Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
1bb48c91e7 |
@@ -1396,8 +1396,6 @@ def normalize_anthropic_response(
|
||||
"tool_use": "tool_calls",
|
||||
"max_tokens": "length",
|
||||
"stop_sequence": "stop",
|
||||
"refusal": "content_filter",
|
||||
"model_context_window_exceeded": "length",
|
||||
}
|
||||
finish_reason = stop_reason_map.get(response.stop_reason, "stop")
|
||||
|
||||
@@ -1411,42 +1409,3 @@ def normalize_anthropic_response(
|
||||
),
|
||||
finish_reason,
|
||||
)
|
||||
|
||||
|
||||
def normalize_anthropic_response_v2(
|
||||
response,
|
||||
strip_tool_prefix: bool = False,
|
||||
) -> "NormalizedResponse":
|
||||
"""Normalize Anthropic response to NormalizedResponse.
|
||||
|
||||
Wraps the existing normalize_anthropic_response() and maps its output
|
||||
to the shared transport types. This allows incremental migration
|
||||
without disturbing the legacy call sites.
|
||||
"""
|
||||
from agent.transports.types import NormalizedResponse, build_tool_call
|
||||
|
||||
assistant_msg, finish_reason = normalize_anthropic_response(response, strip_tool_prefix)
|
||||
|
||||
tool_calls = None
|
||||
if assistant_msg.tool_calls:
|
||||
tool_calls = [
|
||||
build_tool_call(
|
||||
id=tc.id,
|
||||
name=tc.function.name,
|
||||
arguments=tc.function.arguments,
|
||||
)
|
||||
for tc in assistant_msg.tool_calls
|
||||
]
|
||||
|
||||
provider_data = {}
|
||||
if getattr(assistant_msg, "reasoning_details", None):
|
||||
provider_data["reasoning_details"] = assistant_msg.reasoning_details
|
||||
|
||||
return NormalizedResponse(
|
||||
content=assistant_msg.content,
|
||||
tool_calls=tool_calls,
|
||||
finish_reason=finish_reason,
|
||||
reasoning=getattr(assistant_msg, "reasoning", None),
|
||||
usage=None,
|
||||
provider_data=provider_data or None,
|
||||
)
|
||||
|
||||
@@ -1,57 +0,0 @@
|
||||
"""Transport layer types and registry for provider response normalization.
|
||||
|
||||
Usage:
|
||||
from agent.transports import get_transport
|
||||
transport = get_transport("anthropic_messages")
|
||||
result = transport.normalize_response(raw_response)
|
||||
"""
|
||||
|
||||
from agent.transports.types import ( # noqa: F401
|
||||
NormalizedResponse,
|
||||
ToolCall,
|
||||
Usage,
|
||||
build_tool_call,
|
||||
map_finish_reason,
|
||||
)
|
||||
|
||||
_REGISTRY: dict = {}
|
||||
|
||||
|
||||
def register_transport(api_mode: str, transport_cls: type) -> None:
|
||||
"""Register a transport class for an api_mode string."""
|
||||
_REGISTRY[api_mode] = transport_cls
|
||||
|
||||
|
||||
def get_transport(api_mode: str):
|
||||
"""Get a transport instance for the given api_mode.
|
||||
|
||||
Returns None if no transport is registered for this api_mode.
|
||||
This allows gradual migration — call sites can check for None
|
||||
and fall back to the legacy code path.
|
||||
"""
|
||||
if not _REGISTRY:
|
||||
_discover_transports()
|
||||
cls = _REGISTRY.get(api_mode)
|
||||
if cls is None:
|
||||
return None
|
||||
return cls()
|
||||
|
||||
|
||||
def _discover_transports() -> None:
|
||||
"""Import all transport modules to trigger auto-registration."""
|
||||
try:
|
||||
import agent.transports.anthropic # noqa: F401
|
||||
except ImportError:
|
||||
pass
|
||||
try:
|
||||
import agent.transports.codex # noqa: F401
|
||||
except ImportError:
|
||||
pass
|
||||
try:
|
||||
import agent.transports.chat_completions # noqa: F401
|
||||
except ImportError:
|
||||
pass
|
||||
try:
|
||||
import agent.transports.bedrock # noqa: F401
|
||||
except ImportError:
|
||||
pass
|
||||
@@ -1,95 +0,0 @@
|
||||
"""Anthropic Messages API transport.
|
||||
|
||||
Delegates to the existing adapter functions in agent/anthropic_adapter.py.
|
||||
This transport owns format conversion and normalization — NOT client lifecycle.
|
||||
"""
|
||||
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
from agent.transports.base import ProviderTransport
|
||||
from agent.transports.types import NormalizedResponse
|
||||
|
||||
|
||||
class AnthropicTransport(ProviderTransport):
|
||||
"""Transport for api_mode='anthropic_messages'."""
|
||||
|
||||
@property
|
||||
def api_mode(self) -> str:
|
||||
return "anthropic_messages"
|
||||
|
||||
def convert_messages(self, messages: List[Dict[str, Any]], **kwargs) -> Any:
|
||||
from agent.anthropic_adapter import convert_messages_to_anthropic
|
||||
|
||||
base_url = kwargs.get("base_url")
|
||||
return convert_messages_to_anthropic(messages, base_url=base_url)
|
||||
|
||||
def convert_tools(self, tools: List[Dict[str, Any]]) -> Any:
|
||||
from agent.anthropic_adapter import convert_tools_to_anthropic
|
||||
|
||||
return convert_tools_to_anthropic(tools)
|
||||
|
||||
def build_kwargs(
|
||||
self,
|
||||
model: str,
|
||||
messages: List[Dict[str, Any]],
|
||||
tools: Optional[List[Dict[str, Any]]] = None,
|
||||
**params,
|
||||
) -> Dict[str, Any]:
|
||||
from agent.anthropic_adapter import build_anthropic_kwargs
|
||||
|
||||
return build_anthropic_kwargs(
|
||||
model=model,
|
||||
messages=messages,
|
||||
tools=tools,
|
||||
max_tokens=params.get("max_tokens", 16384),
|
||||
reasoning_config=params.get("reasoning_config"),
|
||||
tool_choice=params.get("tool_choice"),
|
||||
is_oauth=params.get("is_oauth", False),
|
||||
preserve_dots=params.get("preserve_dots", False),
|
||||
context_length=params.get("context_length"),
|
||||
base_url=params.get("base_url"),
|
||||
fast_mode=params.get("fast_mode", False),
|
||||
)
|
||||
|
||||
def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:
|
||||
from agent.anthropic_adapter import normalize_anthropic_response_v2
|
||||
|
||||
strip_tool_prefix = kwargs.get("strip_tool_prefix", False)
|
||||
return normalize_anthropic_response_v2(response, strip_tool_prefix=strip_tool_prefix)
|
||||
|
||||
def validate_response(self, response: Any) -> bool:
|
||||
if response is None:
|
||||
return False
|
||||
content_blocks = getattr(response, "content", None)
|
||||
if not isinstance(content_blocks, list):
|
||||
return False
|
||||
if not content_blocks:
|
||||
return False
|
||||
return True
|
||||
|
||||
def extract_cache_stats(self, response: Any):
|
||||
usage = getattr(response, "usage", None)
|
||||
if usage is None:
|
||||
return None
|
||||
cached = getattr(usage, "cache_read_input_tokens", 0) or 0
|
||||
written = getattr(usage, "cache_creation_input_tokens", 0) or 0
|
||||
if cached or written:
|
||||
return {"cached_tokens": cached, "creation_tokens": written}
|
||||
return None
|
||||
|
||||
_STOP_REASON_MAP = {
|
||||
"end_turn": "stop",
|
||||
"tool_use": "tool_calls",
|
||||
"max_tokens": "length",
|
||||
"stop_sequence": "stop",
|
||||
"refusal": "content_filter",
|
||||
"model_context_window_exceeded": "length",
|
||||
}
|
||||
|
||||
def map_finish_reason(self, raw_reason: str) -> str:
|
||||
return self._STOP_REASON_MAP.get(raw_reason, "stop")
|
||||
|
||||
|
||||
from agent.transports import register_transport # noqa: E402
|
||||
|
||||
register_transport("anthropic_messages", AnthropicTransport)
|
||||
@@ -1,61 +0,0 @@
|
||||
"""Abstract base for provider transports.
|
||||
|
||||
A transport owns the data path for one api_mode:
|
||||
convert_messages → convert_tools → build_kwargs → normalize_response
|
||||
|
||||
It does NOT own: client construction, streaming, credential refresh,
|
||||
prompt caching, interrupt handling, or retry logic. Those stay on AIAgent.
|
||||
"""
|
||||
|
||||
from abc import ABC, abstractmethod
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
from agent.transports.types import NormalizedResponse
|
||||
|
||||
|
||||
class ProviderTransport(ABC):
|
||||
"""Base class for provider-specific format conversion and normalization."""
|
||||
|
||||
@property
|
||||
@abstractmethod
|
||||
def api_mode(self) -> str:
|
||||
"""The api_mode string this transport handles."""
|
||||
...
|
||||
|
||||
@abstractmethod
|
||||
def convert_messages(self, messages: List[Dict[str, Any]], **kwargs) -> Any:
|
||||
"""Convert OpenAI-format messages to provider-native format."""
|
||||
...
|
||||
|
||||
@abstractmethod
|
||||
def convert_tools(self, tools: List[Dict[str, Any]]) -> Any:
|
||||
"""Convert OpenAI-format tool definitions to provider-native format."""
|
||||
...
