapsed = now - gen_started
+                token_count = len(generated)
+                tps = token_count / max(elapsed, 1e-6)
+                _write_progress_line(
+                    progress_line,
+                    f"  [node] generating step={step + 1}/{max_tokens} "
+                    f"tokens={token_count} elapsed_s={elapsed:.1f} tps={tps:.2f}",
+                )
+                last_gen_log = now
+
+        if generated:
+            elapsed = time.monotonic() - gen_started
+            token_count = len(generated)
+            tps = token_count / max(elapsed, 1e-6)
+            _write_progress_line(
+                progress_line,
+                f"  [node] generation complete tokens={token_count} "
+                f"elapsed_s={elapsed:.1f} tps={tps:.2f}",
+                final=True,
+            )
 
         result_text = "".join(generated)
         if stream_emit is not None:
@@ -401,6 +619,9 @@ class _TorchHandler(http.server.BaseHTTPRequestHandler):
         start_layer tells each downstream node which layer to begin from,
         enabling correct execution when shard ranges overlap.
         """
+        server: _TorchHTTPServer = self.server  # type: ignore[assignment]
+        active_backend = backend or server.backend
+
         # Fast path: tracker pre-resolved the downstream route and injected it as a header.
         injected = self.headers.get("X-Meshnet-Route")
         if injected:
@@ -419,14 +640,16 @@ class _TorchHandler(http.server.BaseHTTPRequestHandler):
                             hops.append(hop)
                         elif isinstance(item, str):
                             hops.append({"endpoint": item, "start_layer": 0})
-                    print(f"  [node] using injected downstream route: {[h['endpoint'] for h in hops]}", flush=True)
+                    hops = _clamp_downstream_hops(hops, active_backend)
+                    print(
+                        f"  [node] using injected downstream route: {_format_downstream_route(hops)}",
+                        flush=True,
+                    )
                     return hops
             except (json.JSONDecodeError, TypeError, KeyError):
                 pass
 
         # Slow path: query the tracker (direct node-to-node calls, or tracker didn't inject).
-        server: _TorchHTTPServer = self.server  # type: ignore[assignment]
-        active_backend = backend or server.backend
         if server.tracker_url is None:
             return []
         route_model = getattr(active_backend, "model_id", None) or model
@@ -434,23 +657,31 @@ class _TorchHandler(http.server.BaseHTTPRequestHandler):
             url = f"{server.tracker_url}/v1/route?model={urllib.parse.quote(route_model)}"
             with urllib.request.urlopen(url, timeout=server.route_timeout) as r:
                 route_resp = json.loads(r.read())
-            own_port = server.server_address[1]
+            own_key = _own_endpoint_key(server)
             nodes_info = route_resp.get("nodes", [])
-            hops = []
+            hops: list[dict] = []
-            covered_up_to: int | None = None
+            passed_self = False
             for node_info in nodes_info:
                 ep = node_info.get("endpoint", "")
-                if ep.rstrip("/").endswith(f":{own_port}"):
+                if not ep:
-                    covered_up_to = node_info.get("shard_end")
                     continue
-                if covered_up_to is None:
+                if _endpoint_key(ep) == own_key:
-                    covered_up_to = (node_info.get("shard_start") or 1) - 1
+                    passed_self = True
-                hop = {"endpoint": ep, "start_layer": covered_up_to + 1}
+                    continue
+                if not passed_self:
+                    continue
+                hop = {
+                    "endpoint": ep,
+                    "start_layer": int(node_info.get("start_layer", 0)),
+                }
                 if node_info.get("relay_addr"):
                     hop["relay_addr"] = str(node_info["relay_addr"])
                 hops.append(hop)
-                covered_up_to = node_info.get("shard_end", covered_up_to)
+            hops = _clamp_downstream_hops(hops, active_backend)
-            print(f"  [node] tracker downstream route: {[h['endpoint'] for h in hops]}", flush=True)
+            print(
+                f"  [node] tracker downstream route: {_format_downstream_route(hops)}",
+                flush=True,
+            )
             return hops
         except Exception as exc:
             print(f"  [node] WARNING: route lookup failed for {route_model!r}: {exc}", flush=True)
@@ -783,6 +1014,12 @@ class TorchNodeServer:
     def queue_depth(self) -> int:
         return self._server.queue_depth if self._server is not None else 0
 
+    @property
+    def current_requests(self) -> list[dict[str, Any]]:
+        if self._server is None:
+            return []
+        return self._server.snapshot_current_requests()
+
     @property
     def loaded_model_ids(self) -> list[str]:
         return list(self._backends.keys())
@@ -862,6 +1099,11 @@ class TorchNodeServer:
         self._thread.start()
         return self.port
 
+    def set_advertised_endpoint(self, endpoint: str) -> None:
+        """Set the LAN-facing endpoint used for route self-detection."""
+        if self._server is not None:
+            self._server.advertised_endpoint = endpoint
+
     def stop(self) -> None:
         if self._server is None:
             return

packages/node/pyproject.toml

@@ -16,7 +16,8 @@ dependencies = [
     "rich>=13",
     "safetensors>=0.4",
     "torch>=2.1",
-    "transformers>=4.39",
+    "transformers>=5.12",
+    "triton-windows>=3.7; platform_system == 'Windows'",
     "websockets>=13",
     "zstandard>=0.22",
     "kernels>=0.11.1,<0.16",

packages/tracker/meshnet_tracker/accounts.py

@@ -8,7 +8,8 @@ regular user.
 Mutations are append-only events with unique ids — the same replication
 model as ``BillingLedger`` — so accounts and API keys converge across the
 tracker hive via gossip, and every dashboard can serve registration/login.
-Sessions are deliberately local to each tracker (bearer tokens in memory).
+Sessions are local to each tracker and persisted so dashboard cookies survive
+tracker restarts.
 """
 
 from __future__ import annotations
@@ -115,6 +116,8 @@ class AccountStore:
                 "account_id": account_id,
                 "expires": time.time() + SESSION_TTL,
             }
+            self._dirty = True
+        self.save_to_db()
         return token
 
     def session_account(self, token: str | None) -> dict | None:
@@ -134,7 +137,9 @@ class AccountStore:
         if not token:
             return
         with self._lock:
-            self._sessions.pop(token, None)
+            if self._sessions.pop(token, None) is not None:
+                self._dirty = True
+        self.save_to_db()
 
     # ---- API keys ----
 
@@ -271,6 +276,10 @@ class AccountStore:
             "CREATE TABLE IF NOT EXISTS account_events "
             "(event_id TEXT PRIMARY KEY, payload TEXT NOT NULL, ts REAL NOT NULL)"
         )
+        con.execute(
+            "CREATE TABLE IF NOT EXISTS account_sessions "
+            "(token TEXT PRIMARY KEY, account_id TEXT NOT NULL, expires REAL NOT NULL)"
+        )
         con.commit()
         con.close()
 
@@ -279,6 +288,10 @@ class AccountStore:
         rows = con.execute(
             "SELECT payload FROM account_events ORDER BY ts, event_id"
         ).fetchall()
+        session_rows = con.execute(
+            "SELECT token, account_id, expires FROM account_sessions WHERE expires >= ?",
+            (time.time(),),
+        ).fetchall()
         con.close()
         with self._lock:
             for (payload,) in rows:
@@ -288,6 +301,11 @@ class AccountStore:
                     continue
                 if event.get("id") not in self._seen_event_ids:
                     self._apply_locked(event)
+            self._sessions = {
+                token: {"account_id": account_id, "expires": float(expires)}
+                for token, account_id, expires in session_rows
+                if account_id in self._accounts
+            }
             self._dirty = False
 
     def save_to_db(self) -> None:
@@ -297,11 +315,21 @@ class AccountStore:
             if not self._dirty:
                 return
             events = list(self._event_log)
+            sessions = [
+                (token, session["account_id"], float(session["expires"]))
+                for token, session in self._sessions.items()
+                if session["expires"] >= time.time()
+            ]
             self._dirty = False
         con = sqlite3.connect(self._db_path)  # type: ignore[arg-type]
         con.executemany(
             "INSERT OR IGNORE INTO account_events (event_id, payload, ts) VALUES (?, ?, ?)",
             [(e["id"], json.dumps(e), float(e.get("ts", 0.0))) for e in events],
         )
+        con.execute("DELETE FROM account_sessions")
+        con.executemany(
+            "INSERT INTO account_sessions (token, account_id, expires) VALUES (?, ?, ?)",
+            sessions,
+        )
         con.commit()
         con.close()

