fix(memory,prompts): rollover repair + retire-for-all + seedgo #37 path cleanup
Batch of S243/S244 work held for PR640. Only devpulse has git write, so all branches' changes (@memory, @prax, @hooks, @aipass, @skills, @flow, @backup, @seedgo) land through this single commit. Memory rollover (correctness): - @hooks rollover hook now delegates to drone @memory rollover check/run — it had been reading stale .trinity limits (moved to memory.config.json by DPLAN-0210), falling back to a 600-line check that never fired, so rollover was silently dead for weeks. compact.py reads the current list schema. Both fail loud. - @memory removed the v1 line-count/600 fallback entirely — v2-only, fail-loud (959 tests). Retire-for-all (DPLAN-0215): - Legacy global prompt fully removed across every runtime: global_loader.py + tests deleted, hooks.json/project_hooks.json blocks stripped, bootstrap global seeding removed, cadence default + bypass cleaned, global .md files archived. Codex SessionStart + Claude cadence read the same tier files. Hardcoded-path cleanup (seedgo #37): - New HARDCODED_PATH checker (#37). @memory symbolic.py + @prax branch_detector.py home paths -> dynamic/generic. Both 100% Hardcoded_Path. - seedgo provider_hooks_snapshot.json fixture refreshed to the tiered baseline. Genericization: patrick -> user across tracked source, docs, templates. CHANGELOG: 2026-06-19 + 2026-06-23 sections added.
This commit is contained in:
AIOSAI
+2
-2
@@ -1,10 +1,10 @@
|
||||
*
|
||||
!aipass_global_prompt.md
|
||||
!tier0_kernel.md
|
||||
!tier1_navmap.md
|
||||
!hooks.json
|
||||
!.gitignore
|
||||
!README.md
|
||||
!PROMPT_STYLE.md
|
||||
!project_CLAUDE.md
|
||||
!project_global_prompt.md
|
||||
!project_hooks.json
|
||||
#Do not add other exceptions here without careful consideration. Developer permissions0ns needed.
|
||||
@@ -0,0 +1,76 @@
|
||||
# `.aipass/` — project prompt & hook config
|
||||
|
||||
This folder holds the **project-level prompt** and **hook configuration** for the AIPass
|
||||
repo, plus the **templates** `aipass init` stamps into every new project. It is the
|
||||
*project* layer; each branch additionally has its own branch prompt at
|
||||
`src/aipass/<branch>/.aipass/aipass_local_prompt.md`.
|
||||
|
||||
> **Nothing here is dead weight.** Every file is live injection, live config, or a
|
||||
> required new-project template. Superseded files live in `.archive/` (never deleted).
|
||||
|
||||
## One prompt system, every runtime
|
||||
|
||||
There is **one** source of prompt truth — the **tier files** — and **all** runtimes inject
|
||||
the same content. We do **not** keep separate prompts per CLI. Only the *delivery* differs:
|
||||
|
||||
| Runtime | How the same content is delivered |
|
||||
|---|---|
|
||||
| **Claude Code** | **Tiered by cadence** (FPLAN-0284): `tier0_kernel.md` every turn + `tier1_navmap.md` periodically + post-compaction |
|
||||
| **Codex CLI** | Injected **once at SessionStart** (no per-turn cadence): the same tier content, combined |
|
||||
|
||||
> ⚠️ **Migration in progress.** The Codex SessionStart hook
|
||||
> (`.codex/hooks/session_start_identity.py`) currently still reads the legacy
|
||||
> `aipass_global_prompt.md`. @hooks is wiring it onto the tier files. **Retire for one
|
||||
> runtime = retire for all** — once Codex is on the tiers, `aipass_global_prompt.md` is
|
||||
> read by nothing and moves to `.archive/`.
|
||||
|
||||
## Files
|
||||
|
||||
### Live — this repo's prompt + config
|
||||
| File | What it is |
|
||||
|---|---|
|
||||
| `tier0_kernel.md` | **The kernel** — tiny identity + `drone --help` reflex + don't-get-lost rules. The always-on core, for every runtime. |
|
||||
| `tier1_navmap.md` | **The navmap** — full agent roster, framework, terminology. The periodic/fuller layer, for every runtime. |
|
||||
| `hooks.json` | Claude Code **handler registration** for this repo — which prompt/gate/notification handlers fire on which events. |
|
||||
| `PROMPT_STYLE.md` | The writing-style guide every prompt here follows. |
|
||||
| `.gitignore` | Whitelist guard — only files listed here are tracked; everything else in `.aipass/` is ignored. |
|
||||
| `aipass_global_prompt.md` | **Legacy single global — being retired.** Disabled for Claude Code; Codex still reads it until its migration lands, then archived. **Not** the source of truth. |
|
||||
|
||||
### Templates — stamped into new projects by `aipass init` (`bootstrap.py`)
|
||||
| File | Stamps → | Notes |
|
||||
|---|---|---|
|
||||
| `project_hooks.json` | new project's `.aipass/hooks.json` | **REQUIRED** — without it a new project's hooks never fire. Mirrors the live wiring (tier0 + navmap enabled, global disabled). |
|
||||
| `project_CLAUDE.md` | new project's `CLAUDE.md` | the project's Claude Code instructions. |
|
||||
| `project_global_prompt.md` | new project's `aipass_global_prompt.md` | **Legacy** — same retirement path as the global above (new projects ship tiers-only once Codex is migrated). |
|
||||
|
||||
(`AGENTS.md` — Codex's equivalent of `CLAUDE.md` — is **generated** by `bootstrap.py`
|
||||
when no `project_AGENTS.md` template exists, so none is kept here.)
|
||||
|
||||
## What a new project gets (`aipass init`)
|
||||
|
||||
`bootstrap.py` seeds a fresh project with the tiered system:
|
||||
- `tier0_kernel.md` + `tier1_navmap.md` → the prompt content (every runtime)
|
||||
- `hooks.json` (from `project_hooks.json`) → tier0 + navmap enabled, global disabled
|
||||
- `CLAUDE.md` (from `project_CLAUDE.md`) + a generated `AGENTS.md`
|
||||
- `aipass_global_prompt.md` (from `project_global_prompt.md`) → legacy, retiring with the above
|
||||
|
||||
`aipass init update` backfills the tier files + refreshes hooks for existing projects.
|
||||
|
||||
## Changing a prompt here
|
||||
|
||||
Run the **prompt-change playbook** so a change reaches every runtime and every seed path:
|
||||
|
||||
```
|
||||
drone @flow create . "What changed" prompt_change
|
||||
```
|
||||
|
||||
Golden rule: **live ≠ seeded.** Editing this folder fixes *this* repo only. New projects
|
||||
come from the `project_*` templates + `bootstrap.py`; fresh clones get their machine-local
|
||||
wiring from `setup.sh` + `.claude/provider_manifest.json` + `cadence.py` defaults. And
|
||||
**every runtime** (Claude Code + Codex) must point at the same tier content.
|
||||
|
||||
## Archive & recovery
|
||||
|
||||
Superseded files move to `.archive/` (never deleted — house rule). Recover from there, or
|
||||
from git history, any time. Current archive: the pre-tiering
|
||||
`aipass_global_prompt.BACKUP-2026-06-09-S211.md` snapshot.
|
||||
@@ -1,119 +0,0 @@
|
||||
# AIPass — Global Prompt (SUPERSEDED)
|
||||
<!-- SUPERSEDED 2026-06-18 (FPLAN-0284): no longer injected. Split into the tiered prompts — .aipass/tier0_kernel.md (every turn) + .aipass/tier1_navmap.md (periodic). Kept as a reference/rollback snapshot; the `global_prompt` loader is disabled in .aipass/hooks.json. To roll back, re-enable that loader + its settings.json bridge entry. -->
|
||||
<!-- .aipass/aipass_global_prompt.md — Size cap: keep under 8,000 characters — the harness truncates hook output near 10k and the tail silently never arrives. Detail belongs in `drone @agent --help`, not here. Format: .aipass/PROMPT_STYLE.md -->
|
||||
|
||||
Persistent Agent Workspace. AIPass is the system: autonomous agents (citizens) with identity, memory, and a mailbox, providing services to each other and to external projects. Each agent lives in a branch — its home and address. Everything routes through `drone`.
|
||||
|
||||
# Drone — the router
|
||||
|
||||
`drone` reaches every agent and service. Installed binary, always on PATH — run directly, never as a python module.
|
||||
|
||||
```
|
||||
drone @agent <command> [args] # route a command to any agent
|
||||
drone @agent --help # full curated reference for that agent
|
||||
drone @agent # bare → introspection: the agent's live self-map
|
||||
drone systems # list all agents
|
||||
drone --help # drone itself
|
||||
```
|
||||
|
||||
One reflex above all: before using an agent's services, run `drone @agent --help`. This prompt says what exists — `--help` says how. Don't guess syntax; fetch it. Doubly so right after a compaction.
|
||||
|
||||
# Finding your way
|
||||
|
||||
You can't carry everything; you can find anything. This prompt plants breadcrumbs — what exists and where to look, not the full answer. Cheapest, highest-signal sources first:
|
||||
|
||||
- bare `drone @agent` — introspection: the agent's live self-map of modules and commands.
|
||||
- `drone @agent --help` — the full curated reference. Source of truth for usage.
|
||||
- the agent's `README.md` — best quick overview of its domain and shape.
|
||||
|
||||
# Git — drone only, devpulse only
|
||||
|
||||
Raw `git`/`gh` are blocked — `drone @git` is the only interface. Write ops are devpulse-only; everyone else gets read-only awareness: `drone @git status / diff / log`.
|
||||
|
||||
# The framework
|
||||
|
||||
Every branch is built the same. All agents live at `src/aipass/<name>` · mail address `@<name>`.
|
||||
|
||||
```
|
||||
src/aipass/<name>/
|
||||
├── .trinity/ # identity & memory (passport, local, observations)
|
||||
├── .aipass/ # branch prompt
|
||||
├── .ai_mail.local/ # mailbox
|
||||
├── apps/
|
||||
│ ├── <name>.py # entry point
|
||||
│ ├── modules/ # business logic
|
||||
│ └── handlers/ # implementation details
|
||||
├── logs/ # prax log output
|
||||
└── README.md
|
||||
```
|
||||
|
||||
# The agents
|
||||
|
||||
- @drone — command router. Resolves `@agent`, routes commands, enforces tier-based access. Also the only git interface (`drone @git`).
|
||||
- @devpulse — orchestration hub, the user's primary collaborator. Coordinates the other agents, dispatches work, only agent with git write.
|
||||
- @aipass — the user-facing front door and a system-ops collaborator. Onboarding (`aipass init`), `doctor` diagnostics, help chat, handoff; also partners with the user on host-level health (disk, thermal, docker, config). Concierge to other branches: reads, never writes.
|
||||
- @ai_mail — inter-agent email. `dispatch` = send + wake (default for handing work), `email` = no wake, plus inbox/view/reply/close.
|
||||
- @flow — plan lifecycle: create, list, close, templates, registry. Plan types in the Plans section — never create plan files by hand.
|
||||
- @seedgo — code standards and audits. The standard pack, `audit` and `checklist`, the quality gate before and after building.
|
||||
- @prax — logging and monitoring. The only logging system: `from aipass.prax import logger`. Real-time monitor, dashboards. Logs are the first diagnostic tool.
|
||||
- @memory — long-term memory. Archives overflowing `.trinity/` files into searchable vectors; `search` recalls past sessions. Nothing is lost — it moves deeper.
|
||||
- @spawn — branch lifecycle. Creates, updates, syncs, retires agents — scaffolding, passports, registry, templates.
|
||||
- @hooks — Claude Code hook engine. Prompt injection and cadence, security gates (git/edit/rm), bridges, per-project config, sound.
|
||||
- @trigger — event handling. Pub/sub event bus, error detection (medic), log watching, error registry. Detects and dispatches — owners fix.
|
||||
- @api — external API gateway. Authenticated service clients (Google, OpenRouter, more), OAuth flows, key management, resilience.
|
||||
- @cli — display formatting with Rich. Shared rendering for terminal output.
|
||||
- @skills — capability framework. Discoverable, self-contained skill units any agent can run; consume AIPass services as opt-in imports (e.g. the Telegram skill).
|
||||
- @daemon — task scheduler. Cron-triggered firing; each branch owns its `.daemon/schedule.json`, the daemon discovers and fires.
|
||||
- @commons — the social space. Where branches post, comment, vote, and gather as a community.
|
||||
- @backup — local-first backups. Project-owned snapshots and restore for any directory; no external service.
|
||||
|
||||
# Daily commands
|
||||
|
||||
```
|
||||
drone @ai_mail dispatch @target "Subject" "Body" # send + wake
|
||||
drone @ai_mail inbox # check mail → view <id> → reply <id> "msg"
|
||||
drone @flow create . "Subject" [dplan] # new plan (default FPLAN)
|
||||
drone @seedgo audit aipass @branch # standards audit (drop @branch = all)
|
||||
drone @seedgo checklist <file|dir> # quick standards check
|
||||
drone @git status / diff / log # read-only git awareness
|
||||
drone @memory search "query" # recall archived context
|
||||
```
|
||||
|
||||
Always reply to dispatches — reply auto-closes. No silent completions.
|
||||
|
||||
# Plans — flow
|
||||
|
||||
Plans carry context so you don't have to. Create only via `drone @flow create <path> "Subject" [type]` — never by hand.
|
||||
|
||||
- DPLAN — dev plan. Thinking, brainstorming, architecture. Before building.
|
||||
- FPLAN — flow plan, the default. Building and executing. `master` template = multi-phase, spawns sub-FPLANs.
|
||||
- PPLAN — playbook. A throwaway run stamped from a reusable SOP template. Operating the system, not changing it.
|
||||
- More types exist and new ones register over time. Named a type you don't know? `drone @flow templates` lists them all, live.
|
||||
|
||||
# Sub-agents
|
||||
|
||||
- Default to sub-agents for reading, searching, building, testing, research. Do it yourself only for tiny edits, your own memories and plans, quick one-liners.
|
||||
- One clear task per agent. Brief with full context — they know nothing of your conversation.
|
||||
- No git, no memory, no dispatch. They build and report; you decide and act.
|
||||
- Sub-agent = local disposable worker. Dispatch (`@ai_mail`) = wake a citizen with memory and identity. Branch-expert work → dispatch; else → sub-agent.
|
||||
- Models, good practice: opus for build and analysis, sonnet for routine investigation, haiku for trivial mechanical tasks. Never fable for sub-agents.
|
||||
|
||||
# Memory — .trinity/
|
||||
|
||||
Your continuity across sessions. Save proactively — after milestones, decisions, topic switches.
|
||||
|
||||
- `passport.json` — identity. Update only when identity genuinely evolves.
|
||||
- `local.json` — session log, key learnings, todos.
|
||||
- `observations.json` — what you learn about the user.
|
||||
- Overflow rolls to vectors automatically — never trim by hand. Two ChromaDB stores: your branch's `.chroma` (local) + a global one across all branches. `drone @memory search "query"` recalls them. Search before assuming you're cold.
|
||||
|
||||
# House rules
|
||||
|
||||
- No cross-branch file edits. Issue in another agent's code → mail the owner.
|
||||
- Never delete files. Rename `name(disabled).py` or move to a sibling `.archive/`.
|
||||
- Fail to errors, never fall back silently.
|
||||
- Verify after fixing — don't say "fixed" until a test or command confirms it.
|
||||
- Cross-platform, no hardcoded paths. Public repo — `pathlib`, never `/home/...`.
|
||||
- No bare imports — always `from aipass.<agent>.apps...`.
|
||||
- Registries are machine-managed (spawn, flow) — never hand-edit them.
|
||||
- State lives in `.trinity/` and dashboards, never in prompts. Prompts are signposts.
|
||||
@@ -18,12 +18,6 @@
|
||||
"handler": "aipass.hooks.apps.handlers.prompt.branch_loader.handle",
|
||||
"matcher": ""
|
||||
},
|
||||
"global_prompt": {
|
||||
"enabled": false,
|
||||
"_retired": "Superseded by tier0_kernel + navmap (FPLAN-0284, 2026-06-18). Re-enable here to roll back to the single 8k global prompt.",
|
||||
"handler": "aipass.hooks.apps.handlers.prompt.global_loader.handle",
|
||||
"matcher": ""
|
||||
},
|
||||
"tier0_kernel": {
|
||||
"enabled": true,
|
||||
"handler": "aipass.hooks.apps.handlers.prompt.tier0_kernel.handle",
|
||||
|
||||
@@ -1,99 +0,0 @@
|
||||
# {name} — Project Context
|
||||
<!-- File: .aipass/aipass_global_prompt.md — Injected every turn via hook. -->
|
||||
|
||||
Multi-agent framework. Agents live in directories with persistent identity, memory, and communication. All AIPass infrastructure available from any project via `drone`.
|
||||
|
||||
Patterns here are exact. Don't guess command syntax — examples are the API.
|
||||
|
||||
`drone` = installed binary, always on PATH. Run directly.
|
||||
|
||||
# Terminology
|
||||
|
||||
- Branch — directory `src/{name}/<agent>/`. Agent home and address.
|
||||
- Agent (citizen) — persistent identity. Has passport (`.trinity/`), memory, mailbox, code (`apps/`). Addressable as `@name`.
|
||||
- Sub-agent — disposable worker spawned for a task. No passport, no memory.
|
||||
- Registry — `{name}_REGISTRY.json` tracks all agents.
|
||||
- Project — this directory. Contains registry and agents.
|
||||
|
||||
# Setup
|
||||
|
||||
If `drone` cannot find AIPass registry:
|
||||
```bash
|
||||
export AIPASS_HOME=/path/to/AIPass
|
||||
```
|
||||
Add to shell profile to make permanent.
|
||||
|
||||
# Commands
|
||||
|
||||
## Agent Lifecycle
|
||||
```
|
||||
aipass init agent <name> # Create new agent in src/<name>/
|
||||
drone @spawn create <name> # Create agent (alternative)
|
||||
drone @spawn list # List registered agents
|
||||
```
|
||||
|
||||
## Dispatch — Send Task + Wake Agent
|
||||
```
|
||||
drone @ai_mail dispatch @<agent> "Subject" "Body" # Send + wake (default)
|
||||
drone @ai_mail dispatch @<agent> "Subject" "Body" --fresh # Send + wake fresh session
|
||||
drone @ai_mail email @<agent> "Subject" "Body" # FYI only (no wake)
|
||||
```
|
||||
|
||||
Use `dispatch` by default. Use `email` only when you don't need the agent to act now.
|
||||
|
||||
## Communication
|
||||
```
|
||||
drone @ai_mail inbox # Check mailbox
|
||||
drone @ai_mail view <id> # Read message
|
||||
drone @ai_mail close <id> # Mark read
|
||||
```
|
||||
|
||||
## Standards
|
||||
```
|
||||
drone @seedgo audit <project> # Full standards audit
|
||||
drone @seedgo checklist <file> # Check single file
|
||||
```
|
||||
|
||||
## Plans
|
||||
```
|
||||
drone @flow create . "Subject" dplan # DPLAN (design/thinking)
|
||||
drone @flow create . "Subject" # FPLAN (execution)
|
||||
drone @flow create . "Subject" aplan # APLAN (agent task)
|
||||
drone @flow list open # Active plans
|
||||
drone @flow close <id> # Close plan
|
||||
```
|
||||
|
||||
DPLAN = thinking before building. FPLAN = building and executing.
|
||||
|
||||
## Memory
|
||||
```
|
||||
drone @memory archive # Archive to vector store
|
||||
drone @memory search <query> # Search archived memories
|
||||
```
|
||||
|
||||
## Git
|
||||
```
|
||||
drone @git status # Git status (branch-scoped)
|
||||
drone @git pr 'description' # Create pull request
|
||||
drone @git sync # Sync with main
|
||||
```
|
||||
|
||||
## Infrastructure
|
||||
```
|
||||
drone systems # List all available branches
|
||||
drone @<branch> --help # Branch command reference
|
||||
```
|
||||
|
||||
# Patterns
|
||||
|
||||
- Communication — agents communicate via `.ai_mail.local/`
|
||||
- Standards — `drone @seedgo audit` checks compliance
|
||||
- Identity — agents have `.trinity/passport.json`, projects use registry
|
||||
- Memory — update `.trinity/local.json` at session end. Memory is presence.
|
||||
- Use drone commands for all operations. Never raw git, gh, or python -m.
|
||||
|
||||
# Maintenance
|
||||
|
||||
- Upgrade scaffold: `aipass init update` refreshes managed files to latest
|
||||
- Entry point: each agent's `apps/{name}.py` auto-configures sys.path
|
||||
- Layout: `src/{name}/<agent>/` for standalone projects
|
||||
@@ -18,9 +18,14 @@
|
||||
"handler": "aipass.hooks.apps.handlers.prompt.branch_loader.handle",
|
||||
"matcher": ""
|
||||
},
|
||||
"global_prompt": {
|
||||
"tier0_kernel": {
|
||||
"enabled": true,
|
||||
"handler": "aipass.hooks.apps.handlers.prompt.global_loader.handle",
|
||||
"handler": "aipass.hooks.apps.handlers.prompt.tier0_kernel.handle",
|
||||
"matcher": ""
|
||||
},
|
||||
"navmap": {
|
||||
"enabled": true,
|
||||
"handler": "aipass.hooks.apps.handlers.prompt.navmap.handle",
|
||||
"matcher": ""
|
||||
}
|
||||
},
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Compass — Record a Decision
|
||||
|
||||
Purpose: Capture the decision just made into compass (the rated decision engine) with Patrick's rating and note. Patrick fires this when he notices a decision worth recording — he supplies the judgement, you supply the decision text from the conversation. This is the human-triggered answer to the "noticing" problem: Patrick notices, you describe and store.
|
||||
Purpose: Capture the decision just made into compass (the rated decision engine) with the user's rating and note. The user fires this when they notice a decision worth recording — they supply the judgement, you supply the decision text from the conversation. This is the human-triggered answer to the "noticing" problem: the user notices, you describe and store.
|
||||
|
||||
Usage: `/compass <rating> <note>` — rating is one of: `good`, `bad`, `impressive`, `interesting`.
|
||||
|
||||
@@ -14,15 +14,15 @@ Arguments: `$ARGUMENTS`
|
||||
## Execution
|
||||
|
||||
1. Parse `$ARGUMENTS`:
|
||||
- First token = `rating`. It MUST be one of `good | bad | impressive | interesting`. If it isn't, don't guess — ask Patrick which rating he meant and stop.
|
||||
- Everything after the first token = `note` (Patrick's observation; may be empty).
|
||||
- First token = `rating`. It MUST be one of `good | bad | impressive | interesting`. If it isn't, don't guess — ask the user which rating they meant and stop.
|
||||
- Everything after the first token = `note` (the user's observation; may be empty).
|
||||
2. From the recent conversation, identify the decision being rated. Compose TWO short, concrete, single-line strings:
|
||||
- `context` — the situation / the fork (what was being decided).
|
||||
- `decision` — what was actually chosen.
|
||||
This is your job: Patrick rated it, you describe it accurately from what just happened.
|
||||
3. Store it (source is `patrick`, since he triggered the rating):
|
||||
This is your job: the user rated it, you describe it accurately from what just happened.
|
||||
3. Store it (source is `user`, since they triggered the rating):
|
||||
```
|
||||
drone @devpulse compass add "<context>" "<decision>" --rating <rating> --note "<note>" --source patrick
|
||||
drone @devpulse compass add "<context>" "<decision>" --rating <rating> --note "<note>" --source user
|
||||
```
|
||||
Omit `--note` if the note is empty.
|
||||
4. Confirm in one line: the rating, the decision recorded, and the new id.
|
||||
@@ -31,5 +31,5 @@ Arguments: `$ARGUMENTS`
|
||||
|
||||
- Compass is the curated truth-store of decisions — short entries only. Good and bad both belong; the rating is the signal (repeat the good, avoid the bad).
|
||||
- Compass is separate from @memory. Do NOT also write this to `.trinity/` or memory — different store, different purpose.
|
||||
- If the decision Patrick means is ambiguous, ask before storing. One good entry beats a vague one.
|
||||
- If the decision the user means is ambiguous, ask before storing. One good entry beats a vague one.
|
||||
- Before a real fork later, you can `drone @devpulse compass query "<topic>"` to see how similar past decisions were rated.
|
||||
|
||||
@@ -1,11 +1,12 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Codex SessionStart hook: inject AIPass identity context.
|
||||
|
||||
Reads .trinity/passport.json and branch prompt, outputs Codex-format JSON
|
||||
with additionalContext for identity injection.
|
||||
Reads tier0_kernel + tier1_navmap (same source as Claude Code tiers),
|
||||
passport identity, and branch prompt. Outputs Codex-format JSON with
|
||||
additionalContext. Codex fires once at SessionStart — no per-turn cadence.
