Files
Claude Agent c42b95b7db feat(discord-bridge): imagini si fisiere text din Discord ajung la Claude
Puntea trimitea doar `content`-ul mesajului; orice atasament disparea tacut, iar
un mesaj fara text (doar poza) era respins ca "empty". Acum mesajul de utilizator
se construieste ca blocuri, in formatul pe care CLI-ul il accepta pe
`--input-format stream-json` (verificat pe CLI real: Claude descrie corect o
imagine trimisa asa).

- imagini png/jpeg/gif/webp -> blocuri `image` base64, max 4, max 3,5 MB brut
  (base64 umfla cu ~4/3, iar API-ul refuza peste ~5 MB codate)
- fisiere text (mime `text/*`, `application/json`, sau extensie cunoscuta) ->
  continutul intra in prompt, max 4, trunchiat la 100 KB
- restul (PDF, Office, arhive, svg, heic) -> doar numite, cu motivul

Detalii care conteaza:
- `image/jpg` si `image/png; charset=...` se normalizeaza; cand Discord nu
  trimite content_type cadem pe extensie
- marimea se verifica de doua ori: cea declarata (ca sa nu descarcam degeaba) si
  cea reala dupa descarcare
- nimic nu dispare tacut: ce n-a putut fi citit apare in prompt ca
  "Atasamente ignorate: ..."; o imagine stricata nu anuleaza restul mesajului
- merge si mid-tur: o poza trimisa in timpul unui tur intra pe stdin ca steering

31 de teste noi in tests/test_attachments.py (normalizare tipuri, limite,
trunchiere, erori de descarcare, integrare prin punte, steering). Suita: 426 pass.
README: sectiune "Atasamente" + limitarea veche corectata (ramane doar vocea).

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Q4uzvgm7AyJch5WH8QHRhY
2026-08-31 17:47:48 +00:00

