宜博 / lemongraph

"""c_work_graph_plan (03-C §3.4): produces a `graph_manifest`, does not execute.

U-011 scope: a real `claude --agent <org_node> -p` call, recorded as a
`work_graph_run` row with `status='planning'` (04-P `p_work_graph_execution`
start_state).

**Empirical finding (2026-07-31)**: `--json-schema` does NOT constrain output
when combined with `--agent` -- tried it for real, the response came back as
normal prose with an embedded ```json fenced block, `structured_output` was
entirely absent from the payload even though the identity itself came through
correctly (the response referenced "SOUL 原则 #10" by number, i.e. it was
genuinely reasoning as the migrated Planner). So this parses the
graph_manifest out of free-form response text instead of trusting
`structured_output` -- see `_extract_graph_manifest`. Not documented anywhere;
found by actually running it, not assumed.

Does NOT execute the resulting plan or produce artifacts -- that's
U-012 (`c_work_graph_execute` full)/U-013 (`c_work_node_run`), and nothing
today owns `c_artifact_write` either (REQ-02 lists it, no Unit in
development-plan.md builds it -- a real gap, flagged rather than silently
plugged, since it affects more than just this Unit's scope). REQ-02's happy
case (real BRD/PRD/SDD/Benchmark artifacts with lineage) needs all of that;
development-plan.md's U-011 Done line claimed it passes here alone, which
isn't accurate -- corrected in this session's notes, same pattern as
U-009/U-010.
"""

import json
import re
import subprocess
import uuid

GRAPH_MANIFEST_SCHEMA = {
    "type": "object",
    "required": ["nodes", "edges"],
    "properties": {
        "nodes": {
            "type": "array",
            "items": {
                "type": "object",
                "required": ["node_id", "artifact_type", "depends_on"],
                "properties": {
                    "node_id": {"type": "string"},
                    "artifact_type": {
                        "type": "string",
                        "enum": ["brd", "prd", "sdd", "benchmark", "test_dataset", "test_script"],
                    },
                    "depends_on": {"type": "array", "items": {"type": "string"}},
                    # 2026-08-08 (Work Graph self-planning + loop-back) -- both optional,
                    # documentation only (this schema isn't jsonschema-enforced, see
                    # module docstring's --json-schema/--agent note).
                    "judgment": {
                        "type": "object",
                        "properties": {
                            "kind": {"type": "string", "enum": ["none", "mechanical", "llm"]},
                            "check_ref": {"type": "string"},
                            "judge_prompt": {"type": "string"},
                        },
                    },
                    "on_fail": {
                        "type": "object",
                        "properties": {
                            "action": {"type": "string", "enum": ["retry_self", "loop_back", "hard_fail"]},
                            "max_attempts": {"type": "integer"},
                        },
                    },
                },
            },
        },
        "edges": {
            "type": "array",
            "items": {
                "type": "object",
                "required": ["from", "to", "edge_type"],
                "properties": {
                    "from": {"type": "string"},
                    "to": {"type": "string"},
                    # "on_failure" (2026-08-08): a node's failure path, expressed the
                    # same way its success path already is -- see _on_failure_target
                    # in work_graph_orchestrate.py.
                    "edge_type": {"type": "string", "enum": ["zero_token", "needs_judgment", "on_failure"]},
                },
            },
        },
    },
}

# 2026-08-08 (Work Graph self-planning + loop-back, docs/todo/work-graph-
# self-planning-and-loop-back-requirements.md, FR-B4 "全部自由规划"):
# Planner's doc-writing chain is no longer a fixed architectural constant
# (formally reverses docs/done/dynamic-work-graph-design-skill-design.md
# §3's decision) -- the LLM decides which node types this goal needs, in
# what order, and how each one's judgment/on_fail should work. This
# catalog is reference DATA the prompt hands the LLM, not a requirement
# that every entry appears -- FR-B2. test_script (disabled 2026-08-07,
# docs/todo/validator-test-script-narrative-output-issue.md) is back in
# this catalog per that decision's §8 item 7: Part B doesn't wait for the
# narrative-output structural fix, that fix is tracked separately
# alongside a future Coder-side test_script module.
_PRD_JUDGE_PROMPT = (
    "Review the following PRD for internally CONTRADICTORY scenario assumptions -- e.g. two "
    "requirements that cannot both hold at once, or the same scenario described two incompatible "
    "ways. Do NOT flag mere incompleteness, ambiguity, or style issues, only genuine "
    "self-contradiction. Reply via the required schema: ok=false only if you found a real "
    "contradiction, and list each one in issues.\n\nPRD:\n\n{content}"
)

