Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
1bb48c91e7 |
@@ -1,69 +0,0 @@
|
||||
"""First-class context snapshot artifacts for live runtime memory evaluation."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import re
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from hermes_constants import get_hermes_home
|
||||
|
||||
|
||||
_SAFE_SEGMENT_RE = re.compile(r"[^A-Za-z0-9_.-]+")
|
||||
|
||||
|
||||
class ContextSnapshotRecorder:
|
||||
"""Write per-call prompt-composition artifacts for a Hermes session."""
|
||||
|
||||
def __init__(self, session_id: str, *, enabled: bool = False, base_dir: str | Path | None = None):
|
||||
self.session_id = session_id or "session"
|
||||
self.enabled = bool(enabled)
|
||||
self.base_dir = Path(base_dir) if base_dir else get_hermes_home() / "reports" / "context_snapshots"
|
||||
|
||||
@property
|
||||
def session_dir(self) -> Path:
|
||||
safe_session = _SAFE_SEGMENT_RE.sub("_", self.session_id).strip("._") or "session"
|
||||
return self.base_dir / safe_session
|
||||
|
||||
def record_call(
|
||||
self,
|
||||
api_call_count: int,
|
||||
*,
|
||||
system_prompt: str,
|
||||
memory_provider_system_prompt: str = "",
|
||||
memory_prefetch_raw: str = "",
|
||||
memory_context_block: str = "",
|
||||
api_user_message: str = "",
|
||||
api_messages: list[dict[str, Any]] | None = None,
|
||||
metadata: dict[str, Any] | None = None,
|
||||
) -> Path | None:
|
||||
if not self.enabled:
|
||||
return None
|
||||
|
||||
call_dir = self.session_dir / f"call_{api_call_count:03d}"
|
||||
call_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
self._write_text(call_dir / "system_prompt.txt", system_prompt or "")
|
||||
self._write_text(call_dir / "memory_provider_system_prompt.txt", memory_provider_system_prompt or "")
|
||||
self._write_text(call_dir / "memory_prefetch_raw.txt", memory_prefetch_raw or "")
|
||||
self._write_text(call_dir / "memory_context_block.txt", memory_context_block or "")
|
||||
self._write_text(call_dir / "api_user_message.txt", api_user_message or "")
|
||||
self._write_json(call_dir / "api_messages.json", api_messages or [])
|
||||
self._write_json(
|
||||
call_dir / "metadata.json",
|
||||
{
|
||||
"session_id": self.session_id,
|
||||
"api_call_count": api_call_count,
|
||||
**(metadata or {}),
|
||||
},
|
||||
)
|
||||
return call_dir
|
||||
|
||||
@staticmethod
|
||||
def _write_text(path: Path, content: str) -> None:
|
||||
path.write_text(content, encoding="utf-8")
|
||||
|
||||
@staticmethod
|
||||
def _write_json(path: Path, payload: Any) -> None:
|
||||
path.write_text(json.dumps(payload, indent=2, ensure_ascii=False), encoding="utf-8")
|
||||
@@ -1,132 +0,0 @@
|
||||
# Hindsight local eval homes for live Hermes runtime testing
|
||||
|
||||
Issue: #1010
|
||||
Parent: #985
|
||||
|
||||
This document defines a reproducible, profile-scoped evaluation layout for baseline / MemPalace / Hindsight comparisons without requiring Hindsight Cloud.
|
||||
|
||||
## Eval home layout
|
||||
|
||||
Use three separate `HERMES_HOME` directories so each run has isolated config, memory, sessions, and artifacts.