|
||||
|
||||
@abstractmethod
|
||||
def build_kwargs(
|
||||
self,
|
||||
model: str,
|
||||
messages: List[Dict[str, Any]],
|
||||
tools: Optional[List[Dict[str, Any]]] = None,
|
||||
**params,
|
||||
) -> Dict[str, Any]:
|
||||
"""Build the complete provider kwargs dict."""
|
||||
...
|
||||
|
||||
@abstractmethod
|
||||
def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:
|
||||
"""Normalize a raw provider response to the shared NormalizedResponse type."""
|
||||
...
|
||||
|
||||
def validate_response(self, response: Any) -> bool:
|
||||
"""Optional structural validation for raw responses."""
|
||||
return True
|
||||
|
||||
def extract_cache_stats(self, response: Any) -> Optional[Dict[str, int]]:
|
||||
"""Optional cache stats extraction."""
|
||||
return None
|
||||
|
||||
def map_finish_reason(self, raw_reason: str) -> str:
|
||||
"""Optional stop-reason mapping. Defaults to passthrough."""
|
||||
return raw_reason
|
||||
@@ -1,58 +0,0 @@
|
||||
"""Shared types for normalized provider responses."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
|
||||
@dataclass
|
||||
class ToolCall:
|
||||
"""A normalized tool call from any provider."""
|
||||
|
||||
id: Optional[str]
|
||||
name: str
|
||||
arguments: str
|
||||
provider_data: Optional[Dict[str, Any]] = field(default=None, repr=False)
|
||||
|
||||
|
||||
@dataclass
|
||||
class Usage:
|
||||
"""Token usage from an API response."""
|
||||
|
||||
prompt_tokens: int = 0
|
||||
completion_tokens: int = 0
|
||||
total_tokens: int = 0
|
||||
cached_tokens: int = 0
|
||||
|
||||
|
||||
@dataclass
|
||||
class NormalizedResponse:
|
||||
"""Normalized API response from any provider."""
|
||||
|
||||
content: Optional[str]
|
||||
tool_calls: Optional[List[ToolCall]]
|
||||
finish_reason: str
|
||||
reasoning: Optional[str] = None
|
||||
usage: Optional[Usage] = None
|
||||
provider_data: Optional[Dict[str, Any]] = field(default=None, repr=False)
|
||||
|
||||
|
||||
def build_tool_call(
|
||||
id: Optional[str],
|
||||
name: str,
|
||||
arguments: Any,
|
||||
**provider_fields: Any,
|
||||
) -> ToolCall:
|
||||
"""Build a ToolCall, auto-serialising dict arguments."""
|
||||
args_str = json.dumps(arguments) if isinstance(arguments, dict) else str(arguments)
|
||||
provider_data = dict(provider_fields) if provider_fields else None
|
||||
return ToolCall(id=id, name=name, arguments=args_str, provider_data=provider_data)
|
||||
|
||||
|
||||
def map_finish_reason(reason: Optional[str], mapping: Dict[str, str]) -> str:
|
||||
"""Translate a provider-specific stop reason to the normalized set."""
|
||||
if reason is None:
|
||||
return "stop"
|
||||
return mapping.get(reason, "stop")
|
||||
387
docs/review_packets/hermes-harness-2026-04-21.md
Normal file
387
docs/review_packets/hermes-harness-2026-04-21.md
Normal file
@@ -0,0 +1,387 @@
|
||||
# Morning Review Packet
|
||||
|
||||
Source epic: [EPIC: Morning review packet — Hermes harness features landed 2026-04-21](https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/949)
|
||||
|
||||
## Epic context
|
||||
|
||||
EPIC: Morning review packet — Hermes harness features landed 2026-04-21
|
||||
|
||||
Source: git log on upstream/main since 2026-04-21 00:00 EDT, plus the current local branch `burn/921-poka-yoke-hardcoded-paths` for the branch-only path-guard work.
|
||||
|
||||
Important review note:
|
||||
- Validate upstream-landed features on `upstream/main` or a synced branch.
|
||||
- Validate the path-guard work on `burn/921-poka-yoke-hardcoded-paths`.
|
||||
|
||||
This epic is a morning-review packet: one QA issue per feature cluster, each with concrete acceptance criteria and targeted tests or manual checks.
|
||||
|
||||
## Success criteria
|
||||
- [ ] Every issue has a clear PASS / FAIL outcome.
|
||||
- [ ] Test output or manual evidence is attached to each issue.
|
||||
- [ ] Any drift between upstream/main and forge/main is called out explicitly.
|
||||
|
||||
## Sub-issues
|
||||
### Upstream/main features landed 2026-04-21
|
||||
- [ ] #950 [QA] Verify AI Gateway provider UX + attribution headers
|
||||
- [ ] #951 [QA] Verify transport abstraction + AnthropicTransport wiring
|
||||
- [ ] #952 [QA] Verify CLI voice beep toggle
|
||||
- [ ] #953 [QA] Verify bundled skill scripts run out of the box
|
||||
- [ ] #954 [QA] Verify maps skill guest_house / camp_site / bakery expansion
|
||||
- [ ] #955 [QA] Verify KittenTTS local provider end-to-end
|
||||
- [ ] #956 [QA] Verify numbered keyboard shortcuts for approval + clarify prompts
|
||||
- [ ] #957 [QA] Verify optional adversarial-ux-test skill catalog flow
|
||||
- [ ] #958 [QA] Verify /usage account limits in CLI + gateway
|
||||
- [ ] #959 [QA] Verify OpenCode-Go curated catalog additions
|
||||
- [ ] #960 [QA] Verify patch 'did you mean?' suggestions
|
||||
- [ ] #961 [QA] Verify web dashboard update/restart action buttons
|
||||
|
||||
### Local branch-only work
|
||||
- [ ] #962 [QA] Verify hardcoded-home path guard on burn/921 branch
|
||||
|
||||
## Summary
|
||||
|
||||
| Issue | State | Commits | Tests |
|
||||
| --- | --- | --- | --- |
|
||||
| #950 | open | 5 | 2 |
|
||||
| #951 | open | 2 | 2 |
|
||||
| #952 | open | 1 | 1 |
|
||||
| #953 | open | 1 | 2 |
|
||||
| #954 | open | 1 | 0 |
|
||||
| #955 | open | 2 | 1 |
|
||||
| #956 | open | 1 | 0 |
|
||||
| #957 | open | 1 | 0 |
|
||||
| #958 | open | 2 | 2 |
|
||||
| #959 | open | 1 | 1 |
|
||||
| #960 | open | 2 | 1 |
|
||||
| #961 | closed | 1 | 0 |
|
||||
| #962 | closed | 1 | 1 |
|
||||
|
||||
## #950 — [QA] Verify AI Gateway provider UX + attribution headers
|
||||
|
||||
State: open
|
||||
URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/950
|
||||
|
||||
### Branch / checkout
|
||||
- Validate on `upstream/main` or an equivalent synced checkout.
|
||||
|
||||
### Commits
|
||||
- `b11753879` — attribution default_headers for ai-gateway provider
|
||||
- `700437440` — curated picker with live pricing
|
||||
- `ac26a460f` — promote ai-gateway in provider picker ordering
|
||||
- `5bb2d11b0` — auto-promote free Moonshot models
|
||||
- `29f57ec95` — Vercel deep-link for API key creation
|
||||
|
||||
### Targeted tests
|
||||
- `tests/hermes_cli/test_ai_gateway_models.py`
|
||||
- `tests/run_agent/test_provider_attribution_headers.py`
|
||||
|
||||
### Tasks
|
||||
- [ ] Open `hermes model` and verify `ai-gateway` appears near the top.
|
||||
- [ ] Verify live pricing appears in the picker.
|
||||
- [ ] Verify free Moonshot models are promoted.
|
||||
- [ ] Trigger API-key setup flow and verify the Vercel deep link.
|
||||
- [ ] Send one ai-gateway request and verify attribution headers are attached.
|
||||
|
||||
### Acceptance criteria
|
||||
- [ ] UI ordering and pricing match the landed behavior.
|
||||
- [ ] Attribution headers are present on ai-gateway requests.
|
||||
- [ ] Targeted tests pass.
|
||||
|
||||
## #951 — [QA] Verify transport abstraction + AnthropicTransport wiring
|
||||
|
||||
State: open
|
||||
URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/951
|
||||
|
||||
### Branch / checkout
|
||||
- Validate on `upstream/main` or an equivalent synced checkout.
|
||||
|
||||
### Commits
|
||||
- `7ab5eebd0` — transport types + Anthropic normalize migration
|
||||
- `731f4fbae` — transport ABC + AnthropicTransport wired to all paths
|
||||
|
||||
### Targeted tests
|
||||
- `tests/agent/transports/test_types.py`
|
||||
- `tests/agent/test_anthropic_normalize_v2.py`
|
||||
|
||||
### Tasks
|
||||
- [ ] Verify plain-text Anthropic responses normalize correctly.
|
||||
- [ ] Verify tool-call responses preserve IDs, names, and arguments.
|
||||
- [ ] Verify reasoning/thinking is preserved separately from visible content.
|
||||
- [ ] Verify finish_reason mapping remains correct across paths.
|
||||
|
||||
### Acceptance criteria
|
||||
- [ ] Normalized response shape is stable.
|
||||
- [ ] Tool-call and reasoning payloads survive normalization.
|
||||
- [ ] Targeted tests pass.
|
||||
|
||||
## #952 — [QA] Verify CLI voice beep toggle
|
||||
|
||||
State: open
|
||||
URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/952
|
||||
|
||||
### Branch / checkout
|
||||
- Validate on `upstream/main` or an equivalent synced checkout.