_PLANNER_NODE_CATALOG = [
    {"artifact_type": "brd", "description": "Business Requirements Document -- why this goal matters, who it's for."},
    {
        "artifact_type": "prd", "description": "Product Requirements Document -- concrete scenarios/behavior.",
        "suggested_judgment": {"kind": "llm", "judge_prompt": _PRD_JUDGE_PROMPT},
    },
    {"artifact_type": "sdd", "description": "Solution Design Document -- how it will be implemented."},
    {"artifact_type": "benchmark", "description": "Concrete acceptance scenarios with observable pass criteria."},
    {
        "artifact_type": "test_dataset",
        "description": "Concrete test data (inputs + expected outputs) if this goal has a natural one -- "
                        "many goals (UI wiring, config changes) don't, that's fine, omit this node then.",
    },
    {
        "artifact_type": "test_script",
        "description": "A real, runnable script that mechanically checks the Benchmark's scenarios -- "
                        "only include this if a genuine mechanical check is possible for this goal.",
        "suggested_judgment": {"kind": "mechanical", "check_ref": "check_script_compiles"},
    },
]

# NOTE: no `str.format()` involved in building or filling this template
# (unlike _GENERIC_PROMPT_TEMPLATE) -- the embedded catalog JSON and the
# instructional JSON examples below (e.g. {"kind": "none"}) are full of
# their own literal braces, which .format() would try to parse as format
# fields and crash on. plan_work_graph() fills in goal_text with a plain
# `.replace("{goal_text}", goal_text)` instead, which treats every other
# brace in this string as inert literal text -- no escaping needed at all.
_PROMPT_TEMPLATE = (
    "Plan (do not execute) the Work Graph for this goal: {goal_text}\n"
    "Available node types (use any subset, in any order that makes sense -- this goal may not "
    "need all of them, and 'suggested_judgment' entries are starting points you can reuse or "
    "override, not requirements):\n" + json.dumps(_PLANNER_NODE_CATALOG) + "\n"
    "For each node you include, decide: node_id, artifact_type, depends_on (which earlier nodes' "
    "output it genuinely needs), a judgment config (how to tell if this node's output is "
    "acceptable -- {\"kind\": \"none\"} if nothing needs checking, {\"kind\": \"mechanical\", "
    "\"check_ref\": ...} for a named mechanical check, or {\"kind\": \"llm\", \"judge_prompt\": "
    "\"...{content}...\"} for your own judgment prompt with a {content} placeholder), and an "
    "on_fail config (what happens if judgment fails: {\"action\": \"retry_self\"}, "
    "{\"action\": \"loop_back\"}, or {\"action\": \"hard_fail\"}, each optionally with "
    "\"max_attempts\"). If a node's on_fail.action is 'loop_back', you MUST also add a "
    "corresponding edge in the top-level 'edges' array with edge_type 'on_failure', from that "
    "node to the exact earlier node_id it should return to -- the target must be a real upstream "
    "dependency of this node (something that genuinely produced input this node used), not an "
    "arbitrary node. This mirrors how the success path already works: every node's 'yes, this "
    "succeeded, what's next' is expressed as a normal dependency edge, and 'no, this failed, go "
    "back to X' is expressed the same way, just with edge_type 'on_failure' instead. Every other "
    "edge needs edge_type: 'zero_token' for pure aggregation/reduce steps, 'needs_judgment' for "
    "anything requiring the agent to actually reason about content.\n"
    "End your reply with the graph_manifest as a single fenced ```json code block "
    "shaped exactly like {\"nodes\": [...], \"edges\": [...]} -- no extra wrapper key."
)

