Closes a zero-interaction RCE where a hostile repo's .aipass/hooks.json
(discovered via loader CWD walk-up, bridge wired globally) could run an
arbitrary command-type hook on SessionStart. Defense-in-depth:
Layer A (engine): refuse command-type hooks from per-project configs via
unconditional _source clobber; gate handler paths to aipass.* namespace.
Layer B (loader+CLI): trusted-project registry (path+sha256), fail-closed
trust-check, $AIPASS_HOME-only bootstrap (no TOFU), aipass init auto-enroll
+ new aipass trust/revoke commands.
Live acceptance test (real bridge, real payload) proves both gates block
independently. 1105 hooks + 133 aipass tests green.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YEAyLFCuo4uD934fwFxocz
@spawn: owner + registry_id written into the SEALED registry entries (authority lives in registry, not the self-editable passport). ensure_project_has_owner() now keys off citizen_class=manager (was earliest-created, which mislabeled @aipass) and writes the registry entry. get_owner()/is_owner() resolvers added. 315 tests, seedgo 100%.
@hooks: new registry_gate PreToolUse handler seals *_REGISTRY.json — blocks raw writes/tee/sed/rm + Edit/Write/MultiEdit, redirects to drone @spawn; per-clause bypass defeats compound-command smuggling; reads allowed. 82 tests, seedgo 100%.
@ai_mail: wake-back reslope — SKIP_SENDERS blocklist replaced by an is_owner allowlist. Only the project owner is woken when their dispatched agent completes; all other guards intact (depth cap, lock, occupancy, honest messaging, dispatch_wake.log). seedgo 100% on the changed file.
devpulse cross-part verify (REAL unmocked resolver): is_owner resolves devpulse-only; gate 13/13 incl compound-smuggle blocked + reads/drone-@spawn allowed; wake-back wakes owner / skips non-owner / respects depth-cap; 195 new-suite tests green together. Note: AIPASS_REGISTRY.json is gitignored — this ships the CODE; owner data regenerates per-install via ensure_project_has_owner. Still open (PART 4): gate watchdog+feedback on is_owner; portability of owner-only privileges across projects.
Navmap (@hooks): one bullet in the Memory section — caps are hook-enforced,
the live cap is rendered in each file's *_meta line; read it before writing,
draft to ~80%, one-pass rewrite if rejected. Devpulse branch prompt: same
behavior, explicitly notes caps are NOT listed (single source =
memory.config.json → entry_limits, auto-rendered by @memory's tab_renderer).
Change the config → enforcement + in-file docs follow mechanically; prompts
never go stale.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Q3mZT61WsKVN3srCwVDBiW
Activation fixes for the single-session presence gate. Two bugs blocked it,
both caught by live testing after all units were green:
1) Wrong branch key. presence_gate used Path.cwd().name, but under the Claude
Code bridge the hook process cwd is the project root, so every session keyed
to "AIPass": the gate never enforced one-live-session-per-branch and would
have rejected sessions project-globally (any 2nd interactive session in any
branch). Now _resolve_branch(hook_data) reads the event payload's cwd (the
real session dir) and walks up to the branch root (.trinity/ or apps/),
mirroring branch_loader. Applied in handle() and handle_stop().
2) Block never reached Claude Code. engine.dispatch() returned only stdout, so
the bridge could not surface a non-zero exit. dispatch() now returns
(stdout, exit_code) and the bridge exits with it on a block. Pre-existing gap
affecting every block hook on every event; now fixed engine-wide. An
intentional block (exit 2 + {"decision":"block"}) propagates; a crashing hook
(exit 2, non-JSON stdout) is logged and falls through, so the gate fails open.
Proven: 110 hooks unit tests pass (6 new for branch resolution); seedgo @hooks
100%, no type errors. Live bridge end-to-end (real live holder + real bridge):
duplicate into a held branch -> exit 2 + block reason naming the branch; a
different free branch -> exit 0 (per-branch isolation intact). Gate remains
dormant: not yet wired into provider settings.
Design: DPLAN-0225 / FPLAN-0289 P1 activation. Build by @hooks.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CqoxFdbDMirzkQ5kjRVVos
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.