|
||||
|
||||
### Commits
|
||||
- `b48ea41d2` — voice: add CLI beep toggle
|
||||
|
||||
### Targeted tests
|
||||
- `tests/tools/test_voice_cli_integration.py`
|
||||
|
||||
### Tasks
|
||||
- [ ] Enable the beep option in config and confirm voice mode emits the beep.
|
||||
- [ ] Disable the option and confirm the same path is silent.
|
||||
- [ ] Verify voice mode still strips markdown before speech output.
|
||||
- [ ] Verify voice mode does not pollute conversation history with TTS-only text.
|
||||
|
||||
### Acceptance criteria
|
||||
- [ ] Beep behavior is actually toggled by config.
|
||||
- [ ] Existing voice/TTS integration behavior is not regressed.
|
||||
- [ ] Targeted tests pass.
|
||||
|
||||
## #953 — [QA] Verify bundled skill scripts run out of the box
|
||||
|
||||
State: open
|
||||
URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/953
|
||||
|
||||
### Branch / checkout
|
||||
- Validate on `upstream/main` or an equivalent synced checkout.
|
||||
|
||||
### Commits
|
||||
- `328223576` — make bundled skill scripts runnable out of the box
|
||||
|
||||
### Targeted tests
|
||||
- `tests/agent/test_skill_commands.py`
|
||||
- `tests/tools/test_local_shell_init.py`
|
||||
|
||||
### Tasks
|
||||
- [ ] Pick a bundled skill that ships a script and run it without manual chmod/PATH surgery.
|
||||
- [ ] Verify local terminal execution resolves the installed skill script correctly.
|
||||
- [ ] Verify local shell init still behaves correctly.
|
||||
|
||||
### Acceptance criteria
|
||||
- [ ] Bundled skill scripts execute from the installed skill location with no manual prep.
|
||||
- [ ] Local shell init remains healthy.
|
||||
- [ ] Targeted tests pass.
|
||||
|
||||
## #954 — [QA] Verify maps skill guest_house / camp_site / bakery expansion
|
||||
|
||||
State: open
|
||||
URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/954
|
||||
|
||||
### Branch / checkout
|
||||
- Validate on `upstream/main` or an equivalent synced checkout.
|
||||
|
||||
### Commits
|
||||
- `c5a814b23` — maps: add guest_house, camp_site, and dual-key bakery lookup
|
||||
|
||||
### Tasks
|
||||
- [ ] Use the maps skill to search for a guest house in a known populated area.
|
||||
- [ ] Use the maps skill to search for a camp site in a known populated area.
|
||||
- [ ] Use the maps skill to search for a bakery and verify both supported keys resolve correctly.
|
||||
- [ ] Confirm results are sensible and non-empty.
|
||||
|
||||
### Acceptance criteria
|
||||
- [ ] All three place types resolve correctly.
|
||||
- [ ] Bakery lookup works through both supported keys.
|
||||
- [ ] Manual evidence is attached in the issue.
|
||||
|
||||
## #955 — [QA] Verify KittenTTS local provider end-to-end
|
||||
|
||||
State: open
|
||||
URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/955
|
||||
|
||||
### Branch / checkout
|
||||
- Validate on `upstream/main` or an equivalent synced checkout.
|
||||
|
||||
### Commits
|
||||
- `1830ebfc5` — add KittenTTS provider
|
||||
- `2d7ff9c5b` — complete KittenTTS integration across tools/setup/docs/tests
|
||||
|
||||
### Targeted tests
|
||||
- `tests/tools/test_tts_kittentts.py`
|
||||
|
||||
### Tasks
|
||||
- [ ] Configure TTS to use `kittentts`.
|
||||
- [ ] Generate speech to `.wav` and verify playable output.
|
||||
- [ ] Verify voice / speed / cleaned text are passed correctly.
|
||||
- [ ] Generate repeated requests and verify model caching behavior.
|
||||
- [ ] Generate a non-wav output and verify ffmpeg conversion path.
|
||||
- [ ] Verify missing-package behavior returns a helpful error.
|
||||
|
||||
### Acceptance criteria
|
||||
- [ ] KittenTTS works end-to-end when installed.
|
||||
- [ ] Failure mode is operator-friendly when not installed.
|
||||
- [ ] Targeted tests pass.
|
||||
|
||||
## #956 — [QA] Verify numbered keyboard shortcuts for approval + clarify prompts
|
||||
|
||||
State: open
|
||||
URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/956
|
||||
|
||||
### Branch / checkout
|
||||
- Validate on `upstream/main` or an equivalent synced checkout.
|
||||
|
||||
### Commits
|
||||
- `d1ed6f4fb` — CLI: add numbered keyboard shortcuts to approval and clarify prompts
|
||||
|
||||
### Tasks
|
||||
- [ ] Trigger an approval prompt and choose an option with number keys.
|
||||
- [ ] Trigger a clarify prompt and choose an option with number keys.
|
||||
- [ ] Verify the correct option is submitted both times.
|
||||
- [ ] Verify normal keyboard navigation still works.
|
||||
|
||||
### Acceptance criteria
|
||||
- [ ] Number-key selection works for both prompt types.
|
||||
- [ ] Legacy keyboard navigation is not broken.
|
||||
- [ ] Manual evidence is attached in the issue.
|
||||
|
||||
## #957 — [QA] Verify optional adversarial-ux-test skill catalog flow
|
||||
|
||||
State: open
|
||||
URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/957
|
||||
|
||||
### Branch / checkout
|
||||
- Validate on `upstream/main` or an equivalent synced checkout.
|
||||
|
||||
### Commits
|
||||
- `e50e7f11b` — skills: add adversarial-ux-test optional skill
|
||||
|
||||
### Tasks
|
||||
- [ ] Verify the optional skill appears in the optional skill catalog.
|
||||
- [ ] Install or enable the skill.
|
||||
- [ ] Load it successfully through Hermes.
|
||||
- [ ] Disable or remove it and verify catalog state updates cleanly.
|
||||
|
||||
### Acceptance criteria
|
||||
- [ ] Catalog listing is correct.
|
||||
- [ ] Install / load / disable lifecycle works cleanly.
|
||||
- [ ] Manual evidence is attached in the issue.
|
||||
|
||||
## #958 — [QA] Verify /usage account limits in CLI + gateway
|
||||
|
||||
State: open
|
||||
URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/958
|
||||
|
||||
### Branch / checkout
|
||||
- Validate on `upstream/main` or an equivalent synced checkout.
|
||||
|
||||
### Commits
|
||||
- `8a11b0a20` — per-provider account limits module
|
||||
- `bcc5d7b67` — append account limits section in CLI and gateway
|
||||
|
||||
### Targeted tests
|
||||
- `tests/test_account_usage.py`
|
||||
- `tests/gateway/test_usage_command.py`
|
||||
|
||||
### Tasks
|
||||
- [ ] Run `/usage` in CLI for a provider with account limits.
|
||||
- [ ] Verify provider, remaining quota, total limit, and reset window render correctly.
|
||||
- [ ] Run `/usage` through the gateway and verify the same section appears.
|
||||
- [ ] Verify zero-value cache read/write sections stay hidden when appropriate.
|
||||
|
||||
### Acceptance criteria
|
||||
- [ ] CLI and gateway both show the landed account-limits section correctly.
|
||||
- [ ] Targeted tests pass.
|
||||
|
||||
## #959 — [QA] Verify OpenCode-Go curated catalog additions
|
||||
|
||||
State: open
|
||||
URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/959
|
||||
|
||||
### Branch / checkout
|
||||
- Validate on `upstream/main` or an equivalent synced checkout.
|
||||
|
||||
### Commits
|
||||
- `4fea1769d` — opencode-go: add Kimi K2.6 and Qwen3.5/3.6 Plus to curated catalog
|
||||
|
||||
### Targeted tests
|
||||
- `tests/hermes_cli/test_opencode_go_in_model_list.py`
|
||||
|
||||
### Tasks
|
||||
- [ ] With valid OpenCode-Go credentials, open `hermes model`.
|
||||
- [ ] Verify Kimi K2.6 appears.
|
||||
- [ ] Verify Qwen 3.5 Plus and 3.6 Plus appear.
|
||||
- [ ] Unset credentials and verify the provider/catalog hides correctly.
|
||||
|
||||
### Acceptance criteria
|
||||
- [ ] New curated models are present when credentials exist.
|
||||
- [ ] Catalog visibility still respects credential gating.
|
||||
- [ ] Targeted tests pass.
|
||||
|
||||
## #960 — [QA] Verify patch 'did you mean?' suggestions
|
||||
|
||||
State: open
|
||||
URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/960
|
||||
|
||||
### Branch / checkout
|
||||
- Validate on `upstream/main` or an equivalent synced checkout.
|
||||
|
||||
### Commits
|
||||
- `15abf4ed8` — add `did you mean?` feedback when patch fails to match
|
||||
- `5e6427a42` — gate it to true no-match cases and extend to v4a / skill_manage
|
||||
|
||||
### Targeted tests
|
||||
- `tests/tools/test_fuzzy_match.py`
|
||||
|
||||
### Tasks
|
||||
- [ ] Intentionally run a replace/patch with a near-miss `old_string`.
|
||||
- [ ] Verify the tool suggests a useful nearby line/context.
|
||||
- [ ] Verify suggestions only appear on true no-match failures.
|
||||
- [ ] Verify the behavior also works via file tools, v4a patching, and skill_manage.
