feat(harness): typed adapters + format-aware session-inject proxy + multi-turn bandit driver

.github/workflows/ci.yml

@@ -24,8 +24,15 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-        with:
-          submodules: recursive
+
+      - name: Fetch submodules (PAT required for private org repos)
+        env:
+          SUBMODULE_PAT: ${{ secrets.SUBMODULE_PAT }}
+        run: |
+          if [ -n "${SUBMODULE_PAT}" ]; then
+            git config --global url."https://x-access-token:${SUBMODULE_PAT}@github.com/".insteadOf "https://github.com/"
+          fi
+          git submodule update --init --recursive --depth=1
 
       - uses: Jimver/cuda-toolkit@v0.2.35
         with:

.gitignore

@@ -57,6 +57,7 @@ env/
 *.qdrep
 *.sqlite
 bench-out/
+dflash/bench/results/
 profile-out/
 
 # Model weights and caches (pull fresh from HF)

dflash/CMakeLists.txt

@@ -544,6 +544,18 @@ if(DFLASH27B_TESTS)
         target_include_directories(test_gguf_mmap PRIVATE ${DFLASH27B_SRC_INCLUDE_DIRS})
         target_link_libraries(test_gguf_mmap PRIVATE dflash_common)
     endif()
+    if(EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/test/test_adaptive_keep_ratio.cpp")
+        add_executable(test_adaptive_keep_ratio test/test_adaptive_keep_ratio.cpp)
+        target_include_directories(test_adaptive_keep_ratio PRIVATE ${DFLASH27B_SRC_INCLUDE_DIRS})
+        target_link_libraries(test_adaptive_keep_ratio PRIVATE dflash_common)
+        add_test(NAME adaptive_keep COMMAND test_adaptive_keep_ratio)
+    endif()
+    if(EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/test/test_bandit_integration.cpp")
+        add_executable(test_bandit_integration test/test_bandit_integration.cpp)
+        target_include_directories(test_bandit_integration PRIVATE ${DFLASH27B_SRC_INCLUDE_DIRS})
+        target_link_libraries(test_bandit_integration PRIVATE dflash_common)
+        add_test(NAME bandit_integration COMMAND test_bandit_integration)
+    endif()
     if(EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/test/test_draft_vs_reference.cpp")
         add_executable(test_draft_vs_reference test/test_draft_vs_reference.cpp)
         target_link_libraries(test_draft_vs_reference PRIVATE dflash_common)

dflash/bench/results/2026-05-21_mvp_day4_v2/A_fixed_low/client.out

@@ -0,0 +1 @@
+{"type":"result","subtype":"success","is_error":false,"api_error_status":null,"duration_ms":15505,"duration_api_ms":15469,"ttft_ms":15503,"num_turns":1,"result":"The `clamp` function restricts a value `x` to lie within the inclusive range `[lo, hi]`:\n\n1. **Validation:** If the lower bound `lo` is greater than the upper bound `hi`, it raises a `ValueError` since the bounds are invalid.\n2. **Clamping:** It first applies `max(x, lo)` to ensure the value is at least `lo`, then applies `min(..., hi)` to ensure it doesn't exceed `hi`.\n\nIn short, it \"clamps\" or \"clips\" `x` so that the result is always between `lo` and `hi` (inclusive).\n\nOK_DONE","stop_reason":"end_turn","session_id":"369e1eff-7cf4-4b2c-a708-1e42e545c5c1","total_cost_usd":0.058980000000000005,"usage":{"input_tokens":11096,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":140,"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":0},"inference_geo":"","iterations":[],"speed":"standard"},"modelUsage":{"luce-dflash":{"inputTokens":11096,"outputTokens":140,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.058980000000000005,"contextWindow":200000,"maxOutputTokens":32000}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","uuid":"4d133762-5689-47e1-9575-9de7245f1a61"}

dflash/bench/results/2026-05-21_mvp_day4_v2/A_fixed_low/metrics.txt

@@ -0,0 +1,10 @@
+label=A_fixed_low
+keep_ratio=0.05
+session_id=
+wall_s=20
+ok_done=YES
+accept_rate=N/A
+mean_drafter_fwd_ms=N/A
+N/A
+bandit_log:
+none