|
||||
|
||||
```text
|
||||
~/.hermes/profiles/atlas-baseline/
|
||||
config.yaml
|
||||
.env
|
||||
MEMORY.md
|
||||
USER.md
|
||||
reports/context_snapshots/
|
||||
|
||||
~/.hermes/profiles/atlas-mempalace/
|
||||
config.yaml
|
||||
.env
|
||||
MEMORY.md
|
||||
USER.md
|
||||
reports/context_snapshots/
|
||||
plugins/ # if a local MemPalace plugin is installed for this eval lane
|
||||
|
||||
~/.hermes/profiles/atlas-hindsight/
|
||||
config.yaml
|
||||
.env
|
||||
MEMORY.md
|
||||
USER.md
|
||||
hindsight/config.json
|
||||
reports/context_snapshots/
|
||||
```
|
||||
|
||||
## Hindsight local config
|
||||
|
||||
The Hindsight provider already loads config from `$HERMES_HOME/hindsight/config.json` first. For the local eval lane, prefer `local_embedded` so Hermes can bring up a local Hindsight daemon without cloud signup.
|
||||
|
||||
Example `~/.hermes/profiles/atlas-hindsight/hindsight/config.json`:
|
||||
|
||||
```json
|
||||
{
|
||||
"mode": "local_embedded",
|
||||
"memory_mode": "context",
|
||||
"recall_prefetch_method": "recall",
|
||||
"llm_provider": "ollama",
|
||||
"llm_model": "gemma3:12b",
|
||||
"api_url": "http://localhost:8888"
|
||||
}
|
||||
```
|
||||
|
||||
Notes:
|
||||
- `local_embedded` avoids any Hindsight Cloud dependency.
|
||||
- If `profile` is omitted, Hermes now derives a stable local Hindsight profile name from the active profile identity / `HERMES_HOME` instead of collapsing all local runs into the shared legacy `hermes` profile.
|
||||
- `local_external` remains valid if you already run a local Hindsight server yourself.
|
||||
|
||||
## Runtime switching procedure
|
||||
|
||||
Switch by exporting `HERMES_HOME` before launching Hermes.
|
||||
|
||||
### 1. Baseline
|
||||
|
||||
```bash
|
||||
export HERMES_HOME="$HOME/.hermes/profiles/atlas-baseline"
|
||||
unset HERMES_CONTEXT_SNAPSHOTS
|
||||
hermes chat
|
||||
```
|
||||
|
||||
### 2. MemPalace lane
|
||||
|
||||
```bash
|
||||
export HERMES_HOME="$HOME/.hermes/profiles/atlas-mempalace"
|
||||
export HERMES_CONTEXT_SNAPSHOTS=1
|
||||
hermes chat
|
||||
```
|
||||
|
||||
### 3. Hindsight lane
|
||||
|
||||
```bash
|
||||
export HERMES_HOME="$HOME/.hermes/profiles/atlas-hindsight"
|
||||
export HERMES_CONTEXT_SNAPSHOTS=1
|
||||
hermes chat
|
||||
```
|
||||
|
||||
## Raw artifact capture
|
||||
|
||||
When `HERMES_CONTEXT_SNAPSHOTS=1` is enabled, Hermes writes first-class prompt-composition artifacts under the active home by default.
|
||||
|
||||
Artifact tree:
|
||||
|
||||
```text
|
||||
$HERMES_HOME/reports/context_snapshots/<session-id>/call_001/
|
||||
system_prompt.txt
|
||||
memory_provider_system_prompt.txt
|
||||
memory_prefetch_raw.txt
|
||||
memory_context_block.txt
|
||||
api_user_message.txt
|
||||
api_messages.json
|
||||
metadata.json
|
||||
```
|
||||
|
||||
Minimum files a benchmark should inspect:
|
||||
- `system_prompt.txt`
|
||||
- `memory_prefetch_raw.txt`
|
||||
- `memory_context_block.txt`
|
||||
- `api_user_message.txt`
|
||||
- `api_messages.json`
|
||||
|
||||
These prove:
|
||||
- what the system prompt was
|
||||
- what the provider prefetched
|
||||
- what entered `<memory-context>`
|
||||
- what the final API user message looked like
|
||||
- what full payload reached the model
|
||||
|
||||
## Follow-on benchmark workflow
|
||||
|
||||
A benchmark issue can now consume this path without redoing integration work:
|
||||
1. pick one eval home (`atlas-baseline`, `atlas-mempalace`, `atlas-hindsight`)
|
||||
2. export the corresponding `HERMES_HOME`
|
||||
3. run Hermes on the same prompt set
|
||||
4. compare the snapshot artifacts in `reports/context_snapshots/`
|
||||
5. score recall quality and answer quality separately
|
||||
|
||||
## Why this is sovereign
|
||||
|
||||
- no hosted Hindsight Cloud dependency is required
|
||||
- the Hindsight config is profile-scoped under `hindsight/config.json`
|
||||
- the runtime artifacts stay under the active `HERMES_HOME`
|
||||
- switching between baseline / MemPalace / Hindsight is just a `HERMES_HOME` swap
|
||||
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.