|
||||
|
||||
### Acceptance criteria
|
||||
- [ ] Suggestion quality is helpful, not noisy.
|
||||
- [ ] Suggestions are correctly gated to no-match cases.
|
||||
- [ ] Targeted tests pass.
|
||||
|
||||
## #961 — [QA] Verify web dashboard update/restart action buttons
|
||||
|
||||
State: closed
|
||||
URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/961
|
||||
|
||||
### Branch / checkout
|
||||
- Validate on `upstream/main` or an equivalent synced checkout.
|
||||
|
||||
### Commits
|
||||
- `fc21c1420` — add buttons to update Hermes and restart gateway
|
||||
|
||||
### Files touched
|
||||
- `web/src/pages/StatusPage.tsx`
|
||||
- `web/src/lib/api.ts`
|
||||
- `web/src/i18n/en.ts`
|
||||
|
||||
### Tasks
|
||||
- [ ] Open the Web UI status page and verify both buttons are present.
|
||||
- [ ] Click Restart Gateway in a safe environment and verify running/output/success-or-failure states render.
|
||||
- [ ] Click Update Hermes and verify the same action lifecycle.
|
||||
- [ ] Verify the page remains responsive while actions are running.
|
||||
|
||||
### Acceptance criteria
|
||||
- [ ] Both action buttons are present and wired.
|
||||
- [ ] Action status polling and result rendering work end-to-end.
|
||||
- [ ] Manual evidence is attached in the issue.
|
||||
|
||||
## #962 — [QA] Verify hardcoded-home path guard on burn/921 branch
|
||||
|
||||
State: closed
|
||||
URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/962
|
||||
|
||||
### Branch / checkout
|
||||
- Validate specifically on `burn/921-poka-yoke-hardcoded-paths` (not upstream/main).
|
||||
|
||||
### Commits
|
||||
- `5dcb90531` — Poka-yoke: prevent hardcoded home-directory paths
|
||||
|
||||
### Targeted tests
|
||||
- `tests/test_path_guard.py`
|
||||
|
||||
### Tasks
|
||||
- [ ] Verify hardcoded `/Users/...` paths are rejected.
|
||||
- [ ] Verify hardcoded `~/.hermes/...` paths are rejected in guarded contexts.
|
||||
- [ ] Verify valid relative paths still pass.
|
||||
- [ ] Verify appropriate absolute paths still pass where intended.
|
||||
- [ ] Verify linting catches violations in non-test files.
|
||||
|
||||
### Acceptance criteria
|
||||
- [ ] Guard blocks the dangerous patterns and preserves allowed ones.
|
||||
- [ ] Targeted tests pass.
|
||||
301
scripts/morning_review_packet.py
Normal file
301
scripts/morning_review_packet.py
Normal file
@@ -0,0 +1,301 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Build a morning review packet from a Gitea epic and its child QA issues.
|
||||
|
||||
This script fetches a parent epic plus its sub-issues, extracts the structured
|
||||
sections from each QA issue body, and renders a single markdown packet suitable
|
||||
for morning review.
|
||||
|
||||
Usage:
|
||||
python scripts/morning_review_packet.py --epic-number 949
|
||||
python scripts/morning_review_packet.py --epic-number 949 --children 950-962
|
||||
python scripts/morning_review_packet.py --epic-number 949 --output docs/review_packets/hermes-harness-2026-04-21.md
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import urllib.request
|
||||
from dataclasses import dataclass, field
|
||||
from pathlib import Path
|
||||
from typing import Iterable
|
||||
|
||||
DEFAULT_BASE_URL = "https://forge.alexanderwhitestone.com"
|
||||
DEFAULT_OWNER = "Timmy_Foundation"
|
||||
DEFAULT_REPO = "hermes-agent"
|
||||
DEFAULT_TOKEN_PATH = Path.home() / ".config" / "gitea" / "token"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class CommitEvidence:
|
||||
sha: str
|
||||
summary: str
|
||||
|
||||
|
||||
@dataclass
|
||||
class ReviewIssue:
|
||||
number: int
|
||||
title: str
|
||||
state: str
|
||||
url: str
|
||||
comments: int = 0
|
||||
parent_issue: int | None = None
|
||||
checkout_notes: list[str] = field(default_factory=list)
|
||||
commits: list[CommitEvidence] = field(default_factory=list)
|
||||
targeted_tests: list[str] = field(default_factory=list)
|
||||
files_touched: list[str] = field(default_factory=list)
|
||||
tasks: list[str] = field(default_factory=list)
|
||||
acceptance_criteria: list[str] = field(default_factory=list)
|
||||
|
||||
|
||||
def parse_issue_number_spec(spec: str) -> list[int]:
|
||||
"""Parse a comma-separated issue list like ``950-952,955,962``."""
|
||||
numbers: list[int] = []
|
||||
seen: set[int] = set()
|
||||
for chunk in (part.strip() for part in spec.split(",")):
|
||||
if not chunk:
|
||||
continue
|
||||
if "-" in chunk:
|
||||
start_str, end_str = (part.strip() for part in chunk.split("-", 1))
|
||||
start = int(start_str)
|
||||
end = int(end_str)
|
||||
if end < start:
|
||||
raise ValueError(f"Invalid descending issue range: {chunk}")
|
||||
for number in range(start, end + 1):
|
||||
if number not in seen:
|
||||
numbers.append(number)
|
||||
seen.add(number)
|
||||
else:
|
||||
number = int(chunk)
|
||||
if number not in seen:
|
||||
numbers.append(number)
|
||||
seen.add(number)
|
||||
return numbers
|
||||
|
||||
|
||||
def _parse_sections(body: str) -> dict[str, list[str]]:
|
||||
sections: dict[str, list[str]] = {}
|
||||
current: str | None = None
|
||||
for raw_line in body.splitlines():
|
||||
line = raw_line.rstrip()
|
||||
if line.startswith("## "):
|
||||
current = line[3:].strip()
|
||||
sections[current] = []
|
||||
continue
|
||||
if current is not None:
|
||||
sections[current].append(line)
|
||||
return sections
|
||||
|
||||
|
||||
def _clean_bullet(line: str) -> str | None:
|
||||
stripped = line.strip()
|
||||
if not stripped:
|
||||
return None
|
||||
stripped = re.sub(r"^-\s*\[(?: |x|X)\]\s*", "", stripped)
|
||||
stripped = re.sub(r"^-\s*", "", stripped)
|
||||
return stripped.strip() or None
|
||||
|
||||
|
||||
def _extract_bullets(lines: Iterable[str]) -> list[str]:
|
||||
items: list[str] = []
|
||||
for line in lines:
|
||||
cleaned = _clean_bullet(line)
|
||||
if cleaned:
|
||||
items.append(cleaned)
|
||||
return items
|
||||
|
||||
|
||||
def _extract_parent_issue(body: str, sections: dict[str, list[str]]) -> int | None:
|
||||
parent_lines = sections.get("Parent", [])
|
||||
for line in parent_lines:
|
||||
match = re.search(r"#(\d+)", line)
|
||||
if match:
|
||||
return int(match.group(1))
|
||||
match = re.search(r"Linked to Epic\s+#(\d+)", body, flags=re.IGNORECASE)
|
||||
if match:
|
||||
return int(match.group(1))
|
||||
return None
|
||||
|
||||
|
||||
def _extract_commits(lines: Iterable[str]) -> list[CommitEvidence]:
|
||||
commits: list[CommitEvidence] = []
|
||||
for item in _extract_bullets(lines):
|
||||
match = re.match(r"`([^`]+)`\s*(.*)", item)
|
||||
if match:
|
||||
commits.append(CommitEvidence(sha=match.group(1).strip(), summary=match.group(2).strip()))
|
||||
else:
|
||||
commits.append(CommitEvidence(sha="", summary=item))
|
||||
return commits
|
||||
|
||||
|
||||
def _strip_backticks(items: Iterable[str]) -> list[str]:
|
||||
cleaned: list[str] = []
|
||||
for item in items:
|
||||
cleaned.append(item.replace("`", "").strip())
|
||||
return cleaned
|
||||
|
||||
|
||||
def discover_child_issue_numbers(epic_body: str) -> list[int]:
|
||||
"""Discover sub-issue numbers from an epic body."""