dflash/bench/results/2026-05-21_mvp_day4_v2/B_fixed_high/client.out

@@ -0,0 +1 @@
+{"type":"result","subtype":"success","is_error":false,"api_error_status":null,"duration_ms":11518,"duration_api_ms":11475,"ttft_ms":11516,"num_turns":1,"result":"Takes a value `x` and constrains it to the range `[lo, hi]`. If `lo > hi` it raises; otherwise it returns `x` clamped to `[lo, hi]` using `max` then `min`.\n\nOK_DONE.","stop_reason":"end_turn","session_id":"33055a15-378f-424e-91f7-8ae0dfcbe5ac","total_cost_usd":0.056905000000000004,"usage":{"input_tokens":11096,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":57,"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":0},"inference_geo":"","iterations":[],"speed":"standard"},"modelUsage":{"luce-dflash":{"inputTokens":11096,"outputTokens":57,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.056905000000000004,"contextWindow":200000,"maxOutputTokens":32000}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","uuid":"427220ae-d402-4e5c-9ccb-a83998c72a3f"}

dflash/bench/results/2026-05-21_mvp_day4_v2/B_fixed_high/metrics.txt

@@ -0,0 +1,10 @@
+label=B_fixed_high
+keep_ratio=0.20
+session_id=
+wall_s=18
+ok_done=YES
+accept_rate=N/A
+mean_drafter_fwd_ms=N/A
+N/A
+bandit_log:
+none

dflash/bench/results/2026-05-21_mvp_day4_v2/C_bandit/client.out

@@ -0,0 +1 @@
+{"content":[{"text":"The `clamp` function restricts a value `x` to lie within a specified range defined by `lo` (lower bound) and `hi` (upper bound).\n\nHere is a step-by-step breakdown:\n\n1. **Validation**: It first checks if `lo` is greater than `hi`. If so, it raises a `ValueError` because the lower bound cannot be greater than the upper bound.\n2. **Clamping Logic**: It uses `max(x, lo)` to ensure the value is at least `lo`, and then `min(..., hi)` to ensure the result is no more than `hi`.\n   - If `x` is less than `lo`, it returns `lo`.\n   - If `x` is greater than `hi`, it returns `hi`.\n   - If `x` is between `lo` and `hi` (inclusive), it returns `x`.\n\nIn essence, it \"clamps\" or \"caps\" the value `x` to the interval `[lo, hi]`.\n\nOK_DONE","type":"text"}],"id":"msg_0000000000000000","model":"luce-dflash","role":"assistant","stop_reason":"end_turn","type":"message","usage":{"accept_rate":0.34742647409439087,"input_tokens":62,"output_tokens":221}}

dflash/bench/results/2026-05-21_mvp_day4_v2/C_bandit/metrics.txt

@@ -0,0 +1,10 @@
+label=C_bandit
+keep_ratio=0.10
+session_id=claude_code_s1
+wall_s=12
+ok_done=YES
+accept_rate=0.34742647409439087
+mean_drafter_fwd_ms=N/A
+N/A
+bandit_log:
+[pflash-bandit] session=claude_code_s1 turn=1 keep=0.1000->0.1100 (accept=0.347)

dflash/bench/results/2026-05-22_mvp_day5/A_fixed_low/client.out

@@ -0,0 +1 @@
+{"type":"result","subtype":"success","is_error":false,"api_error_status":null,"duration_ms":12759,"duration_api_ms":12725,"ttft_ms":12757,"num_turns":1,"result":"The `clamp` function constrains a value `x` to lie within the closed interval `[lo, hi]`.\n\n1. **Bounds check**: If `lo > hi`, it raises a `ValueError` because the lower bound would be greater than the upper bound, which is invalid.\n2. **Clamping**: It first applies `max(x, lo)` to ensure the value is at least `lo`, then applies `min(..., hi)` to ensure the result is at most `hi`. The net effect is that `x` is \"clamped\" (pinned) to the range `[lo, hi]`.\n\n**Examples:**\n- `clamp(5, 1, 10)` → `5` (already in range)\n- `clamp(-3, 0, 10)` → `0` (below `lo`, so it returns `lo`)\n- `clamp(20, 1, 10)` → `10` (above `hi`, so it returns `hi`)\n- `clamp(5, 10, 1)` → raises `ValueError`\n\nOK_DONE","stop_reason":"end_turn","session_id":"17411438-6c28-45ab-876e-0141de566865","total_cost_usd":0.061655,"usage":{"input_tokens":11126,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":241,"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":0},"inference_geo":"","iterations":[],"speed":"standard"},"modelUsage":{"luce-dflash":{"inputTokens":11126,"outputTokens":241,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.061655,"contextWindow":200000,"maxOutputTokens":32000}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","uuid":"8f175dfd-4dd7-4aa2-9514-ed9bd71ab9f0"}

