From 3c331ef6879d461d5c2c5da007ac072122c0573d Mon Sep 17 00:00:00 2001
From: Antoine <antoinevdp@live.fr>
Date: Thu, 28 May 2026 18:07:51 +0200
Subject: [PATCH] feat: add canonical profile merger with warnings

---
 src/job_research/profile/merge.py | 56 +++++++++++++++++++++++++++++++
 tests/profile/test_merge.py       | 28 ++++++++++++++++
 2 files changed, 84 insertions(+)
 create mode 100644 src/job_research/profile/merge.py
 create mode 100644 tests/profile/test_merge.py

diff --git a/src/job_research/profile/merge.py b/src/job_research/profile/merge.py
new file mode 100644
index 0000000..8718e23
--- /dev/null
+++ b/src/job_research/profile/merge.py
@@ -0,0 +1,56 @@
+from __future__ import annotations
+
+from job_research.models import (
+    CandidateProfileOutput,
+    EducationEntry,
+    ExperienceEntry,
+    WarningItem,
+)
+from job_research.profile.profile_parser import AuthoredProfile
+
+
+def build_candidate_profile_output(
+    cv_signals: dict[str, object], authored: AuthoredProfile
+) -> CandidateProfileOutput:
+    warnings: list[WarningItem] = []
+
+    if "years_of_experience" in cv_signals and any(
+        "experience" in note.lower() for note in authored.notes
+    ):
+        warnings.append(
+            WarningItem(
+                field="years_of_experience",
+                message=(
+                    "CV-derived experience may differ from markdown interpretation. "
+                    "Review manually."
+                ),
+            )
+        )
+
+    merged_skills: list[str] = []
+    for skill in [
+        *(cv_signals.get("skills") or []),
+        *authored.strengths,
+        *authored.skills_to_emphasize,
+    ]:
+        if skill not in merged_skills:
+            merged_skills.append(skill)
+
+    experience_entries = cv_signals.get("experience_entries") or []
+    education_entries = cv_signals.get("education_entries") or []
+
+    return CandidateProfileOutput(
+        name=cv_signals.get("name"),
+        summary=authored.summary,
+        target_roles=authored.target_roles,
+        strengths=authored.strengths,
+        skills_to_emphasize=authored.skills_to_emphasize,
+        constraints=authored.constraints,
+        notes=authored.notes,
+        location=cv_signals.get("location"),
+        languages=cv_signals.get("languages") or [],
+        skills=merged_skills,
+        experience_entries=[ExperienceEntry.model_validate(item) for item in experience_entries],
+        education_entries=[EducationEntry.model_validate(item) for item in education_entries],
+        warnings=warnings,
+    )
diff --git a/tests/profile/test_merge.py b/tests/profile/test_merge.py
new file mode 100644
index 0000000..0892a9a
--- /dev/null
+++ b/tests/profile/test_merge.py
@@ -0,0 +1,28 @@
+from job_research.profile.merge import build_candidate_profile_output
+from job_research.profile.profile_parser import AuthoredProfile
+
+
+def test_build_candidate_profile_output_writes_warning_when_facts_conflict() -> None:
+    cv_signals = {
+        "name": "Tonio",
+        "location": "France",
+        "languages": ["French", "English"],
+        "skills": ["Python", "SQL"],
+        "experience_entries": [{"title": "Data Engineer", "company": "A"}],
+        "education_entries": [],
+        "years_of_experience": 2,
+    }
+    authored = AuthoredProfile(
+        summary="Junior data engineer focused on GCP.",
+        target_roles=["Data Engineer"],
+        strengths=["Python"],
+        skills_to_emphasize=["BigQuery", "GCP"],
+        constraints=["CDI only"],
+        notes=["Years of experience feels closer to 3."],
+    )
+
+    output = build_candidate_profile_output(cv_signals, authored)
+
+    assert output.summary == "Junior data engineer focused on GCP."
+    assert output.constraints == ["CDI only"]
+    assert output.warnings[0].field == "years_of_experience"