Replaces the single 8k always-injected global prompt with cadence-tiered injection:
- Tier 0 (.aipass/tier0_kernel.md, ~2k) injects EVERY turn — identity grounding, the drone --help reflex, disaster-preventer rules. Folds DPLAN-0213 C1 (faithful-reporting) + C2 (no-gold-plating sub-agent brief).
- Tier 1 (.aipass/tier1_navmap.md, ~7.7k) injects every 5th turn + session-start + post-compaction — full agent roster, framework, conventions, plus a new Terminology section migrated from the S211 backup.
- Old global_prompt loader retired (disabled in hooks.json, removed from cadence wiring); aipass_global_prompt.md kept as a reference snapshot.
Engine (built by @hooks): per-loader period in cadence.py should_fire() (back-compatible: unset period falls back to global); new tier0_kernel + navmap handlers; bypass.json extended to cover the two new dynamically-dispatched handlers. 614/614 tests pass, seedgo @hooks 100%.
Live-verified: tier0 fires every turn, navmap on turn 0/5/10, turn counter advances once per turn (not per loader), no double-injection. Machine-local wiring (cadence_config.json, ~/.claude/settings.json bridge) updated on this host; fresh-clone seeding of those is a tracked follow-up.
PROMPT_STYLE.md reference updated to point at the tier files as canonical examples.
- PROMPT_STYLE.md: new 'Writing voice' section (file_path:line refs, no-colon-before-tool-call, no emojis, write-for-a-person, three-tier where-detail-lives) — harvested from Claude Code's own prompt
- devpulse local: blast-radius habit before any drone write-op (reversibility + scope)
- global + devpulse-local: S241 whitespace/structure cleanup (readable English restored)
Add @skills/@daemon/@commons/@backup to global prompt agent list; trim+restyle
devpulse local prompt to PROMPT_STYLE (single # headers, no emphasis, de-dup vs
global); smooth .claude culture doc (kill repeats, drop mechanical overlap).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Rewrite the always-injected global prompt from a ~13.8KB encyclopedia
into a ~7.8KB navigation map. The prompt now carries AWARENESS; detail
is fetched on demand via 'drone @agent --help'. Dissolves the harness
~10k-char truncation bug — the old prompt's tail (Hard Rules onward)
silently never arrived; the slim one injects whole.
- drone pinned at top as the router; one drilled reflex: --help before use
- framework tree restored; all 13 agents as 2-3 sentence bios
- introspection named as our term; breadcrumb-first navigation flow
- git its own section (raw git/gh blocked, drone-only, devpulse-writes)
- plans section (DPLAN/FPLAN/PPLAN/RPLAN + 'drone @flow templates')
- @memory chroma awareness (local + global stores, search before cold)
- sub-agent usage section incl. model practice (never fable)
- PROMPT_STYLE-conformant; 7855 chars (cap 8000, measured in chars)
Backup retained: .aipass/aipass_global_prompt.BACKUP-2026-06-09-S211.md
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Phase 2 of #630. The rm_gate hook + drone rm now own destructive-delete
protection (cross-provider, path-aware, teaching), so the Claude-only blanket
deny is redundant AND harmful (it short-circuits before the hook, suppressing
the teaching message).
- setup.sh: removed Bash(rm -rf*) + Bash(rm -r *) from git_deny (new installs)
- bootstrap.py: removed Bash(rm -rf *) shipped via aipass init (project settings)
- doctor_wire.reconcile_stale_deny(): aipass doctor WARNs on stale rules;
--fix removes them (idempotent, preserves all else) — migration for existing
installs (the 'aipass update should be trusted' goal)
- .aipass/project_hooks.json template: added rm_gate (new projects get it)
Tests: 8 reconcile + 432 aipass total, seedgo 99%. CHANGELOG W23.
- bootstrap.py: write hooks.json from template at init, union-merge on update (preserves user on/off), remove dead _ship_hooks/HOOKS_TO_SHIP
- doctor.py: check .aipass/hooks.json presence
- .aipass/project_hooks.json: base template (all 14 handlers)
- .aipass/.gitignore: whitelist template so it ships in clones
- +13 tests, 421 pass, seedgo 99%
AIOSAI