[staging CI] unslothai/unsloth#7074

.github/scripts/agent-guides-drive.sh

@@ -154,7 +154,12 @@ raw_env() {  # $1 = var name -> value (one shlex-quote layer stripped)
 # writers as a side effect (it writes each agent's relocated session config).
 parse_connect() {
   local raw="$LOGS_DIR/connect-${AGENT}.txt"
-  if ! unsloth start "$AGENT" --no-launch --api-key "$UNSLOTH_API_KEY" > "$raw" 2>&1; then
+  # CONNECT_YOLO=1 adds --yolo. opencode/openclaw gate tool approval through their
+  # config (which now prompts by default), so the file-edit test opts into auto-approval
+  # here, the same intent as claude/codex's per-call bypass flags.
+  local yolo=()
+  [ -n "${CONNECT_YOLO:-}" ] && yolo=(--yolo)
+  if ! unsloth start "$AGENT" --no-launch "${yolo[@]}" --api-key "$UNSLOTH_API_KEY" > "$raw" 2>&1; then
     cat_redacted "$raw"
     guide_fail "'unsloth start ${AGENT} --no-launch' exited non-zero"
   fi
@@ -371,7 +376,7 @@ case "$MODE" in
       hermes)   patch_hermes_tools none
                 invoke_via_connect "$OUT" -z "$PROMPT" ;;
       openclaw) patch_openclaw_agent notools
-                invoke_via_connect "$OUT" agent --local --agent ci \
+                CONNECT_CMD_OVERRIDE=openclaw invoke_via_connect "$OUT" agent --local --agent ci \
                   --model "unsloth/${UNSLOTH_MODEL_ID}" --message "$PROMPT" ;;
       *)        invoke_via_connect "$OUT" "$PROMPT" ;;
     esac
@@ -394,7 +399,10 @@ case "$MODE" in
     T2='Run hello.py with python and show me the exact output.'
 
     # The start.py recipe writers + crosscheck must see the repo; run them
-    # from the repo root BEFORE cd-ing into the scratch work dir.
+    # from the repo root BEFORE cd-ing into the scratch work dir. opencode/openclaw
+    # gate tool approval through their config (prompting by default), so file-edit
+    # opts them into auto-approval to run edits/commands headlessly.
+    case "$AGENT" in opencode|openclaw) CONNECT_YOLO=1 ;; esac
     parse_connect
     crosscheck_contract
     # File-edit needs real tools, so we cannot zero them as in connection.
@@ -441,7 +449,7 @@ case "$MODE" in
           fi ;;
         opencode) invoke_via_connect "$out" run "$prompt" ;;
         hermes)   invoke_via_connect "$out" -z "$prompt" ;;
-        openclaw) invoke_via_connect "$out" agent --local --agent ci \
+        openclaw) CONNECT_CMD_OVERRIDE=openclaw invoke_via_connect "$out" agent --local --agent ci \
                     --model "unsloth/${UNSLOTH_MODEL_ID}" --message "$prompt" ;;
         *)        invoke_via_connect "$out" "$prompt" ;;
       esac
@@ -519,6 +527,154 @@ case "$MODE" in
     echo "[claude] attribution A/B OK (suppressed HIT, header=1 MISS)"
     ;;
 