# E (2026-08-06): the generic, cross-Org-Agent path -- used for every
# org_node OTHER than 'planner'. Planner's own doc-writing chain stays on
# _PROMPT_TEMPLATE above unchanged (zero regression risk, see
# docs/done/dynamic-work-graph-design-skill-design.md §3): that chain is a
# fixed architectural constant (brd->prd->sdd->benchmark->...), not
# something that should vary call to call, whereas Coder/Validator's
# sub-tasks have no such fixed small vocabulary of node types. Each node
# here carries its own self-contained `task_prompt` (see the
# design-dynamic-work-graph Skill this prompt points at) instead of an
# `artifact_type` that a fixed lookup table like _DOC_PROMPTS could resolve.
_GENERIC_PROMPT_TEMPLATE = (
    "Plan (do not execute) a Work Graph for this goal: {goal_text}\n"
    "Follow the design-dynamic-work-graph Skill's methodology: only add a depends_on edge "
    "when a node's task_prompt genuinely needs another node's output content -- nodes with "
    "no real data dependency between them will be scheduled to run CONCURRENTLY, so adding "
    "an edge just to make the graph look ordered actively slows execution down. If this goal "
    "is small enough to finish in one call, output a single-node graph_manifest rather than "
    "forcing a split.\n"
    "Output a graph_manifest whose nodes each have: node_id (a short readable identifier), "
    "depends_on (list of other node_ids), and task_prompt (the FULL, self-contained prompt "
    "for that node's own execution -- assume the agent running it sees nothing except this "
    "task_prompt and its dependencies' outputs, not this planning conversation). Every edge "
    "needs edge_type: 'zero_token' for pure aggregation/reduce steps, 'needs_judgment' for "
    "anything requiring the agent to actually reason about content.\n"
    "End your reply with the graph_manifest as a single fenced ```json code block "
    "shaped exactly like {{\"nodes\": [...], \"edges\": [...]}} -- no extra wrapper key."
)

_JSON_FENCE_RE = re.compile(r"```(?:json)?\s*(\{.*?\})\s*```", re.DOTALL)


class PlanningFailedError(Exception):
    """PLANNING_FAILED -- 03-C §3.4."""


def _extract_graph_manifest(text):
    """--json-schema doesn't constrain output when --agent is set (see module
    docstring) -- pulls the graph_manifest out of free-form response text
    instead: try the whole text as JSON, then each ```json fenced block;
    accept either {"nodes":...,"edges":...} directly or wrapped one level
    deep under a "graph_manifest" key (models sometimes add that wrapper
    despite being asked not to)."""
    candidates = [text] + _JSON_FENCE_RE.findall(text)
    for candidate in candidates:
        try:
            parsed = json.loads(candidate)
        except (json.JSONDecodeError, TypeError):
            continue
        if isinstance(parsed, dict):
            if "nodes" in parsed and "edges" in parsed:
                return parsed
            inner = parsed.get("graph_manifest")
            if isinstance(inner, dict) and "nodes" in inner and "edges" in inner:
                return inner
    return None


def _transitive_ancestors(graph_manifest, node_id):
    """node_id itself + every node it (directly or transitively) depends
    on, via `depends_on`/normal data-dependency edges (`on_failure` edges
    excluded -- they're control-flow, not data dependency, same reasoning
    as work_graph_orchestrate.py's own `_transitive_dependents`/
    `topological_layers`). Deliberately reimplemented here rather than
    imported from work_graph_orchestrate.py -- the two modules don't
    depend on each other today (work_graph_orchestrate.py is a lower-level
    execution engine, work_graph_plan.py is planning-only) and this is a
    small enough function that duplicating it doesn't justify introducing
    that coupling."""
    deps = {n.get("node_id"): set(n.get("depends_on") or []) for n in graph_manifest.get("nodes", [])}
    for edge in graph_manifest.get("edges", []):
        if edge.get("edge_type") == "on_failure":
            continue
        from_id, to_id = edge.get("from"), edge.get("to")
        if to_id in deps and from_id in deps:
            deps[to_id].add(from_id)