packages/tracker/meshnet_tracker/cli.py

@@ -1,336 +1,419 @@
-"""meshnet-tracker CLI entry point."""
+"""meshnet-tracker CLI entry point."""
-
+
-import argparse
+import argparse
-import os
+import os
-import sys
+import sys
-import time
+import time
-from pathlib import Path
+from pathlib import Path
-
+
-from .accounts import DEFAULT_ACCOUNTS_DB_PATH
+from .accounts import DEFAULT_ACCOUNTS_DB_PATH
-from .billing import DEFAULT_BILLING_DB_PATH
+from .billing import DEFAULT_BILLING_DB_PATH
-from .hf_pricing import DEFAULT_HF_PRICING_LOG_DB_PATH
+from .hf_pricing import DEFAULT_HF_PRICING_LOG_DB_PATH
-from .server import (
+from .logging_setup import (
-    DEFAULT_CALLER_CREDIT_USDT,
+    DEFAULT_LOG_BACKUP_COUNT,
-    DEFAULT_DEVNET_TOPUP_USDT,
+    DEFAULT_LOG_DIR,
-    TrackerServer,
+    DEFAULT_LOG_MAX_BYTES,
-    derive_relay_url_from_public_tracker_url,
+    configure_tracker_file_logging,
-)
+)
-
+from .routing_stats import RoutingConfig
-DEFAULT_REGISTRY_DB_PATH = "meshnet_registry.sqlite3"
+from .server import (
-
+    DEFAULT_CALLER_CREDIT_USDT,
-
+    DEFAULT_DEVNET_TOPUP_USDT,
-def _load_env_file(path: Path) -> None:
+    TrackerServer,
-    """Load simple KEY=VALUE pairs from an env file without overriding env vars."""
+    derive_relay_url_from_public_tracker_url,
-    if not path.exists():
+)
-        return
+
-    try:
+DEFAULT_REGISTRY_DB_PATH = "meshnet_registry.sqlite3"
-        lines = path.read_text().splitlines()
+
-    except OSError:
+
-        return
+def _load_env_file(path: Path) -> None:
-    for line in lines:
+    """Load simple KEY=VALUE pairs from an env file without overriding env vars."""
-        text = line.strip()
+    if not path.exists():
-        if not text or text.startswith("#"):
+        return
-            continue
+    try:
-        if text.startswith("export "):
+        lines = path.read_text().splitlines()
-            text = text[len("export "):].strip()
+    except OSError:
-        if "=" not in text:
+        return
-            continue
+    for line in lines:
-        key, value = text.split("=", 1)
+        text = line.strip()
-        key = key.strip()
+        if not text or text.startswith("#"):
-        if not key or key in os.environ:
+            continue
-            continue
+        if text.startswith("export "):
-        value = value.strip()
+            text = text[len("export "):].strip()
-        if len(value) >= 2 and value[0] == value[-1] and value[0] in {"'", '"'}:
+        if "=" not in text:
-            value = value[1:-1]
+            continue
-        os.environ[key] = value
+        key, value = text.split("=", 1)
-
+        key = key.strip()
-
+        if not key or key in os.environ:
-def _load_env_defaults() -> None:
+            continue
-    """Load local and user-level tracker env defaults before parsing arguments."""
+        value = value.strip()
-    _load_env_file(Path.cwd() / ".env")
+        if len(value) >= 2 and value[0] == value[-1] and value[0] in {"'", '"'}:
-    _load_env_file(Path.home() / ".config" / "meshnet" / "secrets.env")
+            value = value[1:-1]
-
+        os.environ[key] = value
-
+
-def main() -> None:
+
-    _load_env_defaults()
+def _load_env_defaults() -> None:
-    common = argparse.ArgumentParser(add_help=False)
+    """Load local and user-level tracker env defaults before parsing arguments."""
-    common.add_argument("--host", default="0.0.0.0", help="Host interface to listen on")
+    _load_env_file(Path.cwd() / ".env")
-    common.add_argument("--port", type=int, default=8080, help="Port to listen on")
+    _load_env_file(Path.home() / ".config" / "meshnet" / "secrets.env")
-    common.add_argument(
+
-        "--heartbeat-timeout",
+
-        type=float,
+def _routing_config_from_args(args: argparse.Namespace) -> RoutingConfig | None:
-        default=30.0,
+    """Build a RoutingConfig from CLI flags; None keeps env-var/server defaults."""
-        help="Seconds before a node is removed from the registry after missed heartbeat",
+    overrides = {
-    )
+        "explore_share": args.route_explore_share,
-    common.add_argument(
+        "weight_alpha": args.route_weight_alpha,
-        "--cluster-peers",
+        "stats_half_life_seconds": args.route_stats_half_life,
-        default="",
+    }
-        help="Comma-separated URLs of peer tracker nodes (enables Raft cluster mode)",
+    set_values = {key: value for key, value in overrides.items() if value is not None}
-    )
+    if not set_values:
-    common.add_argument(
+        return None
-        "--self-url",
+    return RoutingConfig(**set_values)
-        default=None,
+
-        help="This tracker's own URL as seen by peers (auto-derived from --host/--port if omitted)",
+
-    )
+def main() -> None:
-    common.add_argument(
+    _load_env_defaults()
-        "--stats-db",
+    common = argparse.ArgumentParser(add_help=False)
-        default=None,
+    common.add_argument("--host", default="0.0.0.0", help="Host interface to listen on")
-        metavar="PATH",
+    common.add_argument("--port", type=int, default=8080, help="Port to listen on")
-        help="SQLite database path for persistent model usage statistics",
+    common.add_argument(
-    )
+        "--heartbeat-timeout",
-    common.add_argument(
+        type=float,
-        "--relay-url",
+        default=30.0,
-        default=None,
+        help="Seconds before a node is removed from the registry after missed heartbeat",
-        help="Public ws(s):// relay URL advertised to nodes, for example wss://ai.neuron.d-popov.com/ws",
+    )
-    )
+    common.add_argument(
-    common.add_argument(
+        "--cluster-peers",
-        "--billing-db",
+        default="",
-        default=DEFAULT_BILLING_DB_PATH,
+        help="Comma-separated URLs of peer tracker nodes (enables Raft cluster mode)",
-        metavar="PATH",
+    )
-        help=(
+    common.add_argument(
-            "SQLite database path for the USDT billing ledger "
+        "--self-url",
-            f"(default: {DEFAULT_BILLING_DB_PATH}; ADR-0015)"
+        default=None,
-        ),
+        help="This tracker's own URL as seen by peers (auto-derived from --host/--port if omitted)",
-    )
+    )
-    common.add_argument(
+    common.add_argument(
-        "--no-billing",
+        "--stats-db",
-        action="store_true",
+        default=None,
-        help="Disable the USDT billing ledger",
+        metavar="PATH",
-    )
+        help="SQLite database path for persistent model usage statistics",
-    common.add_argument(
+    )
-        "--max-charge-per-request",
+    common.add_argument(
-        type=float,
+        "--relay-url",
-        default=None,
+        default=None,
-        help=(
+        help="Public ws(s):// relay URL advertised to nodes, for example wss://ai.neuron.d-popov.com/ws",
-            "Reject chat completion requests whose prompt plus requested completion "
+    )
-            "token bound would cost more than this many USDT"
+    common.add_argument(
-        ),
+        "--billing-db",
-    )
+        default=DEFAULT_BILLING_DB_PATH,
-    common.add_argument(
+        metavar="PATH",
-        "--starting-credit",
+        help=(
-        type=float,
+            "SQLite database path for the USDT billing ledger "
-        default=DEFAULT_CALLER_CREDIT_USDT,
+            f"(default: {DEFAULT_BILLING_DB_PATH}; ADR-0015)"
-        metavar="USDT",
+        ),
-        help=(
+    )
-            "One-time Caller Credit granted when an account creates its first "
+    common.add_argument(
-            f"API key (default: {DEFAULT_CALLER_CREDIT_USDT}; set 0 to require "
+        "--no-billing",
-            "deposits before inference)"
+        action="store_true",
-        ),
+        help="Disable the USDT billing ledger",
-    )
+    )
-    common.add_argument(
+    common.add_argument(
-        "--devnet-topup",
+        "--max-charge-per-request",
-        type=float,
+        type=float,
-        default=DEFAULT_DEVNET_TOPUP_USDT,
+        default=None,
-        metavar="USDT",
+        help=(
-        help=(
+            "Reject chat completion requests whose prompt plus requested completion "
-            "Dashboard devnet top-up faucet: each click credits this many USDT "
+            "token bound would cost more than this many USDT"
-            f"to one of the account's keys (default: {DEFAULT_DEVNET_TOPUP_USDT}; "
+        ),
-            "MUST be 0 on mainnet deployments)"
+    )
-        ),
+    common.add_argument(
-    )
+        "--starting-credit",
-    common.add_argument(
+        type=float,
-        "--registry-db",
+        default=DEFAULT_CALLER_CREDIT_USDT,
-        default=DEFAULT_REGISTRY_DB_PATH,
+        metavar="USDT",
-        metavar="PATH",
+        help=(
-        help=(
+            "One-time Caller Credit granted when an account creates its first "
-            "SQLite database path for persisted strike/ban/reputation registry "
+            f"API key (default: {DEFAULT_CALLER_CREDIT_USDT}; set 0 to require "
-            f"state (default: {DEFAULT_REGISTRY_DB_PATH})"
+            "deposits before inference)"
-        ),
+        ),
-    )
+    )
-    common.add_argument(
+    common.add_argument(
-        "--no-registry-contracts",
+        "--devnet-topup",
-        action="store_true",
+        type=float,
-        help="Disable the local contract registry used for strike/ban/reputation enforcement",
+        default=DEFAULT_DEVNET_TOPUP_USDT,
-    )
+        metavar="USDT",
-    common.add_argument(
+        help=(
-        "--accounts-db",
+            "Dashboard devnet top-up faucet: each click credits this many USDT "
-        default=DEFAULT_ACCOUNTS_DB_PATH,
+            f"to one of the account's keys (default: {DEFAULT_DEVNET_TOPUP_USDT}; "
-        metavar="PATH",
+            "MUST be 0 on mainnet deployments)"
-        help=(
+        ),
-            "SQLite database path for dashboard user accounts "
+    )
-            f"(default: {DEFAULT_ACCOUNTS_DB_PATH})"
+    common.add_argument(
-        ),
+        "--registry-db",
-    )
+        default=DEFAULT_REGISTRY_DB_PATH,
-    common.add_argument(
+        metavar="PATH",
-        "--no-accounts",
+        help=(
-        action="store_true",
+            "SQLite database path for persisted strike/ban/reputation registry "
-        help="Disable dashboard user accounts (registration/login)",
+            f"state (default: {DEFAULT_REGISTRY_DB_PATH})"
-    )
+        ),
-    common.add_argument(
+    )
-        "--solana-rpc-url",
+    common.add_argument(
-        default=None,
+        "--no-registry-contracts",
-        help="Solana RPC URL (e.g. https://api.devnet.solana.com); enables the on-chain treasury",
+        action="store_true",
-    )
+        help="Disable the local contract registry used for strike/ban/reputation enforcement",
-    common.add_argument(
+    )
-        "--usdt-mint",
+    common.add_argument(
-        default=None,
+        "--accounts-db",
-        help="SPL mint address of (mock) USDT — see scripts/devnet_setup.py",
+        default=DEFAULT_ACCOUNTS_DB_PATH,
-    )
+        metavar="PATH",
-    common.add_argument(
+        help=(
-        "--treasury-keypair",
+            "SQLite database path for dashboard user accounts "
-        default=None,
+            f"(default: {DEFAULT_ACCOUNTS_DB_PATH})"
-        metavar="PATH",
+        ),
-        help="Treasury keypair JSON path (only on settlement-capable trackers)",
+    )
-    )
+    common.add_argument(
-    common.add_argument(
+        "--no-accounts",
-        "--settle-period",
+        action="store_true",
-        type=float,
+        help="Disable dashboard user accounts (registration/login)",
-        default=86400.0,
+    )
-        help="Max seconds between payouts to a node (dev: 60, prod: 86400)",
+    common.add_argument(
-    )
+        "--solana-rpc-url",
-    common.add_argument(
+        default=None,
-        "--payout-threshold",
+        help="Solana RPC URL (e.g. https://api.devnet.solana.com); enables the on-chain treasury",
-        type=float,
+    )
-        default=5.0,
+    common.add_argument(
-        help="Pending USDT that triggers an immediate payout (dev: 0)",
+        "--usdt-mint",
-    )
+        default=None,
-    common.add_argument(
+        help="SPL mint address of (mock) USDT — see scripts/devnet_setup.py",
-        "--payout-dust-floor",
+    )
-        type=float,
+    common.add_argument(
-        default=0.01,
+        "--treasury-keypair",
-        help="Never pay out less than this many USDT",
+        default=None,
-    )
+        metavar="PATH",
-    common.add_argument(
+        help="Treasury keypair JSON path (only on settlement-capable trackers)",
-        "--validator-service-token",
+    )
-        default=None,
+    common.add_argument(
-        help=(
+        "--settle-period",
-            "Service token the validator uses on POST /v1/billing/forfeit "
+        type=float,
-            "(default: MESHNET_VALIDATOR_SERVICE_TOKEN env; ADR-0017)"
+        default=86400.0,
-        ),
+        help="Max seconds between payouts to a node (dev: 60, prod: 86400)",
-    )
+    )
-    common.add_argument(
+    common.add_argument(
-        "--hive-secret",
+        "--payout-threshold",
-        default=None,
+        type=float,
-        help=(
+        default=5.0,
-            "Shared secret authenticating gossip between tracker peers "
+        help="Pending USDT that triggers an immediate payout (dev: 0)",
-            "(default: MESHNET_HIVE_SECRET env; required for multi-tracker replication)"
+    )
-        ),
+    common.add_argument(
-    )
+        "--payout-dust-floor",
-    common.add_argument(
+        type=float,
-        "--toploc-calibration-db",
+        default=0.01,
-        default=None,
+        help="Never pay out less than this many USDT",
-        metavar="PATH",
+    )
-        help=(
+    common.add_argument(
-            "SQLite path for the AH-021 honest-noise TOPLOC calibration corpus "
+        "--validator-service-token",
-            "(enables POST /v1/calibration/toploc/run + GET /v1/calibration/toploc/results)"
+        default=None,
-        ),
+        help=(
-    )
+            "Service token the validator uses on POST /v1/billing/forfeit "
-    common.add_argument(
+            "(default: MESHNET_VALIDATOR_SERVICE_TOKEN env; ADR-0017)"
-        "--toploc-reference-node-url",
+        ),
-        default=None,
+    )
-        help="Reference node the calibration job teacher-forces claimed tokens against (see validator README)",
+    common.add_argument(
-    )
+        "--hive-secret",
-    common.add_argument(
+        default=None,
-        "--toploc-calibration-gate-min-hardware-profiles",
+        help=(
-        type=int,
+            "Shared secret authenticating gossip between tracker peers "
-        default=1,
+            "(default: MESHNET_HIVE_SECRET env; required for multi-tracker replication)"
-        help=(
+        ),
-            "Distinct (GPU model, dtype) profiles the corpus must cover before "
+    )
-            "gate_status.ready is true (alpha exception: fleet size is acceptable)"
+    common.add_argument(
-        ),
+        "--toploc-calibration-db",
-    )
+        default=None,
-    common.add_argument(
+        metavar="PATH",
-        "--enable-hf-pricing",
+        help=(
-        action="store_true",
+            "SQLite path for the AH-021 honest-noise TOPLOC calibration corpus "
-        help=(
+            "(enables POST /v1/calibration/toploc/run + GET /v1/calibration/toploc/results)"
-            "Enable the daily dynamic pricing refresh (issue 23): for presets with a "
+        ),
-            "curated hf_aliases list, sets the client price to 80%% of the cheapest "
+    )
-            "matching HuggingFace inference-marketplace rate. Presets without "
+    common.add_argument(
-            "hf_aliases are unaffected and keep their static price."
+        "--toploc-reference-node-url",
-        ),
+        default=None,
-    )
+        help="Reference node the calibration job teacher-forces claimed tokens against (see validator README)",
-    common.add_argument(
+    )
-        "--hf-pricing-log-db",
+    common.add_argument(
-        default=None,
+        "--toploc-calibration-gate-min-hardware-profiles",
-        metavar="PATH",
+        type=int,
-        help=(
+        default=1,
-            "SQLite database path for the dynamic pricing change log "
+        help=(
-            f"(default when --enable-hf-pricing is set: {DEFAULT_HF_PRICING_LOG_DB_PATH}; "
+            "Distinct (GPU model, dtype) profiles the corpus must cover before "
-            "enables GET /v1/pricing/hf/history)"
+            "gate_status.ready is true (alpha exception: fleet size is acceptable)"
-        ),
+        ),
-    )
+    )
-    common.add_argument(
+    common.add_argument(
-        "--hf-pricing-refresh-interval",
+        "--enable-hf-pricing",
-        type=float,
+        action="store_true",
-        default=86400.0,
+        help=(
-        help="Seconds between dynamic pricing refresh passes (default: daily)",
+            "Enable the daily dynamic pricing refresh (issue 23): for presets with a "
-    )
+            "curated hf_aliases list, sets the client price to 80%% of the cheapest "
-    common.add_argument(
+            "matching HuggingFace inference-marketplace rate. Presets without "
-        "--models-dir",
+            "hf_aliases are unaffected and keep their static price."
-        default=None,
+        ),
-        metavar="PATH",
+    )
-        help="Local HuggingFace snapshot root advertised as tracker model-file source (default: MESHNET_MODELS_DIR)",
+    common.add_argument(
-    )
+        "--hf-pricing-log-db",
-
+        default=None,
-    parser = argparse.ArgumentParser(
+        metavar="PATH",
-        prog="meshnet-tracker",
+        help=(
-        description="Distributed Inference Network node registry and route selection",
+            "SQLite database path for the dynamic pricing change log "
-        parents=[common],
+            f"(default when --enable-hf-pricing is set: {DEFAULT_HF_PRICING_LOG_DB_PATH}; "
-    )
+            "enables GET /v1/pricing/hf/history)"
-    subparsers = parser.add_subparsers(dest="command")
+        ),
-
+    )
-    subparsers.add_parser("start", help="Start the tracker server", parents=[common])
+    common.add_argument(
-
+        "--hf-pricing-refresh-interval",
-    args = parser.parse_args()
+        type=float,
-
+        default=86400.0,
-    if args.command in {None, "start"}:
+        help="Seconds between dynamic pricing refresh passes (default: daily)",
-        cluster_peers = [u.strip() for u in args.cluster_peers.split(",") if u.strip()]
+    )
-        relay_url = args.relay_url or derive_relay_url_from_public_tracker_url(args.self_url)
+    common.add_argument(
-        treasury = None
+        "--models-dir",
-        if args.solana_rpc_url and args.usdt_mint and args.treasury_keypair:
+        default=None,
-            from meshnet_contracts.solana_adapter import SolanaCustodialTreasury
+        metavar="PATH",
-
+        help="Local HuggingFace snapshot root advertised as tracker model-file source (default: MESHNET_MODELS_DIR)",
-            treasury = SolanaCustodialTreasury(
+    )
-                args.solana_rpc_url, args.usdt_mint, args.treasury_keypair,
+    common.add_argument(
-            )
+        "--route-explore-share",
-        contracts = None
+        type=float,
-        if not args.no_registry_contracts:
+        default=None,
-            from meshnet_contracts import LocalSolanaContracts  # type: ignore[import-not-found]
+        metavar="FRACTION",
-
+        help=(
-            contracts = LocalSolanaContracts(registry_db=args.registry_db)
+            "Fraction of requests routed down unproven/stale routes to gather "
-        server = TrackerServer(
+            "throughput statistics (ADR-0021; default 0.3, lower once traffic grows)"
-            host=args.host,
+        ),
-            port=args.port,
+    )
-            heartbeat_timeout=args.heartbeat_timeout,
+    common.add_argument(
-            cluster_peers=cluster_peers or None,
+        "--route-weight-alpha",
-            cluster_self_url=args.self_url,
+        type=float,
-            stats_db=getattr(args, "stats_db", None),
+        default=None,
-            relay_url=relay_url,
+        metavar="ALPHA",
-            enable_billing=not args.no_billing,
+        help=(
-            billing_db=None if args.no_billing else args.billing_db,
+            "Traffic weight exponent among proven routes: share ∝ tps^alpha "
-            max_charge_per_request=args.max_charge_per_request,
+            "(default 1.0 — a 1.5x-faster route gets 1.5x the traffic)"
-            starting_credit=args.starting_credit,
+        ),
-            devnet_topup_amount=args.devnet_topup,
+    )
-            contracts=contracts,
+    common.add_argument(
-            accounts_db=None if args.no_accounts else args.accounts_db,
+        "--route-stats-half-life",
-            treasury=treasury,
+        type=float,
-            settle_period=args.settle_period,
+        default=None,
-            payout_threshold=args.payout_threshold,
+        metavar="SECONDS",
-            payout_dust_floor=args.payout_dust_floor,
+        help="Half-life for decaying route throughput observations (default 600)",
-            validator_service_token=args.validator_service_token,
+    )
-            hive_secret=args.hive_secret,
+    common.add_argument(
-            toploc_calibration_db=args.toploc_calibration_db,
+        "--log-dir",
-            toploc_reference_node_url=args.toploc_reference_node_url,
+        default=DEFAULT_LOG_DIR,
-            toploc_calibration_gate_min_hardware_profiles=args.toploc_calibration_gate_min_hardware_profiles,
+        metavar="PATH",
-            enable_hf_pricing=args.enable_hf_pricing,
+        help=(
-            hf_pricing_log_db=(
+            "Directory for rotating tracker logs "
-                args.hf_pricing_log_db
+            f"(default: {DEFAULT_LOG_DIR}; files: info.log, warning.log, error.log)"
-                or (DEFAULT_HF_PRICING_LOG_DB_PATH if args.enable_hf_pricing else None)
+        ),
-            ),
+    )
-            hf_pricing_refresh_interval=args.hf_pricing_refresh_interval,
+    common.add_argument(
-            models_dir=args.models_dir,
+        "--log-max-bytes",
-        )
+        type=int,
-        port = server.start()
+        default=DEFAULT_LOG_MAX_BYTES,
-        print(f"meshnet-tracker listening on http://{args.host}:{port}", flush=True)
+        metavar="BYTES",
-        try:
+        help=f"Rotate each tracker log file after this many bytes (default: {DEFAULT_LOG_MAX_BYTES})",
-            while True:
+    )
-                time.sleep(1)
+    common.add_argument(
-        except KeyboardInterrupt:
+        "--log-backup-count",
-            server.stop()
+        type=int,
-            sys.exit(0)
+        default=DEFAULT_LOG_BACKUP_COUNT,
-    else:
+        metavar="N",
-        parser.print_help()
+        help=f"Number of rotated tracker log files to keep per level (default: {DEFAULT_LOG_BACKUP_COUNT})",
-
+    )
-
+    common.add_argument(
-if __name__ == "__main__":
+        "--no-file-logs",
-    main()
+        action="store_true",
+        help="Disable rotating tracker log files and only write to the terminal",
+    )
+
+    parser = argparse.ArgumentParser(
+        prog="meshnet-tracker",
+        description="Distributed Inference Network node registry and route selection",
+        parents=[common],
+    )
+    subparsers = parser.add_subparsers(dest="command")
+
+    subparsers.add_parser("start", help="Start the tracker server", parents=[common])
+
+    args = parser.parse_args()
+
+    if args.command in {None, "start"}:
+        if not args.no_file_logs:
+            log_dir = configure_tracker_file_logging(
+                args.log_dir,
+                max_bytes=args.log_max_bytes,
+                backup_count=args.log_backup_count,
+            )
+            print(f"meshnet-tracker logs: {log_dir}", flush=True)
+        cluster_peers = [u.strip() for u in args.cluster_peers.split(",") if u.strip()]
+        relay_url = args.relay_url or derive_relay_url_from_public_tracker_url(args.self_url)
+        treasury = None
+        if args.solana_rpc_url and args.usdt_mint and args.treasury_keypair:
+            from meshnet_contracts.solana_adapter import SolanaCustodialTreasury
+
+            treasury = SolanaCustodialTreasury(
+                args.solana_rpc_url, args.usdt_mint, args.treasury_keypair,
+            )
+        contracts = None
+        if not args.no_registry_contracts:
+            from meshnet_contracts import LocalSolanaContracts  # type: ignore[import-not-found]
+
+            contracts = LocalSolanaContracts(registry_db=args.registry_db)
+        server = TrackerServer(
+            host=args.host,
+            port=args.port,
+            heartbeat_timeout=args.heartbeat_timeout,
+            cluster_peers=cluster_peers or None,
+            cluster_self_url=args.self_url,
+            stats_db=getattr(args, "stats_db", None),
+            relay_url=relay_url,
+            enable_billing=not args.no_billing,
+            billing_db=None if args.no_billing else args.billing_db,
+            max_charge_per_request=args.max_charge_per_request,
+            starting_credit=args.starting_credit,
+            devnet_topup_amount=args.devnet_topup,
+            contracts=contracts,
+            accounts_db=None if args.no_accounts else args.accounts_db,
+            treasury=treasury,
+            settle_period=args.settle_period,
+            payout_threshold=args.payout_threshold,
+            payout_dust_floor=args.payout_dust_floor,
+            validator_service_token=args.validator_service_token,
+            hive_secret=args.hive_secret,
+            toploc_calibration_db=args.toploc_calibration_db,
+            toploc_reference_node_url=args.toploc_reference_node_url,
+            toploc_calibration_gate_min_hardware_profiles=args.toploc_calibration_gate_min_hardware_profiles,
+            enable_hf_pricing=args.enable_hf_pricing,
+            hf_pricing_log_db=(
+                args.hf_pricing_log_db
+                or (DEFAULT_HF_PRICING_LOG_DB_PATH if args.enable_hf_pricing else None)
+            ),
+            hf_pricing_refresh_interval=args.hf_pricing_refresh_interval,
+            models_dir=args.models_dir,
+            routing_config=_routing_config_from_args(args),
+        )
+        port = server.start()
+        print(f"meshnet-tracker listening on http://{args.host}:{port}", flush=True)
+        try:
+            while True:
+                time.sleep(1)
+        except KeyboardInterrupt:
+            server.stop()
+            sys.exit(0)
+    else:
+        parser.print_help()
+
+
+if __name__ == "__main__":
+    main()