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
@@ -36,9 +37,9 @@ def get_branch_from_cwd(repo_root):
|
||||
|
||||
def main():
|
||||
try:
|
||||
input_data = json.loads(sys.stdin.read())
|
||||
json.loads(sys.stdin.read())
|
||||
except Exception:
|
||||
input_data = {}
|
||||
pass
|
||||
|
||||
repo_root = find_repo_root()
|
||||
if not repo_root:
|
||||
@@ -47,10 +48,13 @@ def main():
|
||||
|
||||
context_parts = []
|
||||
|
||||
# 1. Global prompt
|
||||
global_prompt = repo_root / ".aipass" / "aipass_global_prompt.md"
|
||||
if global_prompt.exists():
|
||||
context_parts.append(global_prompt.read_text(encoding="utf-8")[:8000])
|
||||
# 1. Tiered prompts (same source as Claude Code tiers)
|
||||
tier0 = repo_root / ".aipass" / "tier0_kernel.md"
|
||||
if tier0.exists():
|
||||
context_parts.append(tier0.read_text(encoding="utf-8")[:2500])
|
||||
tier1 = repo_root / ".aipass" / "tier1_navmap.md"
|
||||
if tier1.exists():
|
||||
context_parts.append(tier1.read_text(encoding="utf-8")[:8000])
|
||||
|
||||
# 2. Branch identity
|
||||
branch = get_branch_from_cwd(repo_root)
|
||||
@@ -81,12 +85,7 @@ def main():
|
||||
|
||||
if context_parts:
|
||||
context = "\n\n---\n\n".join(context_parts)
|
||||
output = {
|
||||
"hookSpecificOutput": {
|
||||
"hookEventName": "SessionStart",
|
||||
"additionalContext": context
|
||||
}
|
||||
}
|
||||
output = {"hookSpecificOutput": {"hookEventName": "SessionStart", "additionalContext": context}}
|
||||
else:
|
||||
output = {}
|
||||
|
||||
|
||||
@@ -9,6 +9,63 @@ PyPI version — not the changelog header.
|
||||
|
||||
---
|
||||
|
||||
## [2026-06-23]
|
||||
|
||||
### Fixed
|
||||
|
||||
- **Hardcoded home paths removed (seedgo #37 cleanup).** `@memory` `symbolic.py`
|
||||
derived 8 dash-encoded branch-path names from a literal `-home-patrick-` home —
|
||||
now built at runtime from `Path(__file__).resolve().parents[3]`. `@prax`
|
||||
`branch_detector.py` docstring examples genericized to `-home-user-`. Both
|
||||
branches back to 100% `Hardcoded_Path`. (959 / 906 tests green.)
|
||||
|
||||
## [2026-06-19]
|
||||
|
||||
### Fixed
|
||||
|
||||
- **`aipass init` now seeds the tiered prompts to new projects (@aipass).** The
|
||||
init template + bootstrap still handed new projects the retired global prompt
|
||||
with no tiers; now `.aipass/project_hooks.json` mirrors the live wiring
|
||||
(`tier0_kernel` + `navmap` enabled, `global_prompt` disabled) and `bootstrap.py`
|
||||
seeds both tier `.md` files. `init update` backfills existing projects.
|
||||
(77 bootstrap tests, 100% seedgo.)
|
||||
- **Cadence reset observability (@hooks).** `reset_counter()` silently no-op'd
|
||||
when the Claude session id was absent; it now fails loud, logs the session id +
|
||||
prior turn on each reset, falls back to hook data for the id, and handles a
|
||||
corrupt state file. (The post-compaction counter reset was already working —
|
||||
this makes it visible so it can't fail invisibly.)
|
||||
- **Memory rollover was silently dead — fixed end-to-end (@hooks + @memory).** The
|
||||
PreCompact rollover hook read its limits from `.trinity` file metadata, but
|
||||
DPLAN-0210 had moved limits into @memory's `memory.config.json` — so the hook
|
||||
always fell back to a 600-line check the lean files never reached, and rollover
|
||||
never fired (for weeks). The hook is now a thin trigger delegating to
|
||||
`drone @memory rollover check/run`; `compact.py` reads the current list schema
|
||||
(it was calling `.keys()` on a now-list `key_learnings`). Both fail loud instead
|
||||
of a silent exit-0.
|
||||
- **Removed @memory's v1 line-count / 600-line silent fallback entirely.** The
|
||||
detector + extractor are now v2-only (`per_branch` → `defaults` → warn-and-skip);
|
||||
a parse failure logs loud and skips rather than silently falling back. Deleted
|
||||
`_get_max_lines` / `_load_config` / `_detect_growing_array` / the line-count
|
||||
extraction path. (959 tests.)
|
||||
|
||||
### Removed
|
||||
|
||||
- **Legacy global prompt fully retired across every runtime (DPLAN-0215).** After
|
||||
the tiered cutover the old `global_prompt` is now gone, not just disabled:
|
||||
`global_loader.py` + its tests deleted, the `global_prompt` block stripped from
|
||||
`.aipass/hooks.json` + `project_hooks.json`, `_resolve_global_prompt` + all global
|
||||
seeding removed from `aipass init` bootstrap/update, the cadence default + bypass
|
||||
entries cleaned, and both `aipass_global_prompt.md` / `project_global_prompt.md`
|
||||
archived. Claude (cadence) and Codex (SessionStart) now read the same tier files —
|
||||
one prompt source, every runtime.
|
||||
|
||||
### Added
|
||||
|
||||
- **seedgo `HARDCODED_PATH` standard (#37).** A new checker (`hardcoded_path_check.py`
|
||||
+ `hardcoded_path_content.py`, `test_checkers_batch10.py`) flags hardcoded home
|
||||
paths — `/home/<user>` and dash-encoded `-home-<user>-` — in source and docstrings,
|
||||
keeping the public repo clean.
|
||||
|
||||
## [2026-06-18]
|
||||
|
||||
### Changed
|
||||
@@ -24,6 +81,15 @@ PyPI version — not the changelog header.
|
||||
is retired (kept as a reference snapshot). Net: more navigation context
|
||||
reaches agents while less is paid per turn. Fresh-clone wiring is seeded from
|
||||
`cadence.py` defaults + `setup.sh` + `provider_manifest.json`.
|
||||
- **Public source genericized — `Patrick` → generic `user`.** No personal
|
||||
identifiers in tracked code/docs: the compass decision-source enum
|
||||
(`patrick` → `user`) + the `/compass` command, the devpulse local prompt, the
|
||||
`aipass init` onboarding example (`--name Patrick` → `--name YourName`), and
|
||||
stale refs across @ai_mail / @backup / @flow. Private memories (`.trinity/`,
|
||||
compass DB) keep personal context — they're gitignored.
|
||||
- **Telegram skill genericized (@skills).** Retired the inactive `patrick_private`
|
||||
personal bot from the skill's tests; the message sender now defaults to the
|
||||
Telegram user's first name (fallback `User`) instead of a hardcoded `Patrick`.
|
||||
|
||||
### Added
|
||||
|
||||
@@ -35,6 +101,13 @@ PyPI version — not the changelog header.
|
||||
- **Skill frontmatter discipline (@skills).** A `when_to_use` field with trigger
|
||||
phrases (surfaced during discovery scans) and per-step "Done when:" success
|
||||
criteria across the SKILL.md templates.
|
||||
- **`HARDCODED_PATH` standard (@seedgo, 37th checker).** Flags absolute home-dir
|
||||
literals in source — POSIX `/home/<user>/`, macOS `/Users/<user>/`, Windows
|
||||
user-home paths, and Claude Code's dash-encoded `-home-<user>-` form — with a
|
||||
bypass for legitimate test fixtures. Swept the repo for violations.
|
||||
- **`prompt_change` flow playbook (PPLAN template).** A reusable SOP for changing
|
||||
any injected prompt — leads with "live ≠ seeded" and walks every wiring layer +
|
||||
fresh-install seed path; born from the `aipass init` seeding gap this surfaced.
|
||||
|
||||
## [2026-06-16]
|
||||
|
||||
|
||||
@@ -165,7 +165,7 @@ def _is_private_branch_email(email: str) -> bool:
|
||||
email address is registered to a private (isolated) branch.
|
||||
|
||||
Args:
|
||||
email: Email address to check (e.g., "@patrick_private")
|
||||
email: Email address to check (e.g., "@private_branch")
|
||||
|
||||
Returns:
|
||||
True if email belongs to a private branch, False otherwise
|
||||
|
||||
@@ -11,7 +11,8 @@ Init Bootstrap Handler - PRIVATE implementation
|
||||
|
||||
Business logic for `aipass init`. Creates the project scaffold:
|
||||
1. {NAME}_REGISTRY.json — project registry with UUID
|
||||
2. .aipass/aipass_global_prompt.md — global prompt (injected every turn)
|
||||
2. .aipass/tier0_kernel.md — tier 0 kernel prompt (every turn)
|
||||
2b..aipass/tier1_navmap.md — tier 1 navigation map (periodic)
|
||||
3. CLAUDE.md — project prompt (Claude Code reads this)
|
||||
4. AGENTS.md — Codex equivalent of CLAUDE.md
|
||||
5. README.md — getting started guide
|
||||
@@ -69,14 +70,6 @@ def _detect_aipass_home() -> str | None:
|
||||
return None
|
||||
|
||||
|
||||
def _resolve_global_prompt(name: str, aipass_home: str | None, dest: Path) -> str:
|
||||
"""Resolve global prompt content from source template or fallback generator."""
|
||||
source = Path(aipass_home) / ".aipass" / "project_global_prompt.md" if aipass_home else None
|
||||
if source and source.is_file():
|
||||
return source.read_text(encoding="utf-8").replace("{name}", name)
|
||||
return sc.with_source(sc.global_prompt_md(name), dest)
|
||||
|
||||
|
||||
def _hook_fingerprint(hook_entry: dict) -> str:
|
||||
"""Extract a comparable fingerprint from a hook entry."""
|
||||
commands = []
|
||||
@@ -323,10 +316,14 @@ def init_project(target: Path, project_name: str | None = None) -> dict:
|
||||
aipass_dir = target / ".aipass"
|
||||
aipass_dir.mkdir(exist_ok=True)
|
||||
|
||||
global_prompt_path = aipass_dir / "aipass_global_prompt.md"
|
||||
if not global_prompt_path.exists():
|
||||
global_prompt_path.write_text(_resolve_global_prompt(name, aipass_home, global_prompt_path), encoding="utf-8")
|
||||
created.append(str(global_prompt_path))
|
||||
# 2. .aipass/tier0_kernel.md + tier1_navmap.md — tiered prompt injection
|
||||
for tier_file in ("tier0_kernel.md", "tier1_navmap.md"):
|
||||
tier_dest = aipass_dir / tier_file
|
||||
if not tier_dest.exists() and aipass_home:
|
||||
tier_src = Path(aipass_home) / ".aipass" / tier_file
|
||||
if tier_src.is_file():
|
||||
shutil.copy2(str(tier_src), str(tier_dest))
|
||||
created.append(str(tier_dest))
|
||||
|
||||
# 2b. .aipass/hooks.json — project hook config from template
|
||||
hooks_json_path = aipass_dir / "hooks.json"
|
||||
@@ -488,14 +485,21 @@ def update_project(target: Path) -> dict:
|
||||
|
||||
# --- Managed files: write only when content has changed ---
|
||||
|
||||
global_prompt_path = aipass_dir / "aipass_global_prompt.md"
|
||||
aipass_home = aipass_home or _detect_aipass_home()
|
||||
generated = _resolve_global_prompt(name, aipass_home, global_prompt_path)
|
||||
if not global_prompt_path.exists() or global_prompt_path.read_text(encoding="utf-8") != generated:
|
||||
global_prompt_path.write_text(generated, encoding="utf-8")
|
||||
updated.append(str(global_prompt_path))
|
||||
else:
|
||||
already_current.append(str(global_prompt_path))
|
||||
|
||||
# tier0_kernel.md + tier1_navmap.md — tiered prompt injection
|
||||
for tier_file in ("tier0_kernel.md", "tier1_navmap.md"):
|
||||
tier_dest = aipass_dir / tier_file
|
||||
tier_src = Path(aipass_home) / ".aipass" / tier_file if aipass_home else None
|
||||
if tier_src and tier_src.is_file():
|
||||
canonical = tier_src.read_text(encoding="utf-8")
|
||||
if not tier_dest.exists() or tier_dest.read_text(encoding="utf-8") != canonical:
|
||||
tier_dest.write_text(canonical, encoding="utf-8")
|
||||
updated.append(str(tier_dest))
|
||||
else:
|
||||
already_current.append(str(tier_dest))
|
||||
elif tier_dest.exists():
|
||||
already_current.append(str(tier_dest))
|
||||
|
||||
# settings.json — smart merge: preserve user hooks + env, update AIPass hooks
|
||||
settings_path = claude_dir / "settings.json"
|
||||
|
||||
@@ -16,7 +16,7 @@ Usage:
|
||||
aipass init # show progress / introspection
|
||||
aipass init run # interactive
|
||||
aipass init run --non-interactive # CI/headless, all defaults
|
||||
aipass init run --name Patrick --cli claude
|
||||
aipass init run --name YourName --cli claude
|
||||
aipass init run --dry-run # walk all 12 stages, no destructive ops
|
||||
# - skips drone @spawn create (stage 8)
|
||||
# - skips tmux/wt handoff (stage 11)
|
||||
@@ -876,7 +876,7 @@ def print_help() -> None:
|
||||
console.print("[yellow]USAGE:[/yellow]")
|
||||
console.print(" [green]aipass init run[/green] [dim]# interactive[/dim]")
|
||||
console.print(" [green]aipass init run --non-interactive[/green] [dim]# CI/headless[/dim]")
|
||||
console.print(" [green]aipass init run --name Patrick[/green] [dim]# pre-fill name[/dim]")
|
||||
console.print(" [green]aipass init run --name YourName[/green] [dim]# pre-fill name[/dim]")
|
||||
console.print(" [green]aipass init run --cli claude[/green] [dim]# pre-fill CLI[/dim]")
|
||||
console.print(" [green]aipass init run --no-docker[/green] [dim]# skip docker offer[/dim]")
|
||||
console.print(" [green]aipass init run --dry-run[/green] [dim]# walk all stages, no writes[/dim]")
|
||||
|
||||
@@ -98,7 +98,6 @@ def test_init_project_creates_all_expected_files(tmp_path):
|
||||
|
||||
expected_files = [
|
||||
target / "DEMO_REGISTRY.json",
|
||||
target / ".aipass" / "aipass_global_prompt.md",
|
||||
target / "CLAUDE.md",
|
||||
target / "AGENTS.md",
|
||||
target / "README.md",
|
||||
@@ -107,8 +106,13 @@ def test_init_project_creates_all_expected_files(tmp_path):
|
||||
target / ".claude" / "commands" / "prep.md",
|
||||
target / "src" / "demo" / "__init__.py",
|
||||
]
|
||||
# Tier files are env-dependent (need AIPASS_HOME)
|
||||
if result["aipass_home"]:
|
||||
expected_files.append(target / ".aipass" / "tier0_kernel.md")
|
||||
expected_files.append(target / ".aipass" / "tier1_navmap.md")
|
||||
for f in expected_files:
|
||||
assert f.exists(), f"Expected file not created: {f}"
|
||||
assert not (target / ".aipass" / "aipass_global_prompt.md").exists(), "Retired global prompt should NOT be seeded"
|
||||
|
||||
# src/<package>/ is a directory with __init__.py
|
||||
assert (target / "src" / "demo").is_dir(), "Expected src/demo/ package directory"
|
||||
@@ -126,7 +130,7 @@ def test_init_project_creates_all_expected_files(tmp_path):
|
||||
created_basenames = [Path(f).name for f in result["created_files"]]
|
||||
for f in expected_files:
|
||||
assert f.name in created_basenames or f.exists(), f"Expected {f.name} in created_files"
|
||||
assert len(result["created_files"]) >= 11
|
||||
assert len(result["created_files"]) >= 10
|
||||
|
||||
|
||||
def test_init_project_return_dict_structure(tmp_path):
|
||||
@@ -288,19 +292,6 @@ def test_init_project_settings_no_hooks(tmp_path):
|
||||
assert "permissions" in data
|
||||
|
||||
|
||||
def test_init_project_global_prompt_content(tmp_path):
|
||||
"""Global prompt contains project name and AIPass terminology."""
|
||||
target = tmp_path / "proj"
|
||||
target.mkdir()
|
||||
|
||||
init_project(target, project_name="alpha")
|
||||
|
||||
content = (target / ".aipass" / "aipass_global_prompt.md").read_text(encoding="utf-8")
|
||||
assert "# ALPHA" in content
|
||||
assert "ALPHA_REGISTRY.json" in content
|
||||
assert "# Commands" in content
|
||||
|
||||
|
||||
def test_init_project_readme_md_content(tmp_path):
|
||||
"""README.md contains getting started guide with project name."""
|
||||
target = tmp_path / "proj"
|
||||
@@ -324,7 +315,7 @@ def test_init_project_auto_creates_target_dir(tmp_path):
|
||||
|
||||
assert target.is_dir()
|
||||
assert result["project_name"] == "NESTED"
|
||||
assert len(result["created_files"]) >= 11
|
||||
assert len(result["created_files"]) >= 10
|
||||
|
||||
|
||||
def test_init_project_defaults_name_from_directory(tmp_path):
|
||||
@@ -359,7 +350,6 @@ def test_init_project_skips_existing_optional_files(tmp_path):
|
||||
# Pre-create optional files
|
||||
aipass_dir = target / ".aipass"
|
||||
aipass_dir.mkdir()
|
||||
(aipass_dir / "aipass_global_prompt.md").write_text("# Custom global\n", encoding="utf-8")
|
||||
(target / "CLAUDE.md").write_text("# Custom CLAUDE\n", encoding="utf-8")
|
||||
(target / "AGENTS.md").write_text("# Custom AGENTS\n", encoding="utf-8")
|
||||
(target / "README.md").write_text("# Custom README\n", encoding="utf-8")
|
||||
@@ -542,10 +532,12 @@ def test_update_project_creates_missing_managed_dirs(tmp_path):
|
||||
|
||||
result = update_project(target)
|
||||
|
||||
assert (target / ".aipass" / "aipass_global_prompt.md").exists()
|
||||
assert (target / ".claude" / "settings.json").exists()
|
||||
# Managed files in deleted dirs re-written (global_prompt, hooks.json, settings, prep)
|
||||
assert len(result["updated_files"]) == 4
|
||||
# Managed files in deleted dirs re-written (tier0_kernel, tier1_navmap, hooks.json, settings, prep)
|
||||
if result["aipass_home"]:
|
||||
assert len(result["updated_files"]) == 5
|
||||
else:
|
||||
assert len(result["updated_files"]) == 2
|
||||
assert len(result["already_current"]) >= 2
|
||||
|
||||
|
||||
@@ -850,6 +842,154 @@ def test_update_project_hooks_json_already_current(tmp_path):
|
||||
assert any("hooks.json" in f for f in result["already_current"])
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Tiered prompt injection tests (FPLAN-0284)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def test_init_project_creates_tier_files(tmp_path):
|
||||
"""init_project seeds tier0_kernel.md and tier1_navmap.md when AIPASS_HOME available."""
|
||||
target = tmp_path / "proj"
|
||||
target.mkdir()
|
||||
|
||||
result = init_project(target, project_name="tiers")
|
||||
|
||||
if result["aipass_home"] is None:
|
||||
pytest.skip("AIPASS_HOME not detectable in this environment")
|
||||
|
||||
assert (target / ".aipass" / "tier0_kernel.md").exists()
|
||||
assert (target / ".aipass" / "tier1_navmap.md").exists()
|
||||
|
||||
|
||||
def test_init_project_tier_files_match_canonical(tmp_path):
|
||||
"""Tier files in new project match the canonical source exactly."""
|
||||
target = tmp_path / "proj"
|
||||
target.mkdir()
|
||||
|
||||
result = init_project(target, project_name="canon")
|
||||
|
||||
if result["aipass_home"] is None:
|
||||
pytest.skip("AIPASS_HOME not detectable in this environment")
|
||||
|
||||
for tier_file in ("tier0_kernel.md", "tier1_navmap.md"):
|
||||
canonical = Path(result["aipass_home"]) / ".aipass" / tier_file
|
||||
if not canonical.exists():
|
||||
pytest.skip(f"{tier_file} not found in canonical .aipass/")
|
||||
assert (target / ".aipass" / tier_file).read_bytes() == canonical.read_bytes()
|
||||
|
||||
|
||||
def test_init_project_tier_files_in_created_list(tmp_path):
|
||||
"""Tier files appear in created_files list."""
|
||||
target = tmp_path / "proj"
|
||||
target.mkdir()
|
||||
|
||||
result = init_project(target, project_name="listed")
|
||||
|
||||
if result["aipass_home"] is None:
|
||||
pytest.skip("AIPASS_HOME not detectable in this environment")
|
||||
|
||||
assert any("tier0_kernel.md" in f for f in result["created_files"])
|
||||
assert any("tier1_navmap.md" in f for f in result["created_files"])
|
||||
|
||||
|
||||
def test_init_project_no_tier_files_without_aipass_home(tmp_path, monkeypatch):
|
||||
"""Without AIPASS_HOME, tier files are not created."""
|
||||
target = tmp_path / "proj"
|
||||
target.mkdir()
|
||||
|
||||
monkeypatch.setattr(
|
||||
"aipass.aipass.apps.handlers.init.bootstrap._detect_aipass_home",
|
||||
lambda: None,
|
||||
)
|
||||
|
||||
init_project(target, project_name="notiers")
|
||||
|
||||
assert not (target / ".aipass" / "tier0_kernel.md").exists()
|
||||
assert not (target / ".aipass" / "tier1_navmap.md").exists()
|
||||
|
||||
|
||||
def test_init_project_hooks_json_has_tiers_enabled(tmp_path):
|
||||
"""hooks.json from template has tier0_kernel and navmap enabled, no global_prompt."""
|
||||
target = tmp_path / "proj"
|
||||
target.mkdir()
|
||||
|
||||
result = init_project(target, project_name="hookstier")
|
||||
|
||||
if result["aipass_home"] is None:
|
||||
pytest.skip("AIPASS_HOME not detectable in this environment")
|
||||
|
||||
hooks_json = target / ".aipass" / "hooks.json"
|
||||
data = json.loads(hooks_json.read_text(encoding="utf-8"))
|
||||
ups = data["UserPromptSubmit"]
|
||||
|
||||
assert ups["tier0_kernel"]["enabled"] is True
|
||||
assert ups["navmap"]["enabled"] is True
|
||||
assert "global_prompt" not in ups
|
||||
|
||||
|
||||
def test_update_project_adds_tier_files_to_existing(tmp_path):
|
||||
"""update_project adds tier files to a project that lacks them."""
|
||||
target = tmp_path / "proj"
|
||||
target.mkdir()
|
||||
|
||||
registry_data = {
|
||||
"metadata": {
|
||||
"id": "test-id",
|
||||
"name": "OLD",
|
||||
"version": "1.0.0",
|
||||
"created": "2026-01-01",
|
||||
"last_updated": "2026-01-01",
|
||||
"total_branches": 0,
|
||||
},
|
||||
"branches": [],
|
||||
}
|
||||
(target / "OLD_REGISTRY.json").write_text(json.dumps(registry_data), encoding="utf-8")
|
||||
(target / ".aipass").mkdir()
|
||||
|
||||
result = update_project(target)
|
||||
|
||||
if result["aipass_home"] is None:
|
||||
pytest.skip("AIPASS_HOME not detectable in this environment")
|
||||
|
||||
assert (target / ".aipass" / "tier0_kernel.md").exists()
|
||||
assert (target / ".aipass" / "tier1_navmap.md").exists()
|
||||
assert any("tier0_kernel.md" in f for f in result["updated_files"])
|
||||
assert any("tier1_navmap.md" in f for f in result["updated_files"])
|
||||
|
||||
|
||||
def test_update_project_tier_files_already_current(tmp_path):
|
||||
"""update reports tier files as already_current when unchanged."""
|
||||
target = tmp_path / "proj"
|
||||
target.mkdir()
|
||||
result = init_project(target, project_name="tiercurr")
|
||||
|
||||
if result["aipass_home"] is None:
|
||||
pytest.skip("AIPASS_HOME not detectable in this environment")
|
||||
|
||||
result = update_project(target)
|
||||
|
||||
assert any("tier0_kernel.md" in f for f in result["already_current"])
|
||||
assert any("tier1_navmap.md" in f for f in result["already_current"])
|
||||
|
||||
|
||||
def test_update_project_refreshes_stale_tier_files(tmp_path):
|
||||
"""update overwrites tier files when they differ from canonical source."""
|
||||
target = tmp_path / "proj"
|
||||
target.mkdir()
|
||||
result = init_project(target, project_name="stale")
|
||||
|
||||
if result["aipass_home"] is None:
|
||||
pytest.skip("AIPASS_HOME not detectable in this environment")
|
||||
|
||||
(target / ".aipass" / "tier0_kernel.md").write_text("# stale\n", encoding="utf-8")
|
||||
|
||||
result = update_project(target)
|
||||
|
||||
assert any("tier0_kernel.md" in f for f in result["updated_files"])
|
||||
content = (target / ".aipass" / "tier0_kernel.md").read_text(encoding="utf-8")
|
||||
assert "AIPass" in content
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# scaffold_content — global_prompt_md tests
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
@@ -56,7 +56,7 @@ def handle_command(command: str, args: list) -> bool:
|
||||
show_panels = "--quiet" not in args
|
||||
logger.info(f"[backup] Running full backup cycle for {project_root}")
|
||||
|
||||
# ONE scan shared between both modes (Patrick's Law #1)
|
||||
# ONE scan shared between both modes (single-scan rule)
|
||||
config = load_project_config(project_root)
|
||||
spec = load_spec(project_root)
|
||||
whitelist_entries = load_whitelist(project_root)
|
||||
|
||||
@@ -0,0 +1,28 @@
|
||||
# Backup System ignore patterns (gitignore-style)
|
||||
# Lines starting with # are comments. Blank lines are ignored.
|
||||
# Edit this file to customize. Source defaults: handlers/ignore/patterns.py
|
||||
|
||||
.backup/
|
||||
.git/
|
||||
.svn/
|
||||
.hg/
|
||||
__pycache__/
|
||||
.pytest_cache/
|
||||
*.pyc
|
||||
*.pyo
|
||||
*.egg-info/
|
||||
.venv/
|
||||
venv/
|
||||
.tox/
|
||||
node_modules/
|
||||
.vscode/
|
||||
.idea/
|
||||
*.swp
|
||||
*.swo
|
||||
.DS_Store
|
||||
Thumbs.db
|
||||
build/
|
||||
dist/
|
||||
*.log
|
||||
.ruff_cache/
|
||||
.coverage
|
||||
@@ -4,7 +4,7 @@ Breadcrumbs only — details in README, `--help`, `.trinity/`, `DASHBOARD.local.