+  # ── resume: does a launched agent's session survive exit and resume? ────
+  # Unlike the other modes, this drives the real LAUNCH path (`unsloth start
+  # <agent> ...`, the interactive default), not the --no-launch recipe. That
+  # path relocates each agent's home to a throwaway temp dir wiped on exit, so
+  # a session cannot be resumed -- unless --persist routes it to the stable
+  # Unsloth agents dir instead. We run one headless turn per pass and check
+  # whether the turn left a session in a persistent store (deterministic, no
+  # reliance on the model recalling anything), for a baseline pass and a
+  # --persist pass, and assert the expected split for this agent.
+  resume)
+    CODEWORD="PLATYPUS7"
+    T1="Remember this codeword for later: ${CODEWORD}. Reply with just the word OK."
+    T2="What codeword did I ask you to remember? Reply with just that word."
+    WORK="$WORKDIR_BASE/${AGENT}-resume"
+
+    # STABLE_HOME: the stable dir that --no-launch (and --persist) relocate to.
+    # Read it from a --no-launch probe (which also writes the agent's config
+    # there). codex/pi relocate their whole home/HOME here; opencode/claude keep
+    # their session data in a fixed user dir, so STABLE_HOME stays empty for them.
+    parse_connect
+    case "$AGENT" in
+      codex)    STABLE_HOME="$(raw_env CODEX_HOME)" ;;
+      pi)       STABLE_HOME="$(raw_env HOME)" ;;
+      *)        STABLE_HOME="" ;;
+    esac
+
+    # The persistent stores a session would land in if it were NOT wiped. We
+    # count files here before/after each turn; a positive delta means the
+    # session persisted (is resumable), zero means it went to a wiped temp dir.
+    resume_tracked_dirs() {
+      case "$AGENT" in
+        codex)    printf '%s\n' "$HOME/.codex" ;;
+        opencode) printf '%s\n' "$HOME/.local/share/opencode" "$HOME/.config/opencode" ;;
+        claude)   printf '%s\n' "$HOME/.claude" ;;
+        pi)       printf '%s\n' "$HOME/.pi" ;;
+        *)        : ;;
+      esac
+      [ -n "$STABLE_HOME" ] && printf '%s\n' "$STABLE_HOME"
+    }
+    count_session_files() {
+      local total=0 d n
+      while IFS= read -r d; do
+        [ -n "$d" ] && [ -d "$d" ] || continue
+        n="$(find "$d" -type f 2>/dev/null | wc -l)"; total=$((total + n))
+      done < <(resume_tracked_dirs)
+      echo "$total"
+    }
+
+    # The headless first-turn subcommand per agent (mirrors file-edit's map),
+    # forwarded verbatim through the launch path as passthrough args.
+    set_t1_cmd() {
+      case "$AGENT" in
+        claude)   T1_CMD=("${CLAUDE_CONNECT_FLAGS[@]}" -p "$T1") ;;
+        codex)    T1_CMD=(exec "$T1") ;;
+        opencode) T1_CMD=(run "$T1") ;;
+        pi)       T1_CMD=(-p "$T1") ;;
+        *)        guide_fail "resume mode does not cover agent '$AGENT'" ;;
+      esac
+    }
+
+    # Run one headless turn through the launch path. $1=outfile, $2="" or
+    # "--persist", rest = the agent subcommand. --yolo auto-approves so no tool
+    # prompt can hang; --api-key attaches to the already-served CI model.
+    launch_turn() {
+      local out="$1" rflag="$2"; shift 2
+      local flag=(); [ -n "$rflag" ] && flag=("$rflag")
+      run_timed "$out" unsloth start "$AGENT" "${flag[@]}" --yolo \
+        --api-key "$UNSLOTH_API_KEY" "$@"
+      local rc=$?
+      redact "$out"
+      return "$rc"
+    }
+
+    # One pass: fresh work dir, one planting turn, set RESULT to PERSISTED/WIPED
+    # from the session-store delta. Runs in the main shell (not a command
+    # substitution) so a hang's guide_fail actually fails the job and the
+    # progress lines reach the CI log. $1 = "" (baseline) or "--persist".
+    RESULT=""
