homegraph 1.1.2 → 1.2.0

package/scripts/agent-eval/offload-eval-frontload.sh

@@ -1,47 +1,47 @@
-#!/usr/bin/env bash
-# FRONTLOAD arm (approach 1): homegraph attached (offload-disabled) + the front-load
-# UserPromptSubmit hook (offload-eval-hook.mjs), n reps, appended to $RESULTS. Compare against
-# the matrix's raw/nocg baselines. Usage: offload-eval-frontload.sh <indexed-repo> <tier> <reps> "<Q>"
-# Env: MODEL=sonnet EFFORT=high  RESULTS=<file>  AGENT_EVAL_OUT=<scratch dir>
-set -uo pipefail
-HERE="$(cd "$(dirname "$0")" && pwd)"
-ENGINE="$(cd "$HERE/../.." && pwd)"
-BIN="$ENGINE/dist/bin/homegraph.js"
-OUT="${AGENT_EVAL_OUT:-/tmp/cg-offload-eval}"
-TARGET="${1:?repo}"; TIER="${2:?tier}"; REPS="${3:?reps}"; Q="${4:?question}"
-RUNS="$OUT/runs"
-EXTRACT="$HERE/offload-eval-metrics.mjs"
-RESULTS="${RESULTS:-$OUT/results-fl.jsonl}"
-REPO=$(basename "$TARGET")
-mkdir -p "$RUNS"
-[ -d "$TARGET/.homegraph" ] || { echo "not indexed: $TARGET"; exit 1; }
-TARGET=$(cd "$TARGET" && pwd -P)
-
-CFG="$RUNS/mcp-fl-$REPO.json"
-printf '{"mcpServers":{"homegraph":{"command":"env","args":["HOMEGRAPH_WASM_RELAUNCHED=1","HOMEGRAPH_OFFLOAD_DISABLE=1","node","%s","serve","--mcp","--path","%s"]}}}' "$BIN" "$TARGET" > "$CFG"
-# Generate the hook settings pointing at the persisted hook; enable its debug log so we can
-# count injections (claude passes this env down to the spawned hook process).
-HOOKCFG="$RUNS/frontload-settings.json"
-printf '{"hooks":{"UserPromptSubmit":[{"hooks":[{"type":"command","command":"node %s/offload-eval-hook.mjs"}]}]}}' "$HERE" > "$HOOKCFG"
-export CG_FRONTLOAD_DEBUG="$RUNS/hook-debug.log"
-
-prewarm() {
-  pkill -9 -f "serve --mcp --path $1" 2>/dev/null; rm -f "$1/.homegraph/daemon.sock" 2>/dev/null; sleep 0.6
-  env HOMEGRAPH_OFFLOAD_DISABLE=1 HOMEGRAPH_DAEMON_IDLE_TIMEOUT_MS=1800000 node "$BIN" serve --mcp --path "$1" </dev/null >/dev/null 2>&1 &
-  node -e 'const fs=require("fs");let n=0;const t=setInterval(()=>{if(fs.existsSync(process.argv[1]+"/.homegraph/daemon.sock")){clearInterval(t);process.exit(0)}if(n++>150){clearInterval(t);process.exit(1)}},100)' "$1" \
-    && echo "  daemon warm" || echo "  WARN no daemon"
-}
-
-echo "###### FRONTLOAD repo=$REPO tier=$TIER reps=$REPS"
-prewarm "$TARGET"
-for r in $(seq 1 "$REPS"); do
-  tag="$REPO-frontload-$r"
-  ( cd "$TARGET" && claude -p "$Q" --output-format stream-json --verbose --permission-mode bypassPermissions \
-      --model "${MODEL:-sonnet}" --effort "${EFFORT:-high}" --max-budget-usd 4 \
-      --strict-mcp-config --mcp-config "$CFG" --settings "$HOOKCFG" \
-      </dev/null > "$RUNS/$tag.jsonl" 2>"$RUNS/$tag.err" )
-  node "$EXTRACT" --run "$RUNS/$tag.jsonl" --usage "-" --arm frontload --rep "$r" --repo "$REPO" --tier "$TIER" --q "$Q" >> "$RESULTS"
-  node -e 'const o=JSON.parse(require("fs").readFileSync(process.argv[1],"utf8").trim().split("\n").pop());console.log(`  [frontload #${o.rep}] ${o.durationSec}s | main $${o.costUsdMain} ${o.tokBillable}tok | read=${o.read} grep=${o.grep} agentExplore=${o.explore} | ok=${o.ok}`)' "$RESULTS"
-done
-pkill -9 -f "serve --mcp --path $TARGET" 2>/dev/null; rm -f "$TARGET/.homegraph/daemon.sock" 2>/dev/null
-echo "###### FRONTLOAD DONE $REPO (cumulative hook injections: $(grep -c INJECTED "$CG_FRONTLOAD_DEBUG" 2>/dev/null))"
+#!/usr/bin/env bash
+# FRONTLOAD arm (approach 1): homegraph attached (offload-disabled) + the front-load
+# UserPromptSubmit hook (offload-eval-hook.mjs), n reps, appended to $RESULTS. Compare against
+# the matrix's raw/nocg baselines. Usage: offload-eval-frontload.sh <indexed-repo> <tier> <reps> "<Q>"
+# Env: MODEL=sonnet EFFORT=high  RESULTS=<file>  AGENT_EVAL_OUT=<scratch dir>
+set -uo pipefail
+HERE="$(cd "$(dirname "$0")" && pwd)"
+ENGINE="$(cd "$HERE/../.." && pwd)"
+BIN="$ENGINE/dist/bin/homegraph.js"
+OUT="${AGENT_EVAL_OUT:-/tmp/cg-offload-eval}"
+TARGET="${1:?repo}"; TIER="${2:?tier}"; REPS="${3:?reps}"; Q="${4:?question}"
+RUNS="$OUT/runs"
+EXTRACT="$HERE/offload-eval-metrics.mjs"
+RESULTS="${RESULTS:-$OUT/results-fl.jsonl}"
+REPO=$(basename "$TARGET")
+mkdir -p "$RUNS"
+[ -d "$TARGET/.homegraph" ] || { echo "not indexed: $TARGET"; exit 1; }
+TARGET=$(cd "$TARGET" && pwd -P)
+
+CFG="$RUNS/mcp-fl-$REPO.json"
+printf '{"mcpServers":{"homegraph":{"command":"env","args":["HOMEGRAPH_WASM_RELAUNCHED=1","HOMEGRAPH_OFFLOAD_DISABLE=1","node","%s","serve","--mcp","--path","%s"]}}}' "$BIN" "$TARGET" > "$CFG"
+# Generate the hook settings pointing at the persisted hook; enable its debug log so we can
+# count injections (claude passes this env down to the spawned hook process).