packages/tracker/meshnet_tracker/logging_setup.py

@@ -0,0 +1,99 @@
+"""Rotating file logging for the tracker CLI."""
+
+from __future__ import annotations
+
+import logging
+import sys
+from logging.handlers import RotatingFileHandler
+from pathlib import Path
+from typing import TextIO
+
+
+DEFAULT_LOG_DIR = "logs/tracker"
+DEFAULT_LOG_MAX_BYTES = 10 * 1024 * 1024
+DEFAULT_LOG_BACKUP_COUNT = 5
+TRACKER_LOGGER_NAME = "meshnet.tracker"
+
+
+class _ExactLevelFilter(logging.Filter):
+    def __init__(self, level: int) -> None:
+        super().__init__()
+        self._level = level
+
+    def filter(self, record: logging.LogRecord) -> bool:
+        return record.levelno == self._level
+
+
+class _TeeStream:
+    def __init__(self, stream: TextIO, logger: logging.Logger, level: int) -> None:
+        self._stream = stream
+        self._logger = logger
+        self._level = level
+        self._buffer = ""
+
+    def write(self, text: str) -> int:
+        self._stream.write(text)
+        self._stream.flush()
+        self._buffer += text
+        while "\n" in self._buffer:
+            line, self._buffer = self._buffer.split("\n", 1)
+            line = line.rstrip()
+            if line:
+                self._logger.log(self._level, line)
+        return len(text)
+
+    def flush(self) -> None:
+        self._stream.flush()
+        line = self._buffer.rstrip()
+        if line:
+            self._logger.log(self._level, line)
+        self._buffer = ""
+
+    def isatty(self) -> bool:
+        return self._stream.isatty()
+
+
+def _make_handler(path: Path, level: int, *, max_bytes: int, backup_count: int) -> RotatingFileHandler:
+    handler = RotatingFileHandler(
+        path,
+        maxBytes=max_bytes,
+        backupCount=backup_count,
+        encoding="utf-8",
+    )
+    handler.setLevel(level)
+    handler.addFilter(_ExactLevelFilter(level))
+    handler.setFormatter(logging.Formatter("%(asctime)s %(levelname)s %(message)s"))
+    return handler
+
+
+def configure_tracker_file_logging(
+    log_dir: str | Path = DEFAULT_LOG_DIR,
+    *,
+    max_bytes: int = DEFAULT_LOG_MAX_BYTES,
+    backup_count: int = DEFAULT_LOG_BACKUP_COUNT,
+    tee_stdio: bool = True,
+) -> Path:
+    """Configure rotatable info/warning/error log files and return the directory."""
+
+    path = Path(log_dir).expanduser()
+    path.mkdir(parents=True, exist_ok=True)
+
+    logger = logging.getLogger(TRACKER_LOGGER_NAME)
+    logger.setLevel(logging.INFO)
+    logger.propagate = False
+    logger.handlers.clear()
+    logger.addHandler(_make_handler(path / "info.log", logging.INFO, max_bytes=max_bytes, backup_count=backup_count))
+    logger.addHandler(_make_handler(path / "warning.log", logging.WARNING, max_bytes=max_bytes, backup_count=backup_count))
+    logger.addHandler(_make_handler(path / "error.log", logging.ERROR, max_bytes=max_bytes, backup_count=backup_count))
+
+    if tee_stdio:
+        if not isinstance(sys.stdout, _TeeStream):
+            sys.stdout = _TeeStream(sys.stdout, logger, logging.INFO)  # type: ignore[assignment]
+        if not isinstance(sys.stderr, _TeeStream):
+            sys.stderr = _TeeStream(sys.stderr, logger, logging.ERROR)  # type: ignore[assignment]
+
+    return path
+
+
+def tracker_logger() -> logging.Logger:
+    return logging.getLogger(TRACKER_LOGGER_NAME)

packages/tracker/meshnet_tracker/routing_stats.py

@@ -0,0 +1,257 @@
+"""Learned route statistics for dynamic bandit-style route selection (ADR-0021).
+
+The tracker treats each viable route (ordered chain of node shards covering a
+model) as a bandit arm. Observed end-to-end tokens/sec per route is kept as a
+time-decayed EWMA. Selection splits traffic between:
+
+- **exploit**: weighted-random among *proven* routes, weight ∝ tps ** alpha
+  (alpha=1.0 → a 1.5x-faster route gets 1.5x the traffic);
+- **scout**: with probability `explore_share`, the least-measured unproven or
+  stale route is chosen so the tracker keeps learning as the network morphs.
+
+Staleness has two mechanisms:
+- continuous: sample mass decays with `stats_half_life_seconds`, so old
+  observations fade;
+- abrupt: every node join/leave bumps the model's *topology epoch*; stats from
+  an older epoch keep their EWMA as a prior but drop back into the scout pool
+  until re-measured.
+
+Route signatures embed node ids and shard ranges, so a node re-registering
+with a different shard produces a new arm automatically.
+"""
+
+from __future__ import annotations
+
+import random
+import threading
+import time
+from dataclasses import dataclass, field
+from typing import Any, Iterable
+
+
+@dataclass(frozen=True)
+class RoutingConfig:
+    explore_share: float = 0.3
+    weight_alpha: float = 1.0
+    stats_half_life_seconds: float = 600.0
+    min_sample_tokens: int = 8
+    # One fresh sample has mass 1.0 and decays from there; 0.5 keeps a single
+    # observation "proven" for one half-life before demoting it to the scout pool.
+    min_proven_weight: float = 0.5
+    max_candidate_routes: int = 8
+    prune_after_seconds: float = 86400.0
+
+
+@dataclass
+class RouteStat:
+    ewma_tps: float = 0.0
+    weight: float = 0.0  # decayed effective sample mass
+    last_sample_ts: float = 0.0
+    epoch: int = 0
+    samples: int = 0  # lifetime raw sample count (display only)
+
+    def decayed_weight(self, now: float, half_life: float) -> float:
+        if self.weight <= 0.0:
+            return 0.0
+        age = max(0.0, now - self.last_sample_ts)
+        return self.weight * 0.5 ** (age / half_life)
+
+
+@dataclass
+class RouteCandidate:
+    nodes: list[Any]
+    signature: str
+    prior_tps: float = 0.0
+
+
+def route_signature(model_key: str, nodes: Iterable[Any]) -> str:
+    hops = "->".join(
+        f"{getattr(n, 'node_id', '?')}[{getattr(n, 'shard_start', '?')}-{getattr(n, 'shard_end', '?')}]"
+        for n in nodes
+    )
+    return f"{model_key}|{hops}"
+
+
+class RouteStatsStore:
+    """Thread-safe per-route decayed throughput statistics."""
+
+    def __init__(self, config: RoutingConfig | None = None) -> None:
+        self.config = config or RoutingConfig()
+        self._lock = threading.Lock()
+        self._stats: dict[str, RouteStat] = {}
+        self._epochs: dict[str, int] = {}
+
+    def epoch(self, model_key: str) -> int:
+        with self._lock:
+            return self._epochs.get(model_key, 0)
+
+    def bump_epoch(self, model_keys: Iterable[str | None]) -> None:
+        """Mark the topology changed for the given model keys (node join/leave)."""
+        with self._lock:
+            for key in model_keys:
+                if key:
+                    self._epochs[key] = self._epochs.get(key, 0) + 1
+
+    def record_sample(
+        self,
+        model_key: str,
+        signature: str,
+        tokens: int,
+        elapsed_seconds: float,
+        now: float | None = None,
+    ) -> bool:
+        """Fold one completed request into the route's EWMA.
+
+        Returns False (and records nothing) for samples below
+        `min_sample_tokens` — near-empty completions come from broken routes
+        and would poison the arm with meaningless throughput values.
+        """
+        cfg = self.config
+        if tokens < cfg.min_sample_tokens or elapsed_seconds <= 0.0:
+            return False
+        tps = tokens / elapsed_seconds
+        ts = time.time() if now is None else now
+        with self._lock:
+            stat = self._stats.get(signature)
+            if stat is None:
+                stat = RouteStat()
+                self._stats[signature] = stat
+            carried = stat.decayed_weight(ts, cfg.stats_half_life_seconds)
+            total = carried + 1.0
+            stat.ewma_tps = (stat.ewma_tps * carried + tps) / total
+            stat.weight = total
+            stat.last_sample_ts = ts
+            stat.epoch = self._epochs.get(model_key, 0)
+            stat.samples += 1
+        return True
+
+    def snapshot(self, signature: str, model_key: str, now: float | None = None) -> dict:
+        """Point-in-time view of one route's learned state."""
+        ts = time.time() if now is None else now
+        cfg = self.config
+        with self._lock:
+            stat = self._stats.get(signature)
+            current_epoch = self._epochs.get(model_key, 0)
+        if stat is None:
+            return {"tps": None, "weight": 0.0, "samples": 0, "status": "unsampled"}
+        weight = stat.decayed_weight(ts, cfg.stats_half_life_seconds)
+        if stat.epoch != current_epoch:
+            status = "stale"
+        elif weight < cfg.min_proven_weight:
+            status = "decayed" if stat.samples else "unsampled"
+        else:
+            status = "proven"
+        return {
+            "tps": round(stat.ewma_tps, 4) if stat.samples else None,
+            "weight": round(weight, 4),
+            "samples": stat.samples,
+            "status": status,
+        }
+
+    def prune(self, now: float | None = None) -> int:
+        """Drop routes with no samples for `prune_after_seconds`."""
+        ts = time.time() if now is None else now
+        cutoff = ts - self.config.prune_after_seconds
+        with self._lock:
+            dead = [sig for sig, stat in self._stats.items() if stat.last_sample_ts < cutoff]
+            for sig in dead:
+                del self._stats[sig]
+        return len(dead)
+
+
+def choose_route(
+    candidates: list[RouteCandidate],
+    store: RouteStatsStore,
+    model_key: str,
+    rng: random.Random | None = None,
+    now: float | None = None,
+) -> tuple[RouteCandidate | None, dict]:
+    """Pick a route: ε-scout among unproven arms, else weighted ∝ tps**alpha.
+
+    Returns (candidate, decision) where decision explains the pick for logs
+    and diagnostics: {"mode": "scout"|"exploit"|"prior", ...}.
+    """
+    if not candidates:
+        return None, {"mode": "none"}
+    rng = rng or random
+    cfg = store.config
+    proven: list[tuple[RouteCandidate, float]] = []
+    scouts: list[tuple[RouteCandidate, float]] = []
+    for cand in candidates:
+        snap = store.snapshot(cand.signature, model_key, now=now)
+        if snap["status"] == "proven":
+            proven.append((cand, max(float(snap["tps"] or 0.0), 1e-6)))
+        else:
+            scouts.append((cand, float(snap["weight"])))
+    if scouts and (not proven or rng.random() < cfg.explore_share):
+        # Least-measured first so new/stale arms accumulate samples fastest;
+        # tiebreak on prior estimate so plausible routes get scouted first.
+        scouts.sort(key=lambda item: (item[1], -item[0].prior_tps))
+        pick = scouts[0][0]
+        return pick, {"mode": "scout", "signature": pick.signature}
+    if proven:
+        weights = [tps ** cfg.weight_alpha for _, tps in proven]
+        pick = rng.choices([cand for cand, _ in proven], weights=weights, k=1)[0]
+        return pick, {
+            "mode": "exploit",
+            "signature": pick.signature,
+            "candidates": len(proven),
+        }
+    # No stats anywhere yet — fall back to the prior (benchmark-derived) estimate.
+    weights = [max(cand.prior_tps, 1e-6) ** cfg.weight_alpha for cand in candidates]
+    pick = rng.choices(candidates, weights=weights, k=1)[0]
+    return pick, {"mode": "prior", "signature": pick.signature}
+
+
+def route_table(
+    candidates: list[RouteCandidate],
+    store: RouteStatsStore,
+    model_key: str,
+    now: float | None = None,
+) -> list[dict]:
+    """Diagnostics rows: learned tps, coefficient vs best, expected traffic share."""
+    cfg = store.config
+    rows = []
+    for cand in candidates:
+        snap = store.snapshot(cand.signature, model_key, now=now)
+        rows.append({"candidate": cand, **snap})
+    proven = [r for r in rows if r["status"] == "proven"]
+    scouts = [r for r in rows if r["status"] != "proven"]
+    best_tps = max((float(r["tps"]) for r in proven), default=0.0)
+    exploit_budget = 1.0 - (cfg.explore_share if scouts and proven else 0.0)
+    if not proven:
+        exploit_budget = 0.0
+    weight_sum = sum(float(r["tps"]) ** cfg.weight_alpha for r in proven) or 1.0
+    out = []
+    for r in rows:
+        cand: RouteCandidate = r["candidate"]
+        if r["status"] == "proven":
+            share = exploit_budget * (float(r["tps"]) ** cfg.weight_alpha) / weight_sum
+            coefficient = round(float(r["tps"]) / best_tps, 3) if best_tps else None
+        else:
+            share = (
+                (cfg.explore_share if proven else 1.0) / len(scouts)
+                if scouts
+                else 0.0
+            )
+            coefficient = None
+        out.append({
+            "signature": cand.signature,
+            "hops": [
+                {
+                    "node_id": getattr(n, "node_id", "?"),
+                    "shard": f"{getattr(n, 'shard_start', '?')}-{getattr(n, 'shard_end', '?')}",
+                    "endpoint": getattr(n, "endpoint", "?"),
+                }
+                for n in cand.nodes
+            ],
+            "tps": r["tps"],
+            "coefficient": coefficient,
+            "expected_share": round(share, 4),
+            "samples": r["samples"],
+            "weight": r["weight"],
+            "status": r["status"],
+            "prior_tps": round(cand.prior_tps, 4),
+        })
+    out.sort(key=lambda r: (-(r["tps"] or 0.0), -r["prior_tps"]))
+    return out