|
||||
|
||||
# Identity
|
||||
|
||||
DEVPULSE — Patrick's primary collaborator, orchestration hub. Design, plan, debug, dispatch, track. Build own modules (watchdog, feedback), DPLANs, FPLANs, memories. Venture into other branches to investigate, debug, fix small bugs. Delegate heavy multi-file builds to sub-agents. CWD is identity grounding.
|
||||
DEVPULSE — the user's primary collaborator, orchestration hub. Design, plan, debug, dispatch, track. Build own modules (watchdog, feedback), DPLANs, FPLANs, memories. Venture into other branches to investigate, debug, fix small bugs. Delegate heavy multi-file builds to sub-agents. CWD is identity grounding.
|
||||
|
||||
# How you work
|
||||
|
||||
@@ -82,7 +82,7 @@ drone @devpulse watchdog agent @target # Monitor tool, never run_in_b
|
||||
|
||||
# Interactive wake — tmux
|
||||
|
||||
Gives Patrick an interactive session, distinct from autonomous dispatch. Find the agent via `.trinity/passport.json`; use `dangerouslyDisableSandbox: true`.
|
||||
Gives User an interactive session, distinct from autonomous dispatch. Find the agent via `.trinity/passport.json`; use `dangerouslyDisableSandbox: true`.
|
||||
|
||||
```
|
||||
tmux new-session -d -s "name" -c "/path/to/branch"
|
||||
@@ -96,4 +96,4 @@ Compass is the curated truth-store of rated decisions (`good/bad/impressive/inte
|
||||
- Recall what happened / did we do X → `drone @memory search`.
|
||||
- At a fork, setting a pattern, or unsure of a convention → `drone @devpulse compass query "topic"` (rating shows per hit).
|
||||
- A good or bad decision made, or a convention confirmed → `drone @devpulse compass add "context" "decision" --rating good`. Add freely, no asking.
|
||||
- Patrick fires `/compass <rating> <note>` when he notices a decision — you write the entry from context.
|
||||
- User fires `/compass <rating> <note>` when he notices a decision — you write the entry from context.
|
||||
|
||||
@@ -53,7 +53,7 @@ _BRANCH_ROOT = Path(__file__).resolve().parents[3]
|
||||
DEFAULT_DB_PATH = _BRANCH_ROOT / "devpulse_json" / "compass" / "compass.db"
|
||||
|
||||
VALID_RATINGS = ("good", "bad", "impressive", "interesting")
|
||||
VALID_SOURCES = ("devpulse", "patrick")
|
||||
VALID_SOURCES = ("devpulse", "user")
|
||||
VALID_STATUSES = ("active", "archived")
|
||||
|
||||
# Columns we return / surface from the decisions table (everything useful).
|
||||
@@ -177,7 +177,7 @@ def add_decision(
|
||||
rating: One of ``good | bad | impressive | interesting``.
|
||||
note: Optional human observation.
|
||||
tags: Optional comma-separated tags.
|
||||
source: ``devpulse`` or ``patrick`` (default ``devpulse``).
|
||||
source: ``devpulse`` or ``user`` (default ``devpulse``).
|
||||
db_path: Optional DB path override (tests pass a temp path).
|
||||
created: Optional ISO date override; defaults to today. This is the
|
||||
ONLY place a "today" date is stamped.
|
||||
|
||||
@@ -63,13 +63,13 @@ HELP_TEXT = """\
|
||||
compass --help Show this help
|
||||
|
||||
[bold]Ratings:[/bold] good | bad | impressive | interesting
|
||||
[bold]Sources:[/bold] devpulse | patrick
|
||||
[bold]Sources:[/bold] devpulse | user
|
||||
|
||||
[bold]Options (add):[/bold]
|
||||
--rating R Required. One of the ratings above.
|
||||
--note "..." Optional human observation.
|
||||
--tags a,b,c Optional comma-separated tags.
|
||||
--source S Optional. devpulse (default) or patrick.
|
||||
--source S Optional. devpulse (default) or user.
|
||||
|
||||
[bold]Options (all subcommands):[/bold]
|
||||
--db PATH Use an alternate SQLite store (testing / power use).
|
||||
|
||||
@@ -1,10 +1,8 @@
|
||||
# Flow — Plan Lifecycle Management
|
||||
|
||||
Flow is AIPass's unified plan lifecycle system. Creates, tracks, closes, archives numbered work plans across multiple plan types (FPLAN, DPLAN) via data-driven plugin architecture.
|
||||
|
||||
## Commands
|
||||
|
||||
```bash
|
||||
# Commands
|
||||
`bash
|
||||
drone @flow create . "Subject" # FPLAN (default)
|
||||
drone @flow create . "Subject" master # FPLAN master template
|
||||
drone @flow create . "Design topic" dplan # DPLAN
|
||||
@@ -14,17 +12,13 @@ drone @flow list open # List open plans (all types)
|
||||
drone @flow list all # List all plans
|
||||
drone @flow restore FPLAN-0042 # Reopen closed plan
|
||||
```
|
||||
|
||||
## Architecture
|
||||
|
||||
# Architecture
|
||||
- `apps/flow.py` -- Entry point. Auto-discovers modules `apps/modules/` via `handle_command()` convention.
|
||||
- `apps/modules/` -- Thin orchestrators. No business logic. Route handlers, display results.
|
||||
- `apps/handlers/` -- Implementation. Grouped domain: `plan/`, `registry/`, `template/`, `dashboard/`, `mbank/`, `summary/`.
|
||||
- `templates/` -- Plan type directories. Each subdirectory contains Markdown templates. Registered via `drone @flow register`.
|
||||
- `flow_json/` -- Registries: per-type plan registries + `template_registry.json` (plan type definitions).
|
||||
|
||||
## Plan Type System
|
||||
|
||||
- `flow_json/` -- Registries: per-type plan registries + `template_registry.json` (plan type definitions).]
|
||||
# Plan Type System
|
||||
Plan types filesystem-driven. Drop directory `.md` templates into `templates/`, register, done:
|
||||
```bash
|
||||
drone @flow register testing TPLAN # Register new type
|
||||
@@ -32,35 +26,24 @@ drone @flow unregister testing # Remove type
|
||||
drone @flow templates # List registered types
|
||||
drone @flow scan # Find unregistered directories
|
||||
```
|
||||
|
||||
Discovered runtime `plan_type_loader.py` + `registry_ops.py`. No per-directory JSON config needed.
|
||||
|
||||
| Type | Prefix | Registry File | Templates |
|
||||
|------|--------|---------------|-----------|
|
||||
| flow_plans | FPLAN | fplan_registry.json | default, master |
|
||||
| dev_plans | DPLAN | dplan_registry.json | default |
|
||||
|
||||
## Critical Files
|
||||
|
||||
- `apps/flow.py` -- CLI entry point, module discovery, command routing
|
||||
- `apps/modules/create_plan.py` -- Plan creation orchestrator
|
||||
- `apps/modules/close_plan.py` -- Plan closure orchestrator (async post-processing, archival)
|
||||
- `apps/modules/list_plans.py` -- Multi-registry plan listing
|
||||
# Critical Files
|
||||
- `apps/modules/create/close/list_plan.py` -- Plan creation orchestrator
|
||||
- `apps/handlers/plan/list_ops.py` -- Merges plans all registries display
|
||||
- `apps/handlers/plan/display.py` -- All formatting functions (prefix-aware)
|
||||
- `apps/handlers/plan/close_ops.py` -- Close implementation (file ops, registry update, vector intake)
|
||||
- `apps/handlers/template/plan_type_loader.py` -- Plugin discovery + config resolution
|
||||
- `apps/handlers/registry/load_registry.py` -- Registry loader (supports per-type registry files)
|
||||
|
||||
## Integration Points
|
||||
|
||||
#Integration Points
|
||||
- **aipass.cli** -- Rich console output (`console`, `header`, `success`, `error`, `warning`)
|
||||
- **aipass.prax** -- System logger
|
||||
- **aipass.memory** -- Vector intake pipeline plan close
|
||||
- **aipass.trigger** -- Startup events + branch dashboard updates
|
||||
|
||||
## Conventions
|
||||
|
||||
#Conventions
|
||||
- Modules return `True` `handle_command()` when command recognized (even on failure), `False` only "not my command".
|
||||
- Plan IDs follow `{PREFIX}-{NNNN}_topic_slug_YYYY-MM-DD.md`.
|
||||
- All file I/O uses `pathlib.Path` + `encoding='utf-8'`.
|
||||
|
||||
@@ -9,12 +9,12 @@
|
||||
|
||||
## What Are Flow Plans?
|
||||
|
||||
Flow Plans (FPLANs) are **building** - autonomous construction: systems, features, modules.
|
||||
Default Flow Plans (FPLANs) are **building** - autonomous construction: systems, features, modules.
|
||||
|
||||
**FPLANs are disposable.** Exist exactly one task. When task complete, close this plan immediately -- do not leave open. Open FPLANs mean unfinished work. Work done = plan done: `drone @flow close {plan_number}`
|
||||
**FPLANs are disposable.** Exist exactly one task. When task complete, close this plan immediately -- do not leave open. Open FPLANs mean unfinished work. Work done = plan done: `drone @flow close {plan_number}` The plan is never lost. It is strored into our locl and global ,chroma vector db.
|
||||
|
||||
**This is NOT for:**
|
||||
- Research or exploration (use agents directly)
|
||||
- Research or exploration (use DPLANs and APLANs directly)
|
||||
- Quick fixes (just do it)
|
||||
- Discussion or planning (happens before creating FPLAN)
|
||||
|
||||
@@ -22,6 +22,7 @@ Flow Plans (FPLANs) are **building** - autonomous construction: systems, feature
|
||||
- Building features or modules
|
||||
- Single focused construction tasks
|
||||
- Sub-plans within master plan
|
||||
- Mostly use for sub-agents, in some cases may be issued to Agents citizens. Judjmemts calls.
|
||||
|
||||
---
|
||||
|
||||
@@ -49,6 +50,7 @@ Use dedicated directories - don't scatter files:
|
||||
| `tools/` | Utility scripts |
|
||||
| `artifacts/` | Agent outputs |
|
||||
| `docs/` | Documentation |
|
||||
| `Sub-agents/`|Projects/AIPass/src/aipass/flow/docs.local/sub_agent_drops|
|
||||
|
||||
---
|
||||
|
||||
@@ -56,7 +58,7 @@ Use dedicated directories - don't scatter files:
|
||||
|
||||
**You are orchestrator, not builder.**
|
||||
|
||||
Your 200k context is precious. Burning it on file reads + code writing risks compaction during autonomous work. Agents have clean context - use them for * building.
|
||||
Your 200k context is precious. Burning it on file reads + code writing risks compaction tool early during autonomous work. Agents have clean context - use them for
|
||||
|
||||
| You Do (Orchestrator) | Agents Do (Builders) |
|
||||
|-----------------------|----------------------|
|
||||
|
||||
@@ -46,10 +46,11 @@ Master Plan (roadmap)
|
||||
```
|
||||
|
||||
**How to start:**
|
||||
1. User provides planning doc or instructions (coordinate @devpulse)
|
||||
1. User provides planning doc DPLAN or instructions (coordinate @devpulse)
|
||||
2. Branch manager reads + understands scope
|
||||
3. Branch manager creates master plan: `drone @flow create . "Build X" master`
|
||||
3. Branch manager creates master plan: `drone @flow create "Build X" master`
|
||||
4. Branch manager fills phases, then executes autonomously
|
||||
5. Devepulse mayprovide a complete plan to you. Always confirm, Alwayd confirm the plan is sound, acucurate
|
||||
|
||||
---
|
||||
|
||||
@@ -57,7 +58,7 @@ Master Plan (roadmap)
|
||||
|
||||
**You are ORCHESTRATOR, not builder.**
|
||||
|
||||
Your 200k context is precious. Burning it on file reads + code writing risks compaction during autonomous work. Agents have clean context - use them for ALL building.
|
||||
Your 200k context is precious. Burning it on file reads + code writing risks auto compaction during autonomous work. Agents have clean context - use them for ALL building. Only devpulse is this accempion, user decideds when to compact. no auto compct for devpulse.
|
||||
|
||||
| You Do (Orchestrator) | Agents Do (Builders) |
|
||||
|-----------------------|----------------------|
|
||||
|
||||
@@ -17,7 +17,7 @@ Run by **devpulse** (only branch with git write). Tick each step as you go; fill
|
||||
> `.trinity/passport.json` in the cwd; running from the repo root fails with "No
|
||||
> passport found"). Read git (`status`, `log`, `diff`, `rev-parse`) is allowed raw.
|
||||
> ⚠️ `drone @git` has **no `tag` verb** — pushing the release tag is a MANUAL step
|
||||
> (Patrick, or raw `git tag`/`push` via `!`). All other writes go through drone.
|
||||
> (the user, or raw `git tag`/`push` via `!`). All other writes go through drone.
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -0,0 +1,103 @@
|
||||
# {plan_number} - {subject} (PROMPT CHANGE)
|
||||
|
||||
**Created**: {today}
|
||||
**Branch**: {location}
|
||||
**Status**: Active
|
||||
**Type**: Playbook — Prompt Change SOP
|
||||
|
||||
---
|
||||
|
||||
## Purpose
|
||||
|
||||
Any change to an injected prompt — the kernel, the navmap, a branch-local prompt, identity, a brand-new tier, a cadence tweak, or retiring one — must propagate to **every place that injects it AND every place that seeds it into a fresh install**. This SOP is the checklist that makes sure nothing is half-done. Run by **devpulse** (orchestrator); tick as you go; dispatch the owning branch where a step lives in its core. Born from FPLAN-0284, where the live wiring was fixed but `aipass init` kept handing new projects the retired global prompt for days because the *seed* template was never updated.
|
||||
|
||||
---
|
||||
|
||||
## The Law (read first — this is the trap)
|
||||
|
||||
1. **LIVE ≠ SEEDED.** Editing the repo's own `.aipass/hooks.json` makes the change work *for us* — it does **nothing** for a fresh clone, a new `aipass init` project, or a freshly spawned branch. Those are built from **separate seed sources**. A prompt change is not done until every seed path carries it.
|
||||
2. **Three wiring layers, each with its own seed.** A prompt only injects if all three agree:
|
||||
|
||||
| Layer | Live file | Seeded for fresh installs by |
|
||||
|---|---|---|
|
||||
| Handler registration | `.aipass/hooks.json` | git-tracked (travels with clone) **+** `.aipass/project_hooks.json` (what `aipass init` copies) |
|
||||
| Cadence (period/offset) | `hooks_json/custom_config/cadence_config.json` (machine-local, gitignored) | `cadence.py` `DEFAULTS` (the committed backstop) |
|
||||
| Event→handler bridge | `~/.claude/settings.json` (machine-local) | `setup.sh` **+** `.claude/provider_manifest.json` |
|
||||
|
||||
3. **Never delete a retired prompt.** Mark `(superseded)` in its header / disable it in `hooks.json`, or move it to `.archive/`. If a disabled handler still reads it **by path** for rollback, leave the file exactly where the handler looks.
|
||||
4. **The `.md` files travel by git; the wiring does not.** Prompt/tier `.md` files are tracked → a clone gets them free. The machine-local wiring (cadence_config, settings bridge) must be regenerated from the committed seed sources, so those seeds are what you must update.
|
||||
5. **One prompt source, every runtime — retire for one = retire for all.** There is ONE source of prompt truth (the tier `.md` files); both runtimes inject *the same content*, only delivery differs: **Claude Code** tiers by cadence (`UserPromptSubmit`, per turn — tier0 every turn, navmap periodically); **Codex CLI** injects the combined tiers once at **SessionStart** (`.codex/hooks/session_start_identity.py`). A change or retirement is NOT done until *both* runtimes point at the new content. (FPLAN-0284 retired the 8k global for Claude via cadence, but Codex's SessionStart kept reading the old global for days until separately rewired — the classic "fixed one runtime, forgot the other.")
|
||||
|
||||
---
|
||||
|
||||
## 1. Identify the change
|
||||
- [ ] Which prompt? (`.aipass/tier0_kernel.md` / `.aipass/tier1_navmap.md` / a branch's `.aipass/aipass_local_prompt.md` / identity / a NEW prompt / retiring one)
|
||||
- [ ] Kind? edit content · change cadence · add a new injected prompt · retire one
|
||||
- [ ] Owners of the files you'll touch — devpulse owns the tier files + project prompts; **@hooks** owns the engine, handlers, cadence, **and the Codex SessionStart hook** (`.codex/hooks/`); **@aipass** owns init/bootstrap; **@spawn** owns branch templates
|
||||
|
||||
## 2. Content
|
||||
- [ ] Edit the `.md`. Follow `.aipass/PROMPT_STYLE.md`.
|
||||
- [ ] ⚠️ Size caps: tier0 kernel target **< 2,000 chars**; navmap **< 8,000** (the hook truncates near 10k). To shrink, cut CONTENT, not whitespace — newlines are nearly free, so trimming spaces saves almost nothing.
|
||||
- [ ] ⚠️ An unclosed `<!-- comment` swallows the whole prompt downstream — confirm every comment is closed.
|
||||
|
||||
## 3. Wiring — make it inject LIVE (3 layers)
|
||||
- [ ] **Registration** — `.aipass/hooks.json`: handler entry present + `"enabled": true` (or `false` + a `_retired` note if retiring). New prompt → add the handler entry.
|
||||
- [ ] **Cadence** — `cadence_config.json` loaders: correct `period`/`offset` (tier0 `period:1` = every turn; navmap `period:5`). New loader → add it.
|
||||
- [ ] **Bridge (Claude Code)** — `~/.claude/settings.json`: a `UserPromptSubmit:<handler>` bridge line exists (machine-local — edit directly for the live machine). Retiring → remove the stale line.
|
||||
- [ ] **Codex runtime** — `.codex/hooks/session_start_identity.py` reads the tier `.md` files at SessionStart (tier0_kernel + tier1_navmap, each size-capped). New tier → add it to what this hook reads; retiring → stop reading the old prompt. Same content as Claude, different delivery. **@hooks owns — dispatch.**
|
||||
- [ ] New handler file lives at `src/aipass/hooks/apps/handlers/prompt/<name>.py` — **@hooks owns it; dispatch them to build it.**
|
||||
|
||||
## 4. Seed propagation — so FRESH installs get it (the step that's always forgotten)
|
||||
- [ ] **Fresh clone** — `setup.sh`: writes the settings bridge. Grep it for the handler name; add the `UserPromptSubmit:<handler>` line; remove any retired-handler bridge.
|
||||
- [ ] **Doctor source-of-truth** — `.claude/provider_manifest.json`: mirrors setup.sh's bridge list. Add/retire to match.
|
||||
- [ ] **Cadence backstop** — `cadence.py` `DEFAULTS`: contains the loader (so a clone with no `cadence_config.json` still fires it). Remove retired loaders' crumbs.
|
||||
- [ ] **`aipass init` (new projects)** — ⚠️ TWO files, both easy to miss:
|
||||
- `.aipass/project_hooks.json` (the template init copies into new projects) — mirror the live `hooks.json` (right handlers enabled, retired ones off/removed).
|
||||
- `src/aipass/aipass/apps/handlers/init/bootstrap.py` — seeds the prompt `.md` files into the new project's `.aipass/`. New tier → it must copy that `.md`; retiring → stop seeding the old one. **@aipass owns — dispatch.**
|
||||
- [ ] **`@spawn` (new branches)** — branch local-prompt template `src/aipass/spawn/templates/*/.aipass/aipass_local_prompt.md` + any stale doc-prose referencing old prompts. **@spawn owns — dispatch if more than cosmetic.**
|
||||
- [ ] **Codex for new installs** — if a fresh project/clone runs Codex, confirm its SessionStart hook reads the seeded tier files, not a retired prompt (the Codex entry point `AGENTS.md` is generated by `bootstrap.py`). **@hooks/@aipass own — dispatch.**
|
||||
|
||||
## 5. Verify LIVE (don't trust the edit)
|
||||
- [ ] Watch it actually inject — right content, right turns. Tier0 every turn; periodic tiers on their cadence.
|
||||
- [ ] After a `/compact`, confirm the prompt you expect reloads (post-compaction is exactly when the map matters most).
|
||||
- [ ] **seedgo** the touched branches to 100%. ⚠️ importlib-dispatched prompt handlers trip dead-code / unused-function / json-structure false-positives — add **3 `bypass.json` entries per new handler**, mirroring an existing prompt handler (DPLAN-0191).
|
||||
|
||||
## 6. Tidy superseded prompts
|
||||
- [ ] Disable in `hooks.json` (`enabled:false` + `_retired` note pointing at the replacement).
|
||||
- [ ] Mark the file `(superseded-<plan>)` in its header, or move to `.archive/` — **but** if a disabled handler reads it by path for rollback, leave it in place.
|
||||
- [ ] Archive pure snapshots/backups + stale design docs. Never delete.
|
||||
|
||||
## 7. CHANGELOG + wrap
|
||||
- [ ] `CHANGELOG.md`: entry under the dated section (Added / Changed / Fixed).
|
||||
- [ ] Update `.trinity/` memories.
|
||||
- [ ] Fill the Run Summary below; close (vectorizes the run to @memory).
|
||||
|
||||
---
|
||||
|
||||
## Run Summary
|
||||
|
||||
Fill as you go — this becomes the vectorized trail.
|
||||
|
||||
- **Date:** {today}
|
||||
- **Prompt(s) changed:**
|
||||
- **Layers touched:** (hooks.json · cadence · bridge · setup.sh · manifest · DEFAULTS · project_hooks · bootstrap · spawn)
|
||||
- **Dispatched to:** (@hooks / @aipass / @spawn …)
|
||||
- **Verified live:** (how — which turns, post-compaction reload)
|
||||
- **Seedgo:** (touched branches @ 100%?)
|
||||
- **Issues hit:**
|
||||
- **Notes for next run:** (refine this SOP — what was missing or wrong?)
|
||||
|
||||
---
|
||||
|
||||
## Listen (TTS-friendly summary)
|
||||
|
||||
This playbook is the checklist for changing any injected prompt in AIPass. The big lesson it captures is that live is not the same as seeded. When you change a prompt, editing the repository's own hook configuration makes it work for us right now, but it does nothing for a fresh clone, a newly initialised project, or a newly spawned branch, because those are all built from separate seed files. So the checklist walks you through three things. First, the content of the prompt itself, watching the size limits. Second, the three wiring layers that make it inject live, which are the handler registration, the cadence timing, and the event bridge. Third, and most important, every seed path that a fresh install is built from, including the main setup script, the doctor manifest, the cadence defaults, the two files behind the aipass init flow, and the spawn templates. There are also two runtimes — Claude Code and Codex — both injecting the same prompt content, so retiring or changing a prompt for one means doing it for the other; Claude reads it on a per-turn cadence, Codex reads it once at session start. Then you verify it actually injects, including right after a compaction, tidy away any retired prompt without deleting it, and update the changelog. Run it any time a prompt changes so nothing is left half wired.
|
||||
|
||||
---
|
||||
|
||||
## Close Command
|
||||
|
||||
When all steps are ticked and the Run Summary is filled:
|
||||
```bash
|
||||
drone @flow close {plan_number}
|
||||
```
|
||||
@@ -42,7 +42,8 @@ apps/
|
||||
claude.py # Claude Code bridge (provider settings entry point)
|
||||
prompt/ # Prompt injection hooks
|
||||
branch_loader.py # Injects aipass_local_prompt.md
|
||||
global_loader.py # Injects global prompt
|
||||
tier0_kernel.py # Injects tier0 kernel prompt (every turn)
|
||||
navmap.py # Injects tier1 navmap prompt (periodic)
|
||||
identity.py # Injects passport identity block
|
||||
security/ # Enforcement hooks
|
||||
edit_gate.py # Blocks edits while type errors exist
|
||||
@@ -70,7 +71,7 @@ tests/ # 15 test files, 244 tests
|
||||
|
||||
| Category | Count | Handlers |
|
||||
|----------|-------|----------|
|
||||
| prompt | 3 | branch_loader, global_loader, identity |
|
||||
| prompt | 4 | branch_loader, tier0_kernel, navmap, identity |
|
||||
| security | 3 | edit_gate, git_gate, subagent_gate |
|
||||
| lifecycle | 4 | auto_fix, auto_watchdog, compact, rollover |
|
||||
| notification | 4 | announce, email, stop_sound, tool_sound |
|
||||
|
||||
@@ -71,25 +71,10 @@
|
||||
"standard": "json_structure",
|
||||
"reason": "No JSON operations \u2014 reads markdown files and outputs text."
|
||||
},
|
||||
{
|
||||
"file": "apps/handlers/prompt/global_loader.py",
|
||||
"standard": "dead_code",
|
||||
"reason": "Invoked dynamically by engine via importlib from hooks.json handler path 'aipass.hooks.apps.handlers.prompt.global_loader.handle' \u2014 not statically imported by design. Verified wired in UserPromptSubmit.global_prompt + fires in engine.jsonl."
|
||||
},
|
||||
{
|
||||
"file": "apps/handlers/prompt/global_loader.py",
|
||||
"standard": "unused_function",
|
||||
"reason": "handle() called dynamically by engine._run_handler via importlib.import_module + getattr from hooks.json. Verified fires in engine.jsonl (UserPromptSubmit.global_prompt)."
|
||||
},
|
||||
{
|
||||
"file": "apps/handlers/prompt/global_loader.py",
|
||||
"standard": "json_structure",
|
||||
"reason": "No JSON operations \u2014 reads markdown file and outputs text."
|
||||
},
|
||||
{
|
||||
"file": "apps/handlers/prompt/tier0_kernel.py",
|
||||
"standard": "dead_code",
|
||||
"reason": "Invoked dynamically by engine via importlib from hooks.json handler path 'aipass.hooks.apps.handlers.prompt.tier0_kernel.handle' - not statically imported by design. Wired in UserPromptSubmit.tier0_kernel (FPLAN-0284). Same pattern as global_loader.py."
|
||||
"reason": "Invoked dynamically by engine via importlib from hooks.json handler path 'aipass.hooks.apps.handlers.prompt.tier0_kernel.handle' - not statically imported by design. Wired in UserPromptSubmit.tier0_kernel (FPLAN-0284)."