+HOOKCFG="$RUNS/frontload-settings.json"
+printf '{"hooks":{"UserPromptSubmit":[{"hooks":[{"type":"command","command":"node %s/offload-eval-hook.mjs"}]}]}}' "$HERE" > "$HOOKCFG"
+export CG_FRONTLOAD_DEBUG="$RUNS/hook-debug.log"
+
+prewarm() {
+  pkill -9 -f "serve --mcp --path $1" 2>/dev/null; rm -f "$1/.homegraph/daemon.sock" 2>/dev/null; sleep 0.6
+  env HOMEGRAPH_OFFLOAD_DISABLE=1 HOMEGRAPH_DAEMON_IDLE_TIMEOUT_MS=1800000 node "$BIN" serve --mcp --path "$1" </dev/null >/dev/null 2>&1 &
+  node -e 'const fs=require("fs");let n=0;const t=setInterval(()=>{if(fs.existsSync(process.argv[1]+"/.homegraph/daemon.sock")){clearInterval(t);process.exit(0)}if(n++>150){clearInterval(t);process.exit(1)}},100)' "$1" \
+    && echo "  daemon warm" || echo "  WARN no daemon"
+}
+
+echo "###### FRONTLOAD repo=$REPO tier=$TIER reps=$REPS"
+prewarm "$TARGET"
+for r in $(seq 1 "$REPS"); do
+  tag="$REPO-frontload-$r"
+  ( cd "$TARGET" && claude -p "$Q" --output-format stream-json --verbose --permission-mode bypassPermissions \
+      --model "${MODEL:-sonnet}" --effort "${EFFORT:-high}" --max-budget-usd 4 \
+      --strict-mcp-config --mcp-config "$CFG" --settings "$HOOKCFG" \
+      </dev/null > "$RUNS/$tag.jsonl" 2>"$RUNS/$tag.err" )
+  node "$EXTRACT" --run "$RUNS/$tag.jsonl" --usage "-" --arm frontload --rep "$r" --repo "$REPO" --tier "$TIER" --q "$Q" >> "$RESULTS"
+  node -e 'const o=JSON.parse(require("fs").readFileSync(process.argv[1],"utf8").trim().split("\n").pop());console.log(`  [frontload #${o.rep}] ${o.durationSec}s | main $${o.costUsdMain} ${o.tokBillable}tok | read=${o.read} grep=${o.grep} agentExplore=${o.explore} | ok=${o.ok}`)' "$RESULTS"
+done
+pkill -9 -f "serve --mcp --path $TARGET" 2>/dev/null; rm -f "$TARGET/.homegraph/daemon.sock" 2>/dev/null
+echo "###### FRONTLOAD DONE $REPO (cumulative hook injections: $(grep -c INJECTED "$CG_FRONTLOAD_DEBUG" 2>/dev/null))"

package/scripts/agent-eval/offload-eval-ground-truth.json

@@ -1,18 +1,18 @@
-{
-  "mtkruto": {
-    "question": "How does calling the high-level client.sendMessage() method get the message serialized into a TL/MTProto request and sent over the network transport to Telegram's servers? Trace the call path.",
-    "truth": "Verified call path (small TS Telegram-client lib):\n1. Client.sendMessage — client/6_client.ts:1852 → calls this.#messageManager.sendMessage(...) (1853)\n2. MessageManager.sendMessage — client/3_message_manager.ts:330 → builds the TL function {_:\"messages.sendMessage\", peer, message,...} and calls this.#c.invoke(...) (~377)\n3. c.invoke closure / Client.#invoke — client/6_client.ts:279/887 → resolves a ClientEncrypted and calls client.invoke(function_) (897)\n4. ClientEncrypted.invoke — client/2_client_encrypted.ts:324 → this.#send(function_) (325)\n5. ClientEncrypted.#send — client/2_client_encrypted.ts:261 → SERIALIZES via Api.serializeObject(function_) (290), then this.session.send(body) (296)\n   - Serialization: Api.serializeObject (tl/2_telegram.ts:38) → new TLWriter().writeObject(...) (tl/1_tl_writer.ts) writes constructor id + fields\n6. SessionEncrypted.send — session/2_session_encrypted.ts:193 → ENQUEUES a PendingMessage and wakes the send loop (#awakeSendLoop) [DYNAMIC: async queue, not a direct call]\n7. SessionEncrypted.#sendLoopBody (AbortableLoop) — session/2_session_encrypted.ts:282 → #encryptMessage (serializeMessage tl/2_message.ts + IGE-256 AES) then this.transport.transport.send(payload) (339)\n8. Transport.send — TransportAbridged.send (transport/1_transport_abridged.ts:71) or TransportIntermediate → this.#connection.write(encrypt(framed))\n9. ConnectionTCP.write (connection/1_connection_tcp.ts:96) or ConnectionWebSocket.write — bytes exit the process.\nKEY SYMBOLS a correct answer must hit: sendMessage → MessageManager.sendMessage → invoke (ClientEncrypted.invoke/#send) → Api.serializeObject/TLWriter → SessionEncrypted.send (queue) → #sendLoopBody/#encryptMessage → Transport.send → Connection.write.\nDYNAMIC BOUNDARIES: the invoke indirection (closure→#invoke→ClientEncrypted), and the send-loop QUEUE between SessionEncrypted.send and #sendLoopBody (async, no direct edge)."
-  },
-  "postybirb": {
-    "question": "How does submitting/queueing a post reach the website-specific code that actually uploads to a target website? Trace the path from the submission entry point in the NestJS server to a concrete website service's post implementation.",
-    "truth": "Verified call path (NestJS+Electron, server under electron-app/src/server/):\n1. Entry: PostController.queue (submission/post/post.controller.ts:33, POST queue/:id) OR SubmissionService.queueScheduledSubmissions (submission/submission.service.ts, @Interval(60000) scheduler) — both call PostService.queue\n2. PostService.queue — submission/post/post.service.ts:68 → this.post(submission)\n3. PostService.post (private) — post.service.ts:206 → this.createPoster(...) for each non-default SubmissionPart\n4. PostService.createPoster — post.service.ts:373 → website = this.websites.getWebsiteModule(part.website) [part.website is a STRING]\n5. WebsiteProvider.getWebsiteModule — websites/website-provider.service.ts:86 → websiteModulesMap[name.toLowerCase()] [DYNAMIC: string-keyed registry of DI-injected Website singletons]; then new Poster(..., website, ...)\n6. Poster constructor — submission/post/poster.ts:117 → setTimeout(this.post.bind(this), delay) [DYNAMIC: async timer, min ~5s]\n7. Poster.post (poster.ts:131) → performPost (171) → attemptPost (217)\n8. Poster.attemptPost — poster.ts:217 → this.website.postFileSubmission(token, data, accountData) [DYNAMIC: polymorphic dispatch on abstract Website] (or postNotificationSubmission)\n9. Website.postFileSubmission (abstract) — websites/website.base.ts:102\n10. Concrete e.g. FurAffinity.postFileSubmission — websites/fur-affinity/fur-affinity.service.ts:231 → multi-step HTTP upload (GET /submit, POST /submit/upload multipart, POST /submit/finalize)\nKEY SYMBOLS: PostService.queue → PostService.post → createPoster → WebsiteProvider.getWebsiteModule (registry) → Poster (setTimeout) → Poster.attemptPost → Website.postFileSubmission (abstract base) → a concrete website service (e.g. FurAffinity).\nDYNAMIC BOUNDARIES: NestJS DI builds the website registry; string-keyed map lookup; setTimeout defers Poster.post; polymorphic dispatch on the abstract Website base. A correct answer must reach a concrete website's post via the registry + base class, not stop at PostService."