tests/test_accounts.py

@@ -1,319 +1,384 @@
-"""Dashboard user accounts: registration, login, roles, API keys, usage.
+"""Dashboard user accounts: registration, login, roles, API keys, usage.
-
+
-Unit tests for AccountStore plus HTTP integration on the tracker:
+Unit tests for AccountStore plus HTTP integration on the tracker:
-register/login/logout, per-account balance and usage, API-key lifecycle
+register/login/logout, per-account balance and usage, API-key lifecycle
-(revoked keys rejected by the OpenAI proxy), and the admin listing.
+(revoked keys rejected by the OpenAI proxy), and the admin listing.
-"""
+"""
-
+
-import json
+import http.cookies
-import urllib.error
+import json
-import urllib.request
+import urllib.error
-
+import urllib.request
-import pytest
+
-
+import pytest
-from meshnet_tracker.accounts import AccountStore
+
-from meshnet_tracker.auth import sign_hive_request
+from meshnet_tracker.accounts import AccountStore
-from meshnet_tracker.billing import BillingLedger
+from meshnet_tracker.auth import sign_hive_request
-from meshnet_tracker.server import TrackerServer
+from meshnet_tracker.billing import BillingLedger
-
+from meshnet_tracker.server import TrackerServer
-HIVE_SECRET = "test-hive-secret"
+
-
+HIVE_SECRET = "test-hive-secret"
-
+
-# ---------------------------------------------------------------- unit tests
+
-
+# ---------------------------------------------------------------- unit tests
-
+
-def test_first_account_is_admin_then_users():
+
-    store = AccountStore()
+def test_first_account_is_admin_then_users():
-    first = store.register(email="admin@example.com", password="secret-123")
+    store = AccountStore()
-    second = store.register(email="user@example.com", password="secret-123")
+    first = store.register(email="admin@example.com", password="secret-123")
-    assert first["role"] == "admin"
+    second = store.register(email="user@example.com", password="secret-123")
-    assert second["role"] == "user"
+    assert first["role"] == "admin"
-
+    assert second["role"] == "user"
-
+
-def test_register_requires_email_or_wallet_and_password_length():
+
-    store = AccountStore()
+def test_register_requires_email_or_wallet_and_password_length():
-    with pytest.raises(ValueError, match="email or a wallet"):
+    store = AccountStore()
-        store.register(password="secret-123")
+    with pytest.raises(ValueError, match="email or a wallet"):
-    with pytest.raises(ValueError, match="invalid email"):
+        store.register(password="secret-123")
-        store.register(email="not-an-email", password="secret-123")
+    with pytest.raises(ValueError, match="invalid email"):
-    with pytest.raises(ValueError, match="at least 8"):
+        store.register(email="not-an-email", password="secret-123")
-        store.register(email="a@b.co", password="short")
+    with pytest.raises(ValueError, match="at least 8"):
-
+        store.register(email="a@b.co", password="short")
-
+
-def test_register_rejects_duplicate_identifiers():
+
-    store = AccountStore()
+def test_register_rejects_duplicate_identifiers():
-    store.register(email="dup@example.com", password="secret-123")
+    store = AccountStore()
-    with pytest.raises(ValueError, match="already exists"):
+    store.register(email="dup@example.com", password="secret-123")
-        store.register(email="DUP@example.com", password="other-secret")
+    with pytest.raises(ValueError, match="already exists"):
-
+        store.register(email="DUP@example.com", password="other-secret")
-
+
-def test_login_by_email_or_wallet():
+
-    store = AccountStore()
+def test_login_by_email_or_wallet():
-    account = store.register(
+    store = AccountStore()
-        email="both@example.com", wallet="WalletXYZ", password="secret-123"
+    account = store.register(
-    )
+        email="both@example.com", wallet="WalletXYZ", password="secret-123"
-    assert store.verify_login("both@example.com", "secret-123")["account_id"] == account["account_id"]
+    )
-    assert store.verify_login("WalletXYZ", "secret-123")["account_id"] == account["account_id"]
+    assert store.verify_login("both@example.com", "secret-123")["account_id"] == account["account_id"]
-    assert store.verify_login("both@example.com", "wrong-password") is None
+    assert store.verify_login("WalletXYZ", "secret-123")["account_id"] == account["account_id"]
-    assert store.verify_login("nobody@example.com", "secret-123") is None
+    assert store.verify_login("both@example.com", "wrong-password") is None
-
+    assert store.verify_login("nobody@example.com", "secret-123") is None
-
+
-def test_sessions_resolve_and_destroy():
+
-    store = AccountStore()
+def test_sessions_resolve_and_destroy():
-    account = store.register(email="s@example.com", password="secret-123")
+    store = AccountStore()
-    token = store.create_session(account["account_id"])
+    account = store.register(email="s@example.com", password="secret-123")
-    assert store.session_account(token)["account_id"] == account["account_id"]
+    token = store.create_session(account["account_id"])
-    store.destroy_session(token)
+    assert store.session_account(token)["account_id"] == account["account_id"]
-    assert store.session_account(token) is None
+    store.destroy_session(token)
-    assert store.session_account("bogus") is None
+    assert store.session_account(token) is None
-
+    assert store.session_account("bogus") is None
-
+
-def test_api_key_lifecycle():
+
-    store = AccountStore()
+def test_sessions_persist_across_restart(tmp_path):
-    account = store.register(email="k@example.com", password="secret-123")
+    db = str(tmp_path / "accounts.db")
-    other = store.register(email="other@example.com", password="secret-123")
+    store = AccountStore(db_path=db)
-    key = store.create_api_key(account["account_id"])
+    account = store.register(email="cookie@example.com", password="secret-123")
-    assert key.startswith("sk-mesh-")
+    token = store.create_session(account["account_id"])
-    assert store.keys_for(account["account_id"]) == [key]
+    store.save_to_db()
-    # someone else's account cannot revoke it
+
-    assert store.revoke_api_key(other["account_id"], key) is False
+    reloaded = AccountStore(db_path=db)
-    assert store.revoke_api_key(account["account_id"], key) is True
+    assert reloaded.session_account(token)["account_id"] == account["account_id"]
-    assert store.keys_for(account["account_id"]) == []
+
-    assert store.is_key_revoked(key)
+
-
+def test_api_key_lifecycle():
-
+    store = AccountStore()
-def test_accounts_persist_across_restart(tmp_path):
+    account = store.register(email="k@example.com", password="secret-123")
-    db = str(tmp_path / "accounts.db")
+    other = store.register(email="other@example.com", password="secret-123")
-    store = AccountStore(db_path=db)
+    key = store.create_api_key(account["account_id"])
-    account = store.register(email="p@example.com", password="secret-123")
+    assert key.startswith("sk-mesh-")
-    key = store.create_api_key(account["account_id"])
+    assert store.keys_for(account["account_id"]) == [key]
-    store.save_to_db()
+    # someone else's account cannot revoke it
-
+    assert store.revoke_api_key(other["account_id"], key) is False
-    reloaded = AccountStore(db_path=db)
+    assert store.revoke_api_key(account["account_id"], key) is True
-    assert reloaded.verify_login("p@example.com", "secret-123") is not None
+    assert store.keys_for(account["account_id"]) == []
-    assert reloaded.keys_for(account["account_id"]) == [key]
+    assert store.is_key_revoked(key)
-
+
-
+
-def test_account_events_replicate_and_dedupe():
+def test_accounts_persist_across_restart(tmp_path):
-    leader = AccountStore()
+    db = str(tmp_path / "accounts.db")
-    follower = AccountStore()
+    store = AccountStore(db_path=db)
-    account = leader.register(email="r@example.com", password="secret-123")
+    account = store.register(email="p@example.com", password="secret-123")
-    key = leader.create_api_key(account["account_id"])
+    key = store.create_api_key(account["account_id"])
-    leader.revoke_api_key(account["account_id"], key)
+    store.save_to_db()
-
+
-    events, cursor = leader.events_since(0)
+    reloaded = AccountStore(db_path=db)
-    assert follower.apply_events(events) == len(events)
+    assert reloaded.verify_login("p@example.com", "secret-123") is not None
-    assert follower.apply_events(events) == 0  # replay is a no-op
+    assert reloaded.keys_for(account["account_id"]) == [key]
-    assert follower.verify_login("r@example.com", "secret-123") is not None
+
-    assert follower.is_key_revoked(key)
+
-    more, _ = leader.events_since(cursor)
+def test_account_events_replicate_and_dedupe():
-    assert more == []
+    leader = AccountStore()
-
+    follower = AccountStore()
-
+    account = leader.register(email="r@example.com", password="secret-123")
-# ---------------------------------------------------------- HTTP integration
+    key = leader.create_api_key(account["account_id"])
-
+    leader.revoke_api_key(account["account_id"], key)
-
+
-def _call(url, method="GET", body=None, token=None):
+    events, cursor = leader.events_since(0)
-    headers = {"Content-Type": "application/json"}
+    assert follower.apply_events(events) == len(events)
-    if token:
+    assert follower.apply_events(events) == 0  # replay is a no-op
-        headers["Authorization"] = f"Bearer {token}"
+    assert follower.verify_login("r@example.com", "secret-123") is not None
-    data = json.dumps(body).encode() if body is not None else None
+    assert follower.is_key_revoked(key)
-    req = urllib.request.Request(url, data=data, headers=headers, method=method)
+    more, _ = leader.events_since(cursor)
-    with urllib.request.urlopen(req) as r:
+    assert more == []
-        return json.loads(r.read())
+
-
+
-
+# ---------------------------------------------------------- HTTP integration
-@pytest.fixture
+
-def account_tracker():
+
-    """Tracker with credit features pinned OFF (defaults are devnet-friendly 1.0)."""
+def _call(url, method="GET", body=None, token=None):
-    ledger = BillingLedger(starting_credit=0.0, default_price_per_1k=0.02)
+    headers = {"Content-Type": "application/json"}
-    tracker = TrackerServer(
+    if token:
-        billing=ledger,
+        headers["Authorization"] = f"Bearer {token}"
-        accounts=AccountStore(),
+    data = json.dumps(body).encode() if body is not None else None
-        hive_secret=HIVE_SECRET,
+    req = urllib.request.Request(url, data=data, headers=headers, method=method)
-        starting_credit=0.0,
+    with urllib.request.urlopen(req) as r:
-        devnet_topup_amount=0.0,
+        return json.loads(r.read())
-    )
+
-    port = tracker.start()
+
-    yield f"http://127.0.0.1:{port}", ledger
+@pytest.fixture
-    tracker.stop()
+def account_tracker():
-
+    """Tracker with credit features pinned OFF (defaults are devnet-friendly 1.0)."""
-
+    ledger = BillingLedger(starting_credit=0.0, default_price_per_1k=0.02)
-def test_register_login_and_account_view(account_tracker):
+    tracker = TrackerServer(
-    url, _ = account_tracker
+        billing=ledger,
-    reg = _call(f"{url}/v1/auth/register", "POST",
+        accounts=AccountStore(),
-                {"email": "admin@example.com", "password": "secret-123"})
+        hive_secret=HIVE_SECRET,
-    assert reg["account"]["role"] == "admin"
+        starting_credit=0.0,
-    assert reg["api_key"].startswith("sk-mesh-")
+        devnet_topup_amount=0.0,
-    assert reg["session_token"]
+    )
-
+    port = tracker.start()
-    login = _call(f"{url}/v1/auth/login", "POST",
+    yield f"http://127.0.0.1:{port}", ledger
-                  {"identifier": "admin@example.com", "password": "secret-123"})
+    tracker.stop()
-    me = _call(f"{url}/v1/account", token=login["session_token"])
+
-    assert me["account"]["email"] == "admin@example.com"
+
-    assert me["api_keys"] == [reg["api_key"]]
+def test_register_login_and_account_view(account_tracker):
-    assert me["total_balance"] == pytest.approx(0.0)
+    url, _ = account_tracker
-    assert me["usage"]["requests"] == 0
+    reg = _call(f"{url}/v1/auth/register", "POST",
-
+                {"email": "admin@example.com", "password": "secret-123"})
-
+    assert reg["account"]["role"] == "admin"
-def test_bad_credentials_and_missing_session_are_401(account_tracker):
+    assert reg["api_key"].startswith("sk-mesh-")
-    url, _ = account_tracker
+    assert reg["session_token"]
-    _call(f"{url}/v1/auth/register", "POST",
+
-          {"email": "a@example.com", "password": "secret-123"})
+    login = _call(f"{url}/v1/auth/login", "POST",
-    with pytest.raises(urllib.error.HTTPError) as exc_info:
+                  {"identifier": "admin@example.com", "password": "secret-123"})
-        _call(f"{url}/v1/auth/login", "POST",
+    me = _call(f"{url}/v1/account", token=login["session_token"])
-              {"identifier": "a@example.com", "password": "wrong-pass"})
+    assert me["account"]["email"] == "admin@example.com"
-    assert exc_info.value.code == 401
+    assert me["api_keys"] == [reg["api_key"]]
-    with pytest.raises(urllib.error.HTTPError) as exc_info:
+    assert me["total_balance"] == pytest.approx(0.0)
-        _call(f"{url}/v1/account")
+    assert me["usage"]["requests"] == 0
-    assert exc_info.value.code == 401
+
-
+
-
+def test_login_sets_cookie_and_cookie_auth_survives_tracker_restart(tmp_path):
-def test_key_create_revoke_and_revoked_key_rejected_by_proxy(account_tracker):
+    accounts_db = str(tmp_path / "accounts.db")
-    url, _ = account_tracker
+    tracker = TrackerServer(
-    reg = _call(f"{url}/v1/auth/register", "POST",
+        billing=BillingLedger(starting_credit=0.0, default_price_per_1k=0.02),
-                {"email": "k@example.com", "password": "secret-123"})
+        accounts_db=accounts_db,
-    token = reg["session_token"]
+        starting_credit=0.0,
-
+        devnet_topup_amount=0.0,
-    new_key = _call(f"{url}/v1/account/keys", "POST", {}, token=token)["api_key"]
+    )
-    me = _call(f"{url}/v1/account", token=token)
+    port = tracker.start()
-    assert sorted(me["api_keys"]) == sorted([reg["api_key"], new_key])
+    url = f"http://127.0.0.1:{port}"
-
+    try:
-    _call(f"{url}/v1/account/keys/revoke", "POST", {"api_key": new_key}, token=token)
+        _call(f"{url}/v1/auth/register", "POST",