|
||||
sections = _parse_sections(epic_body)
|
||||
sub_lines = sections.get("Sub-issues")
|
||||
if not sub_lines:
|
||||
return []
|
||||
numbers: list[int] = []
|
||||
seen: set[int] = set()
|
||||
for line in sub_lines:
|
||||
for match in re.finditer(r"#(\d+)", line):
|
||||
number = int(match.group(1))
|
||||
if number not in seen:
|
||||
numbers.append(number)
|
||||
seen.add(number)
|
||||
return numbers
|
||||
|
||||
|
||||
def parse_child_issue(issue: dict) -> ReviewIssue:
|
||||
body = issue.get("body") or ""
|
||||
sections = _parse_sections(body)
|
||||
commit_lines = sections.get("Commits landed today", []) or sections.get("Commit landed today", [])
|
||||
|
||||
return ReviewIssue(
|
||||
number=int(issue["number"]),
|
||||
title=issue.get("title") or "",
|
||||
state=(issue.get("state") or "unknown").lower(),
|
||||
url=issue.get("html_url") or issue.get("url") or "",
|
||||
comments=int(issue.get("comments") or 0),
|
||||
parent_issue=_extract_parent_issue(body, sections),
|
||||
checkout_notes=_extract_bullets(sections.get("Branch / checkout", [])),
|
||||
commits=_extract_commits(commit_lines),
|
||||
targeted_tests=_strip_backticks(_extract_bullets(sections.get("Targeted tests", []))),
|
||||
files_touched=_strip_backticks(_extract_bullets(sections.get("Files touched", []))),
|
||||
tasks=_extract_bullets(sections.get("Tasks", [])),
|
||||
acceptance_criteria=_extract_bullets(sections.get("Acceptance Criteria", [])),
|
||||
)
|
||||
|
||||
|
||||
def build_packet_markdown(epic_issue: dict, child_issues: list[ReviewIssue]) -> str:
|
||||
title = epic_issue.get("title") or f"Epic #{epic_issue.get('number')}"
|
||||
url = epic_issue.get("html_url") or epic_issue.get("url") or ""
|
||||
body = epic_issue.get("body") or ""
|
||||
children = sorted(child_issues, key=lambda item: item.number)
|
||||
|
||||
lines: list[str] = []
|
||||
lines.append("# Morning Review Packet")
|
||||
lines.append("")
|
||||
lines.append(f"Source epic: [{title}]({url})")
|
||||
lines.append("")
|
||||
lines.append("## Epic context")
|
||||
lines.append("")
|
||||
lines.append(title)
|
||||
lines.append("")
|
||||
for line in body.splitlines():
|
||||
if line.strip():
|
||||
lines.append(line)
|
||||
else:
|
||||
lines.append("")
|
||||
lines.append("")
|
||||
lines.append("## Summary")
|
||||
lines.append("")
|
||||
lines.append("| Issue | State | Commits | Tests |")
|
||||
lines.append("| --- | --- | --- | --- |")
|
||||
for child in children:
|
||||
lines.append(
|
||||
f"| #{child.number} | {child.state} | {len(child.commits)} | {len(child.targeted_tests)} |"
|
||||
)
|
||||
lines.append("")
|
||||
|
||||
for child in children:
|
||||
lines.append(f"## #{child.number} — {child.title}")
|
||||
lines.append("")
|
||||
lines.append(f"State: {child.state}")
|
||||
lines.append(f"URL: {child.url}")
|
||||
lines.append("")
|
||||
if child.checkout_notes:
|
||||
lines.append("### Branch / checkout")
|
||||
for note in child.checkout_notes:
|
||||
lines.append(f"- {note}")
|
||||
lines.append("")
|
||||
if child.commits:
|
||||
lines.append("### Commits")
|
||||
for commit in child.commits:
|
||||
if commit.sha:
|
||||
lines.append(f"- `{commit.sha}` — {commit.summary}")
|
||||
else:
|
||||
lines.append(f"- {commit.summary}")
|
||||
lines.append("")
|
||||
if child.targeted_tests:
|
||||
lines.append("### Targeted tests")
|
||||
for test_path in child.targeted_tests:
|
||||
lines.append(f"- `{test_path}`")
|
||||
lines.append("")
|
||||
if child.files_touched:
|
||||
lines.append("### Files touched")
|
||||
for file_path in child.files_touched:
|
||||
lines.append(f"- `{file_path}`")
|
||||
lines.append("")
|
||||
if child.tasks:
|
||||
lines.append("### Tasks")
|
||||
for task in child.tasks:
|
||||
lines.append(f"- [ ] {task}")
|
||||
lines.append("")
|
||||
if child.acceptance_criteria:
|
||||
lines.append("### Acceptance criteria")
|
||||
for item in child.acceptance_criteria:
|
||||
lines.append(f"- [ ] {item}")
|
||||
lines.append("")
|
||||
|
||||
return "\n".join(lines).rstrip() + "\n"
|
||||
|
||||
|
||||
def _resolve_token(explicit_token: str | None = None) -> str:
|
||||
if explicit_token:
|
||||
return explicit_token.strip()
|
||||
env_token = os.getenv("GITEA_TOKEN")
|
||||
if env_token:
|
||||
return env_token.strip()
|
||||
if DEFAULT_TOKEN_PATH.exists():
|
||||
return DEFAULT_TOKEN_PATH.read_text().strip()
|
||||
raise FileNotFoundError(f"No Gitea token found. Set GITEA_TOKEN or create {DEFAULT_TOKEN_PATH}")
|
||||
|
||||
|
||||
def fetch_issue(base_url: str, owner: str, repo: str, number: int, token: str) -> dict:
|
||||
url = f"{base_url.rstrip('/')}/api/v1/repos/{owner}/{repo}/issues/{number}"
|
||||
request = urllib.request.Request(url, headers={"Authorization": f"token {token}"})
|
||||
with urllib.request.urlopen(request, timeout=30) as response:
|
||||
return json.loads(response.read().decode())
|
||||
|
||||
|
||||
def collect_child_issues(base_url: str, owner: str, repo: str, epic_issue: dict, token: str, children_spec: str | None = None) -> list[dict]:
|
||||
numbers = parse_issue_number_spec(children_spec) if children_spec else discover_child_issue_numbers(epic_issue.get("body") or "")
|
||||
return [fetch_issue(base_url, owner, repo, number, token) for number in numbers]
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
parser = argparse.ArgumentParser(description="Build a markdown morning review packet from a Gitea epic")
|
||||
parser.add_argument("--base-url", default=DEFAULT_BASE_URL)
|
||||
parser.add_argument("--owner", default=DEFAULT_OWNER)
|
||||
parser.add_argument("--repo", default=DEFAULT_REPO)
|
||||
parser.add_argument("--epic-number", type=int, required=True)
|
||||
parser.add_argument("--children", help="Explicit issue list/ranges, e.g. 950-962")
|
||||
parser.add_argument("--token", help="Gitea token (defaults to GITEA_TOKEN or ~/.config/gitea/token)")
|
||||
parser.add_argument("--output", help="Write markdown packet to this path instead of stdout")
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
token = _resolve_token(args.token)
|
||||
epic_issue = fetch_issue(args.base_url, args.owner, args.repo, args.epic_number, token)
|
||||
child_issue_dicts = collect_child_issues(args.base_url, args.owner, args.repo, epic_issue, token, args.children)
|
||||
packet = build_packet_markdown(epic_issue, [parse_child_issue(issue) for issue in child_issue_dicts])
|
||||
|
||||
if args.output:
|
||||
output_path = Path(args.output)
|
||||
output_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
output_path.write_text(packet)
|
||||
else:
|
||||
print(packet, end="")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -1,213 +0,0 @@
|
||||
"""Regression tests: normalize_anthropic_response_v2 vs v1.
|
||||
|
||||
Constructs mock Anthropic responses and asserts that the v2 function
|
||||
(returning NormalizedResponse) produces identical field values to the
|
||||
original v1 function (returning SimpleNamespace + finish_reason).
|
||||
"""
|
||||
|
||||
from types import SimpleNamespace
|
||||
|
||||
import pytest
|
||||
|
||||
from agent.anthropic_adapter import (
|
||||
normalize_anthropic_response,
|
||||
normalize_anthropic_response_v2,
|
||||
)
|
||||
from agent.transports.types import NormalizedResponse
|
||||
|
||||
|
||||
def _text_block(text: str):
|
||||
return SimpleNamespace(type="text", text=text)
|
||||
|
||||
|
||||
def _thinking_block(thinking: str, signature: str = "sig_abc"):
|
||||
return SimpleNamespace(type="thinking", thinking=thinking, signature=signature)
|
||||
|
||||
|
||||
def _tool_use_block(id: str, name: str, input: dict):
|
||||
return SimpleNamespace(type="tool_use", id=id, name=name, input=input)
|
||||
|
||||
|
||||
def _response(content_blocks, stop_reason="end_turn"):
|
||||
return SimpleNamespace(
|
||||
content=content_blocks,
|
||||
stop_reason=stop_reason,
|
||||
usage=SimpleNamespace(input_tokens=10, output_tokens=5),
|
||||
)
|
||||
|
||||
|
||||
class TestTextOnly:
|
||||
def setup_method(self):
|
||||
self.resp = _response([_text_block("Hello world")])
|
||||
self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
|
||||
self.v2 = normalize_anthropic_response_v2(self.resp)
|
||||
|
||||
def test_type(self):
|
||||
assert isinstance(self.v2, NormalizedResponse)
|
||||
|
||||
def test_content_matches(self):
|
||||
assert self.v2.content == self.v1_msg.content
|
||||
|
||||
def test_finish_reason_matches(self):
|
||||
assert self.v2.finish_reason == self.v1_finish
|
||||
|
||||
def test_no_tool_calls(self):
|
||||
assert self.v2.tool_calls is None
|
||||
assert self.v1_msg.tool_calls is None
|
||||
|
||||
def test_no_reasoning(self):
|
||||
assert self.v2.reasoning is None
|
||||
assert self.v1_msg.reasoning is None
|
||||
|
||||
|
||||
class TestWithToolCalls:
|
||||
def setup_method(self):
|
||||
self.resp = _response(
|
||||
[
|
||||
_text_block("I'll check that"),
|
||||
_tool_use_block("toolu_abc", "terminal", {"command": "ls"}),
|
||||
_tool_use_block("toolu_def", "read_file", {"path": "/tmp"}),
|
||||
],
|
||||
stop_reason="tool_use",
|
||||
)
|
||||
self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
|
||||
self.v2 = normalize_anthropic_response_v2(self.resp)
|
||||
|
||||
def test_finish_reason(self):
|
||||
assert self.v2.finish_reason == "tool_calls"
|
||||
assert self.v1_finish == "tool_calls"
|
||||
|
||||
def test_tool_call_count(self):
|
||||
assert len(self.v2.tool_calls) == 2
|
||||
assert len(self.v1_msg.tool_calls) == 2
|
||||
|
||||
def test_tool_call_ids_match(self):
|
||||
for i in range(2):
|
||||
assert self.v2.tool_calls[i].id == self.v1_msg.tool_calls[i].id
|
||||
|
||||
def test_tool_call_names_match(self):
|
||||
assert self.v2.tool_calls[0].name == "terminal"
|
||||
assert self.v2.tool_calls[1].name == "read_file"
|
||||
for i in range(2):
|
||||
assert self.v2.tool_calls[i].name == self.v1_msg.tool_calls[i].function.name
|
||||
|
||||
def test_tool_call_arguments_match(self):
|
||||
for i in range(2):
|
||||
assert self.v2.tool_calls[i].arguments == self.v1_msg.tool_calls[i].function.arguments
|
||||
|
||||
def test_content_preserved(self):
|
||||
assert self.v2.content == self.v1_msg.content
|
||||
assert "check that" in self.v2.content
|
||||
|
||||
|
||||
class TestWithThinking:
|
||||
def setup_method(self):
|
||||
self.resp = _response([
|
||||
_thinking_block("Let me think about this carefully..."),
|
||||
_text_block("The answer is 42."),
|
||||
])
|
||||
self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
|
||||
self.v2 = normalize_anthropic_response_v2(self.resp)
|
||||
|
||||
def test_reasoning_matches(self):
|
||||
assert self.v2.reasoning == self.v1_msg.reasoning
|
||||
assert "think about this" in self.v2.reasoning
|
||||
|
||||
def test_reasoning_details_in_provider_data(self):
|
||||
v1_details = self.v1_msg.reasoning_details
|
||||
v2_details = self.v2.provider_data.get("reasoning_details") if self.v2.provider_data else None
|
||||
assert v1_details is not None
|
||||
assert v2_details is not None
|
||||
assert len(v2_details) == len(v1_details)
|
||||
|
||||
def test_content_excludes_thinking(self):
|
||||
assert self.v2.content == "The answer is 42."