-  },
-  "shapeshift": {
-    "question": "How does executing a swap work in ShapeShift — from the code that fetches quotes and selects a swapper down to a specific swapper's execute/trade? Name the swapper interface, the registry, and one concrete swapper, and trace the path.",
-    "truth": "Verified call path (large multi-package monorepo; swap logic in packages/swapper + execution in src/lib):\nQUOTE/REGISTRY layer:\n- Swapper interface = the `Swapper` type (execute methods) + `SwapperApi` type (getTradeQuote/getUnsignedTx) — packages/swapper/src/types.ts (~846/897)\n- Registry = `swappers: Record<SwapperName,(SwapperApi & Swapper)>` — packages/swapper/src/constants.ts:52 (merges e.g. thorchainSwapper + thorchainApi)\n- Aggregator: swapperApi RTK endpoint getTradeQuote/getTradeRates (src/state/apis/swapper/swapperApi.ts:78/156) → getTradeQuotes (packages/swapper/src/swapper.ts:18/26): swapper = swappers[swapperName]; swapper.getTradeQuote(...) [DYNAMIC interface dispatch]\n- Concrete (THORChain): thorchainApi.getTradeQuote (swappers/ThorchainSwapper/endpoints.ts → getTradeQuote/getTradeQuote.ts:15) → getL1RateOrQuote → getQuote (thorService HTTP)\nSELECTION: tradeQuoteSlice selectors rank quotes (selectSortedTradeQuotes / selectActiveSwapperName) [DYNAMIC: winner chosen by ranking/user]\nEXECUTION layer:\n- useTradeExecution (src/components/MultiHopTrade/.../hooks/useTradeExecution.tsx:200/476) → new TradeExecution(); execution.execEvmTransaction(...) (CowSwap: execEvmMessage)\n- TradeExecution.execEvmTransaction — src/lib/tradeExecution.ts:326 → _execWalletAgnostic(...) (372)\n- TradeExecution._execWalletAgnostic — tradeExecution.ts:136 → swapper = swappers[swapperName] (149) [DYNAMIC registry]; buildSignBroadcast → swapper.getUnsignedEvmTransaction(...) (355) then swapper.executeEvmTransaction(unsignedTx, {signAndBroadcastTransaction}) (367) [DYNAMIC SwapperApi/Swapper interface]\n- Concrete (THORChain): thorchainSwapper.executeEvmTransaction (swappers/ThorchainSwapper/ThorchainSwapper.ts → utils.ts:181) delegates to callbacks.signAndBroadcastTransaction (wallet). CowSwap alt: cowSwapper.executeEvmMessage → signCowOrder + cowService.post.\nKEY SYMBOLS: Swapper/SwapperApi types, swappers registry (constants.ts), getTradeQuotes (swapper.ts), TradeExecution._execWalletAgnostic, swapper.getUnsignedEvmTransaction/executeEvmTransaction, one concrete swapper (thorchainSwapper/zrxSwapper/cowSwapper).\nDYNAMIC BOUNDARIES: swappers[name] registry lookup (2 sites); all hops into a concrete swapper are via the Swapper/SwapperApi interface, never a direct function. A correct answer must name the interface + registry and reach a concrete swapper through interface dispatch."
-  },
-  "trezor": {
-    "question": "How does sending a crypto transaction flow from the send form's review/sign action through to signing it via @trezor/connect (TrezorConnect.signTransaction)? Trace the call path.",
-    "truth": "Verified call path (trezor-suite monorepo; app in packages/suite, shared logic in suite-common/wallet-core, device API in packages/connect):\n1. ReviewButton.handleButtonReviewClick — packages/suite/src/views/wallet/send/TotalSent/ReviewButton.tsx:120 → signTransaction() (= useSendForm's sign)\n2. useSendForm.sign (exported as signTransaction) — packages/suite/src/hooks/wallet/useSendForm.ts:278 → dispatch(signAndPushSendFormTransactionThunk({formState, precomposedTransaction, selectedAccount})) [DYNAMIC: redux thunk]\n3. signAndPushSendFormTransactionThunk — packages/suite/src/actions/wallet/send/sendFormThunks.ts:237 → (first enhancePrecomposedTransactionThunk) then dispatch(signTransactionThunk({...})) [cross-package: thunk from suite-common/wallet-core]\n4. signTransactionThunk (coin-routing hub) — suite-common/wallet-core/src/send/sendFormThunks.ts:532/573 → networkType branch → dispatch(signBitcoinSendFormTransactionThunk) (ethereum→signEthereumSendFormTransactionThunk, etc.) [DYNAMIC: runtime coin dispatch]\n5. signBitcoinSendFormTransactionThunk — suite-common/wallet-core/src/send/sendFormBitcoinThunks.ts:394 → await TrezorConnect.signTransaction(signPayload)\n6. TrezorConnect.signTransaction (facade) — packages/connect-common/src/factory.ts → closure calls impl.call({method:'signTransaction',...}) [DYNAMIC: facade / iframe-or-module boundary]\n7. CoreInModule.call — packages/connect/src/impl/core-in-module.ts:171 → posts CORE_CALL to core (deferred promise)\n8. Core.onCall → getMethod — packages/connect/src/core/index.ts → getMethod resolves 'signTransaction' → new SignTransaction(message) [DYNAMIC: name→class]\n9. SignTransaction.run — packages/connect/src/api/signTransaction.ts:317 → signTx via device.getCommands().typedCall (protobuf to device). After signing, signAndPushSendFormTransactionThunk → pushSendFormTransactionThunk → TrezorConnect.pushTransaction.\nKEY SYMBOLS: ReviewButton → useSendForm.sign → signAndPushSendFormTransactionThunk (suite) → signTransactionThunk (wallet-core, coin hub) → signBitcoinSendFormTransactionThunk → TrezorConnect.signTransaction → connect factory/CoreInModule.call → SignTransaction.run.\nDYNAMIC BOUNDARIES: every suite→wallet-core hop is a redux thunk dispatch; signTransactionThunk branches by networkType at runtime; TrezorConnect is a dynamically-built facade crossing an iframe/module boundary; the SignTransaction class is resolved by name. A correct answer must cross suite→wallet-core→connect and reach TrezorConnect.signTransaction / SignTransaction.run, not stop at the UI."
-  }
-}
+{
+  "mtkruto": {
+    "question": "How does calling the high-level client.sendMessage() method get the message serialized into a TL/MTProto request and sent over the network transport to Telegram's servers? Trace the call path.",
+    "truth": "Verified call path (small TS Telegram-client lib):\n1. Client.sendMessage — client/6_client.ts:1852 → calls this.#messageManager.sendMessage(...) (1853)\n2. MessageManager.sendMessage — client/3_message_manager.ts:330 → builds the TL function {_:\"messages.sendMessage\", peer, message,...} and calls this.#c.invoke(...) (~377)\n3. c.invoke closure / Client.#invoke — client/6_client.ts:279/887 → resolves a ClientEncrypted and calls client.invoke(function_) (897)\n4. ClientEncrypted.invoke — client/2_client_encrypted.ts:324 → this.#send(function_) (325)\n5. ClientEncrypted.#send — client/2_client_encrypted.ts:261 → SERIALIZES via Api.serializeObject(function_) (290), then this.session.send(body) (296)\n   - Serialization: Api.serializeObject (tl/2_telegram.ts:38) → new TLWriter().writeObject(...) (tl/1_tl_writer.ts) writes constructor id + fields\n6. SessionEncrypted.send — session/2_session_encrypted.ts:193 → ENQUEUES a PendingMessage and wakes the send loop (#awakeSendLoop) [DYNAMIC: async queue, not a direct call]\n7. SessionEncrypted.#sendLoopBody (AbortableLoop) — session/2_session_encrypted.ts:282 → #encryptMessage (serializeMessage tl/2_message.ts + IGE-256 AES) then this.transport.transport.send(payload) (339)\n8. Transport.send — TransportAbridged.send (transport/1_transport_abridged.ts:71) or TransportIntermediate → this.#connection.write(encrypt(framed))\n9. ConnectionTCP.write (connection/1_connection_tcp.ts:96) or ConnectionWebSocket.write — bytes exit the process.\nKEY SYMBOLS a correct answer must hit: sendMessage → MessageManager.sendMessage → invoke (ClientEncrypted.invoke/#send) → Api.serializeObject/TLWriter → SessionEncrypted.send (queue) → #sendLoopBody/#encryptMessage → Transport.send → Connection.write.\nDYNAMIC BOUNDARIES: the invoke indirection (closure→#invoke→ClientEncrypted), and the send-loop QUEUE between SessionEncrypted.send and #sendLoopBody (async, no direct edge)."