-    with pytest.raises(urllib.error.HTTPError) as exc_info:
+              {"email": "cookie-http@example.com", "password": "secret-123"})
-        _call(f"{url}/v1/chat/completions", "POST",
+        req = urllib.request.Request(
-              {"model": "any", "messages": []}, token=new_key)
+            f"{url}/v1/auth/login",
-    assert exc_info.value.code == 401
+            data=json.dumps({
-    assert "revoked" in exc_info.value.read().decode()
+                "identifier": "cookie-http@example.com",
-
+                "password": "secret-123",
-
+            }).encode(),
-def test_admin_listing_requires_admin_role(account_tracker):
+            headers={"Content-Type": "application/json"},
-    url, _ = account_tracker
+            method="POST",
-    admin = _call(f"{url}/v1/auth/register", "POST",
+        )
-                  {"email": "admin@example.com", "password": "secret-123"})
+        with urllib.request.urlopen(req) as r:
-    user = _call(f"{url}/v1/auth/register", "POST",
+            assert json.loads(r.read())["session_token"]
-                 {"wallet": "WalletUser1", "password": "secret-123"})
+            cookie_header = r.headers["Set-Cookie"]
-
+    finally:
-    with pytest.raises(urllib.error.HTTPError) as exc_info:
+        tracker.stop()
-        _call(f"{url}/v1/admin/accounts", token=user["session_token"])
+
-    assert exc_info.value.code == 403
+    cookie = http.cookies.SimpleCookie(cookie_header)
-
+    session_cookie = cookie["meshnet_session"].OutputString()
-    listing = _call(f"{url}/v1/admin/accounts", token=admin["session_token"])
+
-    accounts = listing["accounts"]
+    restarted = TrackerServer(
-    assert len(accounts) == 2
+        billing=BillingLedger(starting_credit=0.0, default_price_per_1k=0.02),
-    assert accounts[0]["role"] == "admin"
+        accounts_db=accounts_db,
-    assert accounts[1]["wallet"] == "WalletUser1"
+        starting_credit=0.0,
-    assert "balances" in accounts[0]
+        devnet_topup_amount=0.0,
-
+    )
-
+    restarted_port = restarted.start()
-def test_accounts_gossip_endpoint_applies_events(account_tracker):
+    restarted_url = f"http://127.0.0.1:{restarted_port}"
-    url, _ = account_tracker
+    try:
-    peer = AccountStore()
+        req = urllib.request.Request(
-    peer.register(email="remote@example.com", password="secret-123")
+            f"{restarted_url}/v1/account",
-    events, _ = peer.events_since(0)
+            headers={"Cookie": session_cookie},
-    body = json.dumps({"events": events}).encode()
+            method="GET",
-    req = urllib.request.Request(
+        )
-        f"{url}/v1/accounts/gossip", data=body,
+        with urllib.request.urlopen(req) as r:
-        headers={"Content-Type": "application/json", **sign_hive_request(HIVE_SECRET, body)},
+            me = json.loads(r.read())
-        method="POST",
+    finally:
-    )
+        restarted.stop()
-    with urllib.request.urlopen(req) as r:
+
-        result = json.loads(r.read())
+    assert me["account"]["email"] == "cookie-http@example.com"
-    assert result["applied"] == len(events)
+
-    login = _call(f"{url}/v1/auth/login", "POST",
+
-                  {"identifier": "remote@example.com", "password": "secret-123"})
+def test_bad_credentials_and_missing_session_are_401(account_tracker):
-    assert login["account"]["email"] == "remote@example.com"
+    url, _ = account_tracker
-
+    _call(f"{url}/v1/auth/register", "POST",
-
+          {"email": "a@example.com", "password": "secret-123"})
-def test_accounts_endpoints_404_when_disabled():
+    with pytest.raises(urllib.error.HTTPError) as exc_info:
-    tracker = TrackerServer()  # no accounts, no billing
+        _call(f"{url}/v1/auth/login", "POST",
-    port = tracker.start()
+              {"identifier": "a@example.com", "password": "wrong-pass"})
-    try:
+    assert exc_info.value.code == 401
-        with pytest.raises(urllib.error.HTTPError) as exc_info:
+    with pytest.raises(urllib.error.HTTPError) as exc_info:
-            _call(f"http://127.0.0.1:{port}/v1/auth/register", "POST",
+        _call(f"{url}/v1/account")
-                  {"email": "x@example.com", "password": "secret-123"})
+    assert exc_info.value.code == 401
-        assert exc_info.value.code == 404
+
-    finally:
+
-        tracker.stop()
+def test_key_create_revoke_and_revoked_key_rejected_by_proxy(account_tracker):
-
+    url, _ = account_tracker
-
+    reg = _call(f"{url}/v1/auth/register", "POST",
-# ------------------------------------------- US-039/US-040: credit and top-up
+                {"email": "k@example.com", "password": "secret-123"})
-
+    token = reg["session_token"]
-
+
-@pytest.fixture
+    new_key = _call(f"{url}/v1/account/keys", "POST", {}, token=token)["api_key"]
-def funded_tracker():
+    me = _call(f"{url}/v1/account", token=token)
-    """Tracker with Caller Credit and the devnet top-up faucet enabled."""
+    assert sorted(me["api_keys"]) == sorted([reg["api_key"], new_key])
-    ledger = BillingLedger(starting_credit=0.0, default_price_per_1k=0.02)
+
-    tracker = TrackerServer(
+    _call(f"{url}/v1/account/keys/revoke", "POST", {"api_key": new_key}, token=token)
-        billing=ledger,
+    with pytest.raises(urllib.error.HTTPError) as exc_info:
-        accounts=AccountStore(),
+        _call(f"{url}/v1/chat/completions", "POST",
-        hive_secret=HIVE_SECRET,
+              {"model": "any", "messages": []}, token=new_key)
-        starting_credit=1.0,
+    assert exc_info.value.code == 401
-        devnet_topup_amount=10.0,
+    assert "revoked" in exc_info.value.read().decode()
-    )
+
-    port = tracker.start()
+
-    yield f"http://127.0.0.1:{port}", ledger
+def test_admin_listing_requires_admin_role(account_tracker):
-    tracker.stop()
+    url, _ = account_tracker
-
+    admin = _call(f"{url}/v1/auth/register", "POST",
-
+                  {"email": "admin@example.com", "password": "secret-123"})
-def test_caller_credit_granted_once_per_account(funded_tracker):
+    user = _call(f"{url}/v1/auth/register", "POST",
-    url, ledger = funded_tracker
+                 {"wallet": "WalletUser1", "password": "secret-123"})
-    reg = _call(f"{url}/v1/auth/register", "POST",
+
-                {"email": "c@example.com", "password": "secret-123"})
+    with pytest.raises(urllib.error.HTTPError) as exc_info:
-    token = reg["session_token"]
+        _call(f"{url}/v1/admin/accounts", token=user["session_token"])
-    first_key = reg["api_key"]
+    assert exc_info.value.code == 403
-    assert ledger.get_client_balance(first_key) == pytest.approx(1.0)
+
-
+    listing = _call(f"{url}/v1/admin/accounts", token=admin["session_token"])
-    # A second key never re-grants — not even after revoking the first.
+    accounts = listing["accounts"]
-    second = _call(f"{url}/v1/account/keys", "POST", {}, token=token)
+    assert len(accounts) == 2
-    assert second["caller_credit_granted"] is False
+    assert accounts[0]["role"] == "admin"
-    assert ledger.get_client_balance(second["api_key"]) == pytest.approx(0.0)
+    assert accounts[1]["wallet"] == "WalletUser1"
-    _call(f"{url}/v1/account/keys/revoke", "POST", {"api_key": first_key}, token=token)
+    assert "balances" in accounts[0]
-    third = _call(f"{url}/v1/account/keys", "POST", {}, token=token)
+
-    assert third["caller_credit_granted"] is False
+
-    assert ledger.get_client_balance(third["api_key"]) == pytest.approx(0.0)
+def test_accounts_gossip_endpoint_applies_events(account_tracker):
-
+    url, _ = account_tracker
-
+    peer = AccountStore()
-def test_unknown_bearer_key_rejected_by_proxy(funded_tracker):
+    peer.register(email="remote@example.com", password="secret-123")
-    url, ledger = funded_tracker
+    events, _ = peer.events_since(0)
-    with pytest.raises(urllib.error.HTTPError) as exc_info:
+    body = json.dumps({"events": events}).encode()
-        _call(f"{url}/v1/chat/completions", "POST",
+    req = urllib.request.Request(
-              {"model": "any", "messages": []}, token="sk-mesh-made-up-key")
+        f"{url}/v1/accounts/gossip", data=body,
-    assert exc_info.value.code == 401
+        headers={"Content-Type": "application/json", **sign_hive_request(HIVE_SECRET, body)},
-    assert "unknown API key" in exc_info.value.read().decode()
+        method="POST",
-    # The invented key must not have become a billable client.
+    )
-    assert ledger.get_client_balance("sk-mesh-made-up-key") == pytest.approx(0.0)
+    with urllib.request.urlopen(req) as r:
-
+        result = json.loads(r.read())
-
+    assert result["applied"] == len(events)
-def test_devnet_topup_credits_own_key_only(funded_tracker):
+    login = _call(f"{url}/v1/auth/login", "POST",
-    url, ledger = funded_tracker
+                  {"identifier": "remote@example.com", "password": "secret-123"})
-    owner = _call(f"{url}/v1/auth/register", "POST",
+    assert login["account"]["email"] == "remote@example.com"
-                  {"email": "own@example.com", "password": "secret-123"})
+
-    other = _call(f"{url}/v1/auth/register", "POST",
+
-                  {"email": "oth@example.com", "password": "secret-123"})
+def test_accounts_endpoints_404_when_disabled():
-
+    tracker = TrackerServer()  # no accounts, no billing
-    me = _call(f"{url}/v1/account", token=owner["session_token"])
+    port = tracker.start()
-    assert me["topup_amount"] == pytest.approx(10.0)
+    try:
-
+        with pytest.raises(urllib.error.HTTPError) as exc_info:
-    result = _call(f"{url}/v1/account/topup", "POST",
+            _call(f"http://127.0.0.1:{port}/v1/auth/register", "POST",
-                   {"api_key": owner["api_key"]}, token=owner["session_token"])
+                  {"email": "x@example.com", "password": "secret-123"})
-    assert result["credited"] == pytest.approx(10.0)
+        assert exc_info.value.code == 404
-    assert result["balance"] == pytest.approx(11.0)  # 1.0 caller credit + 10.0
+    finally:
-
+        tracker.stop()
-    with pytest.raises(urllib.error.HTTPError) as exc_info:
+
-        _call(f"{url}/v1/account/topup", "POST",
+
-              {"api_key": owner["api_key"]}, token=other["session_token"])
+# ------------------------------------------- US-039/US-040: credit and top-up
-    assert exc_info.value.code == 403
+
-    assert ledger.get_client_balance(owner["api_key"]) == pytest.approx(11.0)
+
-
+@pytest.fixture
-
+def funded_tracker():
-def test_topup_404_when_disabled(account_tracker):
+    """Tracker with Caller Credit and the devnet top-up faucet enabled."""
-    url, _ = account_tracker
+    ledger = BillingLedger(starting_credit=0.0, default_price_per_1k=0.02)
-    reg = _call(f"{url}/v1/auth/register", "POST",
+    tracker = TrackerServer(
-                {"email": "t@example.com", "password": "secret-123"})
+        billing=ledger,
-    me = _call(f"{url}/v1/account", token=reg["session_token"])
+        accounts=AccountStore(),
-    assert me["topup_amount"] == pytest.approx(0.0)
+        hive_secret=HIVE_SECRET,
-    with pytest.raises(urllib.error.HTTPError) as exc_info:
+        starting_credit=1.0,
-        _call(f"{url}/v1/account/topup", "POST",
+        devnet_topup_amount=10.0,
-              {"api_key": reg["api_key"]}, token=reg["session_token"])
+    )
-    assert exc_info.value.code == 404
+    port = tracker.start()
+    yield f"http://127.0.0.1:{port}", ledger
+    tracker.stop()
+
+
+def test_caller_credit_granted_once_per_account(funded_tracker):
+    url, ledger = funded_tracker
+    reg = _call(f"{url}/v1/auth/register", "POST",
+                {"email": "c@example.com", "password": "secret-123"})
+    token = reg["session_token"]
+    first_key = reg["api_key"]
+    assert ledger.get_client_balance(first_key) == pytest.approx(1.0)
+
+    # A second key never re-grants — not even after revoking the first.
+    second = _call(f"{url}/v1/account/keys", "POST", {}, token=token)
+    assert second["caller_credit_granted"] is False
+    assert ledger.get_client_balance(second["api_key"]) == pytest.approx(0.0)
+    _call(f"{url}/v1/account/keys/revoke", "POST", {"api_key": first_key}, token=token)
+    third = _call(f"{url}/v1/account/keys", "POST", {}, token=token)
+    assert third["caller_credit_granted"] is False
+    assert ledger.get_client_balance(third["api_key"]) == pytest.approx(0.0)
+
+
+def test_unknown_bearer_key_rejected_by_proxy(funded_tracker):
+    url, ledger = funded_tracker
+    with pytest.raises(urllib.error.HTTPError) as exc_info:
+        _call(f"{url}/v1/chat/completions", "POST",
+              {"model": "any", "messages": []}, token="sk-mesh-made-up-key")
+    assert exc_info.value.code == 401
+    assert "unknown API key" in exc_info.value.read().decode()
+    # The invented key must not have become a billable client.
+    assert ledger.get_client_balance("sk-mesh-made-up-key") == pytest.approx(0.0)
+
+
+def test_devnet_topup_credits_own_key_only(funded_tracker):
+    url, ledger = funded_tracker
+    owner = _call(f"{url}/v1/auth/register", "POST",
+                  {"email": "own@example.com", "password": "secret-123"})
+    other = _call(f"{url}/v1/auth/register", "POST",
+                  {"email": "oth@example.com", "password": "secret-123"})
+
+    me = _call(f"{url}/v1/account", token=owner["session_token"])
+    assert me["topup_amount"] == pytest.approx(10.0)
+
+    result = _call(f"{url}/v1/account/topup", "POST",
+                   {"api_key": owner["api_key"]}, token=owner["session_token"])
+    assert result["credited"] == pytest.approx(10.0)
+    assert result["balance"] == pytest.approx(11.0)  # 1.0 caller credit + 10.0
+
+    with pytest.raises(urllib.error.HTTPError) as exc_info:
+        _call(f"{url}/v1/account/topup", "POST",
+              {"api_key": owner["api_key"]}, token=other["session_token"])
+    assert exc_info.value.code == 403
+    assert ledger.get_client_balance(owner["api_key"]) == pytest.approx(11.0)
+
+
+def test_topup_404_when_disabled(account_tracker):
+    url, _ = account_tracker
+    reg = _call(f"{url}/v1/auth/register", "POST",
+                {"email": "t@example.com", "password": "secret-123"})
+    me = _call(f"{url}/v1/account", token=reg["session_token"])
+    assert me["topup_amount"] == pytest.approx(0.0)
+    with pytest.raises(urllib.error.HTTPError) as exc_info:
+        _call(f"{url}/v1/account/topup", "POST",
+              {"api_key": reg["api_key"]}, token=reg["session_token"])
+    assert exc_info.value.code == 404

