"""Prompt-lock pin (phase 112, task 03 — owner decision iii, 2026-09-14).

The persona + HONESTY GATE text is **locked verbatim** (PLAN §6): it
changes through the plan, never in code. This module byte-pins the
locked prompt constants against their pre-phase-112 anchor values —
sha256 + exact prefix/suffix + total length, so *any* byte change
(option (i)'s copy tightening, option (ii)'s plan amendment, or an
accidental edit) fails loudly until the anchors are re-cut as part of
the same plan revision. ``tests.unit.test_prompts`` pins the
assembled-prompt structure and the behavioral contracts on top of
these constants; this file pins the constants themselves.
"""
from __future__ import annotations

import hashlib

from app.rag.prompts import (
    ORIGIN_RULE,
    PERSONA,
    SEARCH_DISCIPLINE_RULE,
    SUGGEST_INTRO,
    TOOLS_SECTION,
    _base,
    build_deflect_prompt,
)


def _sha256(text: str) -> str:
    return hashlib.sha256(text.encode("utf-8")).hexdigest()


# ---------- PERSONA (the locked base of BOTH the HIGH and LOW prompts) ----------

#: Pre-phase-112 anchors for ``PERSONA`` (the ``{relevance}`` placeholder
#: and the line wrapping included).
PERSONA_SHA256 = "e31792a73e64c53853097e0f7b6df8b96c5f2d05c286944c3edba16dde7777fe"
PERSONA_LEN = 706
PERSONA_PREFIX = (
    'You are "Brain of Reese" — the digital brain of Reese, a self-hoster and\n'
    "homelab tinkerer. Personality: chippy, upbeat, warm, and genuinely\n"
    "optimistic about the user's ability to do things.\n"
    "\n"
    "Rules:\n"
)
PERSONA_SUFFIX = (
    "4. Never invent facts, hosts, or steps that are not in the context.\n"
    "5. Keep answers tight: short paragraphs, bullets where helpful.\n"
    "\n"
    "<relevance>{relevance}</relevance>"
)


def test_persona_byte_locked() -> None:
    """Any byte change to the locked persona (opening, any rule line, the
    ``<relevance>`` placeholder) fails on the sha256; the prefix/suffix
    anchors name the damaged region for the diff."""
    assert len(PERSONA) == PERSONA_LEN
    assert _sha256(PERSONA) == PERSONA_SHA256
    assert PERSONA.startswith(PERSONA_PREFIX)
    assert PERSONA.endswith(PERSONA_SUFFIX)


def test_high_and_low_bases_byte_locked() -> None:
    """``_base`` only substitutes ``{relevance}`` — the per-mode base
    lengths pin the substitution against a moved or re-spelled
    placeholder in the locked text."""
    assert len(_base("HIGH")) == 699  # PERSONA_LEN - 11 + 4
    assert len(_base("LOW")) == 698  # PERSONA_LEN - 11 + 3


# ---------- TOOLS_SECTION (the HIGH prompt's locked ``<tools>`` copy) ----------

#: Anchors for ``TOOLS_SECTION`` — pre-phase-112 values, RE-CUT for
#: phase 118 (task 04, A6, owner directive 2026-09-15): the ``read``
#: clause was rewritten for the summary-seed mode (the ``<documents>``
#: section holds SUMMARIES — ``read`` adds the full text; only an
#: already-read document is refused). RE-CUT again for phase 141
#: (task 02): the re-read sentence was re-cut to the coverage-true
#: form — do not re-read a document read IN FULL (answer from it);
#: a PARTIAL document (a range read, or a truncated read) is not
#: complete in the context until read all — read the other parts with
#: ``offset``/``limit``. RE-CUT again for phase 145 (task 02): the
#: ``read`` clause gains the original-source rule — :data:`ORIGIN_RULE`,
#: the one sentence-group appended at the ``read`` clause's end (the
#: truncation workflow sentence) and BEFORE the ``grep`` clause begins
#: (the ``origin:`` line is a read-result fact; the rule binds the
#: ANSWER that uses what the read added). Only that sentence-group was
#: inserted — the prefix (the ``ls``-clause opening) and the suffix
#: (the discipline-rules ending) survived byte-identical, so they are
#: the same anchors as pre-phase-145; the pre-phase-145 sha/length are
#: kept below for the chained diff-style pin. RE-CUT again for phase 162
#: (task 03, LOCKED A3+A4): the ``grep`` sentence's ``(case-insensitive)``
#: parenthetical widened to the folded contract ``(case- and
#: accent-insensitive — accents fold: besta matches BESTÅ)``, and the
#: LOCKED search-discipline sentence (:data:`SEARCH_DISCIPLINE_RULE`) was
#: inserted immediately after the grep sentence (before the ``For a normal
#: search pass`` clause). Only those two byte-groups moved — the prefix
#: (the ``ls``-clause opening) and the suffix (the discipline-rules
#: ending) survive byte-identical; the pre-phase-162 sha/length are kept
#: below for the chained diff-style pin.
TOOLS_SECTION_SHA256 = "988642f9dc6bb2a4a1d44a83b5368ff4cdb9df4e181b2fe3dc2fb241b1857595"
TOOLS_SECTION_LEN = 3818