|
||||
},
|
||||
{
|
||||
"file": "apps/handlers/prompt/tier0_kernel.py",
|
||||
@@ -104,7 +89,7 @@
|
||||
{
|
||||
"file": "apps/handlers/prompt/navmap.py",
|
||||
"standard": "dead_code",
|
||||
"reason": "Invoked dynamically by engine via importlib from hooks.json handler path 'aipass.hooks.apps.handlers.prompt.navmap.handle' - not statically imported by design. Wired in UserPromptSubmit.navmap (FPLAN-0284). Same pattern as global_loader.py."
|
||||
"reason": "Invoked dynamically by engine via importlib from hooks.json handler path 'aipass.hooks.apps.handlers.prompt.navmap.handle' - not statically imported by design. Wired in UserPromptSubmit.navmap (FPLAN-0284)."
|
||||
},
|
||||
{
|
||||
"file": "apps/handlers/prompt/navmap.py",
|
||||
@@ -259,12 +244,12 @@
|
||||
{
|
||||
"file": "apps/modules/cadence.py",
|
||||
"standard": "dead_code",
|
||||
"reason": "Cadence module \u2014 should_fire() called from global_loader.py and branch_loader.py guard lines; reset_counter() called from compact.py PreCompact handler. Not statically discoverable because callers are themselves dynamically dispatched."
|
||||
"reason": "Cadence module \u2014 should_fire() called from tier0_kernel.py, navmap.py, and branch_loader.py guard lines; reset_counter() called from compact.py PreCompact handler. Not statically discoverable because callers are themselves dynamically dispatched."
|
||||
},
|
||||
{
|
||||
"file": "apps/modules/cadence.py",
|
||||
"standard": "unused_function",
|
||||
"reason": "should_fire() called from global_loader.py + branch_loader.py; reset_counter() called from compact.py. All callers are dynamically dispatched handlers."
|
||||
"reason": "should_fire() called from tier0_kernel.py, navmap.py, branch_loader.py; reset_counter() called from compact.py. All callers are dynamically dispatched handlers."
|
||||
},
|
||||
{
|
||||
"file": "apps/modules/cadence.py",
|
||||
@@ -604,26 +589,6 @@
|
||||
"standard": "meta",
|
||||
"reason": "Test files do not need Version/Modified metadata headers."
|
||||
},
|
||||
{
|
||||
"file": "tests/test_global_loader.py",
|
||||
"standard": "architecture",
|
||||
"reason": "Test files live in tests/, not in the 3-layer apps structure."
|
||||
},
|
||||
{
|
||||
"file": "tests/test_global_loader.py",
|
||||
"standard": "documentation",
|
||||
"reason": "Test methods use descriptive names as documentation per pytest convention."
|
||||
},
|
||||
{
|
||||
"file": "tests/test_global_loader.py",
|
||||
"standard": "encapsulation",
|
||||
"reason": "Tests import handlers directly to test implementation details."
|
||||
},
|
||||
{
|
||||
"file": "tests/test_global_loader.py",
|
||||
"standard": "meta",
|
||||
"reason": "Test files do not need Version/Modified metadata headers."
|
||||
},
|
||||
{
|
||||
"file": "tests/test_compact.py",
|
||||
"standard": "architecture",
|
||||
|
||||
@@ -58,7 +58,8 @@ src/aipass/hooks/
|
||||
│ │ │ └── claude.py # Claude Code bridge
|
||||
│ │ ├── prompt/ # Prompt injection hooks
|
||||
│ │ │ ├── branch_loader.py # Injects aipass_local_prompt.md
|
||||
│ │ │ ├── global_loader.py # Injects global prompt
|
||||
│ │ │ ├── tier0_kernel.py # Injects tier0 kernel prompt (every turn)
|
||||
│ │ │ ├── navmap.py # Injects tier1 navmap prompt (periodic)
|
||||
│ │ │ └── identity.py # Injects passport identity block
|
||||
│ │ ├── security/ # Enforcement hooks
|
||||
│ │ │ ├── edit_gate.py # Blocks unsafe edits (cross-branch, inbox, diagnostics)
|
||||
@@ -102,7 +103,7 @@ Handlers are called **dynamically at runtime** — the engine uses `importlib.im
|
||||
|
||||
| Event | Hooks | Description |
|
||||
|---|---|---|
|
||||
| UserPromptSubmit | identity, email, branch_loader, global_loader | Prompt injection + inbox check |
|
||||
| UserPromptSubmit | identity, email, branch_loader, tier0_kernel, navmap | Prompt injection + inbox check |
|
||||
| PreToolUse | tool_sound, edit_gate, git_gate, rm_gate | Security gates + guardrails + sound |
|
||||
| PostToolUse | auto_fix, auto_watchdog | Diagnostics + watchdog |
|
||||
| SubagentStop | subagent_gate | Seedgo validation |
|
||||
|
||||
@@ -40,13 +40,15 @@ def _read_last_session(branch_dir: Path) -> str | None:
|
||||
sessions = data.get("sessions", [])
|
||||
if sessions:
|
||||
last = sessions[0]
|
||||
result.append(
|
||||
f"Last session (#{last.get('id', '?')}, {last.get('d', '?')}): {last.get('sum', 'no summary')}"
|
||||
)
|
||||
learnings = data.get("key_learnings", {})
|
||||
if learnings:
|
||||
keys = list(learnings.keys())[-10:]
|
||||
result.append(f"Key learnings available: {', '.join(keys)}")
|
||||
sid = last.get("number", "?")
|
||||
sdate = last.get("date", "?")
|
||||
ssum = last.get("summary", "no summary")
|
||||
result.append(f"Last session (#{sid}, {sdate}): {ssum}")
|
||||
learnings = data.get("key_learnings", [])
|
||||
if isinstance(learnings, list) and learnings:
|
||||
keys = [entry.get("key", "?") for entry in learnings[-10:] if isinstance(entry, dict)]
|
||||
if keys:
|
||||
result.append(f"Key learnings available: {', '.join(keys)}")
|
||||
return "\n".join(result) if result else None
|
||||
except Exception as exc:
|
||||
logger.info("[HOOKS] compact: read session failed: %s", exc)
|
||||
@@ -85,7 +87,7 @@ def handle(hook_data: dict) -> dict:
|
||||
import importlib
|
||||
|
||||
cadence = importlib.import_module("aipass.hooks.apps.modules.cadence")
|
||||
cadence.reset_counter()
|
||||
cadence.reset_counter(hook_data=hook_data)
|
||||
except Exception as exc:
|
||||
logger.info("[HOOKS] compact: cadence reset failed: %s", exc)
|
||||
|
||||
|
||||
@@ -1,16 +1,15 @@
|
||||
# =================== AIPass ====================
|
||||
# Name: rollover.py
|
||||
# Version: 1.0.0
|
||||
# Description: Checks branch memory files and runs rollover if overdue (PreCompact)
|
||||
# Version: 2.0.0
|
||||
# Description: Triggers memory rollover via @memory when files are overdue (PreCompact)
|
||||
# Branch: hooks
|
||||
# Layer: apps/handlers/lifecycle
|
||||
# Created: 2026-05-22
|
||||
# Modified: 2026-05-22
|
||||
# Modified: 2026-06-19
|
||||
# =============================================
|
||||
|
||||
"""Scans all branches for over-limit memory files and triggers rollover via drone."""
|
||||
"""Delegates rollover detection to @memory and triggers rollover if overdue."""
|
||||
|
||||
import json
|
||||
import os
|
||||
import subprocess
|
||||
from pathlib import Path
|
||||
@@ -31,83 +30,24 @@ def _find_repo_root() -> Path | None:
|
||||
return None
|
||||
|
||||
|
||||
def _read_registry(repo_root: Path) -> list[dict]:
|
||||
registry_path = repo_root / "AIPASS_REGISTRY.json"
|
||||
if not registry_path.exists():
|
||||
return []
|
||||
def _run_check(repo_root: Path) -> tuple[bool, str]:
|
||||
try:
|
||||
data = json.loads(registry_path.read_text(encoding="utf-8"))
|
||||
branches = data.get("branches", [])
|
||||
for branch in branches:
|
||||
raw_path = branch.get("path", "")
|
||||
resolved = Path(raw_path)
|
||||
if not resolved.is_absolute():
|
||||
resolved = repo_root / raw_path
|
||||
branch["_resolved_path"] = resolved
|
||||
return branches
|
||||
result = subprocess.run(
|
||||
["drone", "@memory", "rollover", "check"],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=30,
|
||||
cwd=str(repo_root),
|
||||
)
|
||||
stdout = result.stdout.strip()
|
||||
has_overdue = "ready for rollover" in stdout.lower()
|
||||
return has_overdue, stdout
|
||||
except subprocess.TimeoutExpired:
|
||||
logger.warning("[HOOKS] rollover: check timed out (30s)")
|
||||
return False, "check timed out"
|
||||
except Exception as exc:
|
||||
logger.info("[HOOKS] rollover: registry read failed: %s", exc)
|
||||
return []
|
||||
|
||||
|
||||
def _check_file(file_path: Path) -> tuple[bool, str]:
|
||||
if not file_path.is_file():
|
||||
return False, ""
|
||||
try:
|
||||
raw = file_path.read_text(encoding="utf-8")
|
||||
data = json.loads(raw)
|
||||
except Exception as exc:
|
||||
logger.info("[HOOKS] rollover: file parse failed %s: %s", file_path, exc)
|
||||
return False, ""
|
||||
|
||||
limits = data.get("document_metadata", {}).get("limits", {})
|
||||
|
||||
has_v2_limits = any(k in limits for k in ("max_sessions", "max_key_learnings", "max_observations"))
|
||||
if has_v2_limits:
|
||||
reasons: list[str] = []
|
||||
max_sessions = limits.get("max_sessions")
|
||||
if max_sessions is not None:
|
||||
sessions = data.get("sessions", [])
|
||||
if isinstance(sessions, list) and len(sessions) >= max_sessions:
|
||||
reasons.append(f"{len(sessions)}/{max_sessions} sessions")
|
||||
|
||||
max_key_learnings = limits.get("max_key_learnings")
|
||||
if max_key_learnings is not None:
|
||||
key_learnings = data.get("key_learnings", {})
|
||||
if isinstance(key_learnings, dict) and len(key_learnings) >= max_key_learnings:
|
||||
reasons.append(f"{len(key_learnings)}/{max_key_learnings} learnings")
|
||||
|
||||
max_observations = limits.get("max_observations")
|
||||
if max_observations is not None:
|
||||
observations = data.get("observations", [])
|
||||
if isinstance(observations, list) and len(observations) >= max_observations:
|
||||
reasons.append(f"{len(observations)}/{max_observations} observations")
|
||||
|
||||
if reasons:
|
||||
return True, ", ".join(reasons)
|
||||
return False, ""
|
||||
|
||||
max_lines = limits.get("max_lines", 600)
|
||||
current_lines = raw.count("\n") + 1
|
||||
if current_lines >= max_lines:
|
||||
return True, f"{current_lines}/{max_lines} lines"
|
||||
return False, ""
|
||||
|
||||
|
||||
def _find_overdue(repo_root: Path) -> list[tuple[str, str, str]]:
|
||||
branches = _read_registry(repo_root)
|
||||
overdue: list[tuple[str, str, str]] = []
|
||||
for branch in branches:
|
||||
name = branch.get("name", "unknown")
|
||||
branch_path = branch.get("_resolved_path")
|
||||
if not branch_path or not branch_path.is_dir():
|
||||
continue
|
||||
for memory_type in ("local", "observations"):
|
||||
file_path = branch_path / ".trinity" / f"{memory_type}.json"
|
||||
is_overdue, reason = _check_file(file_path)
|
||||
if is_overdue:
|
||||
overdue.append((name, memory_type, reason))
|
||||
return overdue
|
||||
logger.warning("[HOOKS] rollover: check failed: %s", exc)
|
||||
return False, str(exc)
|
||||
|
||||
|
||||
def _run_rollover(repo_root: Path) -> tuple[bool, str]:
|
||||
@@ -121,35 +61,30 @@ def _run_rollover(repo_root: Path) -> tuple[bool, str]:
|
||||
)
|
||||
return result.returncode == 0, result.stdout + result.stderr
|
||||
except subprocess.TimeoutExpired:
|
||||
logger.info("[HOOKS] rollover: drone rollover timed out (110s)")
|
||||
logger.warning("[HOOKS] rollover: drone rollover timed out (110s)")
|
||||
return False, "Rollover timed out (110s)"
|
||||
except Exception as exc:
|
||||
logger.info("[HOOKS] rollover: drone rollover failed: %s", exc)
|
||||
logger.warning("[HOOKS] rollover: drone rollover failed: %s", exc)
|
||||
return False, str(exc)
|
||||
|
||||
|
||||
def handle(hook_data: dict) -> dict: # noqa: ARG001
|
||||
"""Check memory files for overflow and trigger rollover if needed."""
|
||||
try:
|
||||
repo_root = _find_repo_root()
|
||||
if not repo_root:
|
||||
return {"stdout": "", "exit_code": 0}
|
||||
|
||||
overdue = _find_overdue(repo_root)
|
||||
if not overdue:
|
||||
return {"stdout": "", "exit_code": 0}
|
||||
|
||||
summary = "; ".join(f"{name}.{mtype} ({reason})" for name, mtype, reason in overdue)
|
||||
logger.info("[HOOKS] rollover: %d overdue — %s", len(overdue), summary)
|
||||
|
||||
success, output = _run_rollover(repo_root)
|
||||
if success:
|
||||
logger.info("[HOOKS] rollover: complete (%d files processed)", len(overdue))
|
||||
else:
|
||||
logger.info("[HOOKS] rollover: failed — %s", output[:200])
|
||||
|
||||
return {"stdout": "", "exit_code": 0, "sound": "pre compact rollover"}
|
||||
|
||||
except Exception as exc:
|
||||
logger.info("[HOOKS] rollover: unexpected error: %s", exc)
|
||||
repo_root = _find_repo_root()
|
||||
if not repo_root:
|
||||
logger.warning("[HOOKS] rollover: no repo root found — cannot check")
|
||||
return {"stdout": "", "exit_code": 0}
|
||||
|
||||
has_overdue, check_output = _run_check(repo_root)
|
||||
if not has_overdue:
|
||||
return {"stdout": "", "exit_code": 0}
|
||||
|
||||
logger.info("[HOOKS] rollover: overdue files detected — %s", check_output.replace("\n", " | "))
|
||||
|
||||
success, output = _run_rollover(repo_root)
|
||||
if success:
|
||||
logger.info("[HOOKS] rollover: complete")
|
||||
else:
|
||||
logger.warning("[HOOKS] rollover: FAILED — %s", output[:300])
|
||||
|
||||
return {"stdout": "", "exit_code": 0, "sound": "pre compact rollover"}
|
||||
|
||||
@@ -1,59 +0,0 @@
|
||||
# =================== AIPass ====================
|
||||
# Name: global_loader.py
|
||||
# Version: 1.0.0
|
||||
# Description: Loads AIPass global prompt for injection (UserPromptSubmit)
|
||||
# Branch: hooks
|
||||
# Layer: apps/handlers/prompt
|
||||
# Created: 2026-05-22
|
||||
# Modified: 2026-05-22
|
||||
# =============================================
|
||||
|
||||
"""Loads .aipass/aipass_global_prompt.md from AIPASS_HOME for prompt injection."""
|
||||
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
from aipass.prax.apps.modules.logger import system_logger as logger
|
||||
|
||||
|
||||
def _find_project_prompt() -> Path | None:
|
||||
"""Walk up from CWD to find the nearest .aipass/aipass_global_prompt.md."""
|
||||
cwd = Path.cwd()
|
||||
for parent in [cwd, *cwd.parents]:
|
||||
candidate = parent / ".aipass" / "aipass_global_prompt.md"
|
||||
if candidate.is_file():
|
||||
return candidate
|
||||
if parent == parent.parent:
|
||||
break
|
||||
return None
|
||||
|
||||
|
||||
def handle(hook_data: dict) -> dict:
|
||||
"""Load global prompt — project-local if outside AIPass, AIPass-internal if inside."""
|
||||
try:
|
||||
import importlib
|
||||
|
||||
cadence = importlib.import_module("aipass.hooks.apps.modules.cadence")
|
||||
if not cadence.should_fire("global", hook_data):
|
||||
return {"stdout": "", "exit_code": 0}
|
||||
except Exception as exc:
|
||||
logger.info("[HOOKS] global_loader: cadence check failed, firing anyway: %s", exc)
|
||||
|
||||
try:
|
||||
aipass_home = os.environ.get("AIPASS_HOME", "")
|
||||
cwd = str(Path.cwd())
|
||||
|
||||
if aipass_home and cwd.startswith(aipass_home):
|
||||
prompt_file = Path(aipass_home) / ".aipass" / "aipass_global_prompt.md"
|
||||
else:
|
||||
prompt_file = _find_project_prompt()
|
||||
|
||||
if not prompt_file or not prompt_file.exists():
|
||||
return {"stdout": "", "exit_code": 0}
|
||||
|
||||
content = prompt_file.read_text(encoding="utf-8")
|
||||
return {"stdout": content, "exit_code": 0, "sound": "global prompt"}
|
||||
|
||||
except Exception as exc:
|
||||
logger.info("[HOOKS] global_loader: unexpected error: %s", exc)
|
||||
return {"stdout": "", "exit_code": 0}
|
||||
@@ -46,7 +46,6 @@ DEFAULTS = {
|
||||
"loaders": {
|
||||
"tier0": {"period": 1},
|
||||
"navmap": {"period": 5, "offset": 0},
|
||||
"global": {"offset": 0},
|
||||
"branch": {"offset": 0},
|
||||
},
|
||||
}
|
||||
@@ -227,10 +226,21 @@ def should_fire(loader_name: str, hook_data: dict | None = None) -> bool:
|
||||
return fired
|
||||
|
||||
|
||||
def reset_counter() -> None:
|
||||
def reset_counter(hook_data: dict | None = None) -> None:
|
||||
"""Reset counter to -1 so next turn reads 0 (all loaders fire). Called from PreCompact."""
|
||||
path = _state_path()
|
||||
session_id = os.environ.get("CLAUDE_CODE_SESSION_ID", "")
|
||||
|
||||
if path is None and hook_data:
|
||||
fallback_id = hook_data.get("session_id", "")
|
||||
if fallback_id:
|
||||
path = _GUARD_DIR / f"aipass-cadence-{fallback_id}.json"
|
||||
session_id = fallback_id
|
||||
|
||||
session_short = session_id[:8] if session_id else "none"
|
||||
|
||||
if path is None:
|
||||
logger.info("[HOOKS] cadence: reset_counter SKIPPED — no session ID (env CLAUDE_CODE_SESSION_ID not set)")
|
||||
return
|
||||
|
||||
fd = None
|
||||
@@ -238,14 +248,26 @@ def reset_counter() -> None:
|
||||
fd = open(path, "a+") # noqa: SIM115
|
||||
_lock(fd)
|
||||
fd.seek(0)
|
||||
content = fd.read()
|
||||
old_turn = -1
|
||||
if content.strip():
|
||||
try:
|
||||
old_turn = json.loads(content).get("turn", -1)
|
||||
except json.JSONDecodeError as exc:
|
||||
logger.info("[HOOKS] cadence: reset read old state failed: %s", exc)
|
||||
fd.seek(0)
|
||||
fd.truncate()
|
||||
fd.write(json.dumps({"turn": -1, "token": -1}))
|
||||
fd.flush()
|
||||
_close_fd(fd)
|
||||
fd = None
|
||||
logger.info("[HOOKS] cadence: counter reset for post-compact re-injection")
|
||||
logger.info(
|
||||
"[HOOKS] cadence: counter reset for post-compact re-injection session=%s prev_turn=%d",
|
||||
session_short,
|
||||
old_turn,
|
||||
)
|
||||
except OSError as exc:
|
||||
logger.info("[HOOKS] cadence: reset write failed: %s", exc)
|
||||
logger.info("[HOOKS] cadence: reset write FAILED session=%s: %s", session_short, exc)
|
||||
if fd is not None:
|
||||
_close_fd(fd)
|
||||
|
||||
|
||||
@@ -322,8 +322,8 @@ class TestConfig:
|
||||
|
||||
assert config["enabled"] is True
|
||||
assert config["period"] == 5
|
||||
assert config["loaders"]["global"]["offset"] == 0
|
||||
assert config["loaders"]["branch"]["offset"] == 0
|
||||
assert "global" not in config["loaders"]
|
||||
|
||||
def test_defaults_include_tiered_loaders(self, tmp_path):
|
||||
"""Fresh clone with no cadence_config.json gets tiered cadence out of the box."""
|
||||
@@ -467,22 +467,31 @@ class TestLoaderCadenceGuard:
|
||||
def setup_method(self):
|
||||
_reset_module_globals()
|
||||
|
||||
def test_global_loader_skips_on_non_fire_turn(self, tmp_path):
|
||||
"""Skip = empty stdout AND no sound key — a skipped loader is SILENT."""
|
||||
from aipass.hooks.apps.handlers.prompt.global_loader import handle
|
||||
def test_tier0_kernel_fires_every_turn(self, tmp_path):
|
||||
"""tier0 has period:1 — fires on every turn including non-fire turns for others."""
|
||||
from aipass.hooks.apps.handlers.prompt.tier0_kernel import handle
|
||||
|
||||
_write_state(tmp_path, turn=0) # next turn = 1 = skip
|
||||
config = tmp_path / "cadence.json"
|
||||
config.write_text(
|
||||
json.dumps(
|
||||
{
|
||||
"enabled": True,
|
||||
"period": 5,
|
||||
"loaders": {"tier0": {"period": 1}},
|
||||
}
|
||||
)
|
||||
)
|
||||
|
||||
_write_state(tmp_path, turn=2)
|
||||
|
||||
with (
|
||||
patch(f"{MODULE}._GUARD_DIR", tmp_path),
|
||||
patch.dict("os.environ", {"CLAUDE_CODE_SESSION_ID": "test-session"}),
|
||||
patch(f"{MODULE}._CONFIG_PATH", tmp_path / "cadence.json"),
|
||||
patch(f"{MODULE}._CONFIG_PATH", config),
|
||||
):
|
||||
result = handle({})
|
||||
|
||||
assert result["stdout"] == ""
|
||||
assert result["exit_code"] == 0
|
||||
assert "sound" not in result
|
||||
|
||||
def test_branch_loader_skips_on_non_fire_turn(self, tmp_path):
|
||||
"""Skip = empty stdout AND no sound key — a skipped loader is SILENT."""
|
||||
@@ -502,6 +511,233 @@ class TestLoaderCadenceGuard:
|
||||
assert "sound" not in result
|
||||
|
||||
|
||||
class TestResetCounterObservability:
|
||||
"""Tests for reset_counter fail-loud logging and session ID tracking."""
|
||||
|
||||
def setup_method(self):
|
||||
_reset_module_globals()
|
||||
|
||||
def test_reset_logs_session_id_and_prev_turn(self, tmp_path):
|
||||
from aipass.hooks.apps.modules.cadence import reset_counter
|
||||
|
||||
_write_state(tmp_path, turn=11)
|
||||
|
||||
with (
|
||||
patch(f"{MODULE}._GUARD_DIR", tmp_path),
|
||||
patch.dict("os.environ", {"CLAUDE_CODE_SESSION_ID": "test-session"}),
|
||||
patch(f"{MODULE}.logger") as mock_logger,
|
||||
):
|
||||
reset_counter()
|
||||
|
||||
reset_calls = [c for c in mock_logger.info.call_args_list if "post-compact re-injection" in str(c)]
|
||||
assert len(reset_calls) == 1
|
||||
fmt_str = reset_calls[0][0][0]
|
||||
fmt_args = reset_calls[0][0][1:]
|
||||
log_line = fmt_str % fmt_args
|
||||
assert "session=test-ses" in log_line
|
||||
assert "prev_turn=11" in log_line
|
||||
|
||||
def test_reset_no_session_logs_warning(self, tmp_path):
|
||||
from aipass.hooks.apps.modules.cadence import reset_counter
|
||||
|
||||
with (
|
||||
patch(f"{MODULE}._GUARD_DIR", tmp_path),
|
||||
patch(f"{MODULE}.logger") as mock_logger,
|
||||
):
|
||||
env = dict(os.environ)
|
||||
env.pop("CLAUDE_CODE_SESSION_ID", None)
|
||||
with patch.dict("os.environ", env, clear=True):
|
||||
reset_counter()
|
||||
|
||||
calls = [str(c) for c in mock_logger.info.call_args_list]
|
||||
warning_calls = [c for c in calls if "SKIPPED" in c]
|
||||
assert len(warning_calls) == 1
|
||||
|
||||
def test_reset_fallback_to_hook_data_session_id(self, tmp_path):
|
||||
from aipass.hooks.apps.modules.cadence import reset_counter
|
||||
|
||||
state_file = tmp_path / "aipass-cadence-fallback-id.json"
|
||||
state_file.write_text(json.dumps({"turn": 5}))
|
||||
|
||||
with (
|
||||
patch(f"{MODULE}._GUARD_DIR", tmp_path),
|
||||
):
|
||||
env = dict(os.environ)
|
||||
env.pop("CLAUDE_CODE_SESSION_ID", None)
|
||||
with patch.dict("os.environ", env, clear=True):
|
||||
reset_counter(hook_data={"session_id": "fallback-id"})
|
||||
|
||||
data = json.loads(state_file.read_text())
|
||||
assert data["turn"] == -1
|
||||
|
||||
def test_reset_fallback_creates_file_if_missing(self, tmp_path):
|
||||
from aipass.hooks.apps.modules.cadence import reset_counter
|
||||
|
||||
with (
|
||||
patch(f"{MODULE}._GUARD_DIR", tmp_path),
|
||||
):
|
||||
env = dict(os.environ)
|
||||
env.pop("CLAUDE_CODE_SESSION_ID", None)
|
||||
with patch.dict("os.environ", env, clear=True):
|
||||
reset_counter(hook_data={"session_id": "new-fallback"})
|
||||
|
||||
state_file = tmp_path / "aipass-cadence-new-fallback.json"
|
||||
assert state_file.exists()
|
||||
assert json.loads(state_file.read_text())["turn"] == -1
|
||||
|
||||
def test_reset_env_takes_priority_over_hook_data(self, tmp_path):
|
||||
from aipass.hooks.apps.modules.cadence import reset_counter
|
||||
|
||||
env_file = tmp_path / "aipass-cadence-env-session.json"
|
||||
env_file.write_text(json.dumps({"turn": 9}))
|
||||
|
||||
hook_file = tmp_path / "aipass-cadence-hook-session.json"
|
||||
hook_file.write_text(json.dumps({"turn": 3}))
|
||||
|
||||
with (
|
||||
patch(f"{MODULE}._GUARD_DIR", tmp_path),
|
||||
patch.dict("os.environ", {"CLAUDE_CODE_SESSION_ID": "env-session"}),
|
||||
):
|
||||
reset_counter(hook_data={"session_id": "hook-session"})
|
||||
|
||||
assert json.loads(env_file.read_text())["turn"] == -1
|
||||
assert json.loads(hook_file.read_text())["turn"] == 3
|
||||
|
||||
def test_reset_hook_data_empty_session_id_logs_skip(self, tmp_path):
|
||||
from aipass.hooks.apps.modules.cadence import reset_counter
|
||||
|
||||
with (
|
||||
patch(f"{MODULE}._GUARD_DIR", tmp_path),
|
||||
patch(f"{MODULE}.logger") as mock_logger,
|
||||
):
|
||||
env = dict(os.environ)
|
||||
env.pop("CLAUDE_CODE_SESSION_ID", None)
|
||||
with patch.dict("os.environ", env, clear=True):
|
||||
reset_counter(hook_data={"session_id": ""})
|
||||
|
||||
calls = [str(c) for c in mock_logger.info.call_args_list]
|
||||
assert any("SKIPPED" in c for c in calls)
|
||||
|
||||
def test_reset_prev_turn_from_corrupt_file(self, tmp_path):
|
||||
from aipass.hooks.apps.modules.cadence import reset_counter
|
||||
|
||||
state_file = tmp_path / "aipass-cadence-test-session.json"
|
||||
state_file.write_text("not valid json{{{")
|
||||
|
||||
with (
|
||||
patch(f"{MODULE}._GUARD_DIR", tmp_path),
|
||||
patch.dict("os.environ", {"CLAUDE_CODE_SESSION_ID": "test-session"}),
|
||||
):
|
||||
reset_counter()
|
||||
|
||||
data = json.loads(state_file.read_text())
|
||||
assert data["turn"] == -1
|
||||
|
||||
|
||||
class TestPostCompactDeterminism:
|
||||
"""Prove that post-compaction reload fires ALL loaders deterministically."""