+    run_pass() {
+      local rflag="$1" label="baseline"
+      [ -n "$rflag" ] && label="resume"
+      rm -rf "$WORK"; mkdir -p "$WORK"
+      set_t1_cmd
+      local out="$LOGS_DIR/${AGENT}-resume-${label}.txt"
+      local before after rc
+      before="$(count_session_files)"
+      pushd "$WORK" >/dev/null || guide_fail "could not enter work dir $WORK"
+      launch_turn "$out" "$rflag" "${T1_CMD[@]}"; rc=$?
+      popd >/dev/null || true
+      after="$(count_session_files)"
+      echo "[$AGENT] ${label}: session files ${before} -> ${after} (rc=${rc})"
+      # The turn must succeed for the delta to mean anything: an agent that writes a
+      # session file then errors would otherwise be misread as PERSISTED. Mirror the
+      # file-edit mode and fail the pass on a non-zero launch (the flagship codex recall
+      # below stays WARN-only, driven by its own launch_turn calls).
+      [ "$rc" -eq 0 ] || { echo "[$AGENT] ${label} transcript (tail):"; tail -30 "$out" 2>/dev/null || true; \
+        guide_fail "resume ${label} turn for ${AGENT} exited non-zero (rc=${rc})"; }
+      if [ "$after" -gt "$before" ]; then RESULT="PERSISTED"; else RESULT="WIPED"; fi
+    }
+
+    run_pass ""; BASELINE="$RESULT"
+    # Only the temp-dir agents (codex/pi) need the --persist pass to prove the fix.
+    # opencode/claude persist either way, so the baseline already proves it and a
+    # second full CPU turn only risks a timeout; skip it for them.
+    case "$AGENT" in
+      codex|pi) run_pass "--persist"; RESUME="$RESULT" ;;
+      *)        RESUME="n/a (persists either way)" ;;
+    esac
+
+    # Expected: codex/pi relocate their whole home to the temp dir, so a plain
+    # launch is WIPED and only --persist PERSISTS. opencode/claude keep their
+    # session data in a fixed user dir, so the baseline already PERSISTS.
+    case "$AGENT" in
+      codex|pi)        EXPECT_BASELINE="WIPED" ;;
+      opencode|claude) EXPECT_BASELINE="PERSISTED" ;;
+    esac
+
+    echo "──────────────────────────────────────────────"
+    echo "[$AGENT] RESUME EXPERIMENT"
+    echo "  baseline (unsloth start ${AGENT}):                 ${BASELINE}  (expected ${EXPECT_BASELINE})"
+    echo "  with --persist (unsloth start ${AGENT} --persist): ${RESUME}"
+    echo "──────────────────────────────────────────────"
+
+    [ "$BASELINE" = "$EXPECT_BASELINE" ] \
+      || guide_fail "baseline resume behavior for ${AGENT} was ${BASELINE}, expected ${EXPECT_BASELINE}"
+    case "$AGENT" in
+      codex|pi)
+        [ "$RESUME" = "PERSISTED" ] \
+          || guide_fail "--persist did not persist ${AGENT}'s session (got ${RESUME}); the session dir is still not stable" ;;
+    esac
+
+    # Flagship behavioral proof (codex only, WARN-only): after a --persist plant,
+    # resume the session and check the model actually recalls the codeword. A
+    # miss is not a failure (the CI model is small); the mechanism gate above is
+    # the real assertion.
+    if [ "$AGENT" = "codex" ]; then
+      rm -rf "$WORK"; mkdir -p "$WORK"
+      ( cd "$WORK" && launch_turn "$LOGS_DIR/codex-resume-plant.txt" "--persist" exec "$T1" ) || true
+      ( cd "$WORK" && launch_turn "$LOGS_DIR/codex-resume-recall.txt" "--persist" exec resume --last "$T2" ) || true
+      if grep -q "$CODEWORD" "$LOGS_DIR/codex-resume-recall.txt" 2>/dev/null; then
+        echo "[codex] behavioral recall HIT: resumed session remembered ${CODEWORD}"
+      else
+        echo "::warning::[codex] behavioral recall MISS (small CI model); mechanism gate still passed"
+      fi
+    fi
+    echo "[$AGENT] resume OK"
+    ;;
+
   *)
     echo "agent-guides-drive.sh: unknown mode '$MODE'" >&2
     exit 2