+  },
+  "postybirb": {
+    "question": "How does submitting/queueing a post reach the website-specific code that actually uploads to a target website? Trace the path from the submission entry point in the NestJS server to a concrete website service's post implementation.",
+    "truth": "Verified call path (NestJS+Electron, server under electron-app/src/server/):\n1. Entry: PostController.queue (submission/post/post.controller.ts:33, POST queue/:id) OR SubmissionService.queueScheduledSubmissions (submission/submission.service.ts, @Interval(60000) scheduler) — both call PostService.queue\n2. PostService.queue — submission/post/post.service.ts:68 → this.post(submission)\n3. PostService.post (private) — post.service.ts:206 → this.createPoster(...) for each non-default SubmissionPart\n4. PostService.createPoster — post.service.ts:373 → website = this.websites.getWebsiteModule(part.website) [part.website is a STRING]\n5. WebsiteProvider.getWebsiteModule — websites/website-provider.service.ts:86 → websiteModulesMap[name.toLowerCase()] [DYNAMIC: string-keyed registry of DI-injected Website singletons]; then new Poster(..., website, ...)\n6. Poster constructor — submission/post/poster.ts:117 → setTimeout(this.post.bind(this), delay) [DYNAMIC: async timer, min ~5s]\n7. Poster.post (poster.ts:131) → performPost (171) → attemptPost (217)\n8. Poster.attemptPost — poster.ts:217 → this.website.postFileSubmission(token, data, accountData) [DYNAMIC: polymorphic dispatch on abstract Website] (or postNotificationSubmission)\n9. Website.postFileSubmission (abstract) — websites/website.base.ts:102\n10. Concrete e.g. FurAffinity.postFileSubmission — websites/fur-affinity/fur-affinity.service.ts:231 → multi-step HTTP upload (GET /submit, POST /submit/upload multipart, POST /submit/finalize)\nKEY SYMBOLS: PostService.queue → PostService.post → createPoster → WebsiteProvider.getWebsiteModule (registry) → Poster (setTimeout) → Poster.attemptPost → Website.postFileSubmission (abstract base) → a concrete website service (e.g. FurAffinity).\nDYNAMIC BOUNDARIES: NestJS DI builds the website registry; string-keyed map lookup; setTimeout defers Poster.post; polymorphic dispatch on the abstract Website base. A correct answer must reach a concrete website's post via the registry + base class, not stop at PostService."
+  },
+  "shapeshift": {
+    "question": "How does executing a swap work in ShapeShift — from the code that fetches quotes and selects a swapper down to a specific swapper's execute/trade? Name the swapper interface, the registry, and one concrete swapper, and trace the path.",
+    "truth": "Verified call path (large multi-package monorepo; swap logic in packages/swapper + execution in src/lib):\nQUOTE/REGISTRY layer:\n- Swapper interface = the `Swapper` type (execute methods) + `SwapperApi` type (getTradeQuote/getUnsignedTx) — packages/swapper/src/types.ts (~846/897)\n- Registry = `swappers: Record<SwapperName,(SwapperApi & Swapper)>` — packages/swapper/src/constants.ts:52 (merges e.g. thorchainSwapper + thorchainApi)\n- Aggregator: swapperApi RTK endpoint getTradeQuote/getTradeRates (src/state/apis/swapper/swapperApi.ts:78/156) → getTradeQuotes (packages/swapper/src/swapper.ts:18/26): swapper = swappers[swapperName]; swapper.getTradeQuote(...) [DYNAMIC interface dispatch]\n- Concrete (THORChain): thorchainApi.getTradeQuote (swappers/ThorchainSwapper/endpoints.ts → getTradeQuote/getTradeQuote.ts:15) → getL1RateOrQuote → getQuote (thorService HTTP)\nSELECTION: tradeQuoteSlice selectors rank quotes (selectSortedTradeQuotes / selectActiveSwapperName) [DYNAMIC: winner chosen by ranking/user]\nEXECUTION layer:\n- useTradeExecution (src/components/MultiHopTrade/.../hooks/useTradeExecution.tsx:200/476) → new TradeExecution(); execution.execEvmTransaction(...) (CowSwap: execEvmMessage)\n- TradeExecution.execEvmTransaction — src/lib/tradeExecution.ts:326 → _execWalletAgnostic(...) (372)\n- TradeExecution._execWalletAgnostic — tradeExecution.ts:136 → swapper = swappers[swapperName] (149) [DYNAMIC registry]; buildSignBroadcast → swapper.getUnsignedEvmTransaction(...) (355) then swapper.executeEvmTransaction(unsignedTx, {signAndBroadcastTransaction}) (367) [DYNAMIC SwapperApi/Swapper interface]\n- Concrete (THORChain): thorchainSwapper.executeEvmTransaction (swappers/ThorchainSwapper/ThorchainSwapper.ts → utils.ts:181) delegates to callbacks.signAndBroadcastTransaction (wallet). CowSwap alt: cowSwapper.executeEvmMessage → signCowOrder + cowService.post.\nKEY SYMBOLS: Swapper/SwapperApi types, swappers registry (constants.ts), getTradeQuotes (swapper.ts), TradeExecution._execWalletAgnostic, swapper.getUnsignedEvmTransaction/executeEvmTransaction, one concrete swapper (thorchainSwapper/zrxSwapper/cowSwapper).\nDYNAMIC BOUNDARIES: swappers[name] registry lookup (2 sites); all hops into a concrete swapper are via the Swapper/SwapperApi interface, never a direct function. A correct answer must name the interface + registry and reach a concrete swapper through interface dispatch."