|
||||
|
||||
def setup_method(self):
|
||||
_reset_module_globals()
|
||||
|
||||
def test_all_tiered_loaders_fire_after_reset(self, tmp_path):
|
||||
from aipass.hooks.apps.modules.cadence import reset_counter, should_fire
|
||||
|
||||
config = tmp_path / "cadence.json"
|
||||
config.write_text(
|
||||
json.dumps(
|
||||
{
|
||||
"enabled": True,
|
||||
"period": 5,
|
||||
"loaders": {
|
||||
"tier0": {"period": 1},
|
||||
"navmap": {"period": 5, "offset": 0},
|
||||
"branch": {"offset": 0},
|
||||
},
|
||||
}
|
||||
)
|
||||
)
|
||||
|
||||
_write_state(tmp_path, turn=11)
|
||||
|
||||
with (
|
||||
patch(f"{MODULE}._GUARD_DIR", tmp_path),
|
||||
patch.dict("os.environ", {"CLAUDE_CODE_SESSION_ID": "test-session"}),
|
||||
patch(f"{MODULE}._CONFIG_PATH", config),
|
||||
):
|
||||
reset_counter()
|
||||
|
||||
_reset_module_globals()
|
||||
|
||||
with (
|
||||
patch(f"{MODULE}._GUARD_DIR", tmp_path),
|
||||
patch.dict("os.environ", {"CLAUDE_CODE_SESSION_ID": "test-session"}),
|
||||
patch(f"{MODULE}._CONFIG_PATH", config),
|
||||
):
|
||||
assert should_fire("tier0") is True
|
||||
_reset_module_globals()
|
||||
assert should_fire("navmap") is True
|
||||
_reset_module_globals()
|
||||
assert should_fire("branch") is True
|
||||
|
||||
def test_reset_at_any_turn_produces_turn_zero(self, tmp_path):
|
||||
from aipass.hooks.apps.modules.cadence import reset_counter, should_fire
|
||||
|
||||
for prev_turn in [0, 1, 4, 5, 10, 11, 99]:
|
||||
_reset_module_globals()
|
||||
_write_state(tmp_path, turn=prev_turn)
|
||||
|
||||
with (
|
||||
patch(f"{MODULE}._GUARD_DIR", tmp_path),
|
||||
patch.dict("os.environ", {"CLAUDE_CODE_SESSION_ID": "test-session"}),
|
||||
patch(f"{MODULE}._CONFIG_PATH", tmp_path / "cadence.json"),
|
||||
):
|
||||
reset_counter()
|
||||
|
||||
_reset_module_globals()
|
||||
|
||||
with (
|
||||
patch(f"{MODULE}._GUARD_DIR", tmp_path),
|
||||
patch.dict("os.environ", {"CLAUDE_CODE_SESSION_ID": "test-session"}),
|
||||
patch(f"{MODULE}._CONFIG_PATH", tmp_path / "cadence.json"),
|
||||
):
|
||||
result = should_fire("navmap")
|
||||
state = json.loads((tmp_path / "aipass-cadence-test-session.json").read_text())
|
||||
assert state["turn"] == 0, f"Expected turn 0 after reset from {prev_turn}"
|
||||
assert result is True, f"navmap should fire after reset from turn {prev_turn}"
|
||||
|
||||
def test_compact_handler_calls_reset_with_hook_data(self):
|
||||
from aipass.hooks.apps.handlers.lifecycle.compact import handle
|
||||
|
||||
hook_data = {"cwd": "/tmp/fake", "session_id": "test-123"}
|
||||
|
||||
with (
|
||||
patch("importlib.import_module") as mock_import,
|
||||
):
|
||||
mock_cadence = mock_import.return_value
|
||||
result = handle(hook_data)
|
||||
|
||||
mock_cadence.reset_counter.assert_called_once_with(hook_data=hook_data)
|
||||
assert result["exit_code"] == 0
|
||||
|
||||
def test_double_reset_is_idempotent(self, tmp_path):
|
||||
from aipass.hooks.apps.modules.cadence import reset_counter
|
||||
|
||||
_write_state(tmp_path, turn=11)
|
||||
|
||||
with (
|
||||
patch(f"{MODULE}._GUARD_DIR", tmp_path),
|
||||
patch.dict("os.environ", {"CLAUDE_CODE_SESSION_ID": "test-session"}),
|
||||
):
|
||||
reset_counter()
|
||||
_reset_module_globals()
|
||||
reset_counter()
|
||||
|
||||
state_file = tmp_path / "aipass-cadence-test-session.json"
|
||||
data = json.loads(state_file.read_text())
|
||||
assert data["turn"] == -1
|
||||
|
||||
|
||||
class TestPerLoaderPeriod:
|
||||
def setup_method(self):
|
||||
_reset_module_globals()
|
||||
|
||||
@@ -23,8 +23,8 @@ class TestCompactHandler:
|
||||
local.write_text(
|
||||
json.dumps(
|
||||
{
|
||||
"sessions": [{"id": "S10", "d": "2026-05-22", "sum": "did stuff"}],
|
||||
"key_learnings": {"learn1": "value1"},
|
||||
"sessions": [{"number": 10, "date": "2026-05-22", "summary": "did stuff", "status": "completed"}],
|
||||
"key_learnings": [{"number": 1, "date": "2026-05-22", "key": "learn1", "value": "value1"}],
|
||||
}
|
||||
),
|
||||
encoding="utf-8",
|
||||
|
||||
@@ -1,85 +0,0 @@
|
||||
# =================== AIPass ====================
|
||||
# Name: test_global_loader.py
|
||||
# Version: 1.0.0
|
||||
# Description: Tests for global_loader prompt handler
|
||||
# Branch: hooks
|
||||
# Created: 2026-05-22
|
||||
# Modified: 2026-05-22
|
||||
# =============================================
|
||||
|
||||
"""Tests for handlers/prompt/global_loader.py."""
|
||||
|
||||
from unittest.mock import patch, MagicMock
|
||||
|
||||
|
||||
def _mock_cadence_fires():
|
||||
"""Return a mock cadence module where should_fire always returns True."""
|
||||
mock = MagicMock()
|
||||
mock.should_fire.return_value = True
|
||||
return mock
|
||||
|
||||
|
||||
class TestGlobalLoaderHandler:
|
||||
def test_loads_global_prompt(self, tmp_path, monkeypatch):
|
||||
from aipass.hooks.apps.handlers.prompt.global_loader import handle
|
||||
|
||||
aipass_dir = tmp_path / ".aipass"
|
||||
aipass_dir.mkdir()
|
||||
prompt = aipass_dir / "aipass_global_prompt.md"
|
||||
prompt.write_text("# AIPass Global\nContext here", encoding="utf-8")
|
||||
monkeypatch.chdir(tmp_path)
|
||||
|
||||
with patch.dict("os.environ", {"AIPASS_HOME": str(tmp_path)}):
|
||||
with patch("importlib.import_module", return_value=_mock_cadence_fires()):
|
||||
result = handle({})
|
||||
|
||||
assert result["exit_code"] == 0
|
||||
assert "AIPass Global" in result["stdout"]
|
||||
assert "Context here" in result["stdout"]
|
||||
assert result["sound"] == "global prompt"
|
||||
|
||||
def test_returns_empty_when_file_missing(self, tmp_path, monkeypatch):
|
||||
from aipass.hooks.apps.handlers.prompt.global_loader import handle
|
||||
|
||||
monkeypatch.chdir(tmp_path)
|
||||
with patch.dict("os.environ", {"AIPASS_HOME": str(tmp_path)}):
|
||||
with patch("importlib.import_module", return_value=_mock_cadence_fires()):
|
||||
result = handle({})
|
||||
|
||||
assert result["exit_code"] == 0
|
||||
assert result["stdout"] == ""
|
||||
assert "sound" not in result
|
||||
|
||||
def test_empty_hook_data(self, tmp_path, monkeypatch):
|
||||
from aipass.hooks.apps.handlers.prompt.global_loader import handle
|
||||
|
||||
aipass_dir = tmp_path / ".aipass"
|
||||
aipass_dir.mkdir()
|
||||
(aipass_dir / "aipass_global_prompt.md").write_text("content", encoding="utf-8")
|
||||
monkeypatch.chdir(tmp_path)
|
||||
|
||||
with patch.dict("os.environ", {"AIPASS_HOME": str(tmp_path)}):
|
||||
with patch("importlib.import_module", return_value=_mock_cadence_fires()):
|
||||
result = handle({})
|
||||
|
||||
assert result["exit_code"] == 0
|
||||
assert result["stdout"] == "content"
|
||||
|
||||
def test_external_project_gets_own_prompt(self, tmp_path, monkeypatch):
|
||||
"""CWD outside AIPASS_HOME → loads project-local prompt, not AIPass."""
|
||||
from aipass.hooks.apps.handlers.prompt.global_loader import handle
|
||||
|
||||
project = tmp_path / "my-project"
|
||||
project.mkdir()
|
||||
aipass_dir = project / ".aipass"
|
||||
aipass_dir.mkdir()
|
||||
(aipass_dir / "aipass_global_prompt.md").write_text("# Project Prompt", encoding="utf-8")
|
||||
monkeypatch.chdir(project)
|
||||
|
||||
with patch.dict("os.environ", {"AIPASS_HOME": "/some/other/path"}):
|
||||
with patch("importlib.import_module", return_value=_mock_cadence_fires()):
|
||||
result = handle({})
|
||||
|
||||
assert result["exit_code"] == 0
|
||||
assert "Project Prompt" in result["stdout"]
|
||||
assert result["sound"] == "global prompt"
|
||||
@@ -1,23 +1,43 @@
|
||||
# =================== AIPass ====================
|
||||
# Name: test_rollover.py
|
||||
# Version: 1.0.0
|
||||
# Version: 2.0.0
|
||||
# Description: Tests for rollover lifecycle handler
|
||||
# Branch: hooks
|
||||
# Created: 2026-05-22
|
||||
# Modified: 2026-05-22
|
||||
# Modified: 2026-06-19
|
||||
# =============================================
|
||||
|
||||
"""Tests for handlers/lifecycle/rollover.py."""
|
||||
|
||||
import json
|
||||
from unittest.mock import patch, MagicMock
|
||||
import subprocess
|
||||
|
||||
|
||||
MOD = "aipass.hooks.apps.handlers.lifecycle.rollover"
|
||||
|
||||
CHECK_OVERDUE_OUTPUT = (
|
||||
"Found 3 files ready for rollover:\n"
|
||||
" * HOOKS.local (15/15 sessions)\n"
|
||||
" * aipass.local (15/15 key_learnings)\n"
|
||||
" * devpulse.local (15/15 key_learnings)\n"
|
||||
)
|
||||
|
||||
CHECK_CLEAN_OUTPUT = "No files need rollover.\n"
|
||||
|
||||
|
||||
def _mock_run(stdout="", returncode=0):
|
||||
m = MagicMock()
|
||||
m.stdout = stdout
|
||||
m.stderr = ""
|
||||
m.returncode = returncode
|
||||
return m
|
||||
|
||||
|
||||
class TestRolloverHandler:
|
||||
def test_no_repo_root_returns_empty(self):
|
||||
from aipass.hooks.apps.handlers.lifecycle.rollover import handle
|
||||
|
||||
with patch("aipass.hooks.apps.handlers.lifecycle.rollover._find_repo_root", return_value=None):
|
||||
with patch(f"{MOD}._find_repo_root", return_value=None):
|
||||
result = handle({})
|
||||
|
||||
assert result["exit_code"] == 0
|
||||
@@ -27,8 +47,8 @@ class TestRolloverHandler:
|
||||
def test_no_overdue_returns_empty(self):
|
||||
from aipass.hooks.apps.handlers.lifecycle.rollover import handle
|
||||
|
||||
with patch("aipass.hooks.apps.handlers.lifecycle.rollover._find_repo_root", return_value=MagicMock()):
|
||||
with patch("aipass.hooks.apps.handlers.lifecycle.rollover._find_overdue", return_value=[]):
|
||||
with patch(f"{MOD}._find_repo_root", return_value=MagicMock()):
|
||||
with patch(f"{MOD}._run_check", return_value=(False, CHECK_CLEAN_OUTPUT)):
|
||||
result = handle({})
|
||||
|
||||
assert result["exit_code"] == 0
|
||||
@@ -38,68 +58,75 @@ class TestRolloverHandler:
|
||||
def test_overdue_triggers_rollover(self):
|
||||
from aipass.hooks.apps.handlers.lifecycle.rollover import handle
|
||||
|
||||
with patch("aipass.hooks.apps.handlers.lifecycle.rollover._find_repo_root", return_value=MagicMock()):
|
||||
with patch(
|
||||
"aipass.hooks.apps.handlers.lifecycle.rollover._find_overdue",
|
||||
return_value=[("devpulse", "local", "21/20 sessions")],
|
||||
):
|
||||
with patch("aipass.hooks.apps.handlers.lifecycle.rollover._run_rollover", return_value=(True, "ok")):
|
||||
with patch(f"{MOD}._find_repo_root", return_value=MagicMock()):
|
||||
with patch(f"{MOD}._run_check", return_value=(True, CHECK_OVERDUE_OUTPUT)):
|
||||
with patch(f"{MOD}._run_rollover", return_value=(True, "ok")):
|
||||
result = handle({})
|
||||
|
||||
assert result["exit_code"] == 0
|
||||
assert result["sound"] == "pre compact rollover"
|
||||
|
||||
def test_check_file_v2_sessions_overdue(self, tmp_path):
|
||||
from aipass.hooks.apps.handlers.lifecycle.rollover import _check_file
|
||||
def test_overdue_rollover_failure_still_returns_sound(self):
|
||||
from aipass.hooks.apps.handlers.lifecycle.rollover import handle
|
||||
|
||||
f = tmp_path / "local.json"
|
||||
f.write_text(
|
||||
json.dumps(
|
||||
{
|
||||
"document_metadata": {"limits": {"max_sessions": 5}},
|
||||
"sessions": [{"id": i} for i in range(6)],
|
||||
}
|
||||
),
|
||||
encoding="utf-8",
|
||||
)
|
||||
with patch(f"{MOD}._find_repo_root", return_value=MagicMock()):
|
||||
with patch(f"{MOD}._run_check", return_value=(True, CHECK_OVERDUE_OUTPUT)):
|
||||
with patch(f"{MOD}._run_rollover", return_value=(False, "error")):
|
||||
result = handle({})
|
||||
|
||||
overdue, reason = _check_file(f)
|
||||
assert overdue
|
||||
assert "6/5" in reason
|
||||
assert result["exit_code"] == 0
|
||||
assert result["sound"] == "pre compact rollover"
|
||||
|
||||
def test_check_file_v2_not_overdue(self, tmp_path):
|
||||
from aipass.hooks.apps.handlers.lifecycle.rollover import _check_file
|
||||
def test_run_check_parses_overdue(self):
|
||||
from aipass.hooks.apps.handlers.lifecycle.rollover import _run_check
|
||||
|
||||
f = tmp_path / "local.json"
|
||||
f.write_text(
|
||||
json.dumps(
|
||||
{
|
||||
"document_metadata": {"limits": {"max_sessions": 20}},
|
||||
"sessions": [{"id": i} for i in range(5)],
|
||||
}
|
||||
),
|
||||
encoding="utf-8",
|
||||
)
|
||||
mock_result = _mock_run(stdout=CHECK_OVERDUE_OUTPUT)
|
||||
with patch("subprocess.run", return_value=mock_result):
|
||||
has_overdue, summary = _run_check(MagicMock())
|
||||
|
||||
overdue, _ = _check_file(f)
|
||||
assert not overdue
|
||||
assert has_overdue
|
||||
assert "ready for rollover" in summary.lower()
|
||||
|
||||
def test_check_file_v1_line_count(self, tmp_path):
|
||||
from aipass.hooks.apps.handlers.lifecycle.rollover import _check_file
|
||||
def test_run_check_parses_clean(self):
|
||||
from aipass.hooks.apps.handlers.lifecycle.rollover import _run_check
|
||||
|
||||
f = tmp_path / "obs.json"
|
||||
content = {"document_metadata": {"limits": {"max_lines": 10}}}
|
||||
text = json.dumps(content, indent=2)
|
||||
lines_needed = 10 - text.count("\n")
|
||||
text += "\n" * lines_needed
|
||||
f.write_text(text, encoding="utf-8")
|
||||
mock_result = _mock_run(stdout=CHECK_CLEAN_OUTPUT)
|
||||
with patch("subprocess.run", return_value=mock_result):
|
||||
has_overdue, _ = _run_check(MagicMock())
|
||||
|
||||
overdue, reason = _check_file(f)
|
||||
assert overdue
|
||||
assert "lines" in reason
|
||||
assert not has_overdue
|
||||
|
||||
def test_check_file_missing(self, tmp_path):
|
||||
from aipass.hooks.apps.handlers.lifecycle.rollover import _check_file
|
||||
def test_run_check_timeout_returns_false(self):
|
||||
from aipass.hooks.apps.handlers.lifecycle.rollover import _run_check
|
||||
|
||||
overdue, _ = _check_file(tmp_path / "nonexistent.json")
|
||||
assert not overdue
|
||||
with patch("subprocess.run", side_effect=subprocess.TimeoutExpired("cmd", 30)):
|
||||
has_overdue, _ = _run_check(MagicMock())
|
||||
|
||||
assert not has_overdue
|
||||
|
||||
def test_run_rollover_success(self):
|
||||
from aipass.hooks.apps.handlers.lifecycle.rollover import _run_rollover
|
||||
|
||||
mock_result = _mock_run(stdout="done", returncode=0)
|
||||
with patch("subprocess.run", return_value=mock_result):
|
||||
success, _ = _run_rollover(MagicMock())
|
||||
|
||||
assert success
|
||||
|
||||
def test_run_rollover_failure(self):
|
||||
from aipass.hooks.apps.handlers.lifecycle.rollover import _run_rollover
|
||||
|
||||
mock_result = _mock_run(stdout="error", returncode=1)
|
||||
with patch("subprocess.run", return_value=mock_result):
|
||||
success, _ = _run_rollover(MagicMock())
|
||||
|
||||
assert not success
|
||||
|
||||
def test_run_rollover_timeout(self):
|
||||
from aipass.hooks.apps.handlers.lifecycle.rollover import _run_rollover
|
||||
|
||||
with patch("subprocess.run", side_effect=subprocess.TimeoutExpired("cmd", 110)):
|
||||
success, msg = _run_rollover(MagicMock())
|
||||
|
||||
assert not success
|
||||
assert "timed out" in msg
|
||||
|
||||
@@ -10,11 +10,13 @@
|
||||
Rollover Trigger Detection Handler
|
||||
|
||||
Monitors branch memory files via AIPASS_REGISTRY.json and detects when
|
||||
files exceed their max_lines threshold (typically 600 lines).
|
||||
entry counts exceed v2 limits (sessions, key_learnings, observations).
|
||||
|
||||
Purpose:
|
||||
Detect rollover conditions without active monitoring. Called by
|
||||
rollover module to check all branches for files needing rollover.
|
||||
All branches use v2 entry-count limits from memory.config.json
|
||||
(per_branch with defaults fallback). No line-count fallbacks.
|
||||
|
||||
Independence:
|
||||
No module imports - pure handler, transportable
|
||||
@@ -74,20 +76,17 @@ def _find_caller_registries() -> List[Path]:
|
||||
|
||||
@dataclass
|
||||
class RolloverTrigger:
|
||||
"""Represents a file that needs rollover"""
|
||||
"""Represents a file that needs rollover (v2 entry-count based)"""
|
||||
|
||||
branch: str
|
||||
memory_type: str # 'observations' or 'local'
|
||||
file_path: Path
|
||||
current_lines: int
|
||||
max_lines: int
|
||||
schema_version: str = "1.0.0"
|
||||
schema_version: str = "3.0.0"
|
||||
v2_reason: str = ""
|
||||
|
||||
def __str__(self):
|
||||
if self.schema_version.startswith("2") and self.v2_reason:
|
||||
return f"{self.branch}.{self.memory_type} ({self.v2_reason})"
|
||||
return f"{self.branch}.{self.memory_type} ({self.current_lines}/{self.max_lines} lines)"
|
||||
return f"{self.branch}.{self.memory_type} ({self.v2_reason})"
|
||||
|
||||
|
||||
# =============================================================================
|
||||
@@ -166,16 +165,6 @@ def _get_memory_file_path(branch: Dict, memory_type: str) -> Path | None:
|
||||
return file_path if file_path.exists() else None
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# CONFIG LOADING
|
||||
# =============================================================================
|
||||
|
||||
|
||||
def _load_config() -> Dict[str, Any]:
|
||||
"""Load memory.config.json via config_loader."""
|
||||
return config_loader.load()
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# LINE COUNTING
|
||||
# =============================================================================
|
||||
@@ -253,86 +242,35 @@ def _recreate_trinity_file(branch_path: Path, branch_name: str, memory_type: str
|
||||
return None
|
||||
|
||||
|
||||
def _get_max_lines(file_path: Path, branch_name: str | None = None) -> int:
|
||||
"""
|
||||
Get max_lines limit with priority: file metadata > branch config > default
|
||||
|
||||
Args:
|
||||
file_path: Path to JSON file
|
||||
branch_name: Optional branch name for config lookup
|
||||
|
||||
Returns:
|
||||
Max lines limit (default 600)
|
||||
"""
|
||||
# 1. Try file-level metadata first (highest priority)
|
||||
try:
|
||||
with open(file_path, "r", encoding="utf-8") as f:
|
||||
data = json.load(f)
|
||||
metadata = data.get("document_metadata", {})
|
||||
limits = metadata.get("limits", {})
|
||||
file_limit = limits.get("max_lines")
|
||||
if file_limit is not None:
|
||||
return file_limit
|
||||
except Exception as e:
|
||||
logger.warning(f"[detector] Failed to read file-level max_lines from {file_path}: {e}")
|
||||
|
||||
# 2. Try branch-level config (if branch_name provided or can be extracted)
|
||||
if branch_name is None:
|
||||
# Derive from directory: .trinity/local.json → parent of .trinity is the branch
|
||||
if file_path.parent.name == ".trinity":
|
||||
branch_name = file_path.parents[1].name.lower()
|
||||
else:
|
||||
# Legacy flat files: SEEDGO.local.json → "SEEDGO"
|
||||
parts = file_path.stem.split(".")
|
||||
branch_name = parts[0].lower() if parts else None
|
||||
|
||||
if branch_name:
|
||||
config = _load_config()
|
||||
branch_limits = config.get("rollover", {}).get("per_branch", {}).get(branch_name, {})
|
||||
if "max_lines" in branch_limits:
|
||||
return branch_limits["max_lines"]
|
||||
|
||||
# 3. Fall back to global default from config
|
||||
config = _load_config()
|
||||
default_limit = config.get("rollover", {}).get("defaults", {}).get("max_lines")
|
||||
if default_limit is not None:
|
||||
return default_limit
|
||||
|
||||
# 4. Final fallback to hardcoded 600
|
||||
return 600
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# ROLLOVER DETECTION
|
||||
# =============================================================================
|
||||
|
||||
|
||||
def _should_rollover(file_path: Path) -> tuple[bool, int, int, str, str]:
|
||||
def _should_rollover(file_path: Path) -> tuple[bool, int, str, str]:
|
||||
"""
|
||||
Check if file should rollover (supports v1 line-based and v2 entry-count based).