dflash/bench/results/2026-05-22_mvp_day5/A_fixed_low/metrics.txt

@@ -0,0 +1,9 @@
+label=A_fixed_low
+keep_ratio=0.05
+session_id=
+wall_s=17
+ok_done=YES
+accept_rate=31.7
+mean_drafter_fwd_ms=1610 ms (n=1)
+bandit_log:
+none

dflash/bench/results/2026-05-22_mvp_day5/B_fixed_high/client.out

@@ -0,0 +1 @@
+{"type":"result","subtype":"success","is_error":false,"api_error_status":null,"duration_ms":11247,"duration_api_ms":11201,"ttft_ms":11245,"num_turns":1,"result":"It constrains `x` to the range `[lo, hi]`:\n\n- If `lo > hi`, it raises a `ValueError`.\n- Otherwise it returns `x` clamped: `lo` if `x < lo`, `hi` if `x > hi`, or `x` itself.\n\nOK_DONE.","stop_reason":"end_turn","session_id":"9a753ecc-fdb7-48c9-bdfb-d25797bcc80e","total_cost_usd":0.05738,"usage":{"input_tokens":11126,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":70,"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":0},"inference_geo":"","iterations":[],"speed":"standard"},"modelUsage":{"luce-dflash":{"inputTokens":11126,"outputTokens":70,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.05738,"contextWindow":200000,"maxOutputTokens":32000}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","uuid":"315cc3b2-95cc-46ea-bc4c-8443e8d0ebed"}

dflash/bench/results/2026-05-22_mvp_day5/B_fixed_high/metrics.txt

@@ -0,0 +1,9 @@
+label=B_fixed_high
+keep_ratio=0.20
+session_id=
+wall_s=19
+ok_done=YES
+accept_rate=25.4
+mean_drafter_fwd_ms=1620 ms (n=1)
+bandit_log:
+none

dflash/bench/results/2026-05-22_mvp_day5/C_bandit/client.out

@@ -0,0 +1 @@
+{"type":"result","subtype":"success","is_error":false,"api_error_status":null,"duration_ms":11537,"duration_api_ms":11490,"ttft_ms":11535,"num_turns":1,"result":"The `clamp` function constrains a value `x` to lie within the inclusive range `[lo, hi]`:\n\n1. **Bounds validation**: If `lo > hi`, it raises a `ValueError` because the lower bound can't exceed the upper bound.\n2. **Clamping**: `max(x, lo)` ensures the result is at least `lo`, then `min(..., hi)` ensures it doesn't exceed `hi`.\n\n**Examples:**\n- `clamp(5, 0, 10)` → `5` (already in range)\n- `clamp(-3, 0, 10)` → `0` (below range, clamped to `lo`)\n- `clamp(15, 0, 10)` → `10` (above range, clamped to `hi`)\n\nOK_DONE","stop_reason":"end_turn","session_id":"d1227ee7-b90b-41ab-9526-97b3b4742e11","total_cost_usd":0.060155,"usage":{"input_tokens":11126,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":181,"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":0},"inference_geo":"","iterations":[],"speed":"standard"},"modelUsage":{"luce-dflash":{"inputTokens":11126,"outputTokens":181,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.060155,"contextWindow":200000,"maxOutputTokens":32000}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","uuid":"c6311f54-3ef7-4448-91d6-1070fb5fe8bf"}

dflash/bench/results/2026-05-22_mvp_day5/C_bandit/metrics.txt

@@ -0,0 +1,9 @@
+label=C_bandit
+keep_ratio=0.10
+session_id=claude_code_day5_s1
+wall_s=16
+ok_done=YES
+accept_rate=31.9
+mean_drafter_fwd_ms=1630 ms (n=1)
+bandit_log:
+[pflash-bandit] session=claude_code_day5_s1 turn=1 keep=0.1000->0.1100 (accept=0.319)

dflash/bench/results/2026-05-23_adaptive_evidence/adaptive_evidence.csv

@@ -0,0 +1,6 @@
+client,turn,session_id,prompt,keep_before,accept_rate,keep_after,ema,wall_s
+claude_code,1,adaptive-evidence-20260523,decode_check.txt,0.1,0.062,0.11,0.062,7.409
+claude_code,2,adaptive-evidence-20260523,logic_check.txt,0.11,0.062,0.12,0.062,4.928
+claude_code,3,adaptive-evidence-20260523,math_check.txt,0.12,0.062,0.13,0.062,4.888
+claude_code,4,adaptive-evidence-20260523,code_gen.txt,0.13,0.062,0.14,0.062,5.185
+claude_code,5,adaptive-evidence-20260523,explain_algo.txt,0.14,0.062,0.15,0.062,5.335