tests/test_dashboard.py

@@ -29,10 +29,29 @@ def test_dashboard_served_with_all_panels():
         for panel in PANELS:
             assert panel in html
         assert "<script>" in html  # polling client embedded, no build step
+        assert "resolveModelGroup" in html
+        assert "buildModelAliasMap" in html
+        assert "modelAliasKey(raw)" in html
     finally:
         tracker.stop()
 
 
+def test_dashboard_chat_uses_streaming_fetch():
+    tracker = TrackerServer(billing=BillingLedger())
+    port = tracker.start()
+    try:
+        html = urllib.request.urlopen(
+            f"http://127.0.0.1:{port}/dashboard"
+        ).read().decode()
+    finally:
+        tracker.stop()
+
+    assert "stream: true" in html
+    assert ".body.getReader()" in html
+    assert '=== "[DONE]"' in html
+    assert 'console.error("chat stream failed", err)' in html
+
+
 def test_dashboard_served_by_follower():
     """A tracker that is not the leader (unreachable peers → never elected)
     still serves the dashboard from its own replicated state."""

tests/test_dynamic_routing.py

@@ -0,0 +1,306 @@
+"""ADR-0021: dynamic bandit-style route selection with learned statistics."""
+
+import http.server
+import json
+import random
+import threading
+import types
+import urllib.request
+
+from meshnet_tracker.routing_stats import (
+    RouteCandidate,
+    RouteStatsStore,
+    RoutingConfig,
+    choose_route,
+    route_signature,
+    route_table,
+)
+from meshnet_tracker.server import TrackerServer, _enumerate_routes
+
+
+def _post_json(url: str, payload: dict) -> dict:
+    req = urllib.request.Request(
+        url,
+        data=json.dumps(payload).encode(),
+        headers={"Content-Type": "application/json"},
+        method="POST",
+    )
+    with urllib.request.urlopen(req, timeout=10.0) as resp:
+        return json.loads(resp.read())
+
+
+def _get_json(url: str) -> dict:
+    with urllib.request.urlopen(url, timeout=10.0) as resp:
+        return json.loads(resp.read())
+
+
+def _fake_node(node_id, shard_start, shard_end, benchmark=100.0, endpoint=None):
+    return types.SimpleNamespace(
+        node_id=node_id,
+        endpoint=endpoint or f"http://{node_id}:7000",
+        model="qwen3.6-35b-a3b",
+        hf_repo="unsloth/Qwen3.6-35B-A3B",
+        shard_start=shard_start,
+        shard_end=shard_end,
+        num_layers=40,
+        benchmark_tokens_per_sec=benchmark,
+        model_tokens_per_sec={},
+        queue_depth=0,
+        proxy_inflight=0,
+        wallet_address=None,
+        relay_addr=None,
+    )
+
+
+# ---- RouteStatsStore ----------------------------------------------------
+
+
+def test_route_stats_sample_becomes_proven_and_decays():
+    store = RouteStatsStore(RoutingConfig(stats_half_life_seconds=100.0))
+    sig = "m|a[0-39]"
+    assert store.snapshot(sig, "m", now=0.0)["status"] == "unsampled"
+    assert store.record_sample("m", sig, tokens=100, elapsed_seconds=10.0, now=0.0)
+    snap = store.snapshot(sig, "m", now=1.0)
+    assert snap["status"] == "proven"
+    assert snap["tps"] == 10.0
+    # After many half-lives the sample mass decays below the proven threshold.
+    assert store.snapshot(sig, "m", now=1000.0)["status"] == "decayed"
+
+
+def test_route_stats_rejects_near_empty_samples():
+    store = RouteStatsStore(RoutingConfig(min_sample_tokens=8))
+    assert not store.record_sample("m", "sig", tokens=3, elapsed_seconds=1.0)
+    assert store.snapshot("sig", "m")["samples"] == 0
+
+
+def test_route_stats_epoch_bump_marks_stale():
+    store = RouteStatsStore()
+    sig = "m|a[0-39]"
+    store.record_sample("m", sig, tokens=100, elapsed_seconds=10.0, now=0.0)
+    assert store.snapshot(sig, "m", now=1.0)["status"] == "proven"
+    store.bump_epoch(["m"])
+    snap = store.snapshot(sig, "m", now=1.0)
+    assert snap["status"] == "stale"
+    assert snap["tps"] == 10.0  # EWMA kept as a prior for display
+    # A fresh sample under the new epoch re-proves the route.
+    store.record_sample("m", sig, tokens=100, elapsed_seconds=10.0, now=2.0)
+    assert store.snapshot(sig, "m", now=3.0)["status"] == "proven"
+
+
+def test_route_stats_ewma_averages_samples():
+    store = RouteStatsStore(RoutingConfig(stats_half_life_seconds=1e9))
+    sig = "m|a"
+    store.record_sample("m", sig, tokens=100, elapsed_seconds=10.0, now=0.0)  # 10 tps
+    store.record_sample("m", sig, tokens=200, elapsed_seconds=10.0, now=1.0)  # 20 tps
+    snap = store.snapshot(sig, "m", now=2.0)
+    assert 14.9 < snap["tps"] < 15.1
+
+
+# ---- choose_route --------------------------------------------------------
+
+
+def _candidates_two_routes():
+    fast = RouteCandidate(nodes=[], signature="m|fast", prior_tps=100.0)
+    slow = RouteCandidate(nodes=[], signature="m|slow", prior_tps=50.0)
+    return fast, slow
+
+
+def test_choose_route_without_samples_is_deterministic_best_prior():
+    store = RouteStatsStore()
+    fast, slow = _candidates_two_routes()
+    for _ in range(20):
+        picked, decision = choose_route([slow, fast], store, "m", rng=random.Random(7))
+        assert picked is fast
+        assert decision["mode"] == "scout"
+
+
+def test_choose_route_traffic_proportional_to_tps():
+    store = RouteStatsStore(RoutingConfig(stats_half_life_seconds=1e9))
+    fast, slow = _candidates_two_routes()
+    now = 0.0
+    for _ in range(5):
+        now += 1.0
+        store.record_sample("m", fast.signature, tokens=150, elapsed_seconds=10.0, now=now)
+        store.record_sample("m", slow.signature, tokens=100, elapsed_seconds=10.0, now=now)
+    rng = random.Random(42)
+    picks = {"m|fast": 0, "m|slow": 0}
+    for _ in range(4000):
+        picked, decision = choose_route([fast, slow], store, "m", rng=rng, now=now)
+        assert decision["mode"] == "exploit"
+        picks[picked.signature] += 1
+    share = picks["m|fast"] / 4000
+    # 15 tps vs 10 tps at alpha=1 → expected fast share 0.6
+    assert 0.55 < share < 0.65
+
+
+def test_choose_route_scouts_unproven_routes_at_explore_share():
+    store = RouteStatsStore(RoutingConfig(explore_share=0.25, stats_half_life_seconds=1e9))
+    fast, slow = _candidates_two_routes()
+    now = 1.0
+    store.record_sample("m", fast.signature, tokens=150, elapsed_seconds=10.0, now=now)
+    rng = random.Random(11)
+    scouted = 0
+    for _ in range(4000):
+        picked, decision = choose_route([fast, slow], store, "m", rng=rng, now=now)
+        if decision["mode"] == "scout":
+            scouted += 1
+            assert picked is slow
+    assert 0.20 < scouted / 4000 < 0.30
+
+
+# ---- _enumerate_routes ---------------------------------------------------
+
+
+def test_enumerate_routes_mixed_topology_yields_both_routes():
+    gpu = _fake_node("gpu", 0, 21, benchmark=11000.0)
+    cpu = _fake_node("cpu", 0, 39, benchmark=425.0)
+    candidates = _enumerate_routes([gpu, cpu], 0, 39, model="qwen3.6-35b-a3b")
+    signatures = {c.signature for c in candidates}
+    assert signatures == {
+        route_signature("qwen3.6-35b-a3b", [gpu, cpu]),
+        route_signature("qwen3.6-35b-a3b", [cpu]),
+    }
+    hybrid = next(c for c in candidates if len(c.nodes) == 2)
+    assert [n.node_id for n in hybrid.nodes] == ["gpu", "cpu"]
+    # Hybrid route's prior is its bottleneck hop, not the fast head.
+    assert hybrid.prior_tps == 425.0
+
+
+def test_enumerate_routes_requires_head_at_first_layer():
+    tail_only = _fake_node("tail", 22, 39)
+    assert _enumerate_routes([tail_only], 0, 39, model="m") == []
+
+
+def test_route_table_reports_coefficient_and_share():
+    store = RouteStatsStore(RoutingConfig(explore_share=0.3, stats_half_life_seconds=1e9))
+    fast, slow = _candidates_two_routes()
+    now = 1.0
+    for _ in range(3):
+        store.record_sample("m", fast.signature, tokens=150, elapsed_seconds=10.0, now=now)
+        store.record_sample("m", slow.signature, tokens=100, elapsed_seconds=10.0, now=now)
+        now += 1.0
+    rows = route_table([fast, slow], store, "m", now=now)
+    by_sig = {r["signature"]: r for r in rows}
+    assert by_sig["m|fast"]["coefficient"] == 1.0
+    assert abs(by_sig["m|slow"]["coefficient"] - (10.0 / 15.0)) < 0.01
+    # No scouts → full exploit budget split 0.6 / 0.4.
+    assert abs(by_sig["m|fast"]["expected_share"] - 0.6) < 0.01
+    assert abs(by_sig["m|slow"]["expected_share"] - 0.4) < 0.01
+
+
+# ---- integration: proxy uses route head + /v1/routing --------------------
+
+
+def test_proxy_head_is_route_head_and_routing_endpoint_lists_routes():
+    """Mixed topology (partial head 0-21 + full node 0-39): the proxy target
+    must be the selected route's own head, downstream hops must continue at
+    head.shard_end + 1 (the ADR-0020 flaw), and /v1/routing must list both
+    candidate routes."""
+
+    class ChatHandler(http.server.BaseHTTPRequestHandler):
+        def log_message(self, *args):  # noqa: ARG002
+            pass
+
+        def do_POST(self):
+            length = int(self.headers.get("Content-Length", 0))
+            self.rfile.read(length)
+            route_header = self.headers.get("X-Meshnet-Route") or "[]"
+            body = json.dumps({
+                "choices": [{"message": {"role": "assistant", "content": route_header}}],
+                "usage": {"prompt_tokens": 10, "completion_tokens": 40},
+            }).encode()
+            self.send_response(200)
+            self.send_header("Content-Type", "application/json")
+            self.send_header("Content-Length", str(len(body)))
+            self.end_headers()
+            self.wfile.write(body)
+
+    stubs = []
+    threads = []
+    for _ in range(2):
+        stub = http.server.HTTPServer(("127.0.0.1", 0), ChatHandler)
+        thread = threading.Thread(target=stub.serve_forever, daemon=True)
+        thread.start()
+        stubs.append(stub)
+        threads.append(thread)
+    gpu_stub, cpu_stub = stubs
+
+    tracker = TrackerServer(model_presets={
+        "qwen3.6-35b-a3b": {
+            "layers_start": 0,
+            "layers_end": 39,
+            "hf_repo": "unsloth/Qwen3.6-35B-A3B",
+            "aliases": ["Qwen3.6-35B-A3B"],
+        }
+    })
+    tracker_port = tracker.start()
+    try:
+        tracker._server.route_rng = random.Random(3)
+        for stub, shard_end, bench in ((gpu_stub, 21, 11000.0), (cpu_stub, 39, 425.0)):
+            _post_json(
+                f"http://127.0.0.1:{tracker_port}/v1/nodes/register",
+                {"endpoint": f"http://127.0.0.1:{stub.server_address[1]}",
+                 "model": "qwen3.6-35b-a3b",
+                 "hf_repo": "unsloth/Qwen3.6-35B-A3B",
+                 "num_layers": 40,
+                 "shard_start": 0,
+                 "shard_end": shard_end,
+                 "tracker_mode": True,
+                 "benchmark_tokens_per_sec": bench,
+                 "hardware_profile": {},
+                 "score": 1.0},
+            )
+
+        for _ in range(8):
+            _post_json(
+                f"http://127.0.0.1:{tracker_port}/v1/chat/completions",
+                {"model": "Qwen3.6-35B-A3B",
+                 "messages": [{"role": "user", "content": "hi"}]},
+            )
+
+        console = _get_json(f"http://127.0.0.1:{tracker_port}/v1/console")
+        routing = _get_json(f"http://127.0.0.1:{tracker_port}/v1/routing")
+    finally:
+        tracker.stop()
+        for stub, thread in zip(stubs, threads):
+            stub.shutdown()
+            stub.server_close()
+            thread.join(timeout=1.0)
+
+    gpu_endpoint = f"http://127.0.0.1:{gpu_stub.server_address[1]}"
+    cpu_endpoint = f"http://127.0.0.1:{cpu_stub.server_address[1]}"
+    selected = [e for e in console["events"] if e["message"] == "proxy route selected"]
+    assert selected
+    for event in selected:
+        fields = event["fields"]
+        nodes = fields["nodes"]
+        # The proxy head must be the route's first hop (ADR-0020 regression).
+        assert fields["head_endpoint"] == nodes[0]["endpoint"]
+        downstream = json.loads(fields["downstream"])
+        if fields["head_endpoint"] == gpu_endpoint:
+            # Partial head: downstream continues at layer 22, never 0.
+            assert downstream == [{"endpoint": cpu_endpoint, "start_layer": 22}]
+        else:
+            assert fields["head_endpoint"] == cpu_endpoint
+            assert downstream == []
+
+    table = routing["models"]["qwen3.6-35b-a3b"]
+    assert len(table["routes"]) == 2
+    sampled = [r for r in table["routes"] if r["samples"] > 0]
+    assert sampled, "completed requests must produce route samples"
+
+
+def test_endpoint_key_distinguishes_same_port_different_hosts():
+    from meshnet_node.torch_server import _clamp_downstream_hops, _endpoint_key
+
+    assert _endpoint_key("http://192.168.0.20:7000") == "192.168.0.20:7000"
+    assert _endpoint_key("http://192.168.0.179:7000") == "192.168.0.179:7000"
+    assert _endpoint_key("http://192.168.0.20:7000") != _endpoint_key("http://192.168.0.179:7000")
+
+    class Backend:
+        shard_end = 21
+
+    hops = [{"endpoint": "http://192.168.0.179:7000", "start_layer": 0}]
+    assert _clamp_downstream_hops(hops, Backend()) == [
+        {"endpoint": "http://192.168.0.179:7000", "start_layer": 22},
+    ]

tests/test_node_startup.py

@@ -1118,7 +1118,7 @@ def test_real_model_startup_summary_shows_total_layers(tmp_path, monkeypatch, ca
     assert captured_registration["vram_bytes"] == 6144 * 1024 * 1024
     assert captured_registration["max_loaded_shards"] == 2
     output = capsys.readouterr().out
-    assert "Shard:        layers 0–23; 24 of 24" in output
+    assert "Shard:        layers 0–23 (24 of 24)" in output
     assert "Node ID:      node-test-123" in output
 
 
@@ -1646,6 +1646,166 @@ def test_preset_model_startup_honors_pinned_shard_range(tmp_path, monkeypatch):
         tracker.stop()
 
 
+def test_preset_startup_rejects_pinned_shard_above_memory_budget(tmp_path, monkeypatch):
+    """Pinned layer ranges that exceed the node memory budget fail before model load."""
+    import meshnet_node.startup as startup_mod
+
+    monkeypatch.setattr(
+        startup_mod,
+        "detect_hardware",
+        lambda: {"device": "cpu", "gpu_name": None, "vram_mb": 0, "ram_mb": 8 * 1024},
+    )
+
+    tracker = TrackerServer(model_presets={
+        "big-model": {
+            "layers_start": 0,
+            "layers_end": 39,
+            "hf_repo": "org/big-model",
+            "bytes_per_layer": {"bfloat16": 2 * 1024 * 1024 * 1024},
+        },
+    })
+    tracker_port = tracker.start()
+    tracker_url = f"http://127.0.0.1:{tracker_port}"
+    try:
+        with pytest.raises(ValueError, match="Pinned shard layers 0–39"):
+            run_startup(
+                tracker_url=tracker_url,
+                model="big-model",
+                shard_start=0,
+                shard_end=39,
+                wallet_path=tmp_path / "wallet.json",
+                cache_dir=tmp_path / "shards",
+            )
+    finally:
+        tracker.stop()
+
+
+def test_network_auto_join_clips_oversized_cpu_assignment(tmp_path, monkeypatch, capsys):
+    """Old trackers may assign too many CPU layers; node clips before model load."""
+    import meshnet_node.startup as startup_mod
+
+    torch_calls: list[dict] = []
+    registrations: list[dict] = []
+
+    class FakeBackend:
+        total_layers = 40
+
+    class FakeTorchNodeServer:
+        def __init__(self, **kwargs):
+            torch_calls.append(kwargs)
+            self.backend = FakeBackend()
+            self.tracker_node_id = None
+
+        def start(self):
+            return 7000
+
+        def stop(self):
+            pass
+
+    oversized_assignment = {
+        "hf_repo": "unsloth/Qwen3.6-35B-A3B",
+        "model": "qwen3.6-35b-a3b",
+        "shard_start": 0,
+        "shard_end": 36,
+        "num_layers": 40,
+        "gap_found": False,
+        "bytes_per_layer": {"bfloat16": 1_797_594_419},
+        "model_sources": [],
+    }
+
+    monkeypatch.setattr(
+        startup_mod,
+        "detect_hardware",
+        lambda: {"device": "cpu", "gpu_name": None, "vram_mb": 0, "ram_mb": 79 * 1024},
+    )
+    monkeypatch.setattr(startup_mod, "TorchNodeServer", FakeTorchNodeServer)
+    monkeypatch.setattr(startup_mod, "_get_json", lambda *_args, **_kwargs: oversized_assignment)
+    monkeypatch.setattr(startup_mod, "_post_json", lambda _url, payload: registrations.append(payload) or {"node_id": "n1"})
+    monkeypatch.setattr(startup_mod, "_start_heartbeat", lambda *_args, **_kwargs: None)
+    monkeypatch.setattr(startup_mod, "model_metadata_for", lambda *_args, **_kwargs: {"num_layers": 40})
+
+    node = run_startup(
+        tracker_url="http://127.0.0.1:8080",
+        wallet_path=tmp_path / "wallet.json",
+        tracker_source_disabled=True,
+    )
+    try:
+        assert torch_calls[0]["shard_start"] == 0
+        assert torch_calls[0]["shard_end"] == 24
+        assert registrations[0]["shard_end"] == 24
+        output = capsys.readouterr().out
+        assert "CPU-safe runtime budget fits 25/40 layers" in output
+        assert "layers 0-24" in output
+    finally:
+        node.stop()
+
+
+def test_preset_model_with_hf_repo_loads_torch_backend(tmp_path, monkeypatch, capsys):
+    """Named presets that advertise hf_repo must load TorchNodeServer, not the stub server."""
+    import meshnet_node.startup as startup_mod
+
+    class FakeBackend:
+        total_layers = 16
+
+    torch_calls: list[dict] = []
+
+    class FakeTorchNodeServer:
+        def __init__(self, **kwargs):
+            torch_calls.append(kwargs)
+            self.backend = FakeBackend()
+            self.port = None
+            self.chat_completion_count = 0
+            self.tracker_node_id = None
+
+        def start(self):
+            self.port = 7002
+            return self.port
+
+        def stop(self):
+            pass
+
+    monkeypatch.setattr(
+        startup_mod,
+        "detect_hardware",
+        lambda: {"device": "cpu", "gpu_name": None, "vram_mb": 0, "ram_mb": 16 * 1024},
+    )
+    monkeypatch.setattr(startup_mod, "TorchNodeServer", FakeTorchNodeServer)
+    monkeypatch.setattr(startup_mod, "StubNodeServer", lambda **_kw: (_ for _ in ()).throw(AssertionError("preset with hf_repo must not use StubNodeServer")))
+
+    model_dir = tmp_path / "node-shards" / "tiny-llama"
+    model_dir.mkdir(parents=True)
+    (model_dir / "config.json").write_text('{"num_hidden_layers": 16}')
+    monkeypatch.setattr(startup_mod, "download_shard", lambda *_a, **_kw: model_dir)
+
+    tracker = TrackerServer(model_presets={
+        "tiny-llama": {"layers_start": 0, "layers_end": 15, "hf_repo": "org/tiny-llama-shards"}
+    })
+    tracker_port = tracker.start()
+    tracker_url = f"http://127.0.0.1:{tracker_port}"
+    try:
+        node = run_startup(
+            tracker_url=tracker_url,
+            model="tiny-llama",
+            wallet_path=tmp_path / "wallet.json",
+            cache_dir=tmp_path / "node-shards",
+        )
+        try:
+            assert len(torch_calls) == 1
+            assert torch_calls[0]["model_id"] == "org/tiny-llama-shards"
+            assert torch_calls[0]["cache_dir"] == model_dir
+            output = capsys.readouterr().out
+            assert "Loading real PyTorch model shard..." in output
+            assert "Model ID:     org/tiny-llama-shards" in output
+            network_map = _get_json(f"{tracker_url}/v1/network/map")
+            registered = network_map["nodes"][0]
+            assert registered["hf_repo"] == "org/tiny-llama-shards"
+            assert registered["num_layers"] == 16
+        finally:
+            node.stop()
+    finally:
+        tracker.stop()
+
+
 def test_torch_startup_retries_registration_when_tracker_unreachable(
     tmp_path,
     monkeypatch,
@@ -1896,6 +2056,55 @@ def test_network_assign_gap_found_field():
         tracker.stop()
 