+  },
+  "trezor": {
+    "question": "How does sending a crypto transaction flow from the send form's review/sign action through to signing it via @trezor/connect (TrezorConnect.signTransaction)? Trace the call path.",
+    "truth": "Verified call path (trezor-suite monorepo; app in packages/suite, shared logic in suite-common/wallet-core, device API in packages/connect):\n1. ReviewButton.handleButtonReviewClick — packages/suite/src/views/wallet/send/TotalSent/ReviewButton.tsx:120 → signTransaction() (= useSendForm's sign)\n2. useSendForm.sign (exported as signTransaction) — packages/suite/src/hooks/wallet/useSendForm.ts:278 → dispatch(signAndPushSendFormTransactionThunk({formState, precomposedTransaction, selectedAccount})) [DYNAMIC: redux thunk]\n3. signAndPushSendFormTransactionThunk — packages/suite/src/actions/wallet/send/sendFormThunks.ts:237 → (first enhancePrecomposedTransactionThunk) then dispatch(signTransactionThunk({...})) [cross-package: thunk from suite-common/wallet-core]\n4. signTransactionThunk (coin-routing hub) — suite-common/wallet-core/src/send/sendFormThunks.ts:532/573 → networkType branch → dispatch(signBitcoinSendFormTransactionThunk) (ethereum→signEthereumSendFormTransactionThunk, etc.) [DYNAMIC: runtime coin dispatch]\n5. signBitcoinSendFormTransactionThunk — suite-common/wallet-core/src/send/sendFormBitcoinThunks.ts:394 → await TrezorConnect.signTransaction(signPayload)\n6. TrezorConnect.signTransaction (facade) — packages/connect-common/src/factory.ts → closure calls impl.call({method:'signTransaction',...}) [DYNAMIC: facade / iframe-or-module boundary]\n7. CoreInModule.call — packages/connect/src/impl/core-in-module.ts:171 → posts CORE_CALL to core (deferred promise)\n8. Core.onCall → getMethod — packages/connect/src/core/index.ts → getMethod resolves 'signTransaction' → new SignTransaction(message) [DYNAMIC: name→class]\n9. SignTransaction.run — packages/connect/src/api/signTransaction.ts:317 → signTx via device.getCommands().typedCall (protobuf to device). After signing, signAndPushSendFormTransactionThunk → pushSendFormTransactionThunk → TrezorConnect.pushTransaction.\nKEY SYMBOLS: ReviewButton → useSendForm.sign → signAndPushSendFormTransactionThunk (suite) → signTransactionThunk (wallet-core, coin hub) → signBitcoinSendFormTransactionThunk → TrezorConnect.signTransaction → connect factory/CoreInModule.call → SignTransaction.run.\nDYNAMIC BOUNDARIES: every suite→wallet-core hop is a redux thunk dispatch; signTransactionThunk branches by networkType at runtime; TrezorConnect is a dynamically-built facade crossing an iframe/module boundary; the SignTransaction class is resolved by name. A correct answer must cross suite→wallet-core→connect and reach TrezorConnect.signTransaction / SignTransaction.run, not stop at the UI."
+  }
+}

package/scripts/agent-eval/offload-eval-hook.mjs

@@ -1,84 +1,84 @@
-#!/usr/bin/env node
-// UserPromptSubmit hook — APPROACH 1: additive context-injection.
-// Front-loads homegraph's structural answer for flow/impact/"how/where" prompts so the
-// agent's reflex grep/read has nothing left to find. Strictly additive (never blocks),
-// gated to structural prompts (no cost otherwise), and uses RAW explore (offload disabled)
-// so the injected context is accurate — never the (currently low-fidelity) synthesis.
-//
-// Reads {prompt, cwd} as JSON on stdin; prints the explore result to stdout (which Claude
-// Code injects into the agent's context). Any failure -> silent exit 0 (degradable).
-import { pathToFileURL, fileURLToPath } from 'node:url';
-import { resolve, join, dirname } from 'node:path';
-import { existsSync, readFileSync, appendFileSync } from 'node:fs';
-
-// Resolve the engine repo from this script's own location (scripts/agent-eval/ -> ../..),
-// overridable with CG_ENGINE. The hook ships inside the repo, so it finds its own dist.
-const HERE = dirname(fileURLToPath(import.meta.url));
-const ENGINE = process.env.CG_ENGINE || resolve(HERE, '..', '..');
-const BUDGET = Number(process.env.CG_FRONTLOAD_BUDGET || 16000);
-
-// Debug log only when CG_FRONTLOAD_DEBUG is set to a file path (the harness points it at a
-// log to count injections); off by default so the shipped hook writes nothing extra.
-const DBG = process.env.CG_FRONTLOAD_DEBUG;
-const dbg = (m) => { if (!DBG) return; try { appendFileSync(DBG, `[${new Date().toISOString()}] ${m}\n`); } catch { /* ignore */ } };
-
-let input = {};
-try { input = JSON.parse(readFileSync(0, 'utf8')); } catch (e) { dbg('stdin parse fail: ' + e.message); }
-const prompt = String(input.prompt || '');
-const cwd = String(input.cwd || process.cwd());
-dbg(`invoked: promptLen=${prompt.length} cwd=${cwd}`);
-
-// Gate: only structural / flow / impact / where-how questions. Cheap regex; silent no-op
-// otherwise so non-structural prompts ("fix this typo") cost nothing.
-const STRUCTURAL = /\b(how|where|trace|flow|path|reach(es|ed)?|call(s|ed|er|ers|ee)?|depend|impact|affect|wire[ds]?|connect|implement|architect|structure|breaks?|what calls|why does)\b/i;
-if (!prompt || !STRUCTURAL.test(prompt)) { dbg('gate: non-structural, no-op'); process.exit(0); }
-dbg('gate: structural PASS');
-
-// Find the index: cwd, then walk up a few levels.
-let root = cwd, found = null;
-for (let i = 0; i < 6 && root; i++) {
-  if (existsSync(join(root, '.homegraph'))) { found = root; break; }
-  const parent = resolve(root, '..'); if (parent === root) break; root = parent;
-}
-if (!found) { dbg(`no .homegraph found from cwd=${cwd}`); process.exit(0); }
-dbg(`found index at ${found}`);
-
-try {
-  process.env.HOMEGRAPH_OFFLOAD_DISABLE = '1'; // raw, accurate — never the unfixed offload
-  process.env.HOMEGRAPH_TELEMETRY = '0'; process.env.DO_NOT_TRACK = '1';
-  const load = async (rel) => import(pathToFileURL(resolve(ENGINE, rel)).href);
-  const idx = await load('dist/index.js');
-  const tools = await load('dist/mcp/tools.js');
-  const HomeGraph = idx.default?.default ?? idx.default ?? idx.HomeGraph;
-  const ToolHandler = tools.ToolHandler ?? tools.default?.ToolHandler;
-  if (typeof HomeGraph?.openSync !== 'function' || typeof ToolHandler !== 'function') process.exit(0);
-
-  // Retry once on a transient busy/locked index (the hook's openSync can race a
-  // freshly-warming daemon on the first prompt of a session).
-  let text = '';
-  for (let attempt = 1; attempt <= 2; attempt++) {
-    try {
-      const cg = HomeGraph.openSync(found);
-      const h = new ToolHandler(cg);
-      const res = await h.execute('homegraph_explore', { query: prompt });
-      text = res?.content?.[0]?.text ?? '';
-      try { cg.close?.(); } catch { /* ignore */ }
-      dbg(`explore attempt ${attempt} returned ${text.length} chars`);
-      break;
-    } catch (e) {
-      dbg(`explore attempt ${attempt} failed: ${e?.message || e}`);
-      if (attempt === 2) throw e;
-      await new Promise((r) => setTimeout(r, 800));
-    }
-  }
-  if (!text.trim()) { dbg('empty explore result, no-op'); process.exit(0); }
-  if (text.length > BUDGET) text = text.slice(0, BUDGET) + '\n…[front-load truncated to budget]';
-
-  process.stdout.write(
-    `## HomeGraph structural context (auto-retrieved for this question)\n` +
-    `The code graph was queried for your question; the relevant symbols, source, and call flow are below. ` +
-    `Treat the quoted source as already read. If you need more, call homegraph_explore with specific symbol names rather than grepping or reading files.\n\n` +
-    text + '\n'
-  );
-  dbg(`INJECTED ${text.length} chars`);
-} catch (e) { dbg('ERROR: ' + (e?.stack || e?.message || e)); process.exit(0); } // degradable
+#!/usr/bin/env node
+// UserPromptSubmit hook — APPROACH 1: additive context-injection.