.github/workflows/consolidated-tests-ci.yml

@@ -364,6 +364,9 @@ jobs:
             tests/utils/test_attention_masks.py \
             tests/utils/test_trunc_normal_patch.py \
             tests/python/test_fast_language_model_text_only.py \
+            tests/test_bad_mappings_redirect.py \
+            tests/test_prefetch_snapshot_scope.py \
+            tests/test_gemma_2b_mapper_key.py \
             --deselect 'tests/utils/test_attention_masks.py::test_run_attention_flash_varlen_receives_window_and_softcap'
           # The deselected test monkeypatches flash_attn_varlen_func, which is
           # only bound on the module when `flash_attn` is importable. flash_attn

.github/workflows/local-agent-guides-ci.yml

@@ -471,6 +471,176 @@ jobs:
             redacted-configs/
           retention-days: 7
 
+  # ═════════════════════════════════════════════════════════════════════
+  # Job: resume
+  #   Does a conversation started with `unsloth start <agent>` survive exit
+  #   and resume? This drives the REAL launch path (not the --no-launch
+  #   recipe the other jobs use). A plain launch relocates the agent home to
+  #   a temp dir wiped on exit, so codex/pi cannot resume; --persist routes the
+  #   session to the stable Unsloth agents dir so it persists. opencode/claude
+  #   keep their session data in a fixed user dir, so they persist either way.
+  #   Dispatch-only: it is an end-to-end experiment, not a PR gate.
+  # ═════════════════════════════════════════════════════════════════════
+  resume:
+    name: resume (${{ matrix.agent }})
+    if: github.event_name == 'workflow_dispatch'
+    runs-on: ubuntu-latest
+    timeout-minutes: 60
+    strategy:
+      fail-fast: false
+      matrix:
+        # codex/pi relocate their whole home (resume broken without --persist);
+        # opencode/claude keep session data in a fixed dir (resume already works).
+        # One agent from each class proves the split end to end; openclaw/hermes
+        # share codex's relocation mechanism and are covered by the unit tests.
+        agent: [codex, opencode, claude, pi]
+    env:
+      GGUF_REPO: unsloth/gemma-4-E4B-it-GGUF
+      GGUF_FILE: gemma-4-E4B-it-UD-Q4_K_XL.gguf
+      STUDIO_PORT: '18904'
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        with:
+          persist-credentials: false
+
+      - name: Linux deps for llama.cpp prebuilt
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y --no-install-recommends \
+            libcurl4-openssl-dev libssl-dev jq
+
+      - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e  # v6.4.0
+        with:
+          node-version: '22'
+
+      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6.2.0
+        with:
+          python-version: '3.12'
+          cache: 'pip'
+
+      - name: Restore GGUF model file
+        id: cache-gguf
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
+        continue-on-error: true
+        with:
+          path: gguf-cache
+          key: ${{ runner.os }}-gguf-${{ env.GGUF_REPO }}-${{ env.GGUF_FILE }}-v1
+
+      - name: Download GGUF if cache miss
+        id: download-gguf
+        if: steps.cache-gguf.outputs.cache-hit != 'true' || steps.cache-gguf.outcome != 'success'
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: |
+          python -m pip install --upgrade huggingface_hub
+          mkdir -p gguf-cache
+          bash .github/scripts/hf-download-with-retry.sh "$GGUF_REPO" "$GGUF_FILE" gguf-cache
+
+      - name: Save GGUF model file
+        if: always() && steps.download-gguf.outcome == 'success'
+        uses: actions/cache/save@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
+        with:
+          path: gguf-cache
+          key: ${{ runner.os }}-gguf-${{ env.GGUF_REPO }}-${{ env.GGUF_FILE }}-v1
+
+      - name: Install Studio (--local, --no-torch)
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: |
+          mkdir -p logs
+          set -o pipefail
+          bash install.sh --local --no-torch 2>&1 | tee logs/install.log
+
+      - name: Serve unsloth run --disable-tools (gemma-4-E4B)
+        run: |
+          unsloth studio reset-password
+          bash .github/scripts/serve-unsloth-run.sh \
+            --gguf-file "$GITHUB_WORKSPACE/gguf-cache/${GGUF_FILE}" \