|
||||
|
||||
|
||||
class TestMixed:
|
||||
def setup_method(self):
|
||||
self.resp = _response(
|
||||
[
|
||||
_thinking_block("Planning my approach..."),
|
||||
_text_block("I'll run the command"),
|
||||
_tool_use_block("toolu_xyz", "terminal", {"command": "pwd"}),
|
||||
],
|
||||
stop_reason="tool_use",
|
||||
)
|
||||
self.v1_msg, self.v1_finish = normalize_anthropic_response(self.resp)
|
||||
self.v2 = normalize_anthropic_response_v2(self.resp)
|
||||
|
||||
def test_all_fields_present(self):
|
||||
assert self.v2.content is not None
|
||||
assert self.v2.tool_calls is not None
|
||||
assert self.v2.reasoning is not None
|
||||
assert self.v2.finish_reason == "tool_calls"
|
||||
|
||||
def test_content_matches(self):
|
||||
assert self.v2.content == self.v1_msg.content
|
||||
|
||||
def test_reasoning_matches(self):
|
||||
assert self.v2.reasoning == self.v1_msg.reasoning
|
||||
|
||||
def test_tool_call_matches(self):
|
||||
assert self.v2.tool_calls[0].id == self.v1_msg.tool_calls[0].id
|
||||
assert self.v2.tool_calls[0].name == self.v1_msg.tool_calls[0].function.name
|
||||
|
||||
|
||||
class TestStopReasons:
|
||||
@pytest.mark.parametrize("stop_reason,expected", [
|
||||
("end_turn", "stop"),
|
||||
("tool_use", "tool_calls"),
|
||||
("max_tokens", "length"),
|
||||
("stop_sequence", "stop"),
|
||||
("refusal", "content_filter"),
|
||||
("model_context_window_exceeded", "length"),
|
||||
("unknown_future_reason", "stop"),
|
||||
])
|
||||
def test_stop_reason_mapping(self, stop_reason, expected):
|
||||
resp = _response([_text_block("x")], stop_reason=stop_reason)
|
||||
_v1_msg, v1_finish = normalize_anthropic_response(resp)
|
||||
v2 = normalize_anthropic_response_v2(resp)
|
||||
assert v2.finish_reason == v1_finish == expected
|
||||
|
||||
|
||||
class TestStripToolPrefix:
|
||||
def test_prefix_stripped(self):
|
||||
resp = _response(
|
||||
[_tool_use_block("toolu_1", "mcp_terminal", {"cmd": "ls"})],
|
||||
stop_reason="tool_use",
|
||||
)
|
||||
v1_msg, _ = normalize_anthropic_response(resp, strip_tool_prefix=True)
|
||||
v2 = normalize_anthropic_response_v2(resp, strip_tool_prefix=True)
|
||||
assert v1_msg.tool_calls[0].function.name == "terminal"
|
||||
assert v2.tool_calls[0].name == "terminal"
|
||||
|
||||
def test_prefix_kept(self):
|
||||
resp = _response(
|
||||
[_tool_use_block("toolu_1", "mcp_terminal", {"cmd": "ls"})],
|
||||
stop_reason="tool_use",
|
||||
)
|
||||
v1_msg, _ = normalize_anthropic_response(resp, strip_tool_prefix=False)
|
||||
v2 = normalize_anthropic_response_v2(resp, strip_tool_prefix=False)
|
||||
assert v1_msg.tool_calls[0].function.name == "mcp_terminal"
|
||||
assert v2.tool_calls[0].name == "mcp_terminal"
|
||||
|
||||
|
||||
class TestEdgeCases:
|
||||
def test_empty_content_blocks(self):
|
||||
resp = _response([])
|
||||
v1_msg, _v1_finish = normalize_anthropic_response(resp)
|
||||
v2 = normalize_anthropic_response_v2(resp)
|
||||
assert v2.content == v1_msg.content
|
||||
assert v2.content is None
|
||||
|
||||
def test_no_reasoning_details_means_none_provider_data(self):
|
||||
resp = _response([_text_block("hi")])
|
||||
v2 = normalize_anthropic_response_v2(resp)
|
||||
assert v2.provider_data is None
|
||||
|
||||
def test_v2_returns_dataclass_not_namespace(self):
|
||||
resp = _response([_text_block("hi")])
|
||||
v2 = normalize_anthropic_response_v2(resp)
|
||||
assert isinstance(v2, NormalizedResponse)
|
||||
assert not isinstance(v2, SimpleNamespace)
|
||||
@@ -1,208 +0,0 @@
|
||||
"""Tests for the transport ABC, registry, and AnthropicTransport."""
|
||||
|
||||
from types import SimpleNamespace
|
||||
|
||||
import pytest
|
||||
|
||||
from agent.transports import _REGISTRY, get_transport, register_transport
|
||||
from agent.transports.base import ProviderTransport
|
||||
from agent.transports.types import NormalizedResponse
|
||||
|
||||
|
||||
class TestProviderTransportABC:
|
||||
def test_cannot_instantiate_abc(self):
|
||||
with pytest.raises(TypeError):
|
||||
ProviderTransport()
|
||||
|
||||
def test_concrete_must_implement_all_abstract(self):
|
||||
class Incomplete(ProviderTransport):
|
||||
@property
|
||||
def api_mode(self):
|
||||
return "test"
|
||||
|
||||
with pytest.raises(TypeError):
|
||||
Incomplete()
|
||||
|
||||
def test_minimal_concrete(self):
|
||||
class Minimal(ProviderTransport):
|
||||
@property
|
||||
def api_mode(self):
|
||||
return "test_minimal"
|
||||
|
||||
def convert_messages(self, messages, **kw):
|
||||
return messages
|
||||
|
||||
def convert_tools(self, tools):
|
||||
return tools
|
||||
|
||||
def build_kwargs(self, model, messages, tools=None, **params):
|
||||
return {"model": model, "messages": messages}
|
||||
|
||||
def normalize_response(self, response, **kw):
|
||||
return NormalizedResponse(content="ok", tool_calls=None, finish_reason="stop")
|
||||
|
||||
t = Minimal()
|
||||
assert t.api_mode == "test_minimal"
|
||||
assert t.validate_response(None) is True
|
||||
assert t.extract_cache_stats(None) is None
|
||||
assert t.map_finish_reason("end_turn") == "end_turn"
|
||||
|
||||
|
||||
class TestTransportRegistry:
|
||||
def test_get_unregistered_returns_none(self):
|
||||
assert get_transport("nonexistent_mode") is None
|
||||
|
||||
def test_anthropic_registered_on_import(self):
|
||||
import agent.transports.anthropic # noqa: F401
|
||||
|
||||
t = get_transport("anthropic_messages")
|
||||
assert t is not None
|
||||
assert t.api_mode == "anthropic_messages"
|
||||
|
||||
def test_register_and_get(self):
|
||||
class DummyTransport(ProviderTransport):
|
||||
@property
|
||||
def api_mode(self):
|
||||
return "dummy_test"
|
||||
|
||||
def convert_messages(self, messages, **kw):
|
||||
return messages
|
||||
|
||||
def convert_tools(self, tools):
|
||||
return tools
|
||||
|
||||
def build_kwargs(self, model, messages, tools=None, **params):
|
||||
return {}
|
||||
|
||||
def normalize_response(self, response, **kw):
|
||||
return NormalizedResponse(content=None, tool_calls=None, finish_reason="stop")
|
||||
|
||||
register_transport("dummy_test", DummyTransport)
|
||||
t = get_transport("dummy_test")
|
||||
assert t.api_mode == "dummy_test"
|
||||
_REGISTRY.pop("dummy_test", None)
|
||||
|
||||
|
||||
class TestAnthropicTransport:
|
||||
@pytest.fixture
|
||||
def transport(self):
|
||||
import agent.transports.anthropic # noqa: F401
|
||||
|
||||
return get_transport("anthropic_messages")
|
||||
|
||||
def test_api_mode(self, transport):
|
||||
assert transport.api_mode == "anthropic_messages"
|
||||
|
||||
def test_convert_tools_simple(self, transport):
|
||||
tools = [{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "test_tool",
|
||||
"description": "A test",
|
||||
"parameters": {"type": "object", "properties": {}},
|
||||
},
|
||||
}]
|
||||
result = transport.convert_tools(tools)
|
||||
assert len(result) == 1
|
||||
assert result[0]["name"] == "test_tool"
|
||||
assert "input_schema" in result[0]
|
||||
|
||||
def test_validate_response_none(self, transport):
|
||||
assert transport.validate_response(None) is False
|
||||
|
||||
def test_validate_response_empty_content(self, transport):
|
||||
r = SimpleNamespace(content=[])
|
||||
assert transport.validate_response(r) is False
|
||||
|
||||
def test_validate_response_valid(self, transport):
|
||||
r = SimpleNamespace(content=[SimpleNamespace(type="text", text="hello")])
|
||||
assert transport.validate_response(r) is True
|
||||
|
||||
def test_map_finish_reason(self, transport):
|
||||
assert transport.map_finish_reason("end_turn") == "stop"
|
||||
assert transport.map_finish_reason("tool_use") == "tool_calls"
|
||||
assert transport.map_finish_reason("max_tokens") == "length"
|
||||
assert transport.map_finish_reason("stop_sequence") == "stop"
|
||||
assert transport.map_finish_reason("refusal") == "content_filter"
|
||||
assert transport.map_finish_reason("model_context_window_exceeded") == "length"
|
||||
assert transport.map_finish_reason("unknown") == "stop"
|
||||
|
||||
def test_extract_cache_stats_none_usage(self, transport):