|
||||
@@ -178,25 +178,6 @@ def _load_config() -> dict:
|
||||
}
|
||||
|
||||
|
||||
def _derive_local_profile_name(agent_identity: str = "", hermes_home: str = "") -> str:
|
||||
"""Return a stable profile name for local embedded Hindsight storage.
|
||||
|
||||
Prefer the active Hermes profile identity when available, otherwise fall back
|
||||
to the basename of the active HERMES_HOME path. This prevents all local
|
||||
Hindsight eval homes from sharing the legacy default profile name "hermes".
|
||||
"""
|
||||
from pathlib import Path
|
||||
import re
|
||||
|
||||
raw = (agent_identity or "").strip()
|
||||
if not raw and hermes_home:
|
||||
raw = Path(hermes_home).name.strip()
|
||||
if not raw:
|
||||
raw = "hermes"
|
||||
safe = re.sub(r"[^A-Za-z0-9_.-]+", "-", raw).strip(".-_")
|
||||
return safe or "hermes"
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# MemoryProvider implementation
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -487,8 +468,6 @@ class HindsightMemoryProvider(MemoryProvider):
|
||||
|
||||
def initialize(self, session_id: str, **kwargs) -> None:
|
||||
self._session_id = session_id
|
||||
hermes_home = str(kwargs.get("hermes_home") or "")
|
||||
agent_identity = str(kwargs.get("agent_identity") or "")
|
||||
|
||||
# Check client version and auto-upgrade if needed
|
||||
try:
|
||||
@@ -521,11 +500,6 @@ class HindsightMemoryProvider(MemoryProvider):
|
||||
# "local" is a legacy alias for "local_embedded"
|
||||
if self._mode == "local":
|
||||
self._mode = "local_embedded"
|
||||
if self._mode == "local_embedded" and not self._config.get("profile"):
|
||||
self._config["profile"] = _derive_local_profile_name(
|
||||
agent_identity=agent_identity,
|
||||
hermes_home=hermes_home,
|
||||
)
|
||||
self._api_key = self._config.get("apiKey") or self._config.get("api_key") or os.environ.get("HINDSIGHT_API_KEY", "")
|
||||
default_url = _DEFAULT_LOCAL_URL if self._mode in ("local_embedded", "local_external") else _DEFAULT_API_URL
|
||||
self._api_url = self._config.get("api_url") or os.environ.get("HINDSIGHT_API_URL", default_url)
|
||||
|
||||
78
run_agent.py
78
run_agent.py
@@ -604,8 +604,6 @@ class AIAgent:
|
||||
checkpoint_max_snapshots: int = 50,
|
||||
pass_session_id: bool = False,
|
||||
persist_session: bool = True,
|
||||
context_snapshots_enabled: bool | None = None,
|
||||
context_snapshots_dir: str | None = None,
|
||||
):
|
||||
"""
|
||||
Initialize the AI Agent.