    ancestors, stack = set(), [node_id]
    while stack:
        current = stack.pop()
        if current in ancestors:
            continue
        ancestors.add(current)
        stack.extend(deps.get(current, []))
    return ancestors


def _validate_loop_back_targets(manifest):
    """2026-08-08 (Work Graph self-planning + loop-back): every node
    declaring `on_fail.action == 'loop_back'` must have exactly one
    `edge_type: 'on_failure'` edge originating from it (see
    work_graph_orchestrate.py's `_on_failure_target`), and that edge's
    target must be a genuine upstream dependency -- looping back to a node
    that never influenced this one has no coherent meaning. Raises
    PlanningFailedError (not a generic ValueError) so this surfaces the
    same way every other planning failure does, before any node ever runs
    -- catching a malformed loop_back here is far cheaper than discovering
    it mid-execution."""
    node_ids = {n.get("node_id") for n in manifest.get("nodes", [])}
    for node in manifest.get("nodes", []):
        if (node.get("on_fail") or {}).get("action") != "loop_back":
            continue
        node_id = node.get("node_id")
        on_failure_edges = [
            e for e in manifest.get("edges", [])
            if e.get("from") == node_id and e.get("edge_type") == "on_failure"
        ]
        if len(on_failure_edges) != 1:
            raise PlanningFailedError(
                "node {} declares on_fail.action='loop_back' but has {} on_failure edge(s), "
                "expected exactly 1".format(node_id, len(on_failure_edges))
            )
        target = on_failure_edges[0].get("to")
        if target not in node_ids:
            raise PlanningFailedError(
                "node {}'s on_failure edge targets {!r}, which does not exist in this graph_manifest".format(
                    node_id, target
                )
            )
        if target not in _transitive_ancestors(manifest, node_id):
            raise PlanningFailedError(
                "node {}'s on_failure edge targets {!r}, which is not an upstream dependency -- "
                "loop_back must target a node that genuinely influenced this one".format(node_id, target)
            )


def _normalize_graph_manifest(manifest):
    """Real LLM output has been observed (2026-08-01, U-031 integration
    validation) to use `id` instead of the documented `node_id` key, and to
    express dependencies purely via `edges` (from/to) without ever
    populating each node's own `depends_on` array -- even though this
    schema requires both. Normalizing here, right after parsing and before
    persisting, means every downstream consumer (work_graph_orchestrate.py's
    topological sort, v_task_detail's to-do tree, v_graph_visualizer's DAG
    layering) gets a manifest that actually matches the documented shape,
    instead of each one needing its own defensive "id or node_id,
    depends_on or edges" fallback logic repeated independently. Mutates and
    returns `manifest`.

    2026-08-08 (Work Graph self-planning + loop-back, FR-B4 "全部自由规划"):
    the canonical-doc-chain forced-order enforcement that used to live here
    (2026-08-03 incident: a real call omitted brd->prd->sdd->benchmark's
    dependency entirely, scheduling nodes out of order) is REMOVED, not
    extended -- Planner's node set/order is no longer a fixed architectural
    constant (formally reverses docs/done/dynamic-work-graph-design-skill-
    design.md §3). Robustness against that same failure mode now rests
    entirely on the edge-derived depends_on backfill below (unchanged) plus
    `_validate_loop_back_targets` (new, below) -- there is no longer a
    hardcoded canonical chain to fall back on if an LLM response omits
    dependency info, so a real reproduction of the 2026-08-03 incident
    shape is a genuine, currently-unmitigated risk this design accepted
    (see docs/done/work-graph-self-planning-and-loop-back-requirements.md
    §7's risk list) -- FR-B3's own acceptance criterion only covers the
    "wrong key names" failure mode this backfill already handles, not a
    complete absence of dependency info with no canonical chain to guess from.
    """
    nodes = manifest.get("nodes", [])
    for node in nodes:
        if "node_id" not in node and "id" in node:
            node["node_id"] = node["id"]
        node.setdefault("depends_on", [])