|
||||
Check if file should rollover (v2 entry-count based only).
|
||||
|
||||
All branches use v2 entry-count limits from config (per_branch with
|
||||
defaults fallback). No line-count fallbacks — errors over silent fallbacks.
|
||||
|
||||
Args:
|
||||
file_path: Path to memory JSON file
|
||||
|
||||
Returns:
|
||||
Tuple of (should_rollover, current_lines, max_lines, schema_version, v2_reason)
|
||||
For v2 files, max_lines is 0 and v2_reason describes which limits are exceeded.
|
||||
Tuple of (should_rollover, current_lines, schema_version, v2_reason)
|
||||
"""
|
||||
current_lines = _count_file_lines(file_path)
|
||||
|
||||
# Read file data once for schema detection + limit checks
|
||||
# Read file data once for limit checks
|
||||
try:
|
||||
with open(file_path, "r", encoding="utf-8") as f:
|
||||
data = json.load(f)
|
||||
except Exception as e:
|
||||
# Can't parse — fall back to line-based with hardcoded default
|
||||
logger.warning(f"[detector] Failed to parse {file_path} for rollover check: {e}")
|
||||
return (current_lines >= 600, current_lines, 600, "1.0.0", "")
|
||||
# Can't parse — do NOT fall back to 600. Fail honestly.
|
||||
logger.warning(f"[detector] PARSE FAILURE for {file_path}: {e} — skipping rollover check")
|
||||
return (False, current_lines, "3.0.0", "parse failure — skipped")
|
||||
|
||||
metadata = data.get("document_metadata", {})
|
||||
limits = metadata.get("limits", {})
|
||||
|
||||
# v2: entry-count based limits — read from config per_branch, not file metadata
|
||||
# Derive branch name from file path: .trinity/local.json → parent of .trinity
|
||||
if file_path.parent.name == ".trinity":
|
||||
branch_name = file_path.parents[1].name.lower()
|
||||
@@ -344,39 +282,46 @@ def _should_rollover(file_path: Path) -> tuple[bool, int, int, str, str]:
|
||||
# .trinity/local.json → "local"; .trinity/observations.json → "observations"
|
||||
|
||||
cfg = config_loader.section("rollover")
|
||||
branch_limits = cfg.get("per_branch", {}).get(branch_name, {})
|
||||
file_limits = branch_limits.get(file_type, {})
|
||||
per_branch = cfg.get("per_branch", {})
|
||||
defaults = cfg.get("defaults", {})
|
||||
|
||||
if file_limits:
|
||||
reasons = []
|
||||
# v2 lookup: per_branch[branch][file_type], fallback to defaults[file_type]
|
||||
file_limits = per_branch.get(branch_name, {}).get(file_type, {})
|
||||
if not file_limits:
|
||||
file_limits = defaults.get(file_type, {})
|
||||
|
||||
max_sessions = file_limits.get("sessions", {}).get("count")
|
||||
if max_sessions is not None:
|
||||
sessions = data.get("sessions", [])
|
||||
if isinstance(sessions, list) and len(sessions) >= max_sessions:
|
||||
reasons.append(f"{len(sessions)}/{max_sessions} sessions")
|
||||
if not file_limits:
|
||||
# Neither per_branch NOR defaults have limits for this branch/file_type
|
||||
logger.warning(
|
||||
f"[detector] CONFIG GAP: no v2 limits for branch={branch_name} file_type={file_type} "
|
||||
f"in per_branch or defaults — skipping rollover"
|
||||
)
|
||||
return (False, current_lines, "3.0.0", f"config gap for {branch_name}/{file_type}")
|
||||
|
||||
max_key_learnings = file_limits.get("key_learnings", {}).get("count")
|
||||
if max_key_learnings is not None:
|
||||
key_learnings = data.get("key_learnings", [])
|
||||
if isinstance(key_learnings, (list, dict)) and len(key_learnings) >= max_key_learnings:
|
||||
reasons.append(f"{len(key_learnings)}/{max_key_learnings} key_learnings")
|
||||
reasons = []
|
||||
|
||||
max_observations = file_limits.get("observations", {}).get("count")
|
||||
if max_observations is not None:
|
||||
observations = data.get("observations", [])
|
||||
if isinstance(observations, list) and len(observations) >= max_observations:
|
||||
reasons.append(f"{len(observations)}/{max_observations} observations")
|
||||
max_sessions = file_limits.get("sessions", {}).get("count")
|
||||
if max_sessions is not None:
|
||||
sessions = data.get("sessions", [])
|
||||
if isinstance(sessions, list) and len(sessions) >= max_sessions:
|
||||
reasons.append(f"{len(sessions)}/{max_sessions} sessions")
|
||||
|
||||
if reasons:
|
||||
return (True, current_lines, 0, "2.0.0", ", ".join(reasons))
|
||||
max_key_learnings = file_limits.get("key_learnings", {}).get("count")
|
||||
if max_key_learnings is not None:
|
||||
key_learnings = data.get("key_learnings", [])
|
||||
if isinstance(key_learnings, (list, dict)) and len(key_learnings) >= max_key_learnings:
|
||||
reasons.append(f"{len(key_learnings)}/{max_key_learnings} key_learnings")
|
||||
|
||||
# v1: line-count based (fallback when no v2 limits triggered)
|
||||
max_lines = limits.get("max_lines")
|
||||
if max_lines is None:
|
||||
max_lines = _get_max_lines(file_path)
|
||||
max_observations = file_limits.get("observations", {}).get("count")
|
||||
if max_observations is not None:
|
||||
observations = data.get("observations", [])
|
||||
if isinstance(observations, list) and len(observations) >= max_observations:
|
||||
reasons.append(f"{len(observations)}/{max_observations} observations")
|
||||
|
||||
return (current_lines >= max_lines, current_lines, max_lines, "1.0.0", "")
|
||||
if reasons:
|
||||
return (True, current_lines, "3.0.0", ", ".join(reasons))
|
||||
|
||||
return (False, current_lines, "3.0.0", "")
|
||||
|
||||
|
||||
def check_all_branches() -> Dict[str, Any]:
|
||||
@@ -411,7 +356,7 @@ def check_all_branches() -> Dict[str, Any]:
|
||||
if file_path is None:
|
||||
continue
|
||||
|
||||
should_trigger, current_lines, max_lines, schema_ver, v2_reason = _should_rollover(file_path)
|
||||
should_trigger, current_lines, schema_ver, v2_reason = _should_rollover(file_path)
|
||||
|
||||
if should_trigger:
|
||||
trigger = RolloverTrigger(
|
||||
@@ -419,7 +364,6 @@ def check_all_branches() -> Dict[str, Any]:
|
||||
memory_type=memory_type,
|
||||
file_path=file_path,
|
||||
current_lines=current_lines,
|
||||
max_lines=max_lines,
|
||||
schema_version=schema_ver,
|
||||
v2_reason=v2_reason,
|
||||
)
|
||||
@@ -450,7 +394,7 @@ def check_single_file(file_path: Path) -> Dict[str, Any]:
|
||||
if not file_path.exists():
|
||||
return {"success": False, "error": f"File not found: {file_path}"}
|
||||
|
||||
should_trigger, current_lines, max_lines, schema_ver, v2_reason = _should_rollover(file_path)
|
||||
should_trigger, current_lines, schema_ver, v2_reason = _should_rollover(file_path)
|
||||
|
||||
if should_trigger:
|
||||
# Extract branch and type from file path
|
||||
@@ -468,21 +412,18 @@ def check_single_file(file_path: Path) -> Dict[str, Any]:
|
||||
memory_type=memory_type,
|
||||
file_path=file_path,
|
||||
current_lines=current_lines,
|
||||
max_lines=max_lines,
|
||||
schema_version=schema_ver,
|
||||
v2_reason=v2_reason,
|
||||
)
|
||||
|
||||
return {"success": True, "trigger": trigger, "should_rollover": True}
|
||||
else:
|
||||
remaining = max_lines - current_lines if max_lines > 0 else 0
|
||||
return {
|
||||
"success": True,
|
||||
"should_rollover": False,
|
||||
"current_lines": current_lines,
|
||||
"max_lines": max_lines,
|
||||
"schema_version": schema_ver,
|
||||
"remaining": remaining,
|
||||
"v2_reason": v2_reason,
|
||||
}
|
||||
|
||||
|
||||
@@ -514,13 +455,11 @@ def get_rollover_stats() -> Dict[str, Any]:
|
||||
continue
|
||||
|
||||
stats["files_checked"] += 1
|
||||
should_trigger, current_lines, max_lines, schema_ver, v2_reason = _should_rollover(file_path)
|
||||
should_trigger, current_lines, schema_ver, v2_reason = _should_rollover(file_path)
|
||||
|
||||
stat_entry = {
|
||||
stat_entry: Dict[str, Any] = {
|
||||
"current": current_lines,
|
||||
"max": max_lines,
|
||||
"ready": should_trigger,
|
||||
"remaining": max_lines - current_lines if max_lines > 0 else 0,
|
||||
"schema_version": schema_ver,
|
||||
}
|
||||
if v2_reason:
|
||||
|
||||
@@ -106,7 +106,7 @@ def check_and_rollover() -> Dict[str, Any]:
|
||||
Check all memory files and trigger rollover if any exceed their threshold.
|
||||
Also processes any new files in memory_pool.
|
||||
|
||||
Threshold is determined per-branch from config (defaults to 600).
|
||||
Threshold is determined per-branch from v2 entry-count limits in config.
|
||||
|
||||
This is a startup check - runs once per command, synchronous.
|
||||
No daemon or file watcher needed.
|
||||
@@ -157,10 +157,10 @@ def check_and_rollover() -> Dict[str, Any]:
|
||||
|
||||
normalize_memory_file(memory_file)
|
||||
|
||||
# Use detector for trigger decision (handles both v1 line-based and v2 entry-count)
|
||||
# Use detector for trigger decision (v2 entry-count based)
|
||||
from aipass.memory.apps.handlers.monitor.detector import _should_rollover
|
||||
|
||||
triggered, current_lines, _, _, _ = _should_rollover(memory_file)
|
||||
triggered, current_lines, _, _ = _should_rollover(memory_file)
|
||||
if triggered:
|
||||
results["files_over_limit"].append(
|
||||
{"file": str(memory_file), "lines": current_lines, "threshold": 0}
|
||||
|
||||
@@ -13,17 +13,15 @@ Surgically extracts oldest items from memory files during rollover.
|
||||
Understands real JSON structure (sessions, observations, key_learnings arrays).
|
||||
|
||||
Purpose:
|
||||
v1 (schema <2.0.0): When file exceeds max_lines, extract oldest items from
|
||||
growing arrays to get under line limit.
|
||||
v2 (schema >=2.0.0): When entry counts exceed limits (max_sessions,
|
||||
max_key_learnings), extract oldest entries by count.
|
||||
v2 entry-count based extraction: When entry counts exceed limits
|
||||
(sessions, key_learnings, observations), extract oldest entries by count.
|
||||
Limits are read from config per_branch with defaults fallback.
|
||||
|
||||
Strategy:
|
||||
- Detect schema version from document_metadata
|
||||
- v1: line-count based extraction (legacy)
|
||||
- v2: entry-count based extraction (sessions + key_learnings + observations arrays)
|
||||
- Extract oldest items (FIFO)
|
||||
- Update document_metadata.status
|
||||
- No line-count fallbacks — errors over silent fallbacks
|
||||
"""
|
||||
|
||||
import shutil
|
||||
@@ -163,95 +161,11 @@ def _derive_branch_and_type(file_path: Path) -> tuple[str, str]:
|
||||
return branch_name, memory_type
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# STRUCTURE DETECTION
|
||||
# =============================================================================
|
||||
|
||||
|
||||
def _detect_growing_array(data: Dict[str, Any]) -> str | None:
|
||||
"""
|
||||
Detect which array field is growing in memory file
|
||||
|
||||
Memory files have different structures:
|
||||
- .local.json → 'sessions' array
|
||||
- .observations.json → 'observations' array
|
||||
- Future types → other array fields
|
||||
|
||||
Args:
|
||||
data: Parsed JSON data
|
||||
|
||||
Returns:
|
||||
Array field name (e.g., 'sessions'), or None if not found
|
||||
"""
|
||||
# Known array fields that grow over time
|
||||
candidates = ["sessions", "observations", "recent_work", "entries", "items", "records"]
|
||||
|
||||
for field in candidates:
|
||||
if field in data and isinstance(data[field], list) and len(data[field]) > 0:
|
||||
return field
|
||||
|
||||
return None
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# EXTRACTION CALCULATION
|
||||
# =============================================================================
|
||||
|
||||
|
||||
def _calculate_items_to_extract_by_lines(
|
||||
data: Dict[str, Any], array_field: str, file_path: Path, max_lines: int, target_buffer: int = 100
|
||||
) -> int:
|
||||
"""
|
||||
Calculate items to extract by SIMULATING line count (accurate)
|
||||
|
||||
Removes items one by one, counting actual lines after each removal,
|
||||
until we reach target line count (max_lines - buffer).
|
||||
|
||||
Args:
|
||||
data: Full memory file data
|
||||
array_field: Name of array field to extract from
|
||||
file_path: Path (for line counting)
|
||||
max_lines: Maximum allowed lines
|
||||
target_buffer: Lines of buffer to leave (default 100)
|
||||
|
||||
Returns:
|
||||
Number of items to extract
|
||||
|
||||
Example:
|
||||
File is 645 lines, limit is 600, buffer is 100
|
||||
Target: 500 lines (600 - 100)
|
||||
Simulate removing items until file is ~500 lines
|
||||
"""
|
||||
import tempfile
|
||||
import json
|
||||
|
||||
target_lines = max_lines - target_buffer
|
||||
total_items = len(data[array_field])
|
||||
|
||||
# Binary search for optimal item count
|
||||
for items_to_remove in range(1, total_items + 1):
|
||||
# Simulate removal (remove from END - oldest items)
|
||||
test_data = data.copy()
|
||||
test_data[array_field] = data[array_field][:-items_to_remove] # Keep newest
|
||||
|
||||
# Count lines in simulated result
|
||||
with tempfile.NamedTemporaryFile(mode="w", delete=False, suffix=".json") as tmp:
|
||||
json.dump(test_data, tmp, indent=2, ensure_ascii=False)
|
||||
tmp_path = Path(tmp.name)
|
||||
|
||||
with open(tmp_path, "r") as f:
|
||||
line_count = len(f.readlines())
|
||||
|
||||
tmp_path.unlink()
|
||||
|
||||
# Check if we've reached target
|
||||
if line_count <= target_lines:
|
||||
return items_to_remove
|
||||
|
||||
# Fallback: remove 50% if simulation fails
|
||||
return max(1, total_items // 2)
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# V2 EXTRACTION (ENTRY-COUNT BASED)
|
||||
# =============================================================================
|
||||
@@ -375,7 +289,6 @@ def extract_items(file_path: Path, percentage: int | None = None) -> Dict[str, A
|
||||
data = _read_memory_file(file_path)
|
||||
if data is None:
|
||||
return {"success": False, "error": f"Failed to parse memory file: {file_path.name}"}
|
||||
current_lines = _count_file_lines(file_path)
|
||||
except Exception as e:
|
||||
logger.warning(f"[extractor] Failed to read file {file_path}: {e}")
|
||||
return {"success": False, "error": f"Failed to read file: {e}"}
|
||||
@@ -389,71 +302,25 @@ def extract_items(file_path: Path, percentage: int | None = None) -> Dict[str, A
|
||||
_ext_ftype = file_path.stem.split(".")[-1]
|
||||
_ext_cfg = config_loader.section("rollover")
|
||||
_ext_file_limits = _ext_cfg.get("per_branch", {}).get(_ext_branch, {}).get(_ext_ftype, {})
|
||||
if not _ext_file_limits:
|
||||
# Also check defaults fallback
|
||||
_ext_file_limits = _ext_cfg.get("defaults", {}).get(_ext_ftype, {})
|
||||
|
||||
if _ext_file_limits:
|
||||
return _extract_items_v2(file_path, data)
|
||||
|
||||
# v1: line-count based extraction
|
||||
# Detect structure
|
||||
array_field = _detect_growing_array(data)
|
||||
if not array_field:
|
||||
return {"success": False, "error": f"No growing array found in {file_path.name}"}
|
||||
|
||||
# Get metadata
|
||||
_cfg_max = config_loader.section("rollover").get("defaults", {}).get("max_lines", 600)
|
||||
max_lines = data.get("document_metadata", {}).get("limits", {}).get("max_lines", _cfg_max)
|
||||
|
||||
# Check if under limit
|
||||
if current_lines < max_lines:
|
||||
return {"success": True, "skipped": True, "message": f"File under limit ({current_lines}/{max_lines} lines)"}
|
||||
|
||||
# Calculate extraction amount (simulate actual line reduction)
|
||||
total_items = len(data[array_field])
|
||||
|
||||
if percentage is None:
|
||||
# Use line-based calculation for accuracy
|
||||
items_to_extract = _calculate_items_to_extract_by_lines(
|
||||
data, array_field, file_path, max_lines, target_buffer=100
|
||||
)
|
||||
else:
|
||||
# Manual percentage override (for testing)
|
||||
items_to_extract = max(1, int(total_items * percentage / 100))
|
||||
|
||||
# Extract oldest items (LAST N in array - newest first, oldest last)
|
||||
extracted = data[array_field][-items_to_extract:] # Take from end (oldest)
|
||||
remaining = data[array_field][:-items_to_extract] # Keep from start (newest)
|
||||
|
||||
# Update array
|
||||
data[array_field] = remaining
|
||||
|
||||
# Update metadata
|
||||
_update_metadata_after_extraction(data)
|
||||
|
||||
# Write back
|
||||
try:
|
||||
_write_memory_file(file_path, data)
|
||||
new_line_count = _count_file_lines(file_path)
|
||||
except Exception as e:
|
||||
logger.error(f"[extractor] Failed to write file after v1 extraction: {e}")
|
||||
return {"success": False, "error": f"Failed to write file: {e}"}
|
||||
|
||||
# Derive branch and type from path
|
||||
branch_name, memory_type = _derive_branch_and_type(file_path)
|
||||
|
||||
# No v2 limits found — fail loud, never fall back to v1 line-count
|
||||
logger.warning(
|
||||
f"[extractor] NO V2 LIMITS for branch={_ext_branch} file_type={_ext_ftype} "
|
||||
f"— cannot extract without config. Check per_branch and defaults in memory.config.json"
|
||||
)
|
||||
json_handler.log_operation(
|
||||
"extract_items", {"branch": branch_name, "type": memory_type, "extracted_count": items_to_extract}
|
||||
"extract_items_no_limits",
|
||||
{"branch": _ext_branch, "file_type": _ext_ftype, "error": "no v2 limits configured"},
|
||||
)
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"file": str(file_path),
|
||||
"branch": branch_name,
|
||||
"type": memory_type,
|
||||
"array_field": array_field,
|
||||
"extracted": extracted,
|
||||
"extracted_count": items_to_extract,
|
||||
"remaining_count": len(remaining),
|
||||
"old_lines": current_lines,
|
||||
"new_lines": new_line_count,
|
||||
"success": False,
|
||||
"error": f"No v2 extraction limits configured for {_ext_branch}/{_ext_ftype}",
|
||||
}
|
||||
|
||||
|
||||
|
||||
@@ -257,8 +257,8 @@ def start_watch() -> None:
|
||||
"""
|
||||
Start memory watcher - monitors branch memory files for auto-rollover
|
||||
|
||||
Watches all branches from AIPASS_REGISTRY.json. When a memory file
|
||||
exceeds 600 lines, automatically triggers rollover.
|
||||
Watches all branches from AIPASS_REGISTRY.json. When entry counts
|
||||
exceed v2 limits, automatically triggers rollover.
|
||||
|
||||
Press Ctrl+C to stop.
|
||||
"""
|
||||
|
||||
@@ -167,11 +167,10 @@ def print_help() -> None:
|
||||
console.print(" [cyan]help[/cyan] Show this help message")
|
||||
console.print()
|
||||
console.print("[bold]LIMITS:[/bold]")
|
||||
console.print(" v1 (schema <2.0): Line-count based (max_lines, default 600)")
|
||||
console.print(" v2 (schema 2.0+): Entry-count based (max_sessions, max_key_learnings)")
|
||||
console.print(" v2 entry-count based (sessions, key_learnings, observations) from config")
|
||||
console.print()
|
||||
console.print("[bold]WORKFLOW:[/bold]")
|
||||
console.print(" 1. Detect files exceeding limits (line count or entry count)")
|
||||
console.print(" 1. Detect files exceeding v2 entry-count limits")
|
||||
console.print(" 2. Extract oldest entries")
|
||||
console.print(" 3. Generate embeddings via fastembed")
|
||||
console.print(" 4. Store vectors in local + global ChromaDB")
|
||||
@@ -400,21 +399,12 @@ def show_status() -> None:
|
||||
console.print(f" [bold]{branch_name}[/bold]")
|
||||
|
||||
for memory_type, file_stats in branch_stats.items():
|
||||
current = file_stats["current"]
|
||||
max_val = file_stats["max"]
|
||||
ready = file_stats["ready"]
|
||||
remaining = file_stats["remaining"]
|
||||
schema_ver = file_stats.get("schema_version", "1.0.0")
|
||||
v2_reason = file_stats.get("v2_reason", "")
|
||||
|
||||
status_marker = "[red]![/red]" if ready else "[green]OK[/green]"
|
||||
|
||||
if schema_ver.startswith("2"):
|
||||
status_text = f"READY ({v2_reason})" if ready else "OK (v2)"
|
||||
console.print(f" {status_marker} {memory_type}: {status_text}")
|
||||
else:
|
||||
status_text = "READY" if ready else f"{remaining} remaining"
|
||||
console.print(f" {status_marker} {memory_type}: {current}/{max_val} lines ({status_text})")
|
||||
status_text = f"READY ({v2_reason})" if ready else "OK"
|
||||
console.print(f" {status_marker} {memory_type}: {status_text}")
|
||||
|
||||
console.print()
|
||||
|
||||
|
||||
@@ -869,7 +869,8 @@ def run_demo() -> None:
|
||||
|
||||
mock_fragments = [
|
||||
{
|
||||
"summary": "User was stuck on a code error for a while, then solved it with assistant's step-by-step debugging guidance",
|
||||
"summary": "User was stuck on a code error for a while, then solved it with "
|
||||
"assistant's step-by-step debugging guidance",
|
||||
"insight": "Step-by-step debugging with explanation is more effective than just providing the fix",
|
||||
"type": "episodic",
|
||||
"triggers": ["error", "debug", "stuck", "breakthrough"],
|
||||
@@ -877,7 +878,8 @@ def run_demo() -> None:
|
||||
"technical_domain": "debugging",
|
||||
},
|
||||
{
|
||||
"summary": "Collaborative pattern where assistant explains reasoning before giving solutions leads to better understanding",
|
||||
"summary": "Collaborative pattern where assistant explains reasoning before giving "
|
||||
"solutions leads to better understanding",
|
||||
"insight": "Teaching approach builds deeper knowledge than direct answers",
|
||||
"type": "procedural",
|
||||
"triggers": ["explain", "step by step", "understanding"],
|
||||
@@ -1408,15 +1410,10 @@ def _find_bootstrap_sessions(max_sessions: int = 8) -> List[Path]:
|
||||
return []
|
||||
|
||||
# Priority branch directories (diverse content sources)
|
||||
aipass_src = Path(__file__).resolve().parents[3]
|
||||
priority_dirs = [
|
||||
"-home-patrick-Projects-AIPass-src-aipass-memory",
|
||||
"-home-patrick-Projects-AIPass-src-aipass-devpulse",
|
||||
"-home-patrick-Projects-AIPass-src-aipass-seedgo",
|
||||
"-home-patrick-Projects-AIPass-src-aipass-drone",
|
||||
"-home-patrick-Projects-AIPass-src-aipass-flow",
|
||||
"-home-patrick-Projects-AIPass-src-aipass-prax",
|
||||
"-home-patrick-Projects-AIPass-src-aipass-ai-mail",
|
||||
"-home-patrick-Projects-AIPass-src-aipass-api",
|
||||
str(aipass_src / name).replace("/", "-").replace("_", "-")
|
||||
for name in ["memory", "devpulse", "seedgo", "drone", "flow", "prax", "ai_mail", "api"]
|
||||
]
|
||||
|
||||
selected = []
|
||||
|
||||
@@ -139,81 +139,6 @@ class TestGetMemoryFilePath:
|
||||
assert result.name == "local.json"
|
||||
|
||||
|
||||
# ===========================================================================
|
||||
# _load_config
|
||||
# ===========================================================================
|
||||
|
||||
|
||||
class TestLoadConfig:
|
||||
"""Tests for _load_config()."""
|
||||
|
||||
def test_returns_config_dict_when_file_exists(self, tmp_path: Path, monkeypatch):
|
||||
"""Valid config file should return parsed dict with rollover settings."""
|
||||
config_dir = tmp_path / "config"
|
||||
config_dir.mkdir()
|
||||
config_file = config_dir / "memory.config.json"
|
||||
config_data = {
|
||||
"rollover": {
|
||||
"defaults": {"max_lines": 500},
|
||||
"per_branch": {"SEEDGO": {"max_lines": 800}},
|
||||
}
|
||||
}
|
||||
config_file.write_text(json.dumps(config_data), encoding="utf-8")
|
||||
|
||||
from aipass.memory.apps.handlers.monitor import detector
|
||||
|
||||
# Patch the config path resolution to point at our tmp_path
|
||||
monkeypatch.setattr(
|
||||
detector,
|
||||
"_load_config",
|
||||
lambda: json.loads(config_file.read_text(encoding="utf-8")),
|
||||
)
|
||||
|
||||
result = detector._load_config()
|
||||
|
||||
assert result == config_data
|
||||
assert result["rollover"]["defaults"]["max_lines"] == 500
|
||||
|
||||
def test_returns_empty_dict_when_file_missing(self, monkeypatch):
|
||||
"""Missing config file should return empty dict."""