 
+def test_network_assign_uses_conservative_cpu_runtime_budget():
+    """CPU assignments leave headroom for partial-load overhead, not just raw weights."""
+    import json as _json
+    import urllib.request as _ur
+
+    tracker = TrackerServer(model_presets={
+        "qwen3.6-35b-a3b": {
+            "hf_repo": "unsloth/Qwen3.6-35B-A3B",
+            "aliases": ["unsloth/Qwen3.6-35B-A3B"],
+            "layers_start": 0,
+            "layers_end": 39,
+            "recommended": True,
+            "bytes_per_layer": {"bfloat16": 1_797_594_419},
+        },
+    })
+    port = tracker.start()
+    try:
+        data = _json.dumps({
+            "endpoint": "http://127.0.0.1:9200",
+            "model": "qwen3.6-35b-a3b",
+            "hf_repo": "unsloth/Qwen3.6-35B-A3B",
+            "num_layers": 40,
+            "shard_start": 0,
+            "shard_end": 39,
+            "hardware_profile": {},
+            "score": 1.0,
+        }).encode()
+        req = _ur.Request(
+            f"http://127.0.0.1:{port}/v1/nodes/register",
+            data=data,
+            headers={"Content-Type": "application/json"},
+            method="POST",
+        )
+        with _ur.urlopen(req) as r:
+            r.read()
+
+        resp = _get_json(
+            f"http://127.0.0.1:{port}/v1/network/assign"
+            "?device=cpu&vram_mb=0&ram_mb=80896"
+            "&hf_repo=unsloth/Qwen3.6-35B-A3B"
+        )
+
+        assert resp["gap_found"] is False
+        assert resp["shard_start"] == 0
+        assert resp["shard_end"] == 24
+    finally:
+        tracker.stop()
+
+
 def test_route_finds_hf_model_across_two_nodes():
     """Tracker /v1/route returns ordered route for HF model even without a preset."""
     import json as _json

tests/test_real_model_backend.py

@@ -17,6 +17,7 @@ from meshnet_node.model_backend import (
     TensorPayload,
     TorchModelShard,
     _call_layer,
+    _checkpoint_tensor_name_for_model,
     _load_partial_model_from_snapshot,
     _should_partial_materialize_shard,
     _decoder_attention_mask,
@@ -225,7 +226,7 @@ def test_tail_forward_returns_text_completion_from_binary_activations():
         node.stop()
 
 
-def test_full_model_chat_completion_uses_generation_not_single_token_decode():
+def test_full_model_chat_completion_uses_generation_not_single_token_decode(capsys):
     node = TorchNodeServer(backend=_FakeFullBackend())
     port = node.start()
     try:
@@ -237,7 +238,10 @@ def test_full_model_chat_completion_uses_generation_not_single_token_decode():
         req = urllib.request.Request(
             f"http://127.0.0.1:{port}/v1/chat/completions",
             data=payload,
-            headers={"Content-Type": "application/json"},
+            headers={
+                "Content-Type": "application/json",
+                "X-Meshnet-Request-Id": "req-test-123",
+            },
             method="POST",
         )
         with urllib.request.urlopen(req, timeout=5) as resp:
@@ -248,6 +252,10 @@ def test_full_model_chat_completion_uses_generation_not_single_token_decode():
     finally:
         node.stop()
 
+    out = capsys.readouterr().out
+    assert "  [node] processing chat model='fake-model' stream=False max_tokens=7 request_id=req-test-123" in out
+    assert "  [node] chat complete tokens=1 elapsed_s=" in out
+
 
 def test_pipeline_hop_logs_are_suppressed_without_debug(capsys):
     tail_backend = _FakePipelineTailBackend()
@@ -368,6 +376,92 @@ def test_split_shard_chat_streams_each_generated_token_incrementally():
     assert "data: [DONE]" in rest
 
 
+def test_current_requests_snapshot_while_generating():
+    release_second = threading.Event()
+    head = TorchNodeServer(backend=_FakePipelineHeadBackend(), tracker_mode=True)
+    tail = TorchNodeServer(backend=_BlockingStreamingTailBackend(release_second))
+    head_port = head.start()
+    tail_port = tail.start()
+    response = None
+    try:
+        payload = json.dumps({
+            "model": "fake-model",
+            "messages": [{"role": "user", "content": "hello"}],
+            "stream": True,
+            "max_tokens": 2,
+        }).encode()
+        req = urllib.request.Request(
+            f"http://127.0.0.1:{head_port}/v1/chat/completions",
+            data=payload,
+            headers={
+                "Content-Type": "application/json",
+                "X-Meshnet-Request-Id": "req-live-1",
+                "X-Meshnet-Route": json.dumps([
+                    {"endpoint": f"http://127.0.0.1:{tail_port}", "start_layer": 22},
+                ]),
+            },
+            method="POST",
+        )
+        response = urllib.request.urlopen(req, timeout=5)
+        deadline = time.time() + 2.0
+        while time.time() < deadline:
+            live = head.current_requests
+            if live and live[0]["request_id"] == "req-live-1" and live[0]["tokens"] >= 1:
+                break
+            time.sleep(0.02)
+        assert head.current_requests
+        snap = head.current_requests[0]
+        assert snap["request_id"] == "req-live-1"
+        assert snap["tokens"] >= 1
+        assert snap["tokens_per_sec"] >= 0
+        assert snap["routing_complete"] is True
+        release_second.set()
+        response.read()
+    finally:
+        release_second.set()
+        if response is not None:
+            response.close()
+        head.stop()
+        tail.stop()
+
+    assert head.current_requests == []
+
+
+def test_distributed_generating_log_includes_tps(capsys):
+    head = TorchNodeServer(backend=_FakePipelineHeadBackend(), tracker_mode=True)
+    tail = TorchNodeServer(backend=_FakePipelineTailBackend())
+    head_port = head.start()
+    tail_port = tail.start()
+    try:
+        payload = json.dumps({
+            "model": "fake-model",
+            "messages": [{"role": "user", "content": "hello"}],
+            "max_tokens": 1,
+        }).encode()
+        req = urllib.request.Request(
+            f"http://127.0.0.1:{head_port}/v1/chat/completions",
+            data=payload,
+            headers={
+                "Content-Type": "application/json",
+                "X-Meshnet-Route": json.dumps([
+                    {"endpoint": f"http://127.0.0.1:{tail_port}", "start_layer": 22},
+                ]),
+            },
+            method="POST",
+        )
+        with urllib.request.urlopen(req, timeout=5) as resp:
+            json.loads(resp.read())
+    finally:
+        head.stop()
+        tail.stop()
+
+    out = capsys.readouterr().out
+    assert "generating step=1/1" in out
+    assert " tps=" in out
+    assert "generation complete tokens=1" in out
+    assert out.count("generating step=1/1") == 1
+
+
 def test_int_tensor_header_serializes_torch_tensors():
     torch = pytest.importorskip("torch")
 
@@ -422,7 +516,7 @@ def test_partial_materialize_guard_requires_local_non_full_non_quantized_snapsho
         39,
         total_layers_hint=40,
         uses_quantized_weights=False,
-    ) is False
+    ) is True
     assert _should_partial_materialize_shard(
         str(snapshot_dir),
         4,
@@ -439,6 +533,208 @@ def test_partial_materialize_guard_requires_local_non_full_non_quantized_snapsho
     ) is False
 
 
+def test_checkpoint_tensor_name_remapped_for_text_only_causal_lm():
+    class TextOnlyModel:
+        def __init__(self):
+            self.model = types.SimpleNamespace(layers=[])
+
+    model = TextOnlyModel()
+    assert _checkpoint_tensor_name_for_model(
+        model,
+        "model.language_model.layers.0.mlp.gate.weight",
+    ) == "model.layers.0.mlp.gate.weight"
+    assert _checkpoint_tensor_name_for_model(
+        model,
+        "model.language_model.embed_tokens.weight",
+    ) == "model.embed_tokens.weight"
+
+
+def test_checkpoint_tensor_name_kept_for_multimodal_backbone():
+    class MultimodalModel:
+        def __init__(self):
+            self.model = types.SimpleNamespace(language_model=types.SimpleNamespace())
+
+    model = MultimodalModel()
+    name = "model.language_model.layers.0.mlp.gate.weight"
+    assert _checkpoint_tensor_name_for_model(model, name) == name
+
+
+def test_partial_snapshot_loader_remaps_language_model_checkpoint_keys(tmp_path):
+    snapshot_dir = tmp_path / "snapshot"
+    snapshot_dir.mkdir()
+    (snapshot_dir / "config.json").write_text(json.dumps({
+        "text_config": {"num_hidden_layers": 3},
+    }))
+    (snapshot_dir / "model.safetensors.index.json").write_text(json.dumps({
+        "weight_map": {
+            "model.language_model.layers.1.self_attn.q_proj.weight": "shard-2.safetensors",
+        }
+    }))
+    (snapshot_dir / "shard-2.safetensors").write_bytes(b"stub")
+
+    class FakeModule:
+        def __init__(self):
+            self.to_calls = []
+
+        def to(self, device):
+            self.to_calls.append(device)
+            return self
+
+    class FakeModel:
+        def __init__(self):
+            self.model = types.SimpleNamespace(
+                layers=[FakeModule(), FakeModule(), FakeModule()],
+                rotary_emb=FakeModule(),
+            )
+
+        def tie_weights(self):
+            pass
+
+    class AutoConfigStub:
+        @staticmethod
+        def from_pretrained(model_id):
+            return types.SimpleNamespace(
+                text_config=types.SimpleNamespace(num_hidden_layers=3),
+                get_text_config=lambda: types.SimpleNamespace(num_hidden_layers=3),
+            )
+
+    class AutoModelStub:
+        @staticmethod
+        def from_config(cfg, torch_dtype=None):
+            return FakeModel()
+
+    set_calls = []
+
+    def fake_set_tensor(module, tensor_name, device, value=None, dtype=None):
+        set_calls.append(tensor_name)
+
+    class FakeSafeOpen:
+        def __init__(self, filename, framework, device):
+            self.filename = Path(filename).name
+
+        def __enter__(self):
+            return self
+
+        def __exit__(self, exc_type, exc, tb):
+            return False
+
+        def get_tensor(self, tensor_name):
+            return tensor_name
+
+    class UnusedContext:
+        def __enter__(self):
+            return None
+
+        def __exit__(self, exc_type, exc, tb):
+            return False
+
+    _load_partial_model_from_snapshot(
+        AutoConfigStub,
+        AutoModelStub,
+        types.SimpleNamespace(),
+        str(snapshot_dir),
+        1,
+        1,
+        "bf16",
+        "cpu:0",
+        init_empty_weights_fn=UnusedContext,
+        set_tensor_fn=fake_set_tensor,
+        safe_open_fn=FakeSafeOpen,
+    )
+
+    assert set_calls == ["model.layers.1.self_attn.q_proj.weight"]
+
+
+def test_partial_snapshot_loader_skips_tensors_absent_from_causal_lm(tmp_path):
+    # Multimodal/MTP checkpoints (Qwen3.5/3.6-MoE) carry mtp.* and model.visual.*
+    # tensors that the text-only CausalLM never builds — they must be skipped,
+    # not assigned (assignment raises AttributeError: 'mtp' / 'visual').
+    snapshot_dir = tmp_path / "snapshot"
+    snapshot_dir.mkdir()
+    (snapshot_dir / "config.json").write_text(json.dumps({
+        "text_config": {"num_hidden_layers": 3},
+    }))
+    (snapshot_dir / "model.safetensors.index.json").write_text(json.dumps({
+        "weight_map": {
+            "model.language_model.layers.1.self_attn.q_proj.weight": "shard-2.safetensors",
+            "mtp.layers.1.input_layernorm.weight": "shard-2.safetensors",
+            "model.visual.blocks.1.attn.qkv.weight": "shard-2.safetensors",
+        }
+    }))
+    (snapshot_dir / "shard-2.safetensors").write_bytes(b"stub")
+
+    class FakeModule:
+        def to(self, device):
+            return self
+
+    class FakeModel:
+        def __init__(self):
+            self.model = types.SimpleNamespace(
+                layers=[FakeModule(), FakeModule(), FakeModule()],
+                rotary_emb=FakeModule(),
+            )
+
+        def tie_weights(self):
+            pass
+
+        def state_dict(self):
+            return {"model.layers.1.self_attn.q_proj.weight": None}
+
+    class AutoConfigStub:
+        @staticmethod
+        def from_pretrained(model_id):
+            return types.SimpleNamespace(
+                text_config=types.SimpleNamespace(num_hidden_layers=3),
+                get_text_config=lambda: types.SimpleNamespace(num_hidden_layers=3),
+            )
+
+    class AutoModelStub:
+        @staticmethod
+        def from_config(cfg, torch_dtype=None):
+            return FakeModel()
+
+    set_calls = []
+
+    def fake_set_tensor(module, tensor_name, device, value=None, dtype=None):
+        set_calls.append(tensor_name)
+
+    class FakeSafeOpen:
+        def __init__(self, filename, framework, device):
+            pass
+
+        def __enter__(self):
+            return self
+
+        def __exit__(self, exc_type, exc, tb):
+            return False
+
+        def get_tensor(self, tensor_name):
+            return tensor_name
+
+    class UnusedContext:
+        def __enter__(self):
+            return None
+
+        def __exit__(self, exc_type, exc, tb):
+            return False
+
+    _load_partial_model_from_snapshot(
+        AutoConfigStub,
+        AutoModelStub,
+        types.SimpleNamespace(),
+        str(snapshot_dir),
+        1,
+        1,
+        "bf16",
+        "cpu:0",
+        init_empty_weights_fn=UnusedContext,
+        set_tensor_fn=fake_set_tensor,
+        safe_open_fn=FakeSafeOpen,
+    )
+
+    assert set_calls == ["model.layers.1.self_attn.q_proj.weight"]
+
+
 def test_partial_snapshot_loader_materializes_only_assigned_tensors(tmp_path):
     snapshot_dir = tmp_path / "snapshot"
     snapshot_dir.mkdir()

tests/test_tracker_as_node.py

@@ -142,6 +142,21 @@ def _send_chat_request(gateway_url: str, prompt: str) -> dict:
         return json.loads(r.read())
 