|
||||
r = SimpleNamespace(usage=None)
|
||||
assert transport.extract_cache_stats(r) is None
|
||||
|
||||
def test_extract_cache_stats_with_cache(self, transport):
|
||||
usage = SimpleNamespace(cache_read_input_tokens=100, cache_creation_input_tokens=50)
|
||||
r = SimpleNamespace(usage=usage)
|
||||
result = transport.extract_cache_stats(r)
|
||||
assert result == {"cached_tokens": 100, "creation_tokens": 50}
|
||||
|
||||
def test_extract_cache_stats_zero(self, transport):
|
||||
usage = SimpleNamespace(cache_read_input_tokens=0, cache_creation_input_tokens=0)
|
||||
r = SimpleNamespace(usage=usage)
|
||||
assert transport.extract_cache_stats(r) is None
|
||||
|
||||
def test_normalize_response_text(self, transport):
|
||||
r = SimpleNamespace(
|
||||
content=[SimpleNamespace(type="text", text="Hello world")],
|
||||
stop_reason="end_turn",
|
||||
usage=SimpleNamespace(input_tokens=10, output_tokens=5),
|
||||
model="claude-sonnet-4-6",
|
||||
)
|
||||
nr = transport.normalize_response(r)
|
||||
assert isinstance(nr, NormalizedResponse)
|
||||
assert nr.content == "Hello world"
|
||||
assert nr.tool_calls is None or nr.tool_calls == []
|
||||
assert nr.finish_reason == "stop"
|
||||
|
||||
def test_normalize_response_tool_calls(self, transport):
|
||||
r = SimpleNamespace(
|
||||
content=[
|
||||
SimpleNamespace(type="tool_use", id="toolu_123", name="terminal", input={"command": "ls"}),
|
||||
],
|
||||
stop_reason="tool_use",
|
||||
usage=SimpleNamespace(input_tokens=10, output_tokens=20),
|
||||
model="claude-sonnet-4-6",
|
||||
)
|
||||
nr = transport.normalize_response(r)
|
||||
assert nr.finish_reason == "tool_calls"
|
||||
assert len(nr.tool_calls) == 1
|
||||
tc = nr.tool_calls[0]
|
||||
assert tc.name == "terminal"
|
||||
assert tc.id == "toolu_123"
|
||||
assert '"command"' in tc.arguments
|
||||
|
||||
def test_normalize_response_thinking(self, transport):
|
||||
r = SimpleNamespace(
|
||||
content=[
|
||||
SimpleNamespace(type="thinking", thinking="Let me think..."),
|
||||
SimpleNamespace(type="text", text="The answer is 42"),
|
||||
],
|
||||
stop_reason="end_turn",
|
||||
usage=SimpleNamespace(input_tokens=10, output_tokens=15),
|
||||
model="claude-sonnet-4-6",
|
||||
)
|
||||
nr = transport.normalize_response(r)
|
||||
assert nr.content == "The answer is 42"
|
||||
assert nr.reasoning == "Let me think..."
|
||||
|
||||
def test_build_kwargs_returns_dict(self, transport):
|
||||
messages = [{"role": "user", "content": "Hello"}]
|
||||
kw = transport.build_kwargs(
|
||||
model="claude-sonnet-4-6",
|
||||
messages=messages,
|
||||
max_tokens=1024,
|
||||
)
|
||||
assert isinstance(kw, dict)
|
||||
assert "model" in kw
|
||||
assert "max_tokens" in kw
|
||||
assert "messages" in kw
|
||||
|
||||
def test_convert_messages_extracts_system(self, transport):
|
||||
messages = [
|
||||
{"role": "system", "content": "You are helpful."},
|
||||
{"role": "user", "content": "Hi"},
|
||||
]
|
||||
system, msgs = transport.convert_messages(messages)
|
||||
assert system is not None
|
||||
assert len(msgs) >= 1
|
||||
@@ -1,130 +0,0 @@
|
||||
"""Tests for agent/transports/types.py — dataclass construction + helpers."""
|
||||
|
||||
import json
|
||||
|
||||
from agent.transports.types import (
|
||||
NormalizedResponse,
|
||||
ToolCall,
|
||||
Usage,
|
||||
build_tool_call,
|
||||
map_finish_reason,
|
||||
)
|
||||
|
||||
|
||||
class TestToolCall:
|
||||
def test_basic_construction(self):
|
||||
tc = ToolCall(id="call_abc", name="terminal", arguments='{"cmd": "ls"}')
|
||||
assert tc.id == "call_abc"
|
||||
assert tc.name == "terminal"
|
||||
assert tc.arguments == '{"cmd": "ls"}'
|
||||
assert tc.provider_data is None
|
||||
|
||||
def test_none_id(self):
|
||||
tc = ToolCall(id=None, name="read_file", arguments="{}")
|
||||
assert tc.id is None
|
||||
|
||||
def test_provider_data(self):
|
||||
tc = ToolCall(
|
||||
id="call_x",
|
||||
name="t",
|
||||
arguments="{}",
|
||||
provider_data={"call_id": "call_x", "response_item_id": "fc_x"},
|
||||
)
|
||||
assert tc.provider_data["call_id"] == "call_x"
|
||||
assert tc.provider_data["response_item_id"] == "fc_x"
|
||||
|
||||
|
||||
class TestUsage:
|
||||
def test_defaults(self):
|
||||
u = Usage()
|
||||
assert u.prompt_tokens == 0
|
||||
assert u.completion_tokens == 0
|
||||
assert u.total_tokens == 0
|
||||
assert u.cached_tokens == 0
|
||||
|
||||
def test_explicit(self):
|
||||
u = Usage(prompt_tokens=100, completion_tokens=50, total_tokens=150, cached_tokens=80)
|
||||
assert u.total_tokens == 150
|
||||
|
||||
|
||||
class TestNormalizedResponse:
|
||||
def test_text_only(self):
|
||||
r = NormalizedResponse(content="hello", tool_calls=None, finish_reason="stop")
|
||||
assert r.content == "hello"
|
||||
assert r.tool_calls is None
|
||||
assert r.finish_reason == "stop"
|
||||
assert r.reasoning is None
|
||||
assert r.usage is None
|
||||
assert r.provider_data is None
|
||||
|
||||
def test_with_tool_calls(self):
|
||||
tcs = [ToolCall(id="call_1", name="terminal", arguments='{"cmd":"pwd"}')]
|
||||
r = NormalizedResponse(content=None, tool_calls=tcs, finish_reason="tool_calls")
|
||||
assert r.finish_reason == "tool_calls"
|
||||
assert len(r.tool_calls) == 1
|
||||
assert r.tool_calls[0].name == "terminal"
|
||||
|
||||
def test_with_reasoning(self):
|
||||
r = NormalizedResponse(
|
||||
content="answer",
|
||||
tool_calls=None,
|
||||
finish_reason="stop",
|
||||
reasoning="I thought about it",
|
||||
)
|
||||
assert r.reasoning == "I thought about it"
|
||||
|
||||
def test_with_provider_data(self):
|
||||
r = NormalizedResponse(
|
||||
content=None,
|
||||
tool_calls=None,
|
||||
finish_reason="stop",
|
||||
provider_data={"reasoning_details": [{"type": "thinking", "thinking": "hmm"}]},
|
||||
)
|
||||
assert r.provider_data["reasoning_details"][0]["type"] == "thinking"
|
||||
|
||||
|
||||
class TestBuildToolCall:
|
||||
def test_dict_arguments_serialized(self):
|
||||
tc = build_tool_call(id="call_1", name="terminal", arguments={"cmd": "ls"})
|
||||
assert tc.arguments == json.dumps({"cmd": "ls"})
|
||||
assert tc.provider_data is None
|
||||
|
||||
def test_string_arguments_passthrough(self):
|
||||
tc = build_tool_call(id="call_2", name="read_file", arguments='{"path": "/tmp"}')
|
||||
assert tc.arguments == '{"path": "/tmp"}'
|
||||
|
||||
def test_provider_fields(self):
|
||||
tc = build_tool_call(
|
||||
id="call_3",
|
||||
name="terminal",
|
||||
arguments="{}",
|
||||
call_id="call_3",
|
||||
response_item_id="fc_3",
|
||||
)
|
||||
assert tc.provider_data == {"call_id": "call_3", "response_item_id": "fc_3"}
|
||||
|
||||
def test_none_id(self):
|
||||
tc = build_tool_call(id=None, name="t", arguments="{}")
|
||||
assert tc.id is None
|
||||
|
||||
|
||||
class TestMapFinishReason:
|
||||
ANTHROPIC_MAP = {
|
||||
"end_turn": "stop",
|
||||
"tool_use": "tool_calls",
|
||||
"max_tokens": "length",
|
||||
"stop_sequence": "stop",
|
||||
"refusal": "content_filter",
|
||||
}
|
||||
|
||||
def test_known_reason(self):
|
||||
assert map_finish_reason("end_turn", self.ANTHROPIC_MAP) == "stop"
|
||||
assert map_finish_reason("tool_use", self.ANTHROPIC_MAP) == "tool_calls"
|
||||
assert map_finish_reason("max_tokens", self.ANTHROPIC_MAP) == "length"
|
||||
assert map_finish_reason("refusal", self.ANTHROPIC_MAP) == "content_filter"
|
||||
|
||||
def test_unknown_reason_defaults_to_stop(self):
|
||||
assert map_finish_reason("something_new", self.ANTHROPIC_MAP) == "stop"
|
||||
|
||||
def test_none_reason(self):
|
||||
assert map_finish_reason(None, self.ANTHROPIC_MAP) == "stop"
|
||||
162
tests/test_morning_review_packet.py
Normal file
162
tests/test_morning_review_packet.py
Normal file
@@ -0,0 +1,162 @@
|
||||
from pathlib import Path
|
||||
import sys
|
||||
|
||||
SCRIPT_DIR = Path(__file__).resolve().parents[1] / "scripts"
|
||||
sys.path.insert(0, str(SCRIPT_DIR))
|
||||
|
||||
import morning_review_packet as mrp
|
||||
|
||||
|
||||
EPIC_BODY = """Source: git log on upstream/main since 2026-04-21 00:00 EDT.