|
||||
from aipass.memory.apps.handlers.monitor import detector
|
||||
|
||||
# Point config resolution at a path that does not exist
|
||||
monkeypatch.setattr(
|
||||
detector,
|
||||
"_load_config",
|
||||
lambda: {},
|
||||
)
|
||||
|
||||
result = detector._load_config()
|
||||
|
||||
assert result == {}
|
||||
|
||||
def test_returns_empty_dict_on_invalid_json(self, tmp_path: Path, monkeypatch):
|
||||
"""Malformed JSON config should return empty dict and log the error."""
|
||||
config_dir = tmp_path / "config"
|
||||
config_dir.mkdir()
|
||||
config_file = config_dir / "memory.config.json"
|
||||
config_file.write_text("NOT VALID JSON {{", encoding="utf-8")
|
||||
|
||||
from aipass.memory.apps.handlers.monitor import detector
|
||||
|
||||
# Simulate the real _load_config behavior on bad JSON
|
||||
def _broken_load() -> dict:
|
||||
try:
|
||||
with open(config_file, "r", encoding="utf-8") as f:
|
||||
return json.load(f)
|
||||
except Exception as exc:
|
||||
logger.warning("Failed to parse config file %s: %s", config_file, exc)
|
||||
return {}
|
||||
|
||||
monkeypatch.setattr(detector, "_load_config", _broken_load)
|
||||
|
||||
result = detector._load_config()
|
||||
|
||||
assert result == {}
|
||||
|
||||
|
||||
# ===========================================================================
|
||||
# check_single_file
|
||||
# ===========================================================================
|
||||
@@ -222,14 +147,11 @@ class TestLoadConfig:
|
||||
class TestCheckSingleFile:
|
||||
"""Tests for check_single_file(file_path)."""
|
||||
|
||||
def test_file_under_threshold_no_rollover(self, tmp_path: Path):
|
||||
"""A small file should not trigger rollover."""
|
||||
def test_file_under_threshold_no_rollover(self, tmp_path: Path, monkeypatch):
|
||||
"""A small file with entries under v2 limits should not trigger rollover."""
|
||||
mem_file = tmp_path / "SEEDGO.observations.json"
|
||||
data = {
|
||||
"document_metadata": {
|
||||
"schema_version": "1.0.0",
|
||||
"limits": {"max_lines": 600},
|
||||
},
|
||||
"document_metadata": {"schema_version": "3.0.0"},
|
||||
"observations": [],
|
||||
}
|
||||
content = json.dumps(data, indent=2)
|
||||
@@ -237,28 +159,35 @@ class TestCheckSingleFile:
|
||||
|
||||
from aipass.memory.apps.handlers.monitor import detector
|
||||
|
||||
monkeypatch.setattr(
|
||||
detector.config_loader,
|
||||
"section",
|
||||
lambda name: {"per_branch": {"seedgo": {"observations": {"observations": {"count": 10}}}}, "defaults": {}},
|
||||
)
|
||||
|
||||
result = detector.check_single_file(mem_file)
|
||||
|
||||
assert result["success"] is True
|
||||
assert result["should_rollover"] is False
|
||||
assert result["current_lines"] < 600
|
||||
|
||||
def test_file_over_threshold_triggers_rollover(self, tmp_path: Path):
|
||||
"""A file exceeding max_lines should trigger rollover."""
|
||||
def test_file_over_threshold_triggers_rollover(self, tmp_path: Path, monkeypatch):
|
||||
"""A file exceeding v2 entry-count limits should trigger rollover."""
|
||||
mem_file = tmp_path / "SEEDGO.local.json"
|
||||
# Build a file with many lines so it exceeds threshold of 10
|
||||
data = {
|
||||
"document_metadata": {
|
||||
"schema_version": "1.0.0",
|
||||
"limits": {"max_lines": 10},
|
||||
},
|
||||
"sessions": [{"id": f"s{i}", "notes": "padding " * 20} for i in range(50)],
|
||||
"document_metadata": {"schema_version": "3.0.0"},
|
||||
"sessions": [{"id": f"s{i}", "notes": "padding"} for i in range(50)],
|
||||
}
|
||||
content = json.dumps(data, indent=2)
|
||||
mem_file.write_text(content, encoding="utf-8")
|
||||
|
||||
from aipass.memory.apps.handlers.monitor import detector
|
||||
|
||||
monkeypatch.setattr(
|
||||
detector.config_loader,
|
||||
"section",
|
||||
lambda name: {"per_branch": {"seedgo": {"local": {"sessions": {"count": 10}}}}, "defaults": {}},
|
||||
)
|
||||
|
||||
result = detector.check_single_file(mem_file)
|
||||
|
||||
assert result["success"] is True
|
||||
@@ -371,6 +300,76 @@ class TestCheckSingleFile:
|
||||
assert result["success"] is True
|
||||
assert result["should_rollover"] is False
|
||||
|
||||
def test_parse_failure_returns_no_rollover(self, tmp_path: Path, monkeypatch):
|
||||
"""JSON parse failure should return should_rollover=False, not 600-line fallback."""
|
||||
mem_file = tmp_path / "BROKEN.local.json"
|
||||
mem_file.write_text("NOT VALID JSON {{{", encoding="utf-8")
|
||||
|
||||
from aipass.memory.apps.handlers.monitor import detector
|
||||
|
||||
monkeypatch.setattr(
|
||||
detector.config_loader,
|
||||
"section",
|
||||
lambda name: {"per_branch": {"broken": {"local": {"sessions": {"count": 5}}}}, "defaults": {}},
|
||||
)
|
||||
|
||||
result = detector.check_single_file(mem_file)
|
||||
|
||||
assert result["success"] is True
|
||||
assert result["should_rollover"] is False
|
||||
assert "parse failure" in result.get("v2_reason", "")
|
||||
|
||||
def test_defaults_fallback_when_branch_missing_from_per_branch(self, tmp_path: Path, monkeypatch):
|
||||
"""Branch not in per_branch should fall back to defaults and still trigger on entry count."""
|
||||
mem_file = tmp_path / "NEWBRANCH.local.json"
|
||||
data = {
|
||||
"document_metadata": {"schema_version": "3.0.0"},
|
||||
"sessions": [{"id": f"s{i}"} for i in range(15)],
|
||||
}
|
||||
mem_file.write_text(json.dumps(data, indent=2), encoding="utf-8")
|
||||
|
||||
from aipass.memory.apps.handlers.monitor import detector
|
||||
|
||||
# per_branch has NO entry for "newbranch", but defaults has local limits
|
||||
monkeypatch.setattr(
|
||||
detector.config_loader,
|
||||
"section",
|
||||
lambda name: {
|
||||
"per_branch": {},
|
||||
"defaults": {"local": {"sessions": {"count": 10}}},
|
||||
},
|
||||
)
|
||||
|
||||
result = detector.check_single_file(mem_file)
|
||||
|
||||
assert result["success"] is True
|
||||
assert result["should_rollover"] is True
|
||||
assert "15/10 sessions" in result["trigger"].v2_reason
|
||||
|
||||
def test_no_limits_in_per_branch_or_defaults_skips_rollover(self, tmp_path: Path, monkeypatch):
|
||||
"""Branch missing from BOTH per_branch AND defaults should not roll and log config gap."""
|
||||
mem_file = tmp_path / "ORPHAN.local.json"
|
||||
data = {
|
||||
"document_metadata": {"schema_version": "3.0.0"},
|
||||
"sessions": [{"id": f"s{i}"} for i in range(100)],
|
||||
}
|
||||
mem_file.write_text(json.dumps(data, indent=2), encoding="utf-8")
|
||||
|
||||
from aipass.memory.apps.handlers.monitor import detector
|
||||
|
||||
# Neither per_branch nor defaults have anything for "orphan"/"local"
|
||||
monkeypatch.setattr(
|
||||
detector.config_loader,
|
||||
"section",
|
||||
lambda name: {"per_branch": {}, "defaults": {}},
|
||||
)
|
||||
|
||||
result = detector.check_single_file(mem_file)
|
||||
|
||||
assert result["success"] is True
|
||||
assert result["should_rollover"] is False
|
||||
assert "config gap" in result.get("v2_reason", "")
|
||||
|
||||
|
||||
# ===========================================================================
|
||||
# _read_registry
|
||||
|
||||
@@ -9,7 +9,7 @@
|
||||
"""Targeted handler-layer tests for critical untested handlers.
|
||||
|
||||
Covers:
|
||||
- rollover/extractor.py (_extract_items_v2, _detect_growing_array, helpers)
|
||||
- rollover/extractor.py (_extract_items_v2, helpers)
|
||||
- tracking/line_counter.py (_count_physical_lines, update_line_count)
|
||||
- schema/normalize.py (normalize_memory_file)
|
||||
- todos[] operational schema (rollover ignores, caps enforced)
|
||||
@@ -117,48 +117,19 @@ def _import_normalize(monkeypatch):
|
||||
# ===========================================================================
|
||||
|
||||
|
||||
class TestDetectGrowingArray:
|
||||
"""Test _detect_growing_array helper."""
|
||||
|
||||
def test_detects_sessions_array(self, monkeypatch):
|
||||
ext, _ = _import_extractor(monkeypatch)
|
||||
data = {"sessions": [{"id": 1}, {"id": 2}], "metadata": {}}
|
||||
assert ext._detect_growing_array(data) == "sessions"
|
||||
|
||||
def test_detects_observations_array(self, monkeypatch):
|
||||
ext, _ = _import_extractor(monkeypatch)
|
||||
data = {"observations": [{"note": "x"}]}
|
||||
assert ext._detect_growing_array(data) == "observations"
|
||||
|
||||
def test_returns_none_for_empty_arrays(self, monkeypatch):
|
||||
ext, _ = _import_extractor(monkeypatch)
|
||||
data = {"sessions": [], "observations": []}
|
||||
assert ext._detect_growing_array(data) is None
|
||||
|
||||
def test_returns_none_when_no_array_fields(self, monkeypatch):
|
||||
ext, _ = _import_extractor(monkeypatch)
|
||||
data = {"document_metadata": {}, "key_learnings": {"a": "b"}}
|
||||
assert ext._detect_growing_array(data) is None
|
||||
|
||||
def test_prefers_sessions_over_later_candidates(self, monkeypatch):
|
||||
ext, _ = _import_extractor(monkeypatch)
|
||||
data = {"sessions": [{"id": 1}], "entries": [{"id": 2}]}
|
||||
assert ext._detect_growing_array(data) == "sessions"
|
||||
|
||||
|
||||
class TestDerivebranchAndType:
|
||||
"""Test _derive_branch_and_type path helper."""
|
||||
|
||||
def test_trinity_path_local(self, monkeypatch):
|
||||
def test_trinity_path_local(self, monkeypatch, tmp_path):
|
||||
ext, _ = _import_extractor(monkeypatch)
|
||||
p = Path("/home/user/src/aipass/devpulse/.trinity/local.json")
|
||||
p = tmp_path / "devpulse" / ".trinity" / "local.json"
|
||||
branch, mtype = ext._derive_branch_and_type(p)
|
||||
assert branch == "DEVPULSE"
|
||||
assert mtype == "local"
|
||||
|
||||
def test_trinity_path_observations(self, monkeypatch):
|
||||
def test_trinity_path_observations(self, monkeypatch, tmp_path):
|
||||
ext, _ = _import_extractor(monkeypatch)
|
||||
p = Path("/home/user/src/aipass/memory/.trinity/observations.json")
|
||||
p = tmp_path / "memory" / ".trinity" / "observations.json"
|
||||
branch, mtype = ext._derive_branch_and_type(p)
|
||||
assert branch == "MEMORY"
|
||||
assert mtype == "observations"
|
||||
@@ -632,26 +603,6 @@ class TestTodosOperational:
|
||||
assert data["todos"][0]["id"] == "t1"
|
||||
assert data["todos"][4]["id"] == "t5"
|
||||
|
||||
def test_v1_detect_growing_array_ignores_todos(self, monkeypatch):
|
||||
"""v1 _detect_growing_array does NOT consider todos as a growing array."""
|
||||
ext, _ = _import_extractor(monkeypatch)
|
||||
data = {
|
||||
"sessions": [{"session_number": 1}],
|
||||
"todos": [{"id": "t1", "text": "Something"}],
|
||||
}
|
||||
result = ext._detect_growing_array(data)
|
||||
assert result == "sessions"
|
||||
|
||||
def test_v1_detect_growing_array_skips_todos_only(self, monkeypatch):
|
||||
"""If only todos[] exists (no memory arrays), _detect_growing_array returns None."""
|
||||
ext, _ = _import_extractor(monkeypatch)
|
||||
data = {
|
||||
"todos": [{"id": "t1", "text": "Something"}],
|
||||
"key_learnings": {"k1": "v1"},
|
||||
}
|
||||
result = ext._detect_growing_array(data)
|
||||
assert result is None
|
||||
|
||||
def test_todos_schema_shape(self):
|
||||
"""Validate the expected todos[] item schema: id, text, created, optional priority."""
|
||||
todo_item = {"id": "t1", "text": "Fix the bug", "created": "2026-06-07"}
|
||||
|
||||
@@ -634,8 +634,8 @@ class TestExtractWithMetadata:
|
||||
assert "branch" in entry["_metadata"]
|
||||
assert "extracted_at" in entry["_metadata"]
|
||||
|
||||
def test_v1_extracts_at_exactly_max_lines(self, monkeypatch, tmp_path):
|
||||
"""v1 file at exactly max_lines should extract, not skip."""
|
||||
def test_v2_extracts_when_observations_at_limit(self, monkeypatch, tmp_path):
|
||||
"""v2 file at entry-count limit should extract, not skip."""
|
||||
ext, mocks = _import_extractor(monkeypatch)
|
||||
|
||||
observations = [
|
||||
@@ -643,20 +643,20 @@ class TestExtractWithMetadata:
|
||||
]
|
||||
data = {
|
||||
"document_metadata": {
|
||||
"schema_version": "1.0.0",
|
||||
"limits": {"max_lines": 50},
|
||||
"schema_version": "3.0.0",
|
||||
"status": {},
|
||||
},
|
||||
"observations": observations,
|
||||
}
|
||||
file_path = tmp_path / "DEVPULSE.observations.json"
|
||||
content = json.dumps(data, indent=2)
|
||||
file_path.write_text(content, encoding="utf-8")
|
||||
actual_lines = len(content.splitlines())
|
||||
|
||||
data["document_metadata"]["limits"]["max_lines"] = actual_lines
|
||||
|
||||
file_path = tmp_path / ".trinity" / "observations.json"
|
||||
file_path.parent.mkdir(parents=True)
|
||||
file_path.write_text(json.dumps(data, indent=2), encoding="utf-8")
|
||||
|
||||
branch_key = tmp_path.name.lower()
|
||||
mocks["config_loader"].section.return_value = {
|
||||
"defaults": {},
|
||||
"per_branch": {branch_key: {"observations": {"observations": {"count": 5}}}},
|
||||
}
|
||||
mocks["memory_files"].read_memory_file_data.return_value = data
|
||||
|
||||
def fake_write(fp, d):
|
||||
@@ -676,8 +676,7 @@ class TestExtractWithMetadata:
|
||||
# v2 file under limits (no extraction needed)
|
||||
data = {
|
||||
"document_metadata": {
|
||||
"schema_version": "2.0.0",
|
||||
"limits": {"max_sessions": 10},
|
||||
"schema_version": "3.0.0",
|
||||
"status": {},
|
||||
},
|
||||
"sessions": [{"session_number": 1, "summary": "only one"}],
|
||||
@@ -686,6 +685,11 @@ class TestExtractWithMetadata:
|
||||
file_path.parent.mkdir(parents=True)
|
||||
file_path.write_text(json.dumps(data, indent=2), encoding="utf-8")
|
||||
|
||||
branch_key = tmp_path.name.lower()
|
||||
mocks["config_loader"].section.return_value = {
|
||||
"defaults": {},
|
||||
"per_branch": {branch_key: {"local": {"sessions": {"count": 10}}}},
|
||||
}
|
||||
mocks["memory_files"].read_memory_file_data.return_value = data
|
||||
|
||||
result = ext.extract_with_metadata(file_path)
|
||||
@@ -787,10 +791,8 @@ class TestShowStatus:
|
||||
"TEST": {
|
||||
"local": {
|
||||
"current": 500,
|
||||
"max": 600,
|
||||
"ready": False,
|
||||
"remaining": 100,
|
||||
"schema_version": "1.0.0",
|
||||
"schema_version": "3.0.0",
|
||||
}
|
||||
}
|
||||
},
|
||||
@@ -818,10 +820,8 @@ class TestShowStatus:
|
||||
"V2BRANCH": {
|
||||
"local": {
|
||||
"current": 25,
|
||||
"max": 20,
|
||||
"ready": True,
|
||||
"remaining": 0,
|
||||
"schema_version": "2.0.0",
|
||||
"schema_version": "3.0.0",
|
||||
"v2_reason": "sessions: 25/20",
|
||||
}
|
||||
}
|
||||
|
||||
@@ -404,7 +404,7 @@ class TestMemoryFileWatcherOnModified:
|
||||
mocks["check_single_file"].return_value = {
|
||||
"success": True,
|
||||
"should_rollover": True,
|
||||
"trigger": "lines exceeded 600",
|
||||
"trigger": "5/3 sessions",
|
||||
}
|
||||
|
||||
watcher = mod.MemoryFileWatcher()
|
||||
@@ -498,7 +498,7 @@ class TestMemoryFileWatcherOnModified:
|
||||
mocks["check_single_file"].return_value = {
|
||||
"success": True,
|
||||
"should_rollover": True,
|
||||
"trigger": "lines exceeded",
|
||||
"trigger": "10/5 sessions",
|
||||
}
|
||||
mocks["execute_rollover"].side_effect = RuntimeError("Rollover crashed")
|
||||
|
||||
|
||||
@@ -137,9 +137,9 @@ class BranchDetector:
|
||||
Handles hyphens in project names by splitting on -Projects- and -src-.
|
||||
|
||||
Examples:
|
||||
-home-patrick-Projects-Vera-Studio -> ('VERA-STUDIO', None)
|
||||
-home-patrick-Projects-AIPL-src-polyglot -> ('AIPL', 'POLYGLOT')
|
||||
-home-patrick-Projects-Vera-Studio-src-vera -> ('VERA-STUDIO', 'VERA')
|
||||
-home-user-Projects-Vera-Studio -> ('VERA-STUDIO', None)
|
||||
-home-user-Projects-AIPL-src-polyglot -> ('AIPL', 'POLYGLOT')
|
||||
-home-user-Projects-Vera-Studio-src-vera -> ('VERA-STUDIO', 'VERA')
|
||||
|
||||
Returns:
|
||||
(project_name, agent_name) -- agent_name is None if no src subdir
|
||||
|
||||
@@ -271,6 +271,10 @@
|
||||
"file": "apps/handlers/aipass_proof/",
|
||||
"standard": "handlers",
|
||||
"reason": "Proof handlers import SOURCE_SKIP_DIRS from aipass_standards/skip_dirs.py — shared constant, same-branch cross-handler import, intentional (FPLAN-0261)."
|
||||
},
|
||||
{
|
||||
"file": "tests/test_checkers_batch10.py",
|
||||
"reason": "Test file: outside 3-layer structure by convention, imports handlers directly for unit testing, and contains intentional hardcoded-path strings as test input data."
|
||||
}
|
||||
],
|
||||
"notes": {
|
||||
|
||||
@@ -0,0 +1,187 @@
|
||||
# =================== AIPass ====================
|
||||
# Name: hardcoded_path_check.py
|
||||
# Description: Hardcoded Absolute Path Standards Checker Handler
|
||||
# Version: 1.0.0
|
||||
# Created: 2026-06-18
|
||||
# Modified: 2026-06-18
|
||||
# =============================================
|
||||
|
||||
"""Hardcoded Absolute Path Standards Checker Handler."""
|
||||
|
||||
import re
|
||||
from pathlib import Path
|
||||
from typing import Dict
|
||||
|
||||
from aipass.prax import logger
|
||||
from aipass.seedgo.apps.handlers.bypass.utils import is_bypassed
|
||||
from aipass.seedgo.apps.handlers.json import json_handler
|
||||
|
||||
AUDIT_SCOPE = "all_files"
|
||||
|
||||
_POSIX_HOME = re.compile(r"/home/[a-zA-Z][a-zA-Z0-9_.-]+/")
|
||||
_MACOS_HOME = re.compile(r"/Users/[a-zA-Z][a-zA-Z0-9_.-]+/")
|
||||
_WINDOWS_HOME = re.compile(r"[A-Z]:\\\\?Users\\\\?[a-zA-Z]")
|
||||
_DASH_POSIX = re.compile(r"-home-[a-zA-Z][a-zA-Z0-9_.]+-")
|
||||
_DASH_MACOS = re.compile(r"-Users-[a-zA-Z][a-zA-Z0-9_.]+-")
|
||||
|
||||
_ALL_PATTERNS = [
|
||||
(_POSIX_HOME, "POSIX home path"),
|
||||
(_MACOS_HOME, "macOS home path"),
|
||||
(_WINDOWS_HOME, "Windows home path"),
|
||||
(_DASH_POSIX, "dash-encoded POSIX home"),
|
||||
(_DASH_MACOS, "dash-encoded macOS home"),
|
||||
]
|
||||
|
||||
_COMMENT_RE = re.compile(r"^\s*#")
|
||||
_DOCSTRING_DELIMITERS = ('"""', "'''")
|
||||
|
||||
|
||||
def _in_docstring(lines: list[str], line_idx: int) -> bool:
|
||||
"""Return True if line_idx falls inside a docstring."""
|
||||
in_ds = False
|
||||
for i, line in enumerate(lines):
|
||||
stripped = line.strip()
|
||||
for delim in _DOCSTRING_DELIMITERS:
|
||||
count = stripped.count(delim)
|
||||
if count >= 2:
|
||||
continue
|
||||
if count == 1:
|
||||
in_ds = not in_ds
|
||||
if i == line_idx:
|
||||
return in_ds
|
||||
return False
|
||||
|
||||
|
||||
def _scan_file(content: str) -> list[tuple[int, str, str]]:
|
||||
"""Scan content for hardcoded home paths.
|
||||
|
||||
Returns list of (line_number, description, matched_text).
|
||||
"""
|
||||
violations: list[tuple[int, str, str]] = []
|
||||
lines = content.split("\n")
|
||||
|
||||
for idx, line in enumerate(lines):
|
||||
lineno = idx + 1
|
||||
if _COMMENT_RE.match(line):
|
||||
continue
|
||||
if _in_docstring(lines, idx):
|
||||
continue
|
||||
for pattern, desc in _ALL_PATTERNS:
|
||||
match = pattern.search(line)
|
||||
if match:
|
||||
violations.append((lineno, desc, match.group()))
|
||||
break
|
||||
return violations
|
||||
|
||||
|
||||
def check_module(module_path: str, bypass_rules: list | None = None) -> Dict:
|
||||
"""Check a Python file for hardcoded absolute home-directory paths."""
|
||||
path = Path(module_path)
|
||||
module_path = Path(module_path).as_posix()
|
||||
|
||||
if is_bypassed(module_path, "hardcoded_path", bypass_rules=bypass_rules):
|
||||
return {
|
||||
"passed": True,
|
||||
"checks": [
|
||||
{
|
||||
"name": "Bypassed",
|
||||
"passed": True,
|
||||
"message": "Standard bypassed via .seedgo/bypass.json",
|
||||
}
|
||||
],
|
||||
"score": 100,
|
||||
"standard": "HARDCODED_PATH",
|
||||
}
|
||||
|
||||
if path.suffix != ".py" or path.name == "__init__.py":
|
||||
return {
|
||||
"passed": True,
|
||||
"checks": [
|
||||
{
|
||||
"name": "Hardcoded path",
|
||||
"passed": True,
|
||||
"message": "File skipped (non-target)",
|
||||
}
|
||||
],
|
||||
"score": 100,
|
||||
"standard": "HARDCODED_PATH",
|
||||
}
|
||||
|
||||
if not path.exists():
|
||||
return {
|
||||
"passed": False,
|
||||
"checks": [
|
||||
{
|
||||
"name": "File exists",
|
||||
"passed": False,
|
||||
"message": f"File not found: {module_path}",
|
||||
}
|
||||
],
|
||||
"score": 0,
|
||||
"standard": "HARDCODED_PATH",
|
||||
}
|
||||
|
||||
try:
|
||||
source = path.read_text(encoding="utf-8")
|
||||
except Exception as e:
|
||||
logger.info("Cannot read %s: %s", path, e)
|
||||
return {
|
||||
"passed": False,
|
||||
"checks": [
|
||||
{
|
||||
"name": "File readable",
|
||||
"passed": False,
|
||||
"message": f"Error reading file: {e}",
|
||||
}
|
||||
],
|
||||
"score": 0,
|
||||
"standard": "HARDCODED_PATH",
|
||||
}
|
||||
|
||||
all_violations = _scan_file(source)
|
||||
|
||||
non_bypassed = [
|
||||
(ln, desc, txt)
|
||||
for ln, desc, txt in all_violations
|
||||
if not is_bypassed(module_path, "hardcoded_path", ln, bypass_rules)
|
||||
]
|
||||
non_bypassed.sort(key=lambda x: x[0])
|
||||
|
||||
checks = []
|
||||
violation_count = len(non_bypassed)
|
||||
|
||||
if violation_count == 0:
|
||||
checks.append(
|
||||
{
|
||||
"name": "Hardcoded path",
|
||||
"passed": True,
|
||||
"message": "No hardcoded absolute home paths found",
|
||||
}
|
||||
)
|
||||
else:
|
||||
previews = [f"L{ln}: {desc} ({txt})" for ln, desc, txt in non_bypassed[:3]]
|
||||
preview_str = "; ".join(previews)
|
||||
suffix = f" (and {violation_count - 3} more)" if violation_count > 3 else ""
|
||||
checks.append(
|
||||
{
|
||||
"name": "Hardcoded path",
|
||||
"passed": False,
|
||||
"message": f"{violation_count} hardcoded path(s): {preview_str}{suffix}",
|
||||
}
|
||||
)
|
||||
|
||||
passed_checks = sum(1 for c in checks if c["passed"])
|
||||
total_checks = len(checks)
|
||||
score = int((passed_checks / total_checks) * 100) if total_checks > 0 else 0
|
||||
overall_passed = score >= 75
|
||||
|
||||
json_handler.log_operation(
|
||||
"check_completed",
|
||||
{"file": str(module_path), "score": score, "standard": "hardcoded_path"},
|
||||
)
|
||||
return {
|
||||
"passed": overall_passed,
|
||||
"checks": checks,
|
||||
"score": score,
|
||||
"standard": "HARDCODED_PATH",
|
||||
}
|
||||
@@ -0,0 +1,93 @@
|
||||
# =================== AIPass ====================
|
||||
# Name: hardcoded_path_content.py
|
||||
# Description: Hardcoded Absolute Path Standards Content Handler
|
||||
# Version: 1.0.0
|
||||
# Created: 2026-06-18
|
||||
# Modified: 2026-06-18
|
||||
# =============================================
|
||||
|
||||
"""
|
||||
Hardcoded Absolute Path Standards Content Handler
|
||||
|
||||
Provides formatted hardcoded path standards content.