# The pre-phase-162 anchors — the section BEFORE phase 162's grep-fold +
# search-discipline insertion. Kept for the chained diff-style pin.
TOOLS_SECTION_PRE_PHASE_162_SHA256 = (
    "41a84885be98d4e15b95205694d59d364296a30e27758d39ae737881d5bacaa7"
)
TOOLS_SECTION_PRE_PHASE_162_LEN = 3279

# The grep contract parenthetical exactly as it changed in phase 162
# (LOCKED A3): the pre-phase ``(case-insensitive)`` vs the folded one now
# embedded in ``TOOLS_SECTION``. Used to revert phase 162 for the diff pin.
_GREP_CONTRACT_PRE_PHASE_162 = "(case-insensitive)"
_GREP_CONTRACT_PHASE_162 = (
    "(case- and accent-insensitive — accents fold: `besta` matches `BESTÅ`)"
)

TOOLS_SECTION_PREFIX = (
    "<tools>\n"
    "You may extend your context with three tools. `ls` lists the "
    "knowledge base as a tree, one level at a time: "
)
TOOLS_SECTION_SUFFIX = (
    "Never repeat a call that was refused or already succeeded — the refusal "
    "already told you the correct form. Answer as soon as you have what "
    "you need.\n</tools>"
)

#: The pre-phase-145 anchors — the section BEFORE :data:`ORIGIN_RULE` was
#: inserted. Kept for the diff-style pin: the ONLY byte change is the
#: rule's insertion, so removing the rule reproduces these exact bytes.
TOOLS_SECTION_PRE_PHASE_145_SHA256 = (
    "3671680bbf4e04efe1186690c18d24869e4974ceb29485cedc3e34a9286bf3b2"
)
TOOLS_SECTION_PRE_PHASE_145_LEN = 2656


#: Phase 145 (task 02) — the original-source rule the ``read`` teaching
#: carries is :data:`app.rag.prompts.ORIGIN_RULE` (imported above, LOCKED
#: verbatim). :data:`TOOLS_SECTION` embeds that exact sentence-group at
#: the ``read`` clause's end (the truncation workflow sentence) and
#: BEFORE the ``grep`` clause begins. A read result for a git-sourced
#: document carries an ``origin:`` line (and a ``branch:`` line when a
#: branch is pinned) — the read contract's fact — so when the answer uses
#: such a document it includes the original source in the answer: a link
#: to the repository (the ``origin`` line) with the document's path (the
#: ``Document …`` header) named and the pinned branch when one is shown,
#: as the repository's file-view URL where the model can tell it
#: (``<repo-url>/blob/<branch>/<path>``), or the repository URL plus the
#: path as plain text otherwise. The rule is CONDITIONAL on the ``origin``
#: line's presence — a local-sourced document's read result carries none,
#: so the rule adds nothing to those answers (the model has no URL to
#: cite; it must not invent one — the sentence's conditioning does that
#: job).


def test_tools_section_byte_locked() -> None:
    """The ``<tools>`` teaching is LOCKED verbatim too (the E2E mock keys
    on the ``<tools>`` marker's presence; the wording is the owner's):
    sha256 + exact prefix/suffix + total length."""
    assert len(TOOLS_SECTION) == TOOLS_SECTION_LEN
    assert _sha256(TOOLS_SECTION) == TOOLS_SECTION_SHA256
    assert TOOLS_SECTION.startswith(TOOLS_SECTION_PREFIX)
    assert TOOLS_SECTION.endswith(TOOLS_SECTION_SUFFIX)