+// Front-loads homegraph's structural answer for flow/impact/"how/where" prompts so the
+// agent's reflex grep/read has nothing left to find. Strictly additive (never blocks),
+// gated to structural prompts (no cost otherwise), and uses RAW explore (offload disabled)
+// so the injected context is accurate — never the (currently low-fidelity) synthesis.
+//
+// Reads {prompt, cwd} as JSON on stdin; prints the explore result to stdout (which Claude
+// Code injects into the agent's context). Any failure -> silent exit 0 (degradable).
+import { pathToFileURL, fileURLToPath } from 'node:url';
+import { resolve, join, dirname } from 'node:path';
+import { existsSync, readFileSync, appendFileSync } from 'node:fs';
+
+// Resolve the engine repo from this script's own location (scripts/agent-eval/ -> ../..),
+// overridable with CG_ENGINE. The hook ships inside the repo, so it finds its own dist.
+const HERE = dirname(fileURLToPath(import.meta.url));
+const ENGINE = process.env.CG_ENGINE || resolve(HERE, '..', '..');
+const BUDGET = Number(process.env.CG_FRONTLOAD_BUDGET || 16000);
+
+// Debug log only when CG_FRONTLOAD_DEBUG is set to a file path (the harness points it at a
+// log to count injections); off by default so the shipped hook writes nothing extra.
+const DBG = process.env.CG_FRONTLOAD_DEBUG;
+const dbg = (m) => { if (!DBG) return; try { appendFileSync(DBG, `[${new Date().toISOString()}] ${m}\n`); } catch { /* ignore */ } };
+
+let input = {};
+try { input = JSON.parse(readFileSync(0, 'utf8')); } catch (e) { dbg('stdin parse fail: ' + e.message); }
+const prompt = String(input.prompt || '');
+const cwd = String(input.cwd || process.cwd());
+dbg(`invoked: promptLen=${prompt.length} cwd=${cwd}`);
+
+// Gate: only structural / flow / impact / where-how questions. Cheap regex; silent no-op
+// otherwise so non-structural prompts ("fix this typo") cost nothing.
+const STRUCTURAL = /\b(how|where|trace|flow|path|reach(es|ed)?|call(s|ed|er|ers|ee)?|depend|impact|affect|wire[ds]?|connect|implement|architect|structure|breaks?|what calls|why does)\b/i;
+if (!prompt || !STRUCTURAL.test(prompt)) { dbg('gate: non-structural, no-op'); process.exit(0); }
+dbg('gate: structural PASS');
+
+// Find the index: cwd, then walk up a few levels.
+let root = cwd, found = null;
+for (let i = 0; i < 6 && root; i++) {
+  if (existsSync(join(root, '.homegraph'))) { found = root; break; }
+  const parent = resolve(root, '..'); if (parent === root) break; root = parent;
+}
+if (!found) { dbg(`no .homegraph found from cwd=${cwd}`); process.exit(0); }
+dbg(`found index at ${found}`);
+
+try {
+  process.env.HOMEGRAPH_OFFLOAD_DISABLE = '1'; // raw, accurate — never the unfixed offload
+  process.env.HOMEGRAPH_TELEMETRY = '0'; process.env.DO_NOT_TRACK = '1';
+  const load = async (rel) => import(pathToFileURL(resolve(ENGINE, rel)).href);
+  const idx = await load('dist/index.js');
+  const tools = await load('dist/mcp/tools.js');
+  const HomeGraph = idx.default?.default ?? idx.default ?? idx.HomeGraph;
+  const ToolHandler = tools.ToolHandler ?? tools.default?.ToolHandler;
+  if (typeof HomeGraph?.openSync !== 'function' || typeof ToolHandler !== 'function') process.exit(0);
+
+  // Retry once on a transient busy/locked index (the hook's openSync can race a
+  // freshly-warming daemon on the first prompt of a session).
+  let text = '';
+  for (let attempt = 1; attempt <= 2; attempt++) {
+    try {
+      const cg = HomeGraph.openSync(found);
+      const h = new ToolHandler(cg);
+      const res = await h.execute('homegraph_explore', { query: prompt });
+      text = res?.content?.[0]?.text ?? '';
+      try { cg.close?.(); } catch { /* ignore */ }
+      dbg(`explore attempt ${attempt} returned ${text.length} chars`);
+      break;
+    } catch (e) {
+      dbg(`explore attempt ${attempt} failed: ${e?.message || e}`);
+      if (attempt === 2) throw e;
+      await new Promise((r) => setTimeout(r, 800));
+    }
+  }
+  if (!text.trim()) { dbg('empty explore result, no-op'); process.exit(0); }
+  if (text.length > BUDGET) text = text.slice(0, BUDGET) + '\n…[front-load truncated to budget]';
+
+  process.stdout.write(
+    `## HomeGraph structural context (auto-retrieved for this question)\n` +
+    `The code graph was queried for your question; the relevant symbols, source, and call flow are below. ` +
+    `Treat the quoted source as already read. If you need more, call homegraph_explore with specific symbol names rather than grepping or reading files.\n\n` +
+    text + '\n'
+  );
+  dbg(`INJECTED ${text.length} chars`);
+} catch (e) { dbg('ERROR: ' + (e?.stack || e?.message || e)); process.exit(0); } // degradable

package/scripts/agent-eval/offload-eval-judge.mjs

@@ -1,103 +1,103 @@
-#!/usr/bin/env node
-// Accuracy judge. For each run in results.jsonl:
-//   - end-to-end: agent finalAnswer vs verified ground truth (all arms)
-//   - fidelity:   offload synthesized answer vs ground truth (offload arm only)
-// Judge = claude -p sonnet --effort high, no tools, run from a neutral cwd,
-// JSON-only verdicts. Writes judged.jsonl (one line per run, verdicts merged).
-//
-// Usage: judge.mjs --results <f> --truth <f> --out <f> [--concurrency 4]
-import { readFileSync, writeFileSync, existsSync } from 'fs';
-import { execFile } from 'child_process';
-
-const A = {};
-for (let i = 2; i < process.argv.length; i += 2) A[process.argv[i].replace(/^--/, '')] = process.argv[i + 1];
-const results = readFileSync(A.results, 'utf8').split('\n').filter(Boolean).map(l => JSON.parse(l));
-const truth = JSON.parse(readFileSync(A.truth, 'utf8'));
-const OUT = A.out || '/tmp/cg-offload-eval/judged.jsonl';
-const CONC = Number(A.concurrency || 4);
-
-function askJudge(prompt) {
-  return new Promise((resolve) => {
-    execFile('claude', ['-p', prompt, '--model', 'sonnet', '--effort', 'high',
-      '--max-budget-usd', '0.5', '--strict-mcp-config', '--mcp-config', '{"mcpServers":{}}'],
-      // Run from a neutral dir with no repo files so the judge can't "cheat" by reading source.