|
||||
Module orchestrates, handler implements.
|
||||
"""
|
||||
|
||||
from aipass.seedgo.apps.handlers.json import json_handler
|
||||
|
||||
|
||||
def get_hardcoded_path_standards() -> str:
|
||||
"""Return formatted hardcoded_path standards content with Rich markup.
|
||||
|
||||
Returns:
|
||||
str: Formatted standards text with Rich styling
|
||||
"""
|
||||
lines = [
|
||||
"[bold cyan]CORE PRINCIPLE:[/bold cyan]",
|
||||
" AIPass is a cross-platform PUBLIC repo. Source code must NEVER contain",
|
||||
" hardcoded absolute home-directory paths. They leak usernames, break on",
|
||||
" other machines, and violate cross-platform portability.",
|
||||
"",
|
||||
"[bold cyan]WHAT IT CHECKS:[/bold cyan]",
|
||||
" Scans Python source lines (excluding comments and docstrings) for:",
|
||||
"",
|
||||
" 1. [red]POSIX home paths[/red]: /home/<user>/...",
|
||||
" 2. [red]macOS home paths[/red]: /Users/<user>/...",
|
||||
" 3. [red]Windows home paths[/red]: C:\\Users\\<user>\\...",
|
||||
" 4. [red]Dash-encoded POSIX[/red]: -home-<user>-... (Claude Code project-dir encoding)",
|
||||
" 5. [red]Dash-encoded macOS[/red]: -Users-<user>-... (Claude Code project-dir encoding)",
|
||||
"",
|
||||
"[bold cyan]FALSE-POSITIVE GUARDS:[/bold cyan]",
|
||||
" - [dim]# comments[/dim] are skipped (line-level)",
|
||||
" - [dim]Docstrings[/dim] are skipped (triple-quote blocks)",
|
||||
" - [dim]__init__.py[/dim] files are skipped",
|
||||
" - [dim]Test files[/dim] are NOT skipped by default -- use line-level bypass",
|
||||
" for test fixtures that must assert on literal path strings",
|
||||
"",
|
||||
"[bold cyan]VIOLATIONS:[/bold cyan]",
|
||||
"",
|
||||
" [red]Bad -- hardcoded POSIX home:[/red]",
|
||||
' [dim]ROOT = "/home/patrick/Projects/AIPass"[/dim]',
|
||||
"",
|
||||
" [red]Bad -- dash-encoded home (leaks username):[/red]",
|
||||
' [dim]dirs = ["-home-patrick-Projects-AIPass-src-aipass-memory"][/dim]',
|
||||
"",
|
||||
"[bold cyan]HOW TO FIX:[/bold cyan]",
|
||||
"",
|
||||
" [green]Good -- use Path(__file__) or env:[/green]",
|
||||
" [dim]ROOT = Path(__file__).resolve().parents[3][/dim]",
|
||||
" [dim]ROOT = Path(os.environ['AIPASS_HOME'])[/dim]",
|
||||
"",
|
||||
" [green]Good -- use pathlib for home:[/green]",
|
||||
" [dim]home = Path.home()[/dim]",
|
||||
"",
|
||||
" [green]Good -- test fixtures with generic paths:[/green]",
|
||||
' [dim]path = "/home/user/Projects/AIPass/..." # generic, no real username[/dim]',
|
||||
"",
|
||||
"[yellow]SCOPE:[/yellow]",
|
||||
" AUDIT_SCOPE = [bold]all_files[/bold]",
|
||||
" Checks every .py file in the branch",
|
||||
"",
|
||||
"[bold cyan]SCORING:[/bold cyan]",
|
||||
" One check per file (Hardcoded path)",
|
||||
" [green]100[/green] = no hardcoded absolute home paths found",
|
||||
" [red]0[/red] = one or more hardcoded paths found",
|
||||
" Reports up to 3 offending line numbers with descriptions",
|
||||
" Overall pass threshold: [yellow]75%[/yellow]",
|
||||
"",
|
||||
"[bold cyan]BYPASS:[/bold cyan]",
|
||||
" Via [dim].seedgo/bypass.json[/dim] -- supports standard, file-level,",
|
||||
" and line-level bypass rules",
|
||||
"",
|
||||
" [dim]Example bypass entry (test fixture):[/dim]",
|
||||
' [dim]{{"file": "tests/test_paths.py", "standard": "hardcoded_path",[/dim]',
|
||||
' [dim] "lines": [42, 43], "reason": "Test asserts on literal path"}}[/dim]',
|
||||
"",
|
||||
"[bold cyan]REFERENCE:[/bold cyan]",
|
||||
" [dim]See: seedgo standards pack (hardcoded_path)[/dim]",
|
||||
" [dim]Checker: hardcoded_path_check.py[/dim]",
|
||||
" [dim]House rule: cross-platform, no hardcoded paths, use pathlib[/dim]",
|
||||
]
|
||||
|
||||
json_handler.log_operation("standard_content_queried", {"standard": "hardcoded_path"})
|
||||
return "\n".join(lines)
|
||||
@@ -4,7 +4,15 @@
|
||||
"hooks": [
|
||||
{
|
||||
"type": "command",
|
||||
"command": "$AIPASS_HOME/.venv/bin/python3 $AIPASS_HOME/src/aipass/hooks/apps/handlers/bridges/claude.py UserPromptSubmit:global_prompt"
|
||||
"command": "$AIPASS_HOME/.venv/bin/python3 $AIPASS_HOME/src/aipass/hooks/apps/handlers/bridges/claude.py UserPromptSubmit:tier0_kernel"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"hooks": [
|
||||
{
|
||||
"type": "command",
|
||||
"command": "$AIPASS_HOME/.venv/bin/python3 $AIPASS_HOME/src/aipass/hooks/apps/handlers/bridges/claude.py UserPromptSubmit:navmap"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -0,0 +1,283 @@
|
||||
"""Tests for seedgo checker handlers -- batch 10 (hardcoded_path_check)."""
|
||||
|
||||
# =================== META ====================
|
||||
# Name: test_checkers_batch10.py
|
||||
# Description: Unit tests for hardcoded_path_check
|
||||
# Version: 1.0.0
|
||||
# Created: 2026-06-18
|
||||
# Modified: 2026-06-18
|
||||
# =============================================
|
||||
|
||||
import pytest
|
||||
from unittest.mock import MagicMock
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Fixtures
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def _mock_infrastructure(monkeypatch):
|
||||
"""Mock heavy infrastructure imports for standards checkers."""
|
||||
import sys
|
||||
|
||||
mock_logger = MagicMock()
|
||||
mock_json_handler = MagicMock()
|
||||
mock_json_handler.log_operation = MagicMock(return_value=True)
|
||||
|
||||
prax_mod = MagicMock()
|
||||
prax_mod.logger = mock_logger
|
||||
monkeypatch.setitem(sys.modules, "aipass.prax", prax_mod)
|
||||
|
||||
json_pkg = MagicMock()
|
||||
json_pkg.json_handler = mock_json_handler
|
||||
monkeypatch.setitem(sys.modules, "aipass.seedgo.apps.handlers.json", json_pkg)
|
||||
json_mod = MagicMock()
|
||||
json_mod.log_operation = mock_json_handler.log_operation
|
||||
monkeypatch.setitem(sys.modules, "aipass.seedgo.apps.handlers.json.json_handler", json_mod)
|
||||
|
||||
from aipass.seedgo.apps.handlers.bypass.utils import is_bypassed as real_is_bypassed
|
||||
|
||||
bypass_pkg = MagicMock()
|
||||
bypass_utils = MagicMock()
|
||||
bypass_utils.is_bypassed = real_is_bypassed
|
||||
bypass_pkg.utils = bypass_utils
|
||||
bypass_ignore = MagicMock()
|
||||
bypass_ignore.get_template_ignore_patterns = MagicMock(return_value=[])
|
||||
bypass_pkg.ignore_handler = bypass_ignore
|
||||
monkeypatch.setitem(sys.modules, "aipass.seedgo.apps.handlers.bypass", bypass_pkg)
|
||||
monkeypatch.setitem(sys.modules, "aipass.seedgo.apps.handlers.bypass.utils", bypass_utils)
|
||||
monkeypatch.setitem(
|
||||
sys.modules,
|
||||
"aipass.seedgo.apps.handlers.bypass.ignore_handler",
|
||||
bypass_ignore,
|
||||
)
|
||||
|
||||
for mod_name in [
|
||||
"aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check",
|
||||
]:
|
||||
monkeypatch.delitem(sys.modules, mod_name, raising=False)
|
||||
|
||||
|
||||
# ===========================================================================
|
||||
# 1. _scan_file — core scanning logic
|
||||
# ===========================================================================
|
||||
|
||||
|
||||
class TestScanFile:
|
||||
"""Tests for the _scan_file helper."""
|
||||
|
||||
def test_posix_home_detected(self):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import _scan_file
|
||||
|
||||
content = 'ROOT = "/home/patrick/Projects/AIPass"\n'
|
||||
result = _scan_file(content)
|
||||
assert len(result) == 1
|
||||
assert result[0][1] == "POSIX home path"
|
||||
|
||||
def test_macos_home_detected(self):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import _scan_file
|
||||
|
||||
content = 'ROOT = "/Users/patrick/Projects/AIPass"\n'
|
||||
result = _scan_file(content)
|
||||
assert len(result) == 1
|
||||
assert result[0][1] == "macOS home path"
|
||||
|
||||
def test_windows_home_detected(self):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import _scan_file
|
||||
|
||||
content = 'ROOT = "C:\\\\Users\\\\patrick\\\\Projects"\n'
|
||||
result = _scan_file(content)
|
||||
assert len(result) == 1
|
||||
assert result[0][1] == "Windows home path"
|
||||
|
||||
def test_dash_encoded_posix_detected(self):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import _scan_file
|
||||
|
||||
content = 'dirs = ["-home-patrick-Projects-AIPass"]\n'
|
||||
result = _scan_file(content)
|
||||
assert len(result) == 1
|
||||
assert result[0][1] == "dash-encoded POSIX home"
|
||||
|
||||
def test_dash_encoded_macos_detected(self):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import _scan_file
|
||||
|
||||
content = 'dirs = ["-Users-patrick-Projects-AIPass"]\n'
|
||||
result = _scan_file(content)
|
||||
assert len(result) == 1
|
||||
assert result[0][1] == "dash-encoded macOS home"
|
||||
|
||||
def test_comment_skipped(self):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import _scan_file
|
||||
|
||||
content = '# ROOT = "/home/patrick/Projects/AIPass"\n'
|
||||
result = _scan_file(content)
|
||||
assert len(result) == 0
|
||||
|
||||
def test_indented_comment_skipped(self):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import _scan_file
|
||||
|
||||
content = ' # path = "/home/patrick/test"\n'
|
||||
result = _scan_file(content)
|
||||
assert len(result) == 0
|
||||
|
||||
def test_docstring_skipped(self):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import _scan_file
|
||||
|
||||
content = '"""\nExample: /home/patrick/Projects\n"""\nx = 1\n'
|
||||
result = _scan_file(content)
|
||||
assert len(result) == 0
|
||||
|
||||
def test_clean_file(self):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import _scan_file
|
||||
|
||||
content = "from pathlib import Path\nROOT = Path(__file__).parent\n"
|
||||
result = _scan_file(content)
|
||||
assert len(result) == 0
|
||||
|
||||
def test_generic_user_not_flagged(self):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import _scan_file
|
||||
|
||||
content = 'path = "/home/user/Projects/AIPass"\n'
|
||||
result = _scan_file(content)
|
||||
assert len(result) == 1
|
||||
assert result[0][1] == "POSIX home path"
|
||||
|
||||
def test_multiple_violations_same_file(self):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import _scan_file
|
||||
|
||||
content = 'A = "/home/alice/foo"\nB = "/Users/bob/bar"\nC = "-home-charlie-baz"\n'
|
||||
result = _scan_file(content)
|
||||
assert len(result) == 3
|
||||
|
||||
def test_line_numbers_correct(self):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import _scan_file
|
||||
|
||||
content = 'clean = 1\nbad = "/home/patrick/x"\nalso_clean = 2\n'
|
||||
result = _scan_file(content)
|
||||
assert len(result) == 1
|
||||
assert result[0][0] == 2
|
||||
|
||||
|
||||
# ===========================================================================
|
||||
# 2. check_module — full integration via tmp files
|
||||
# ===========================================================================
|
||||
|
||||
|
||||
class TestCheckModule:
|
||||
"""Tests for check_module entry point."""
|
||||
|
||||
def test_clean_file_passes(self, tmp_path):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import check_module
|
||||
|
||||
f = tmp_path / "clean.py"
|
||||
f.write_text("from pathlib import Path\nROOT = Path(__file__).parent\n")
|
||||
result = check_module(str(f))
|
||||
assert result["passed"] is True
|
||||
assert result["score"] == 100
|
||||
assert result["standard"] == "HARDCODED_PATH"
|
||||
|
||||
def test_violation_fails(self, tmp_path):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import check_module
|
||||
|
||||
f = tmp_path / "bad.py"
|
||||
f.write_text('ROOT = "/home/patrick/Projects/AIPass"\n')
|
||||
result = check_module(str(f))
|
||||
assert result["passed"] is False
|
||||
assert result["score"] == 0
|
||||
|
||||
def test_bypass_whole_standard(self, tmp_path):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import check_module
|
||||
|
||||
f = tmp_path / "bypassed.py"
|
||||
f.write_text('ROOT = "/home/patrick/Projects/AIPass"\n')
|
||||
rules = [{"standard": "hardcoded_path", "file": "bypassed.py"}]
|
||||
result = check_module(str(f), bypass_rules=rules)
|
||||
assert result["passed"] is True
|
||||
assert result["score"] == 100
|
||||
|
||||
def test_bypass_specific_line(self, tmp_path):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import check_module
|
||||
|
||||
f = tmp_path / "partial.py"
|
||||
f.write_text('A = "/home/alice/ok"\nB = "/home/bob/also_ok"\n')
|
||||
rules = [
|
||||
{"standard": "hardcoded_path", "file": "partial.py", "lines": [1, 2]},
|
||||
]
|
||||
result = check_module(str(f), bypass_rules=rules)
|
||||
assert result["passed"] is True
|
||||
|
||||
def test_init_py_skipped(self, tmp_path):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import check_module
|
||||
|
||||
f = tmp_path / "__init__.py"
|
||||
f.write_text('X = "/home/patrick/nope"\n')
|
||||
result = check_module(str(f))
|
||||
assert result["passed"] is True
|
||||
assert "skipped" in result["checks"][0]["message"].lower()
|
||||
|
||||
def test_nonexistent_file(self):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import check_module
|
||||
|
||||
result = check_module("/no/such/file.py")
|
||||
assert result["passed"] is False
|
||||
assert result["score"] == 0
|
||||
|
||||
def test_non_python_skipped(self, tmp_path):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import check_module
|
||||
|
||||
f = tmp_path / "readme.md"
|
||||
f.write_text("/home/patrick/whatever\n")
|
||||
result = check_module(str(f))
|
||||
assert result["passed"] is True
|
||||
|
||||
def test_violation_message_includes_line_info(self, tmp_path):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import check_module
|
||||
|
||||
f = tmp_path / "info.py"
|
||||
f.write_text('x = "/home/alice/stuff"\n')
|
||||
result = check_module(str(f))
|
||||
msg = result["checks"][0]["message"]
|
||||
assert "L1" in msg
|
||||
assert "POSIX home path" in msg
|
||||
|
||||
def test_more_than_three_violations_truncates(self, tmp_path):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import check_module
|
||||
|
||||
f = tmp_path / "many.py"
|
||||
lines = [f'v{i} = "/home/u{i}/x"\n' for i in range(5)]
|
||||
f.write_text("".join(lines))
|
||||
result = check_module(str(f))
|
||||
msg = result["checks"][0]["message"]
|
||||
assert "and 2 more" in msg
|
||||
|
||||
|
||||
# ===========================================================================
|
||||
# 3. _in_docstring — edge cases
|
||||
# ===========================================================================
|
||||
|
||||
|
||||
class TestInDocstring:
|
||||
"""Tests for docstring detection."""
|
||||
|
||||
def test_single_line_docstring(self):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import _in_docstring
|
||||
|
||||
lines = ['"""This is a docstring."""', 'x = "/home/pat/y"']
|
||||
assert _in_docstring(lines, 0) is False
|
||||
assert _in_docstring(lines, 1) is False
|
||||
|
||||
def test_multiline_docstring(self):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import _in_docstring
|
||||
|
||||
lines = ['"""', "/home/patrick/inside", '"""', "/home/patrick/outside"]
|
||||
assert _in_docstring(lines, 1) is True
|
||||
assert _in_docstring(lines, 3) is False
|
||||
|
||||
def test_single_quote_docstring(self):
|
||||
from aipass.seedgo.apps.handlers.aipass_standards.hardcoded_path_check import _in_docstring
|
||||
|
||||
lines = ["'''", "/home/patrick/inside", "'''", "/home/patrick/outside"]
|
||||
assert _in_docstring(lines, 1) is True
|
||||
assert _in_docstring(lines, 3) is False
|
||||
@@ -13,7 +13,7 @@ has_handler: true
|
||||
|
||||
# Telegram Bridge
|
||||
|
||||
Multi-bot personal-assistant bridge: long-polling listener routes Patrick's Telegram messages into Claude tmux sessions; Claude's Stop hook writes a pending file and the bot sends the response back to Telegram.
|
||||
Multi-bot personal-assistant bridge: long-polling listener routes user Telegram messages into Claude tmux sessions; Claude's Stop hook writes a pending file and the bot sends the response back to Telegram.
|
||||
|
||||
## Architecture
|
||||
|
||||
|
||||
@@ -16,7 +16,7 @@ Stdlib-only implementation using urllib for Telegram API. No python-telegram-bot
|
||||
dependency. Follows the same polling/tmux injection pattern as direct_chat.py.
|
||||
|
||||
Flow:
|
||||
Patrick sends Telegram message
|
||||
User sends Telegram message
|
||||
-> BaseBot receives it via getUpdates long-polling
|
||||
-> If /command -> handle via telegram_standards, reply, return
|
||||
-> If /new -> kill tmux session, reply, return
|
||||
@@ -169,8 +169,8 @@ class BaseBot:
|
||||
custom_commands: Dict of bot-specific commands in telegram_standards format
|
||||
branch_name: Branch name for log streaming (None = no streaming, e.g. base bot)
|
||||
shared_session: tmux session name to inject into instead of creating own session.
|
||||
When set, the bot attaches to an existing session (e.g., Patrick's
|
||||
running Claude Code on PC). Falls back to own session if not found.
|
||||
When set, the bot attaches to an existing session (e.g., the user's
|
||||
running Claude Code session). Falls back to own session if not found.
|
||||
"""
|
||||
self.bot_id = bot_id
|
||||
self.bot_token = bot_token
|
||||
@@ -182,6 +182,8 @@ class BaseBot:
|
||||
if not hasattr(self, "branch_name"):
|
||||
self.branch_name = branch_name
|
||||
|
||||
self._current_sender_name: str = "User"
|
||||
|
||||
self.session_name = f"telegram-{bot_id}"
|
||||
self.pending_file = PENDING_DIR / f"bot-{bot_id}.json"
|
||||
|
||||
@@ -470,6 +472,7 @@ class BaseBot:
|
||||
from_user = message.get("from", {})
|
||||
user_id = from_user.get("id", 0)
|
||||
username = from_user.get("username", "unknown")
|
||||
self._current_sender_name = from_user.get("first_name", "User")
|
||||
_ = message.get("message_id", 0) # Available for future use
|
||||
|
||||
# Start log streamer on first valid message (if branch has a name)
|
||||
@@ -711,7 +714,7 @@ class BaseBot:
|
||||
|
||||
# Detect type and build prompt
|
||||
file_type = detect_file_type(file_path)
|
||||
prompt = build_file_prompt(file_path, file_type, caption=caption or None, sender_name="Patrick")
|
||||
prompt = build_file_prompt(file_path, file_type, caption=caption or None, sender_name=self._current_sender_name)
|
||||
|
||||
# Hook: pre-process
|
||||
prompt = self.on_message(prompt)
|
||||
@@ -1205,7 +1208,7 @@ class BaseBot:
|
||||
Ensure a tmux session is available for message injection.
|
||||
|
||||
In shared-session mode: attaches to an existing tmux session (e.g.,
|
||||
Patrick's running Claude Code on PC). Falls back to own session if
|
||||
the user's running Claude Code session). Falls back to own session if
|
||||
the shared session is not found.
|
||||
|
||||
In normal mode: creates telegram-{bot_id} session with Claude Code.
|
||||
|
||||
@@ -47,9 +47,10 @@ class BranchPlugin(BaseBot):
|
||||
text: Raw message text from Telegram
|
||||
|
||||
Returns:
|
||||
Prefixed text for Claude: "Patrick via Telegram: {text}"
|
||||
Prefixed text for Claude: "{sender_name} via Telegram: {text}"
|
||||
"""
|
||||
return f"Patrick via Telegram: {text}"
|
||||
sender = getattr(self, "_current_sender_name", "User")
|
||||
return f"{sender} via Telegram: {text}"
|
||||
|
||||
def on_response(self, text: str) -> str:
|
||||
"""
|
||||
|
||||
@@ -162,7 +162,7 @@ def detect_file_type(file_path: Path) -> str:
|
||||
return "binary"
|
||||
|
||||
|
||||
def build_file_prompt(file_path: Path, file_type: str, caption: str | None = None, sender_name: str = "Patrick") -> str:
|
||||
def build_file_prompt(file_path: Path, file_type: str, caption: str | None = None, sender_name: str = "User") -> str:
|
||||
"""
|
||||
Build a Claude prompt that includes file content.
|
||||
|
||||
|
||||
@@ -203,7 +203,7 @@ class TestBotFatherClientConnect:
|
||||
"""connect() returns True when session is authorized."""
|
||||
mock_client_instance = AsyncMock()
|
||||
mock_client_instance.is_user_authorized.return_value = True
|
||||
mock_client_instance.get_me.return_value = MagicMock(first_name="Patrick", id=123)
|
||||
mock_client_instance.get_me.return_value = MagicMock(first_name="TestUser", id=123)
|
||||
|
||||
with patch(
|
||||
"apps.handlers.botfather_client._telethon_check",
|
||||
|
||||
@@ -281,11 +281,11 @@ class TestBranchPluginHooks:
|
||||
|
||||
def test_on_message_prefixes_text(self, branch_bot):
|
||||
result = branch_bot.on_message("deploy the fix")
|
||||
assert result == "Patrick via Telegram: deploy the fix"
|
||||
assert result == "User via Telegram: deploy the fix"
|
||||
|
||||
def test_on_message_empty_text(self, branch_bot):
|
||||
result = branch_bot.on_message("")
|
||||
assert result == "Patrick via Telegram: "
|
||||
assert result == "User via Telegram: "
|
||||
|
||||
def test_on_response_tags_with_branch(self, branch_bot):
|
||||
result = branch_bot.on_response("Done. Everything is deployed.")
|
||||
@@ -850,7 +850,7 @@ class TestProcessUpdate:
|
||||
"message": {
|
||||
"text": "do something",
|
||||
"chat": {"id": 1},
|
||||
"from": {"id": 111, "username": "patrick"},
|
||||
"from": {"id": 111, "username": "testuser"},
|
||||
"message_id": 1,
|
||||
},
|
||||
}
|
||||
@@ -868,7 +868,7 @@ class TestProcessUpdate:
|
||||
"message": {
|
||||
"text": "hello",
|
||||
"chat": {"id": 1},
|
||||
"from": {"id": 111, "username": "patrick"},
|
||||
"from": {"id": 111, "username": "testuser"},
|
||||
"message_id": 1,
|
||||
},
|
||||
}
|
||||
@@ -1786,7 +1786,7 @@ class TestLockPidReuse:
|
||||
)
|
||||
# Mock /proc read to return different bot's cmdline
|
||||
with patch("pathlib.Path.read_bytes") as mock_read:
|
||||
mock_read.return_value = b"python3\x00base_bot.py\x00--bot-id\x00patrick_private"
|
||||
mock_read.return_value = b"python3\x00base_bot.py\x00--bot-id\x00other_bot"
|
||||
assert self.bot._check_lock() is False
|
||||
assert not self.bot._lock_file.exists() # Stale lock cleaned
|
||||
|
||||
|
||||
Reference in New Issue
Block a user