def test_tools_section_origin_rule_verbatim_at_its_position() -> None:
    """Phase 145 (task 02): the original-source rule is LOCKED verbatim
    and sits at its EXACT position — the ``read`` clause's end (the
    truncation workflow sentence) and BEFORE the ``grep`` clause begins.
    The sentence-group is pinned byte-for-byte, and the surrounding
    boundary (the truncation sentence's tail → the rule → the ``grep``
    clause's opening) is pinned as one contiguous substring, so a move
    or re-spelling of ANY byte (the rule's or the boundary's) fails."""
    # Verbatim presence.
    assert ORIGIN_RULE in TOOLS_SECTION
    assert TOOLS_SECTION.count(ORIGIN_RULE) == 1  # exactly once
    # Exact position: after the truncation sentence, before the grep
    # clause — one contiguous span, no drift at either seam.
    assert (
        "it searches the whole document. "
        + ORIGIN_RULE
        + " `grep` locates an exact string"
    ) in TOOLS_SECTION


def test_tools_section_search_discipline_rule_verbatim_at_its_position() -> None:
    """Phase 162 (task 03, LOCKED A4): the search-discipline rule is
    LOCKED verbatim and sits at its EXACT position — immediately after
    the grep sentence (the ``…retry with the plain text you expect to
    see.`` clause) and BEFORE the ``For a normal search pass`` clause.
    The rule + its exact boundaries are pinned as one contiguous span, so
    a move or re-spelling of ANY byte fails."""
    assert SEARCH_DISCIPLINE_RULE in TOOLS_SECTION
    assert TOOLS_SECTION.count(SEARCH_DISCIPLINE_RULE) == 1  # exactly once
    assert (
        "retry with the plain text you expect to see. "
        + SEARCH_DISCIPLINE_RULE
        + " For a normal search pass only `pattern`"
    ) in TOOLS_SECTION


def test_tools_section_grep_fold_contract_present() -> None:
    """Phase 162 (task 03, LOCKED A3): the grep sentence now states the
    FOLDED contract — the ``(case-insensitive)`` parenthetical is replaced
    byte-for-byte by the folded one, and the old one is gone."""
    assert _GREP_CONTRACT_PHASE_162 in TOOLS_SECTION
    assert _GREP_CONTRACT_PRE_PHASE_162 not in TOOLS_SECTION


def test_tools_section_phase162_and_145_are_the_only_byte_changes() -> None:
    """Chained diff-style pin: the ONLY byte changes are phase 162's (the
    folded grep contract + :data:`SEARCH_DISCIPLINE_RULE`) and phase 145's
    (:data:`ORIGIN_RULE`). Reverting phase 162 (drop the rule + its
    separating space, restore the pre-phase grep parenthetical) reproduces
    the pre-phase-162 section byte-for-byte; reverting the origin rule on
    top of that reproduces the pre-phase-145 section byte-for-byte."""
    # Revert phase 162 -> pre-phase-162.
    pre_162 = TOOLS_SECTION.replace(SEARCH_DISCIPLINE_RULE + " ", "")
    pre_162 = pre_162.replace(_GREP_CONTRACT_PHASE_162, _GREP_CONTRACT_PRE_PHASE_162)
    assert len(pre_162) == TOOLS_SECTION_PRE_PHASE_162_LEN
    assert _sha256(pre_162) == TOOLS_SECTION_PRE_PHASE_162_SHA256
    # Revert phase 145 -> pre-phase-145.
    pre_145 = pre_162.replace(ORIGIN_RULE + " ", "")
    assert len(pre_145) == TOOLS_SECTION_PRE_PHASE_145_LEN
    assert _sha256(pre_145) == TOOLS_SECTION_PRE_PHASE_145_SHA256


# ---------- the LOW prompt's locked DEFLECT_MODE body ----------

#: The ``DEFLECT_MODE`` body exactly as it was pre-phase-112 (the
#: phase-71 plain-text line included) — inline in
#: :func:`app.rag.prompts.build_deflect_prompt`, so it is pinned through
#: the built prompt rather than a module constant.
LOW_BODY_SHA256 = "c9868cfccdd0ff79d7c1de5df5f6dea0182d3726ca912c9ef609ab54b563a0a4"
LOW_BODY_LEN = 259
LOW_BODY = (
    "DEFLECT_MODE: retrieval was weak — the titles below are the closest "
    "your notes come to the question. They are titles only; do not pretend "
    "they answer it. Use them to propose 2-3 alternative questions.\n"
    "Reply in plain text only — you have no tools in this mode."
)


def test_deflect_body_byte_locked() -> None:
    """The LOW build = locked base + exactly the locked DEFLECT_MODE body
    + the weak-hit title list — byte for byte (the mock keys on the
    ``DEFLECT_MODE`` marker's presence; the body wording is locked)."""
    assert len(LOW_BODY) == LOW_BODY_LEN
    assert _sha256(LOW_BODY) == LOW_BODY_SHA256
    assert build_deflect_prompt(["T1", "T2"]) == _base("LOW") + "\n" + LOW_BODY + "\n- T1\n- T2"
    prompt = build_deflect_prompt(["T1", "T2"])
    assert prompt.count(LOW_BODY) == 1
    assert prompt.index("DEFLECT_MODE") < prompt.index(
        "Reply in plain text only"
    )  # the marker precedes the plain-text line