239 lines
8.4 KiB
Python

"""Atasamente Discord -> blocuri de continut pentru Claude.
Imaginile ajung blocuri `image` (base64), fisierele text sunt inserate in prompt,
restul sunt doar numite. Zero retea: `FakeAttachment.read()` returneaza octeti locali.
"""
from __future__ import annotations
import base64
import pytest
import bot
import runner as runner_mod
from tests.test_bot import ( # noqa: F401 (bridge/store/allowed sunt fixturi)
FakeAttachment, FakeBrokenAttachment, FakeMessage, allowed, bridge,
)
PNG = b"\x89PNG\r\n\x1a\n" + b"x" * 40
def image(name="poza.png", data=PNG, content_type="image/png", size=None):
return FakeAttachment(name, data, content_type, size)
async def build(content="", attachments=()):
msg = FakeMessage(content, attachments=list(attachments))
return await bot.build_user_content(msg, content)
def text_block(blocks) -> str:
return blocks[-1]["text"]
# ------------------------------------------------------------------ normalizare
@pytest.mark.parametrize(
"content_type,filename,expected",
[
("image/png", "a.png", "image/png"),
("image/jpeg", "a.jpg", "image/jpeg"),
("image/jpg", "a.jpg", "image/jpeg"), # nestandard, normalizat
("image/png; charset=utf-8", "a.png", "image/png"),
("IMAGE/PNG", "a.png", "image/png"),
("", "a.webp", "image/webp"), # rezerva pe extensie
("application/octet-stream", "a.gif", "image/gif"),
("image/svg+xml", "a.svg", None), # nesuportat de API
("image/heic", "a.heic", None),
("application/pdf", "a.pdf", None),
("", "a.bin", None),
],
)
def test_tipul_imaginii_e_normalizat_si_filtrat(content_type, filename, expected):
assert bot.image_media_type(content_type, filename) == expected
def test_fisierele_text_sunt_recunoscute_dupa_mime_sau_extensie():
assert bot.is_text_attachment("text/plain", "x.txt")
assert bot.is_text_attachment("application/json", "x.json")
assert bot.is_text_attachment("", "eroare.log")
assert bot.is_text_attachment("application/octet-stream", "script.py")
assert not bot.is_text_attachment("application/pdf", "manual.pdf")
assert not bot.is_text_attachment("", "arhiva.zip")
# ------------------------------------------------------------------ constructie
@pytest.mark.asyncio
async def test_fara_atasamente_ramane_text_simplu():
assert await build("salut") == "salut"
@pytest.mark.asyncio
async def test_imaginea_devine_bloc_base64_iar_textul_e_ultimul():
blocks = await build("ce vezi?", [image()])
assert [b["type"] for b in blocks] == ["image", "text"]
src = blocks[0]["source"]
assert src["media_type"] == "image/png"
assert base64.b64decode(src["data"]) == PNG
assert text_block(blocks) == "ce vezi?"
@pytest.mark.asyncio
async def test_imagine_fara_text_primeste_instructiune_implicita():
blocks = await build("", [image()])
assert "Analizeaza imaginea" in text_block(blocks)
@pytest.mark.asyncio
async def test_maxim_patru_imagini_restul_sunt_raportate():
atts = [image(f"p{i}.png") for i in range(6)]
blocks = await build("hai", atts)
assert sum(1 for b in blocks if b["type"] == "image") == bot.MAX_IMAGE_ATTACHMENTS
assert "p4.png" in text_block(blocks) and "p5.png" in text_block(blocks)
@pytest.mark.asyncio
async def test_imaginea_prea_mare_e_sarita_fara_descarcare():
att = image("uriasa.png", size=bot.MAX_IMAGE_BYTES + 1)
blocks = await build("hai", [att])
assert isinstance(blocks, str) # nimic lizibil ramas
assert "uriasa.png" in blocks
assert att.reads == 0 # nu descarcam ce stim ca nu incape
@pytest.mark.asyncio
async def test_marimea_reala_e_recontrolata_dupa_descarcare():
"""Discord poate declara mai putin decat trimite; contam octetii primiti."""
att = image("mincinoasa.png", data=b"y" * (bot.MAX_IMAGE_BYTES + 10), size=10)
blocks = await build("hai", [att])
assert att.reads == 1
assert isinstance(blocks, str) and "mincinoasa.png" in blocks
@pytest.mark.asyncio
async def test_fisierul_text_e_inserat_in_prompt():
att = FakeAttachment("eroare.log", b"ORA-03113 end-of-file", "text/plain")
blocks = await build("ce inseamna?", [att])
body = text_block(blocks)
assert "ce inseamna?" in body
assert "eroare.log" in body and "ORA-03113" in body
@pytest.mark.asyncio
async def test_fisierul_text_prea_mare_e_trunchiat_nu_aruncat():
data = b"a" * (bot.MAX_TEXT_BYTES + 500)
blocks = await build("vezi", [FakeAttachment("mare.log", data, "text/plain")])
body = text_block(blocks)
assert "trunchiat" in body
assert len(body) < len(data)
@pytest.mark.asyncio
async def test_text_binar_nu_arunca_exceptie():
att = FakeAttachment("stricat.txt", b"\xff\xfe\x00binar", "text/plain")
blocks = await build("vezi", [att])
assert "stricat.txt" in text_block(blocks)
@pytest.mark.asyncio
async def test_imagini_si_text_impreuna():
atts = [image(), FakeAttachment("note.md", b"# titlu", "text/markdown")]
blocks = await build("analizeaza", atts)
assert [b["type"] for b in blocks] == ["image", "text"]
assert "# titlu" in text_block(blocks)
@pytest.mark.asyncio
async def test_atasamentul_nesuportat_e_numit_nu_ignorat_tacut():
blocks = await build("uite", [FakeAttachment("manual.pdf", b"%PDF", "application/pdf")])
assert isinstance(blocks, str)
assert "manual.pdf" in blocks and "uite" in blocks
@pytest.mark.asyncio
async def test_eroarea_de_descarcare_nu_pica_turul():
att = FakeBrokenAttachment("poza.png", PNG, "image/png")
blocks = await build("vezi", [att])
assert isinstance(blocks, str)
assert "poza.png" in blocks
@pytest.mark.asyncio
async def test_o_imagine_buna_supravietuieste_langa_una_stricata():
atts = [FakeBrokenAttachment("rea.png", PNG, "image/png"), image("buna.png")]
blocks = await build("vezi", atts)
assert sum(1 for b in blocks if b["type"] == "image") == 1
assert "rea.png" in text_block(blocks)
# ------------------------------------------------------------------ transport
def test_blocurile_ajung_intacte_in_mesajul_de_pe_stdin():
blocks = [
{"type": "image", "source": {"type": "base64", "media_type": "image/png", "data": "QQ=="}},
{"type": "text", "text": "ce vezi?"},
]
import json
payload = json.loads(runner_mod.user_message(blocks))
assert payload["message"]["content"] == blocks
def test_textul_simplu_ramane_un_singur_bloc_text():
import json
payload = json.loads(runner_mod.user_message("salut"))
assert payload["message"]["content"] == [{"type": "text", "text": "salut"}]
# ---------------------------------------------------- integrare prin punte
@pytest.mark.asyncio
async def test_mesaj_cu_imagine_trece_prin_punte_pana_la_cli(bridge, monkeypatch):
"""Blocurile construite in bot ajung neatinse la `proc.run_turn`."""
vazut = {}
async def fake_turn(prompt, on_event=None, timeout=None):
vazut["prompt"] = prompt
return runner_mod.TurnOutcome(
result=bot.stream_mod.Result(0.01, 10, False, 1, text="ok")
)
msg = FakeMessage("ce vezi?", attachments=[image()])
proc = bridge.runner.get(str(msg.channel.id))
monkeypatch.setattr(proc, "run_turn", fake_turn)
assert await bridge.handle_message(msg) == "ok"
blocks = vazut["prompt"]
assert [b["type"] for b in blocks] == ["image", "text"]
assert base64.b64decode(blocks[0]["source"]["data"]) == PNG
@pytest.mark.asyncio
async def test_mesaj_doar_cu_atasament_nu_mai_e_gol(bridge):
"""Inainte, un mesaj fara text era respins ca 'empty' si poza se pierdea."""
msg = FakeMessage("", attachments=[image()])
assert await bridge.handle_message(msg) == "ok"
@pytest.mark.asyncio
async def test_mesaj_complet_gol_ramane_respins(bridge):
assert await bridge.handle_message(FakeMessage("")) == "empty"
@pytest.mark.asyncio
async def test_steering_mid_tur_trimite_si_imaginea(bridge, monkeypatch):
"""O poza trimisa in timpul unui tur intra pe stdin, nu deschide tur nou."""
trimis = {}
tid = "200"
proc = bridge.runner.get(tid)
async def fake_send(content):
trimis["content"] = content
monkeypatch.setattr(proc, "send", fake_send)
monkeypatch.setattr(type(proc), "alive", property(lambda self: True))
proc.inflight = True
msg = FakeMessage("uite eroarea", attachments=[image()])
assert await bridge.handle_message(msg) == "steered"
assert [b["type"] for b in trimis["content"]] == ["image", "text"]