+            --port "$STUDIO_PORT" --log-dir logs \
+            --extra "--seed $UNSLOTH_SEED --temp 0" \
+            --health-timeout 900
+
+      - name: Preflight the agent's API dialect (class-a isolation)
+        env:
+          AGENT: ${{ matrix.agent }}
+        run: |
+          set -uo pipefail
+          B="$UNSLOTH_BASE_URL"; K="$UNSLOTH_API_KEY"
+          preflight_fail() {
+            echo "::error::[server/API regression] agent=$AGENT: $* (preflight failed BEFORE install/connect). Endpoint contract lives in studio/backend/routes/**.";
+            exit 1
+          }
+          code=$(curl -s -o /tmp/pf.json -w '%{http_code}' "$B/v1/models" \
+            -H "Authorization: Bearer $K") || true
+          [ "$code" = "200" ] || preflight_fail "/v1/models returned HTTP $code"
+          case "$AGENT" in
+            claude)
+              code=$(curl -s -o /tmp/pf.json -w '%{http_code}' "$B/v1/messages" \
+                -H "Authorization: Bearer $K" -H 'content-type: application/json' \
+                --max-time 120 \
+                -d "{\"model\":\"$UNSLOTH_MODEL_ID\",\"max_tokens\":16,\"messages\":[{\"role\":\"user\",\"content\":\"Hi\"}]}") || true
+              [ "$code" = "200" ] || preflight_fail "/v1/messages returned HTTP $code"
+              ;;
+            codex)
+              code=$(curl -s -o /tmp/pf.json -w '%{http_code}' "$B/v1/responses" \
+                -H "Authorization: Bearer $K" -H 'content-type: application/json' \
+                --max-time 120 \
+                -d "{\"model\":\"$UNSLOTH_MODEL_ID\",\"input\":\"Hi\",\"max_output_tokens\":16,\"stream\":true}") || true
+              [ "$code" = "200" ] || preflight_fail "/v1/responses returned HTTP $code"
+              ;;
+            *)
+              code=$(curl -s -o /tmp/pf.json -w '%{http_code}' "$B/v1/chat/completions" \
+                -H "Authorization: Bearer $K" -H 'content-type: application/json' \
+                --max-time 120 \
+                -d "{\"model\":\"$UNSLOTH_MODEL_ID\",\"max_tokens\":16,\"messages\":[{\"role\":\"user\",\"content\":\"Hi\"}]}") || true
+              [ "$code" = "200" ] || preflight_fail "/v1/chat/completions returned HTTP $code"
+              ;;
+          esac
+          echo "preflight OK for $AGENT"
+
+      - name: Install agent CLI (class-b isolation)
+        env:
+          AGENT: ${{ matrix.agent }}
+        run: bash .github/scripts/agent-guides-install.sh "$AGENT"
+
+      - name: Resume experiment (launch path)
+        env:
+          AGENT: ${{ matrix.agent }}
+        run: bash .github/scripts/agent-guides-drive.sh resume "$AGENT"
+
+      - name: Collect server logs (debug)
+        if: always()
+        run: |
+          mkdir -p logs/studio-logs
+          cp -r "$HOME/.unsloth/studio/logs/." logs/studio-logs/ 2>/dev/null || true
+          if [ -n "${UNSLOTH_API_KEY:-}" ]; then
+            grep -rlF "$UNSLOTH_API_KEY" logs redacted-configs agent-workdir 2>/dev/null | while IFS= read -r f; do
+              sed -i "s#${UNSLOTH_API_KEY}#<REDACTED>#g" "$f" 2>/dev/null || true
+            done
+          fi
+
+      - name: Stop Studio
+        if: always()
+        run: |
+          if [ -n "${UNSLOTH_SERVER_PID:-}" ] && [ "${UNSLOTH_SERVER_PID}" != "0" ]; then
+            kill "${UNSLOTH_SERVER_PID}" 2>/dev/null || true
+          fi
+          sleep 2
+          ss -tln 2>/dev/null | grep ":${STUDIO_PORT}" || true
+
+      - name: Upload logs
+        if: always()
+        continue-on-error: true
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a  # v7.0.1
+        with:
+          name: resume-${{ matrix.agent }}-log
+          path: |
+            logs/
+            agent-workdir/
+            redacted-configs/
+          retention-days: 7
+
   # ═════════════════════════════════════════════════════════════════════
   # Job 3: prompt-cache
   #   (a) curl 2-turn /v1/chat/completions: assert turn-2 cached_tokens > 0

.github/workflows/lockfile-audit.yml

@@ -60,11 +60,11 @@ jobs:
     runs-on: ubuntu-latest
     timeout-minutes: 5
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
         with:
           persist-credentials: false
 
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1  # v6.3.0
         with:
           python-version: '3.12'