-      { cwd: process.env.AGENT_EVAL_OUT || '/tmp', maxBuffer: 1 << 24, timeout: 120000 },
-      (err, stdout) => {
-        const raw = (stdout || '').trim();
-        const m = raw.match(/\{[\s\S]*\}/);
-        if (!m) return resolve({ verdict: 'error', score: null, note: (err ? 'exec ' + err.message : 'no json').slice(0, 80) });
-        try { resolve(JSON.parse(m[0])); } catch { resolve({ verdict: 'error', score: null, note: 'parse fail' }); }
-      });
-  });
-}
-
-const e2ePrompt = (gt, ans) => `You are scoring whether an AI coding agent correctly answered a code-flow question about a repository. Judge ONLY against the verified ground truth. Do NOT use any tools.
-
-QUESTION: ${gt.question}
-
-VERIFIED GROUND TRUTH (the actual call path + files):
-${gt.truth}
-
-AGENT'S ANSWER:
-${ans || '(empty)'}
-
-Score how correct the agent's answer is vs the ground truth. A "pass" means it identifies the core mechanism and the major hops with the right files/symbols and makes no materially wrong claim. "partial" = right area but misses major hops or has notable errors. "fail" = wrong layer, fabricated, or misses the mechanism.
-Output ONLY minified JSON, no prose, no code fences:
-{"verdict":"pass|partial|fail","score":<0-100>,"missedHops":["..."],"wrongClaims":["..."],"note":"<=20 words"}`;
-
-const fidPrompt = (gt, ans) => `You are scoring the FIDELITY of a machine-synthesized code-exploration answer against verified ground truth. The synthesized answer claims to trace a flow and cite file:line locations. Do NOT use any tools.
-
-QUESTION: ${gt.question}
-
-VERIFIED GROUND TRUTH (the actual call path + files):
-${gt.truth}
-
-SYNTHESIZED ANSWER (to score):
-${ans || '(empty)'}
-
-Judge: (1) is the traced call path correct vs ground truth? (2) are the cited files/symbols correct (not fabricated)? (3) if it gave a "Coverage:" verdict, was that verdict honest about what it actually covered? A confident WRONG trace is the worst outcome — penalize it harder than an honest "partial/not found".
-Output ONLY minified JSON, no prose, no code fences:
-{"verdict":"pass|partial|fail","score":<0-100>,"fabrication":<true|false>,"coverageHonest":<true|false>,"missedHops":["..."],"note":"<=20 words"}`;
-
-// Build the job list
-const jobs = [];
-for (const r of results) {
-  const gt = truth[r.repo];
-  if (!gt) { r._nojudge = true; continue; }
-  jobs.push({ r, kind: 'e2e', prompt: e2ePrompt(gt, r.finalAnswer) });
-  if (r.arm === 'offload' && Array.isArray(r.offloadAnswers))
-    r.offloadAnswers.forEach((ans, i) => { if (ans && ans.trim()) jobs.push({ r, kind: 'fid', idx: i, prompt: fidPrompt(gt, ans) }); });
-}
-console.error(`judging ${jobs.length} verdicts across ${results.length} runs (concurrency ${CONC})...`);
-
-let done = 0;
-async function worker(queue) {
-  while (queue.length) {
-    const job = queue.shift();
-    const v = await askJudge(job.prompt);
-    if (job.kind === 'e2e') job.r.e2e = v; else (job.r._fid ??= []).push(v);
-    console.error(`  [${++done}/${jobs.length}] ${job.r.repo}/${job.r.arm}#${job.r.rep} ${job.kind}: ${v.verdict}${v.score != null ? ' ' + v.score : ''}`);
-  }
-}
-const q = [...jobs];
-await Promise.all(Array.from({ length: CONC }, () => worker(q)));
-
-// Aggregate per-answer fidelity verdicts into one fidelity object per offload run.
-const medOf = (a) => { a = [...a].sort((x, y) => x - y); return a.length ? (a.length % 2 ? a[(a.length - 1) / 2] : (a[a.length / 2 - 1] + a[a.length / 2]) / 2) : null; };
-for (const r of results) {
-  if (r._fid?.length) {
-    const scores = r._fid.map(v => v.score).filter(x => x != null);
-    r.fidelity = {
-      n: r._fid.length, scores,
-      max: scores.length ? Math.max(...scores) : null,
-      min: scores.length ? Math.min(...scores) : null,
-      median: medOf(scores),
-      anyFabrication: r._fid.some(v => v.fabrication === true),
-      allCoverageHonest: r._fid.every(v => v.coverageHonest !== false),
-      verdicts: r._fid.map(v => v.verdict),
-    };
-  }
-  delete r._fid;
-}
-writeFileSync(OUT, results.map(r => JSON.stringify(r)).join('\n') + '\n');
-console.error(`wrote ${OUT}`);
+#!/usr/bin/env node
+// Accuracy judge. For each run in results.jsonl:
+//   - end-to-end: agent finalAnswer vs verified ground truth (all arms)
+//   - fidelity:   offload synthesized answer vs ground truth (offload arm only)
+// Judge = claude -p sonnet --effort high, no tools, run from a neutral cwd,
+// JSON-only verdicts. Writes judged.jsonl (one line per run, verdicts merged).
+//
+// Usage: judge.mjs --results <f> --truth <f> --out <f> [--concurrency 4]
+import { readFileSync, writeFileSync, existsSync } from 'fs';
+import { execFile } from 'child_process';
+
+const A = {};
+for (let i = 2; i < process.argv.length; i += 2) A[process.argv[i].replace(/^--/, '')] = process.argv[i + 1];
+const results = readFileSync(A.results, 'utf8').split('\n').filter(Boolean).map(l => JSON.parse(l));
+const truth = JSON.parse(readFileSync(A.truth, 'utf8'));
+const OUT = A.out || '/tmp/cg-offload-eval/judged.jsonl';
+const CONC = Number(A.concurrency || 4);
+
+function askJudge(prompt) {
+  return new Promise((resolve) => {
+    execFile('claude', ['-p', prompt, '--model', 'sonnet', '--effort', 'high',
+      '--max-budget-usd', '0.5', '--strict-mcp-config', '--mcp-config', '{"mcpServers":{}}'],
+      // Run from a neutral dir with no repo files so the judge can't "cheat" by reading source.
+      { cwd: process.env.AGENT_EVAL_OUT || '/tmp', maxBuffer: 1 << 24, timeout: 120000 },
+      (err, stdout) => {
+        const raw = (stdout || '').trim();
+        const m = raw.match(/\{[\s\S]*\}/);
+        if (!m) return resolve({ verdict: 'error', score: null, note: (err ? 'exec ' + err.message : 'no json').slice(0, 80) });
+        try { resolve(JSON.parse(m[0])); } catch { resolve({ verdict: 'error', score: null, note: 'parse fail' }); }
+      });
+  });
+}
+
+const e2ePrompt = (gt, ans) => `You are scoring whether an AI coding agent correctly answered a code-flow question about a repository. Judge ONLY against the verified ground truth. Do NOT use any tools.