|
||||
@@ -1131,43 +1129,6 @@ class AIAgent:
|
||||
except Exception:
|
||||
_agent_cfg = {}
|
||||
|
||||
def _is_enabled(value):
|
||||
if isinstance(value, bool):
|
||||
return value
|
||||
return str(value).strip().lower() in {"1", "true", "yes", "on"}
|
||||
|
||||
_debug_cfg = _agent_cfg.get("debug", {}) if isinstance(_agent_cfg, dict) else {}
|
||||
if not isinstance(_debug_cfg, dict):
|
||||
_debug_cfg = {}
|
||||
_snapshot_cfg = _debug_cfg.get("context_snapshots", {})
|
||||
if not isinstance(_snapshot_cfg, dict):
|
||||
_snapshot_cfg = {}
|
||||
_snapshots_env = os.getenv("HERMES_CONTEXT_SNAPSHOTS")
|
||||
_snapshots_dir_env = os.getenv("HERMES_CONTEXT_SNAPSHOTS_DIR")
|
||||
if context_snapshots_enabled is None:
|
||||
if _snapshots_env is not None:
|
||||
self._context_snapshots_enabled = _is_enabled(_snapshots_env)
|
||||
else:
|
||||
self._context_snapshots_enabled = _is_enabled(_snapshot_cfg.get("enabled", False))
|
||||
else:
|
||||
self._context_snapshots_enabled = bool(context_snapshots_enabled)
|
||||
self._context_snapshots_dir = (
|
||||
context_snapshots_dir
|
||||
or _snapshots_dir_env
|
||||
or _snapshot_cfg.get("dir")
|
||||
or None
|
||||
)
|
||||
try:
|
||||
from agent.context_snapshots import ContextSnapshotRecorder
|
||||
self._context_snapshot_recorder = ContextSnapshotRecorder(
|
||||
session_id=self.session_id,
|
||||
enabled=self._context_snapshots_enabled,
|
||||
base_dir=self._context_snapshots_dir,
|
||||
)
|
||||
except Exception as _snapshot_err:
|
||||
logger.debug("Context snapshot recorder init failed: %s", _snapshot_err)
|
||||
self._context_snapshot_recorder = None
|
||||
|
||||
# Persistent memory (MEMORY.md + USER.md) -- loaded from disk
|
||||
self._memory_store = None
|
||||
self._memory_enabled = False
|
||||
@@ -8183,17 +8144,12 @@ class AIAgent:
|
||||
# Use original_user_message (clean input) — user_message may contain
|
||||
# injected skill content that bloats / breaks provider queries.
|
||||
_ext_prefetch_cache = ""
|
||||
_memory_provider_prompt_cache = ""
|
||||
if self._memory_manager:
|
||||
try:
|
||||
_query = original_user_message if isinstance(original_user_message, str) else ""
|
||||
_ext_prefetch_cache = self._memory_manager.prefetch_all(_query) or ""
|
||||
except Exception:
|
||||
pass
|
||||
try:
|
||||
_memory_provider_prompt_cache = self._memory_manager.build_system_prompt() or ""
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
while (api_call_count < self.max_iterations and self.iteration_budget.remaining > 0) or self._budget_grace_call:
|
||||
# Reset per-turn checkpoint dedup so each iteration can take one snapshot
|
||||
@@ -8261,8 +8217,6 @@ class AIAgent:
|
||||
# However, providers like Moonshot AI require a separate 'reasoning_content' field
|
||||
# on assistant messages with tool_calls. We handle both cases here.
|
||||
api_messages = []
|
||||
_current_api_user_message = ""
|
||||
_current_memory_context_block = ""
|
||||
for idx, msg in enumerate(messages):
|
||||
api_msg = msg.copy()
|
||||
|
||||
@@ -8277,15 +8231,12 @@ class AIAgent:
|
||||
_fenced = build_memory_context_block(_ext_prefetch_cache)
|
||||
if _fenced:
|
||||
_injections.append(_fenced)
|
||||
_current_memory_context_block = _fenced
|
||||
if _plugin_user_context:
|
||||
_injections.append(_plugin_user_context)
|
||||
if _injections:
|
||||
_base = api_msg.get("content", "")
|
||||
if isinstance(_base, str):
|
||||
api_msg["content"] = _base + "\n\n" + "\n\n".join(_injections)
|
||||
if isinstance(api_msg.get("content"), str):
|
||||
_current_api_user_message = api_msg["content"]
|
||||
|
||||
# For ALL assistant messages, pass reasoning back to the API
|
||||
# This ensures multi-turn reasoning context is preserved
|
||||
@@ -8320,13 +8271,7 @@ class AIAgent:
|
||||
from agent.privacy_filter import PrivacyFilter
|
||||
pf = PrivacyFilter()
|
||||
# Sanitize messages before they reach the provider
|
||||
_pf_result = pf.sanitize_messages(api_messages)
|
||||
if isinstance(_pf_result, tuple):
|
||||
api_messages, _pf_report = _pf_result
|
||||
if getattr(pf, "last_report", None) is None:
|
||||
pf.last_report = _pf_report
|
||||
else:
|
||||
api_messages = _pf_result
|
||||
api_messages = pf.sanitize_messages(api_messages)
|
||||
if pf.last_report and pf.last_report.had_redactions:
|
||||
logger.info(f"Privacy Filter: Redacted sensitive data from turn payload. Details: {pf.last_report.summary()}")
|
||||
except Exception as e:
|
||||
@@ -8397,27 +8342,6 @@ class AIAgent:
|
||||
new_tcs.append(tc)
|
||||
am["tool_calls"] = new_tcs
|
||||
|
||||
if self._context_snapshot_recorder:
|
||||
try:
|
||||
self._context_snapshot_recorder.record_call(
|
||||
api_call_count,
|
||||
system_prompt=effective_system,
|
||||
memory_provider_system_prompt=_memory_provider_prompt_cache,
|
||||
memory_prefetch_raw=_ext_prefetch_cache,
|
||||
memory_context_block=_current_memory_context_block,
|
||||
api_user_message=_current_api_user_message,
|
||||
api_messages=api_messages,
|
||||
metadata={
|
||||
"model": self.model,
|
||||
"provider": self.provider,
|
||||
"platform": self.platform or "",
|
||||
"api_mode": self.api_mode,
|
||||
"memory_providers": [p.name for p in getattr(self._memory_manager, "providers", [])],
|
||||
},
|
||||
)
|
||||
except Exception as _snapshot_err:
|
||||
logger.debug("Context snapshot capture failed: %s", _snapshot_err)
|
||||
|
||||
# Calculate approximate request size for logging
|
||||
total_chars = sum(len(str(msg)) for msg in api_messages)
|
||||
approx_tokens = estimate_messages_tokens_rough(api_messages)
|
||||
|
||||
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())
|
||||
@@ -1,43 +0,0 @@
|
||||
from pathlib import Path
|
||||
|
||||
from agent.context_snapshots import ContextSnapshotRecorder
|
||||
|
||||
|
||||
def test_disabled_recorder_writes_nothing(tmp_path):
|
||||
recorder = ContextSnapshotRecorder(session_id="session-1", enabled=False, base_dir=tmp_path)
|
||||
|
||||
out = recorder.record_call(
|
||||
1,
|
||||
system_prompt="system",
|
||||
api_messages=[{"role": "user", "content": "hello"}],
|
||||
)
|
||||
|
||||
assert out is None
|
||||
assert not (tmp_path / "session-1").exists()
|
||||