 
+def _send_streaming_chat_request(gateway_url: str, prompt: str):
+    data = json.dumps({
+        "model": GPT2_MODEL,
+        "messages": [{"role": "user", "content": prompt}],
+        "stream": True,
+    }).encode()
+    req = urllib.request.Request(
+        f"{gateway_url}/v1/chat/completions",
+        data=data,
+        headers={"Content-Type": "application/json"},
+        method="POST",
+    )
+    return urllib.request.urlopen(req)
+
+
 def test_all_responses_valid_openai_format(tracker_node_setup):
     """Ten requests via gateway all return valid OpenAI chat completion format."""
     gateway_url, _, _ = tracker_node_setup
@@ -155,6 +170,30 @@ def test_all_responses_valid_openai_format(tracker_node_setup):
         assert isinstance(message.get("content"), str), f"request {i}: content must be a string"
 
 
+def test_streaming_head_worker_response_is_not_buffered_with_content_length(tracker_node_setup):
+    """Gateway must relay head-worker SSE as a live stream, not a buffered JSON-sized body."""
+    gateway_url, _, _ = tracker_node_setup
+
+    with _send_streaming_chat_request(gateway_url, "stream through head worker") as resp:
+        assert resp.status == 200
+        assert "text/event-stream" in resp.headers["Content-Type"]
+        assert "Content-Length" not in resp.headers
+        data_lines = []
+        while len(data_lines) < 4:
+            line = resp.readline().decode().strip()
+            if line.startswith("data: "):
+                data_lines.append(line)
+            if line == "data: [DONE]":
+                break
+
+    assert data_lines[-1] == "data: [DONE]"
+    content = "".join(
+        json.loads(line[6:])["choices"][0].get("delta", {}).get("content", "")
+        for line in data_lines[:-1]
+    )
+    assert "head-worker" in content
+
+
 def test_both_tracker_nodes_receive_load(tracker_node_setup):
     """Both head workers handle at least one request each out of ten."""
     gateway_url, tracker_node_a, tracker_node_b = tracker_node_setup

tests/test_tracker_logging.py

@@ -0,0 +1,67 @@
+import logging
+import sys
+
+from meshnet_tracker.logging_setup import configure_tracker_file_logging, tracker_logger
+
+
+def test_tracker_file_logging_writes_separate_level_files(tmp_path):
+    original_stdout = sys.stdout
+    original_stderr = sys.stderr
+    try:
+        log_dir = configure_tracker_file_logging(tmp_path, tee_stdio=False)
+        logger = tracker_logger()
+
+        logger.info("info-event")
+        logger.warning("warning-event")
+        logger.error("error-event")
+        for handler in logger.handlers:
+            handler.flush()
+
+        assert (log_dir / "info.log").read_text().count("info-event") == 1
+        assert "warning-event" not in (log_dir / "info.log").read_text()
+        assert "error-event" not in (log_dir / "info.log").read_text()
+
+        assert "warning-event" in (log_dir / "warning.log").read_text()
+        assert "info-event" not in (log_dir / "warning.log").read_text()
+        assert "error-event" not in (log_dir / "warning.log").read_text()
+
+        assert "error-event" in (log_dir / "error.log").read_text()
+        assert "info-event" not in (log_dir / "error.log").read_text()
+        assert "warning-event" not in (log_dir / "error.log").read_text()
+    finally:
+        sys.stdout = original_stdout
+        sys.stderr = original_stderr
+
+
+def test_tracker_file_logging_tees_stdio_and_rotates(tmp_path):
+    original_stdout = sys.stdout
+    original_stderr = sys.stderr
+    try:
+        log_dir = configure_tracker_file_logging(
+            tmp_path,
+            max_bytes=120,
+            backup_count=1,
+        )
+
+        print("stdout goes to info", flush=True)
+        print("stderr goes to error", file=sys.stderr, flush=True)
+        for handler in tracker_logger().handlers:
+            handler.flush()
+
+        assert "stdout goes to info" in (log_dir / "info.log").read_text()
+        assert "stderr goes to error" in (log_dir / "error.log").read_text()
+
+        for index in range(12):
+            tracker_logger().info("rotating-info-line-%02d", index)
+        for handler in tracker_logger().handlers:
+            handler.flush()
+
+        assert (log_dir / "info.log.1").exists()
+    finally:
+        sys.stdout = original_stdout
+        sys.stderr = original_stderr
+        logger = tracker_logger()
+        for handler in logger.handlers:
+            handler.close()
+        logger.handlers.clear()
+        logger.setLevel(logging.NOTSET)

tests/test_tracker_routing.py

@@ -5,6 +5,7 @@ import json
 import threading
 import time
 import urllib.error
+import urllib.parse
 import urllib.request
 
 import pytest
@@ -466,6 +467,7 @@ def test_tracker_logs_stream_progress_before_request_completes():
             method="POST",
         )
         response = urllib.request.urlopen(req, timeout=3.0)
+        assert response.headers["X-Accel-Buffering"] == "no"
         first_line = response.readline()
         assert first_line.startswith(b"data:")
         assert chunk_sent.wait(timeout=1.0)
@@ -501,6 +503,169 @@ def test_tracker_logs_stream_progress_before_request_completes():
         node_thread.join(timeout=1.0)
 
 
+def test_tracker_stream_survives_idle_gap_between_sse_chunks():
+    first_chunk_sent = threading.Event()
+
+    class IdleStreamingChatHandler(http.server.BaseHTTPRequestHandler):
+        def log_message(self, format, *args):
+            pass
+
+        def do_POST(self):
+            if self.path != "/v1/chat/completions":
+                self.send_response(404)
+                self.end_headers()
+                return
+            self.rfile.read(int(self.headers.get("Content-Length", 0)))
+            self.send_response(200)
+            self.send_header("Content-Type", "text/event-stream; charset=utf-8")
+            self.end_headers()
+            first = json.dumps({
+                "choices": [{"delta": {"content": "hello"}}],
+            }).encode()
+            second = json.dumps({
+                "choices": [{"delta": {"content": " world"}}],
+            }).encode()
+            self.wfile.write(b"data: " + first + b"\n\n")
+            self.wfile.flush()
+            first_chunk_sent.set()
+            time.sleep(1.0)
+            self.wfile.write(b"data: " + second + b"\n\n")
+            self.wfile.write(b"data: [DONE]\n\n")
+            self.wfile.flush()
+
+    node = http.server.HTTPServer(("127.0.0.1", 0), IdleStreamingChatHandler)
+    node_thread = threading.Thread(target=node.serve_forever, daemon=True)
+    node_thread.start()
+    tracker = TrackerServer(heartbeat_timeout=60.0)
+    tracker_port = tracker.start()
+    response = None
+    try:
+        _post_json(
+            f"http://127.0.0.1:{tracker_port}/v1/nodes/register",
+            {"endpoint": f"http://127.0.0.1:{node.server_address[1]}",
+             "model": "idle-stream-model", "num_layers": 1,
+             "shard_start": 0, "shard_end": 0,
+             "hardware_profile": {}, "score": 1.0},
+        )
+        req = urllib.request.Request(
+            f"http://127.0.0.1:{tracker_port}/v1/chat/completions",
+            data=json.dumps({
+                "model": "idle-stream-model",
+                "stream": True,
+                "messages": [{"role": "user", "content": "hi"}],
+            }).encode(),
+            headers={"Content-Type": "application/json"},
+            method="POST",
+        )
+        response = urllib.request.urlopen(req, timeout=3.0)
+        assert response.readline().startswith(b"data:")
+        assert first_chunk_sent.wait(timeout=1.0)
+
+        remaining = response.read().splitlines()
+        assert b"data: [DONE]" in remaining
+    finally:
+        if response is not None:
+            response.close()
+        tracker.stop()
+        node.shutdown()
+        node.server_close()
+        node_thread.join(timeout=1.0)
+
+
+def test_tracker_dashboard_can_cancel_inflight_proxy():
+    chunk_sent = threading.Event()
+    release = threading.Event()
+
+    class StreamingChatHandler(http.server.BaseHTTPRequestHandler):
+        def log_message(self, fmt, *args):
+            pass
+
+        def do_POST(self):
+            if self.path != "/v1/chat/completions":
+                self.send_response(404)
+                self.end_headers()
+                return
+            self.rfile.read(int(self.headers.get("Content-Length", 0)))
+            self.send_response(200)
+            self.send_header("Content-Type", "text/event-stream; charset=utf-8")
+            self.end_headers()
+            payload = json.dumps({
+                "choices": [{"delta": {"content": "hello world"}}],
+            }).encode()
+            self.wfile.write(b"data: " + payload + b"\n\n")
+            self.wfile.flush()
+            chunk_sent.set()
+            release.wait(timeout=3.0)
+            self.wfile.write(b"data: [DONE]\n\n")
+            self.wfile.flush()
+
+    node = http.server.HTTPServer(("127.0.0.1", 0), StreamingChatHandler)
+    node_thread = threading.Thread(target=node.serve_forever, daemon=True)
+    node_thread.start()
+    tracker = TrackerServer(heartbeat_timeout=60.0)
+    tracker_port = tracker.start()
+    response = None
+    request_id = None
+    try:
+        _post_json(
+            f"http://127.0.0.1:{tracker_port}/v1/nodes/register",
+            {"endpoint": f"http://127.0.0.1:{node.server_address[1]}",
+             "model": "cancel-proxy-model", "num_layers": 1,
+             "shard_start": 0, "shard_end": 0,
+             "hardware_profile": {}, "score": 1.0},
+        )
+        req = urllib.request.Request(
+            f"http://127.0.0.1:{tracker_port}/v1/chat/completions",
+            data=json.dumps({
+                "model": "cancel-proxy-model",
+                "stream": True,
+                "messages": [{"role": "user", "content": "hi"}],
+            }).encode(),
+            headers={"Content-Type": "application/json"},
+            method="POST",
+        )
+        response = urllib.request.urlopen(req, timeout=3.0)
+        first_line = response.readline()
+        assert first_line.startswith(b"data:")
+        assert chunk_sent.wait(timeout=1.0)
+
+        console = _get_json(f"http://127.0.0.1:{tracker_port}/v1/console")
+        selected = [
+            event for event in console["events"]
+            if event["message"] == "proxy route selected"
+        ]
+        assert selected
+        request_id = selected[-1]["fields"]["request_id"]
+
+        cancel = _post_json(
+            f"http://127.0.0.1:{tracker_port}/v1/proxy/requests/{urllib.parse.quote(request_id, safe='')}/cancel",
+            {},
+        )
+        assert cancel["status"] == "canceled"
+
+        deadline = time.time() + 5.0
+        canceled_events = []
+        while time.time() < deadline:
+            console = _get_json(f"http://127.0.0.1:{tracker_port}/v1/console")
+            canceled_events = [
+                event for event in console["events"]
+                if event["message"] == "proxy canceled"
+                and event["fields"].get("request_id") == request_id
+            ]
+            if canceled_events:
+                break
+            time.sleep(0.05)
+        assert canceled_events
+    finally:
+        release.set()
+        if response is not None:
+            response.close()
+        tracker.stop()
+        node.shutdown()
+        node.server_close()
+        node_thread.join(timeout=1.0)
+
+
 def test_tracker_routes_hf_model_alias_from_quickstart():
     """The documented qwen2.5-0.5b alias resolves a full HF repo registration."""
     tracker = TrackerServer()
@@ -746,6 +911,57 @@ def test_tracker_route_endpoint_ignores_model_case_and_outer_whitespace():
     assert response["route"] == ["http://127.0.0.1:9101"]
 
 
+def test_tracker_route_prefers_distributed_over_single_full_shard():
+    """When a full 0-39 node and a partial 0-21 head coexist, /v1/route
+    should return both hops — not the full shard alone."""
+    tracker = TrackerServer(model_presets={
+        "qwen3.6-35b-a3b": {
+            "layers_start": 0,
+            "layers_end": 39,
+            "hf_repo": "unsloth/Qwen3.6-35B-A3B",
+            "aliases": ["Qwen3.6-35B-A3B"],
+        }
+    })
+    tracker_port = tracker.start()
+    try:
+        _post_json(
+            f"http://127.0.0.1:{tracker_port}/v1/nodes/register",
+            {"endpoint": "http://192.168.0.179:7000",
+             "model": "qwen3.6-35b-a3b",
+             "hf_repo": "unsloth/Qwen3.6-35B-A3B",
+             "num_layers": 40,
+             "shard_start": 0,
+             "shard_end": 39,
+             "tracker_mode": True,
+             "hardware_profile": {},
+             "score": 1.0},
+        )
+        _post_json(
+            f"http://127.0.0.1:{tracker_port}/v1/nodes/register",
+            {"endpoint": "http://192.168.0.20:7000",
+             "model": "Qwen3.6-35B-A3B",
+             "hf_repo": "unsloth/Qwen3.6-35B-A3B",
+             "num_layers": 40,
+             "shard_start": 0,
+             "shard_end": 21,
+             "tracker_mode": True,
+             "hardware_profile": {},
+             "score": 1.0},
+        )
+
+        response = _get_json(
+            f"http://127.0.0.1:{tracker_port}/v1/route?model=qwen3.6-35b-a3b"
+        )
+    finally:
+        tracker.stop()
+
+    assert response["route"] == [
+        "http://192.168.0.20:7000",
+        "http://192.168.0.179:7000",
+    ]
+    assert [node["start_layer"] for node in response["nodes"]] == [0, 22]
+
+
 def test_tracker_proxy_ignores_model_case_and_outer_whitespace():
     class ChatHandler(http.server.BaseHTTPRequestHandler):
         def log_message(self, fmt, *args):
@@ -1403,6 +1619,70 @@ def test_tracker_heartbeat_updates_node():
         tracker.stop()
 
 
+def test_tracker_heartbeat_stores_current_requests():
+    """Node-reported in-flight request snapshots appear on the network map."""
+    tracker = TrackerServer()
+    tracker_port = tracker.start()
+    try:
+        reg = _post_json(
+            f"http://127.0.0.1:{tracker_port}/v1/nodes/register",
+            {
+                "endpoint": "http://127.0.0.1:9001",
+                "model": "progress-model",
+                "shard_start": 0,
+                "shard_end": 31,
+                "hardware_profile": {},
+                "score": 1.0,
+            },
+        )
+        node_id = reg["node_id"]
+        _post_json(
+            f"http://127.0.0.1:{tracker_port}/v1/nodes/{node_id}/heartbeat",
+            {
+                "queue_depth": 1,
+                "current_requests": [{
+                    "request_id": "req-abc123",
+                    "model": "progress-model",
+                    "kind": "chat",
+                    "tokens": 17,
+                    "elapsed_seconds": 42.5,
+                    "tokens_per_sec": 0.4,
+                    "routing_complete": True,
+                }],
+            },
+        )
+        network = _get_json(f"http://127.0.0.1:{tracker_port}/v1/network/map")
+        node = next(item for item in network["nodes"] if item["node_id"] == node_id)
+        assert node["stats"]["queue_depth"] == 1
+        assert node["stats"]["current_requests"] == [{
+            "request_id": "req-abc123",
+            "model": "progress-model",
+            "kind": "chat",
+            "tokens": 17,
+            "elapsed_seconds": 42.5,
+            "tokens_per_sec": 0.4,
+            "routing_complete": True,
+        }]
+    finally:
+        tracker.stop()
+
+
+def test_normalize_current_requests_sanitizes_payload():
+    from meshnet_tracker.server import _normalize_current_requests
+
+    assert _normalize_current_requests(None) == []
+    assert _normalize_current_requests([
+        {"request_id": "req-1", "model": "m", "tokens": "9", "tokens_per_sec": "1.5"},
+        {"model": "missing-id"},
+        "bad",
+    ]) == [{
+        "request_id": "req-1",
+        "model": "m",
+        "tokens": 9,
+        "tokens_per_sec": 1.5,
+    }]
+
+
 def test_tracker_heartbeat_expiry():
     """Nodes that miss their heartbeat window are excluded from routes."""
     tracker = TrackerServer(heartbeat_timeout=0.05)  # 50 ms