|
||||
|
||||
## Success criteria
|
||||
- [ ] Every issue has a clear PASS / FAIL outcome.
|
||||
|
||||
## Sub-issues
|
||||
- [ ] #950 [QA] Verify AI Gateway provider UX + attribution headers
|
||||
- [ ] #951 [QA] Verify transport abstraction + AnthropicTransport wiring
|
||||
- [x] #962 [QA] Verify hardcoded-home path guard on burn/921 branch
|
||||
"""
|
||||
|
||||
|
||||
CHILD_BODY_PLURAL = """## Parent
|
||||
#949
|
||||
|
||||
## Branch / checkout
|
||||
- Validate on `upstream/main` or an equivalent synced checkout.
|
||||
|
||||
## Commits landed today
|
||||
- `b11753879` attribution default_headers for ai-gateway provider
|
||||
- `700437440` curated picker with live pricing
|
||||
|
||||
## Targeted tests
|
||||
- `tests/hermes_cli/test_ai_gateway_models.py`
|
||||
- `tests/run_agent/test_provider_attribution_headers.py`
|
||||
|
||||
## Tasks
|
||||
- [ ] Verify the picker ordering.
|
||||
- [ ] Verify attribution headers.
|
||||
|
||||
## Acceptance Criteria
|
||||
- [ ] Picker shows AI Gateway prominently.
|
||||
- [ ] Headers appear on OpenRouter calls.
|
||||
"""
|
||||
|
||||
|
||||
CHILD_BODY_SINGULAR = """## Parent
|
||||
#949
|
||||
|
||||
## Branch / checkout
|
||||
- Validate on `upstream/main` or an equivalent synced checkout.
|
||||
|
||||
## Commit landed today
|
||||
- `fc21c1420` add buttons to update Hermes and restart gateway
|
||||
|
||||
## Files touched
|
||||
- `web/src/pages/StatusPage.tsx`
|
||||
- `web/src/lib/api.ts`
|
||||
- `web/src/i18n/en.ts`
|
||||
|
||||
## Tasks
|
||||
- [ ] Open the Web UI status page and verify both buttons are present.
|
||||
- [ ] Click Restart Gateway in a safe environment.
|
||||
"""
|
||||
|
||||
|
||||
def test_discover_child_issue_numbers_from_epic_body():
|
||||
assert mrp.discover_child_issue_numbers(EPIC_BODY) == [950, 951, 962]
|
||||
|
||||
|
||||
def test_parse_issue_number_spec_supports_ranges_and_lists():
|
||||
assert mrp.parse_issue_number_spec("950-952,955,962") == [950, 951, 952, 955, 962]
|
||||
|
||||
|
||||
def test_parse_child_issue_extracts_structured_sections():
|
||||
issue = {
|
||||
"number": 950,
|
||||
"title": "[QA] Verify AI Gateway provider UX + attribution headers",
|
||||
"state": "open",
|
||||
"html_url": "https://forge.example/950",
|
||||
"comments": 0,
|
||||
"body": CHILD_BODY_PLURAL,
|
||||
}
|
||||
|
||||
parsed = mrp.parse_child_issue(issue)
|
||||
|
||||
assert parsed.number == 950
|
||||
assert parsed.parent_issue == 949
|
||||
assert parsed.checkout_notes == ["Validate on `upstream/main` or an equivalent synced checkout."]
|
||||
assert [c.sha for c in parsed.commits] == ["b11753879", "700437440"]
|
||||
assert parsed.targeted_tests == [
|
||||
"tests/hermes_cli/test_ai_gateway_models.py",
|
||||
"tests/run_agent/test_provider_attribution_headers.py",
|
||||
]
|
||||
assert parsed.tasks == [
|
||||
"Verify the picker ordering.",
|
||||
"Verify attribution headers.",
|
||||
]
|
||||
assert parsed.acceptance_criteria == [
|
||||
"Picker shows AI Gateway prominently.",
|
||||
"Headers appear on OpenRouter calls.",
|
||||
]
|
||||
|
||||
|
||||
def test_parse_child_issue_handles_singular_commit_heading_and_files_touched():
|
||||
issue = {
|
||||
"number": 961,
|
||||
"title": "[QA] Verify web dashboard update/restart action buttons",
|
||||
"state": "closed",
|
||||
"html_url": "https://forge.example/961",
|
||||
"comments": 16,
|
||||
"body": CHILD_BODY_SINGULAR,
|
||||
}
|
||||
|
||||
parsed = mrp.parse_child_issue(issue)
|
||||
|
||||
assert [c.sha for c in parsed.commits] == ["fc21c1420"]
|
||||
assert parsed.files_touched == [
|
||||
"web/src/pages/StatusPage.tsx",
|
||||
"web/src/lib/api.ts",
|
||||
"web/src/i18n/en.ts",
|
||||
]
|
||||
assert parsed.tasks == [
|
||||
"Open the Web UI status page and verify both buttons are present.",
|
||||
"Click Restart Gateway in a safe environment.",
|
||||
]
|
||||
|
||||
|
||||
def test_build_packet_markdown_renders_summary_and_details():
|
||||
epic_issue = {
|
||||
"number": 949,
|
||||
"title": "EPIC: Morning review packet — Hermes harness features landed 2026-04-21",
|
||||
"state": "open",
|
||||
"html_url": "https://forge.example/949",
|
||||
"body": EPIC_BODY,
|
||||
}
|
||||
child_a = mrp.parse_child_issue({
|
||||
"number": 950,
|
||||
"title": "[QA] Verify AI Gateway provider UX + attribution headers",
|
||||
"state": "open",
|
||||
"html_url": "https://forge.example/950",
|
||||
"comments": 0,
|
||||
"body": CHILD_BODY_PLURAL,
|
||||
})
|
||||
child_b = mrp.parse_child_issue({
|
||||
"number": 961,
|
||||
"title": "[QA] Verify web dashboard update/restart action buttons",
|
||||
"state": "closed",
|
||||
"html_url": "https://forge.example/961",
|
||||
"comments": 16,
|
||||
"body": CHILD_BODY_SINGULAR,
|
||||
})
|
||||
|
||||
markdown = mrp.build_packet_markdown(epic_issue, [child_a, child_b])
|
||||
|
||||
assert "# Morning Review Packet" in markdown
|
||||
assert "EPIC: Morning review packet — Hermes harness features landed 2026-04-21" in markdown
|
||||
assert "| #950 | open | 2 | 2 |" in markdown
|
||||
assert "| #961 | closed | 1 | 0 |" in markdown
|
||||
assert "## #950 — [QA] Verify AI Gateway provider UX + attribution headers" in markdown
|
||||
assert "## #961 — [QA] Verify web dashboard update/restart action buttons" in markdown
|
||||
assert "`b11753879` — attribution default_headers for ai-gateway provider" in markdown
|
||||
assert "`web/src/pages/StatusPage.tsx`" in markdown
|
||||
Reference in New Issue
Block a user