|
||||
|
||||
def test_enabled_recorder_writes_expected_artifacts(tmp_path):
|
||||
recorder = ContextSnapshotRecorder(session_id="session-1", enabled=True, base_dir=tmp_path)
|
||||
|
||||
out = recorder.record_call(
|
||||
1,
|
||||
system_prompt="system prompt",
|
||||
memory_provider_system_prompt="# Hindsight Memory\nActive.",
|
||||
memory_prefetch_raw="- remembered fact",
|
||||
memory_context_block="<memory-context>\nremembered\n</memory-context>",
|
||||
api_user_message="What do I prefer?\n\n<memory-context>\nremembered\n</memory-context>",
|
||||
api_messages=[
|
||||
{"role": "system", "content": "system prompt"},
|
||||
{"role": "user", "content": "What do I prefer?"},
|
||||
],
|
||||
metadata={"provider": "openai", "memory_providers": ["builtin", "hindsight"]},
|
||||
)
|
||||
|
||||
assert out == tmp_path / "session-1" / "call_001"
|
||||
assert (out / "system_prompt.txt").read_text(encoding="utf-8") == "system prompt"
|
||||
assert (out / "memory_provider_system_prompt.txt").read_text(encoding="utf-8").startswith("# Hindsight Memory")
|
||||
assert (out / "memory_prefetch_raw.txt").read_text(encoding="utf-8") == "- remembered fact"
|
||||
assert "<memory-context>" in (out / "memory_context_block.txt").read_text(encoding="utf-8")
|
||||
assert "What do I prefer?" in (out / "api_user_message.txt").read_text(encoding="utf-8")
|
||||
assert (out / "api_messages.json").read_text(encoding="utf-8").startswith("[")
|
||||
assert '"hindsight"' in (out / "metadata.json").read_text(encoding="utf-8")
|
||||
@@ -596,26 +596,3 @@ class TestAvailability:
|
||||
monkeypatch.setenv("HINDSIGHT_MODE", "local")
|
||||
p = HindsightMemoryProvider()
|
||||
assert p.is_available()
|
||||
|
||||
def test_local_embedded_profile_defaults_to_agent_identity(self, tmp_path, monkeypatch):
|
||||
config_path = tmp_path / "hindsight" / "config.json"
|
||||
config_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
config_path.write_text(json.dumps({
|
||||
"mode": "local_embedded",
|
||||
"llm_provider": "ollama",
|
||||
"llm_model": "gemma3:12b",
|
||||
}))
|
||||
monkeypatch.setattr(
|
||||
"plugins.memory.hindsight.get_hermes_home",
|
||||
lambda: tmp_path,
|
||||
)
|
||||
|
||||
p = HindsightMemoryProvider()
|
||||
p.initialize(
|
||||
session_id="test-session",
|
||||
hermes_home=str(tmp_path / "profiles" / "atlas-hindsight"),
|
||||
platform="cli",
|
||||
agent_identity="atlas-hindsight",
|
||||
)
|
||||
|
||||
assert p._config["profile"] == "atlas-hindsight"
|
||||
|
||||
@@ -1,94 +0,0 @@
|
||||
from pathlib import Path
|
||||
from types import SimpleNamespace
|
||||
from unittest.mock import MagicMock, patch
|
||||
import importlib
|
||||
import sys
|
||||
import types
|
||||
|
||||
|
||||
|
||||
def _make_tool_defs(*names: str) -> list:
|
||||
return [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": n,
|
||||
"description": f"{n} tool",
|
||||
"parameters": {"type": "object", "properties": {}},
|
||||
},
|
||||
}
|
||||
for n in names
|
||||
]
|
||||
|
||||
|
||||
|
||||
def _mock_response(content="Done", finish_reason="stop"):
|
||||
msg = SimpleNamespace(content=content, tool_calls=None)
|
||||
choice = SimpleNamespace(message=msg, finish_reason=finish_reason)
|
||||
return SimpleNamespace(choices=[choice], usage=SimpleNamespace(prompt_tokens=1, completion_tokens=1, total_tokens=2))
|
||||
|
||||
|
||||
|
||||
def _load_ai_agent():
|
||||
sys.modules.setdefault("agent.auxiliary_client", types.SimpleNamespace(call_llm=lambda *a, **k: ""))
|