+
+QUESTION: ${gt.question}
+
+VERIFIED GROUND TRUTH (the actual call path + files):
+${gt.truth}
+
+AGENT'S ANSWER:
+${ans || '(empty)'}
+
+Score how correct the agent's answer is vs the ground truth. A "pass" means it identifies the core mechanism and the major hops with the right files/symbols and makes no materially wrong claim. "partial" = right area but misses major hops or has notable errors. "fail" = wrong layer, fabricated, or misses the mechanism.
+Output ONLY minified JSON, no prose, no code fences:
+{"verdict":"pass|partial|fail","score":<0-100>,"missedHops":["..."],"wrongClaims":["..."],"note":"<=20 words"}`;
+
+const fidPrompt = (gt, ans) => `You are scoring the FIDELITY of a machine-synthesized code-exploration answer against verified ground truth. The synthesized answer claims to trace a flow and cite file:line locations. Do NOT use any tools.
+
+QUESTION: ${gt.question}
+
+VERIFIED GROUND TRUTH (the actual call path + files):
+${gt.truth}
+
+SYNTHESIZED ANSWER (to score):
+${ans || '(empty)'}
+
+Judge: (1) is the traced call path correct vs ground truth? (2) are the cited files/symbols correct (not fabricated)? (3) if it gave a "Coverage:" verdict, was that verdict honest about what it actually covered? A confident WRONG trace is the worst outcome — penalize it harder than an honest "partial/not found".
+Output ONLY minified JSON, no prose, no code fences:
+{"verdict":"pass|partial|fail","score":<0-100>,"fabrication":<true|false>,"coverageHonest":<true|false>,"missedHops":["..."],"note":"<=20 words"}`;
+
+// Build the job list
+const jobs = [];
+for (const r of results) {
+  const gt = truth[r.repo];
+  if (!gt) { r._nojudge = true; continue; }
+  jobs.push({ r, kind: 'e2e', prompt: e2ePrompt(gt, r.finalAnswer) });
+  if (r.arm === 'offload' && Array.isArray(r.offloadAnswers))
+    r.offloadAnswers.forEach((ans, i) => { if (ans && ans.trim()) jobs.push({ r, kind: 'fid', idx: i, prompt: fidPrompt(gt, ans) }); });
+}
+console.error(`judging ${jobs.length} verdicts across ${results.length} runs (concurrency ${CONC})...`);
+
+let done = 0;
+async function worker(queue) {
+  while (queue.length) {
+    const job = queue.shift();
+    const v = await askJudge(job.prompt);
+    if (job.kind === 'e2e') job.r.e2e = v; else (job.r._fid ??= []).push(v);
+    console.error(`  [${++done}/${jobs.length}] ${job.r.repo}/${job.r.arm}#${job.r.rep} ${job.kind}: ${v.verdict}${v.score != null ? ' ' + v.score : ''}`);
+  }
+}
+const q = [...jobs];
+await Promise.all(Array.from({ length: CONC }, () => worker(q)));
+
+// Aggregate per-answer fidelity verdicts into one fidelity object per offload run.
+const medOf = (a) => { a = [...a].sort((x, y) => x - y); return a.length ? (a.length % 2 ? a[(a.length - 1) / 2] : (a[a.length / 2 - 1] + a[a.length / 2]) / 2) : null; };
+for (const r of results) {
+  if (r._fid?.length) {
+    const scores = r._fid.map(v => v.score).filter(x => x != null);
+    r.fidelity = {
+      n: r._fid.length, scores,
+      max: scores.length ? Math.max(...scores) : null,
+      min: scores.length ? Math.min(...scores) : null,
+      median: medOf(scores),
+      anyFabrication: r._fid.some(v => v.fabrication === true),
+      allCoverageHonest: r._fid.every(v => v.coverageHonest !== false),
+      verdicts: r._fid.map(v => v.verdict),
+    };
+  }
+  delete r._fid;
+}
+writeFileSync(OUT, results.map(r => JSON.stringify(r)).join('\n') + '\n');
+console.error(`wrote ${OUT}`);

package/scripts/agent-eval/offload-eval-matrix.sh

@@ -1,20 +1,20 @@
-#!/usr/bin/env bash
-# Drive the 3-arm campaign (offload/raw/nocg) across all 4 tiers, n reps each, into one
-# results.jsonl. Reads the canonical question per repo from offload-eval-ground-truth.json.
-# Env: REPS (default 3)  AGENT_EVAL_OUT=<scratch dir>
-set -uo pipefail
-HERE="$(cd "$(dirname "$0")" && pwd)"
-OUT="${AGENT_EVAL_OUT:-/tmp/cg-offload-eval}"
-GT="$HERE/offload-eval-ground-truth.json"
-REPS="${REPS:-3}"
-export RESULTS="$OUT/results.jsonl"
-: > "$RESULTS"
-for repo in mtkruto postybirb shapeshift trezor; do
-  case "$repo" in mtkruto) tier=small;; postybirb) tier=medium;; shapeshift) tier=complex;; trezor) tier=large;; esac
-  Q=$(node -e "console.log(JSON.parse(require('fs').readFileSync(process.argv[1],'utf8'))[process.argv[2]].question)" "$GT" "$repo")
-  echo ""; echo "### $repo ($tier)  $(date +%H:%M:%S)"
-  bash "$HERE/offload-eval-3arm.sh" "$OUT/repos/$repo" "$tier" "$REPS" "$Q"
-done
-echo ""; echo "###### MATRIX DONE -> $RESULTS ($(wc -l < "$RESULTS") runs).  Judge + summarize with:"
-echo "  node $HERE/offload-eval-judge.mjs --results $RESULTS --truth $GT --out $OUT/judged.jsonl"
-echo "  node $HERE/offload-eval-summarize.mjs $OUT/judged.jsonl"
+#!/usr/bin/env bash
+# Drive the 3-arm campaign (offload/raw/nocg) across all 4 tiers, n reps each, into one
+# results.jsonl. Reads the canonical question per repo from offload-eval-ground-truth.json.
+# Env: REPS (default 3)  AGENT_EVAL_OUT=<scratch dir>
+set -uo pipefail
+HERE="$(cd "$(dirname "$0")" && pwd)"
+OUT="${AGENT_EVAL_OUT:-/tmp/cg-offload-eval}"
+GT="$HERE/offload-eval-ground-truth.json"
+REPS="${REPS:-3}"
+export RESULTS="$OUT/results.jsonl"
+: > "$RESULTS"
+for repo in mtkruto postybirb shapeshift trezor; do
+  case "$repo" in mtkruto) tier=small;; postybirb) tier=medium;; shapeshift) tier=complex;; trezor) tier=large;; esac
+  Q=$(node -e "console.log(JSON.parse(require('fs').readFileSync(process.argv[1],'utf8'))[process.argv[2]].question)" "$GT" "$repo")
+  echo ""; echo "### $repo ($tier)  $(date +%H:%M:%S)"
+  bash "$HERE/offload-eval-3arm.sh" "$OUT/repos/$repo" "$tier" "$REPS" "$Q"
+done
+echo ""; echo "###### MATRIX DONE -> $RESULTS ($(wc -l < "$RESULTS") runs).  Judge + summarize with:"
+echo "  node $HERE/offload-eval-judge.mjs --results $RESULTS --truth $GT --out $OUT/judged.jsonl"
+echo "  node $HERE/offload-eval-summarize.mjs $OUT/judged.jsonl"