#: The full LOW prompt build on the canonical fixture titles — sha-pinned
#: (phase 118, task 03): the deflection path is UNTOUCHED by the
#: summary-seed re-revision (LOCKED A8) — the same inputs must produce
#: the pre-phase bytes, so this anchor is a pre-phase-118 value.
LOW_PROMPT_SHA256 = "726eddb4eb3bcc26c840011f6f8635d6af55aa09d4d064bbb9e256caa9665837"
LOW_PROMPT_LEN = 968


def test_low_prompt_build_byte_identical_to_pre_phase() -> None:
    """Phase 118 contract: the LOW prompt output is byte-identical to
    pre-phase for identical inputs — the summary seeding (and the new
    ``SUGGEST_INTRO`` line) never leaks into the deflection path."""
    prompt = build_deflect_prompt(["T1", "T2"])
    assert len(prompt) == LOW_PROMPT_LEN
    assert _sha256(prompt) == LOW_PROMPT_SHA256
    assert "SUGGEST_INTRO" not in prompt and "<documents>" not in prompt


# ---------- SUGGEST_INTRO (phase 118 framing, re-cut for phase 119, LOCKED A5) ----------

#: Anchors for ``SUGGEST_INTRO`` — the ``<documents>`` section's intro
#: line (the owner's "start here if these summaries seem right to you"
#: framing, TODO L3, phase 118). RE-CUT for phase 119 (task 04, LOCKED
#: A5, owner directive 2026-09-16): the final sentence was replaced
#: with the cite-discipline sentence (cite only the documents read — or
#: the suggested document answered from without reading — never a
#: document neither read nor used), closing the live confabulation in
#: which the model cited a file it never read; the phase-118 "cite the
#: document(s) you used, by path" sentence is retired. Only that
#: sentence moved — the start-here framing, the ``read`` pointer, and
#: the full-text clause survive byte-identical, so the prefix anchor is
#: the same as pre-phase-119. The E2E mock's ``_document_block`` parser
#: is regex-based over the block markup (which stays byte-stable around
#: the intro), so this constant is a prompt-copy lock, pinned the way
#: ``TOOLS_SECTION`` is: sha256 + prefix + total length. ``PERSONA``,
#: ``TOOLS_SECTION``, and the LOW body anchors above stay byte-identical
#: — this change touches no other constant.
SUGGEST_INTRO_SHA256 = "c6ffbb19975cbf184910a9a8e8fdea101c16f5d3eecb872fb07afeabd2763302"
SUGGEST_INTRO_LEN = 460
SUGGEST_INTRO_PREFIX = (
    "The blocks below are the summaries of the top-ranked documents for "
    "your question — start here if one seems right to you: "
)


def test_suggest_intro_byte_locked() -> None:
    """The start-here framing is LOCKED copy (phase 118; the final
    sentence re-cut by phase 119, LOCKED A5): sha256 + exact prefix +
    total length; the four contracts it must carry (summaries are the
    starting points; ``read`` adds the full text, which is NOT in the
    prompt until read; the phase-119 cite discipline — cite only what
    was read, or the suggested document answered from without reading,
    never a document neither read nor used) are pinned as substrings."""
    assert len(SUGGEST_INTRO) == SUGGEST_INTRO_LEN
    assert _sha256(SUGGEST_INTRO) == SUGGEST_INTRO_SHA256
    assert SUGGEST_INTRO.startswith(SUGGEST_INTRO_PREFIX)
    assert "call `read" in SUGGEST_INTRO
    assert "combined `source/path`" in SUGGEST_INTRO
    assert "its full text is not in the prompt until you read it" in SUGGEST_INTRO
    assert (
        "Cite only the document(s) you read — or, if you answered from a "
        "suggested summary without reading it, cite that suggested "
        "document — never a document you neither read nor used."
    ) in SUGGEST_INTRO
    # The retired phase-118 final sentence is gone from the constant.
    assert "Cite the document(s) you used, by path." not in SUGGEST_INTRO