||||
run_agent = importlib.import_module("run_agent")
|
||||
return run_agent.AIAgent
|
||||
|
||||
|
||||
|
||||
def test_run_conversation_writes_context_snapshot_artifacts(tmp_path):
|
||||
AIAgent = _load_ai_agent()
|
||||
|
||||
class _FakePrivacyFilter:
|
||||
def __init__(self):
|
||||
self.last_report = None
|
||||
|
||||
def sanitize_messages(self, messages):
|
||||
return list(messages)
|
||||
|
||||
with (
|
||||
patch("run_agent.get_tool_definitions", return_value=_make_tool_defs("web_search")),
|
||||
patch("run_agent.check_toolset_requirements", return_value={}),
|
||||
patch("run_agent.OpenAI"),
|
||||
patch("hermes_cli.plugins.invoke_hook", return_value=[]),
|
||||
patch.dict(sys.modules, {"agent.privacy_filter": types.SimpleNamespace(PrivacyFilter=_FakePrivacyFilter)}),
|
||||
):
|
||||
agent = AIAgent(
|
||||
api_key="test-key-1234567890",
|
||||
base_url="https://example.com/v1",
|
||||
quiet_mode=True,
|
||||
skip_context_files=True,
|
||||
skip_memory=True,
|
||||
context_snapshots_enabled=True,
|
||||
context_snapshots_dir=str(tmp_path),
|
||||
)
|
||||
|
||||
agent.client = MagicMock()
|
||||
agent.client.chat.completions.create.return_value = _mock_response(content="Done")
|
||||
agent._build_system_prompt = MagicMock(return_value="Core system prompt")
|
||||
agent._memory_manager = MagicMock()
|
||||
agent._memory_manager.prefetch_all.return_value = "- remembered preference"
|
||||
agent._memory_manager.build_system_prompt.return_value = "# Hindsight Memory\nActive."
|
||||
agent._memory_manager.providers = [
|
||||
SimpleNamespace(name="builtin"),
|
||||
SimpleNamespace(name="hindsight"),
|
||||
]
|
||||
|
||||
result = agent.run_conversation("What do I prefer?")
|
||||
|
||||
assert result["final_response"] == "Done"
|
||||
|
||||
call_dir = tmp_path / agent.session_id / "call_001"
|
||||
assert call_dir.exists()
|
||||
assert (call_dir / "system_prompt.txt").read_text(encoding="utf-8") == "Core system prompt"
|
||||
assert (call_dir / "memory_provider_system_prompt.txt").read_text(encoding="utf-8").startswith("# Hindsight Memory")
|
||||
assert (call_dir / "memory_prefetch_raw.txt").read_text(encoding="utf-8") == "- remembered preference"
|
||||
assert "<memory-context>" in (call_dir / "memory_context_block.txt").read_text(encoding="utf-8")
|
||||
api_user_message = (call_dir / "api_user_message.txt").read_text(encoding="utf-8")
|
||||
assert "What do I prefer?" in api_user_message
|
||||
assert "remembered preference" in api_user_message
|
||||
api_messages = (call_dir / "api_messages.json").read_text(encoding="utf-8")
|
||||
assert '"role": "system"' in api_messages
|
||||
assert '"role": "user"' in api_messages
|
||||
metadata = (call_dir / "metadata.json").read_text(encoding="utf-8")
|
||||
assert '"hindsight"' in metadata
|
||||
@@ -1,22 +0,0 @@
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[1]
|
||||
DOC = ROOT / "docs" / "hindsight-local-eval.md"
|
||||
|
||||
|
||||
def test_hindsight_local_eval_doc_exists_and_covers_switching():
|
||||
assert DOC.exists(), "missing Hindsight local eval doc"
|
||||
text = DOC.read_text(encoding="utf-8")
|
||||
for snippet in (
|
||||
"atlas-baseline",
|
||||
"atlas-mempalace",
|
||||
"atlas-hindsight",
|
||||
"HERMES_HOME",
|
||||
"HERMES_CONTEXT_SNAPSHOTS",
|
||||
"memory_prefetch_raw.txt",
|
||||
"api_user_message.txt",
|
||||
"local_embedded",
|
||||
"hindsight/config.json",
|
||||
):
|
||||
assert snippet in text
|
||||
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