    node_ids = {n.get("node_id") for n in nodes}
    for edge in manifest.get("edges", []):
        if edge.get("edge_type") == "on_failure":
            continue  # control-flow, not a data dependency -- see _transitive_ancestors
        from_id, to_id = edge.get("from"), edge.get("to")
        if from_id in node_ids and to_id in node_ids:
            for node in nodes:
                if node.get("node_id") == to_id and from_id not in node["depends_on"]:
                    node["depends_on"].append(from_id)

    _validate_loop_back_targets(manifest)
    return manifest


def plan_work_graph(conn, org_node, task_id, goal_text, target_folder_path, timeout=300):
    """Returns {"run_id", "graph_manifest"}. Creates one `work_graph_run` row
    (status='planning') -- moving it to 'running'/executing it is out of scope.

    2026-08-08: `org_node == 'planner'` gets `_PROMPT_TEMPLATE` (now a
    genuine self-planning prompt over `_PLANNER_NODE_CATALOG`, see that
    template's own comment for why goal_text is filled in via `.replace()`
    rather than `.format()`). Every other org_node gets
    `_GENERIC_PROMPT_TEMPLATE` -- the cross-Org-Agent dynamic planning path
    described in the design-dynamic-work-graph Skill, whose nodes carry
    their own task_prompt instead of a fixed artifact_type. Function
    signature/return shape are unchanged either way."""
    if org_node == "planner":
        prompt = _PROMPT_TEMPLATE.replace("{goal_text}", goal_text)
    else:
        prompt = _GENERIC_PROMPT_TEMPLATE.format(goal_text=goal_text)

    result = subprocess.run(
        [
            "claude", "--agent", org_node,
            "-p", prompt,
            "--output-format", "json",
            "--permission-mode", "auto",
        ],
        cwd=target_folder_path,
        stdin=subprocess.DEVNULL,
        capture_output=True,
        text=True,
        timeout=timeout,
    )
    if result.returncode != 0:
        # 2026-07-31 fix (same bug as org_node_trigger.py): include stdout too.
        raise PlanningFailedError(
            "plan failed for task {}\nstderr: {}\nstdout (truncated): {}".format(
                task_id, result.stderr, result.stdout[:4000]
            )
        )

    payload = json.loads(result.stdout)
    if payload.get("is_error"):
        raise PlanningFailedError("plan failed for task {}: {}".format(task_id, payload))
    graph_manifest = _extract_graph_manifest(payload.get("result", ""))
    if not graph_manifest:
        raise PlanningFailedError("could not extract a graph_manifest for task {}: {}".format(task_id, payload))
    graph_manifest = _normalize_graph_manifest(graph_manifest)

    run_id = str(uuid.uuid4())
    conn.execute(
        "INSERT INTO work_graph_run (run_id, task_id, org_node, graph_manifest, status) "
        "VALUES (?, ?, ?, ?, 'planning')",
        (run_id, task_id, org_node, json.dumps(graph_manifest)),
    )
    conn.commit()
    return {"run_id": run_id, "graph_manifest": graph_manifest}


def generic_node_prompt_builder(node, outputs):
    """E (2026-08-06): the `build_prompt(node, outputs)` run_graph() needs
    for a graph_manifest produced via _GENERIC_PROMPT_TEMPLATE -- lives
    here, not in e2e_pipeline.py, because it's tightly coupled to the
    `task_prompt` field convention that prompt asks for (keeping both in
    the same module means a field rename can't silently desync producer
    and consumer). No factory/closure needed: every node is self-contained
    per the design-dynamic-work-graph Skill's contract, so `outputs`
    (already-completed dependency content) isn't needed here."""
    return node["task_prompt"]