- Drop per-session agent runtime markers (CLAUDECODE, CLAUDE_CODE_CHILD_SESSION,
CLAUDE_CODE_SESSION_ID, Claude Code messaging/bridge/pid markers, and the
agy/hermes/grok/opencode session ids) from the environment lib.sh's shim hands
to a bootstrapped `herdr --session <name> server`; user configuration such as
CLAUDE_PROJECT_DIR still inherits
- Add MAM_NO_AUTOSTART=1 so query-only callers never bootstrap a server as a side
effect; status.sh and reconcile.sh export it, and the shim's `ls` reports a down
server as "no server running" so reconcile keeps herdr_confirmed instead of
freezing drift detection for every server
- send_keys_safe: treat `timeout` / `agent_prompt_stalled` from `agent prompt
--wait` as an accepted submission and confirm delivery for SKS_DELIVERY_GRACE_S
(default 15 s) via agent_status working, a busy token the pane did not show
before, or the pane moving on from its pre-submit snapshot; no signal at all
still fails closed (rc 4). Codex under herdr 0.9.0 never reports `working`, so
every delivered prompt was closed as agent_blocked and its later
started/completed events refused
- delegate wrapper: before closing an unconfirmed inject as agent_blocked, honour
the registry's own acknowledgement for MAM_INJECT_ACK_GRACE_S (default 10 s)
- Switch T1-7's failure trigger to transport_error (timeout now means accepted);
add test_issue9_server_env.py (5 cases) and test_issue14_delivery_ack.py (7)
- Verified live: a freshly bootstrapped multi-agent-mux server carries no markers
and the claude panes save transcripts again; codex job d04ebcb5 had its
started/completed accepted with no agent_blocked
Closes#9Closes#14
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
The four delegation scripts become a real package. Their old paths stay as
shims because those paths are a wire contract: agent instructions, the bash
wrapper, SKILL.md, BOOTSTRAP.md, deploy/install.sh and three test modules all
call them literally.
The shim binds the lib_py.delegation *package* to the tree beside it, once per
process, and never touches sys.path. Two cheaper designs were rejected with
evidence (the context matrix now lives in the test suite):
* inserting the sibling skills dir at sys.path[0] makes the first sandbox
copy imported under pytest shadow lib_py.agents/layout/state for the whole
session, and the identity assertion cannot see it -- `is` proves same
object, not same tree.
* loading only the named module by file path leaves a module that imports
siblings pulling them from whichever tree is on the path, so a frozen
publish_event ran against live dependencies and lost half of B-13.
Binding the package fixes both: one tree for all delegation modules, the parent
lib_py untouched, and a sys.path append only when no lib_py exists anywhere
(true standalone). Bind-once rather than nearest-wins, because rebinding would
split existing references and break monkeypatching.
Also moves the env-file load off import (_load_dotenv -> ensure_env_loaded,
called by each process entry point including reconcile.sh's embedded
subscriber), so importing the library no longer mutates os.environ.
Verified: PV-1 identity+provenance, PV-4's ten import scenarios plus K1/K3/K6
in fresh interpreters, PV-5 shim byte-identity, an AST check that the package
imports no sibling lib_py module, and --help output diffed against the
pre-move capture.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UrDNJkHmm18uu7n7JwV5Qd
- Implement CodexAdapter in lib_py/agents/adapters/codex.py with safe flags and TUI readiness
- Extend create_session, resume_session, stop_session, and reconcile for codex CLI
- Support codex agent delegation and loop integration across all multi-agent skills
- Add unit, component, and contract test suites for codex integration
- Verify all 462 tests passing cleanly
- Add --yolo and --accept-hooks headless auto-approval flags to spawn_spec and resume_spec
- Define Hermes TUI input delimiters (input_prompt='❯', input_rule_pattern='─{10,}')
- Refactor verify_artifact and discover in hermes.py using session started_at timestamps
- Fix HERDR_EPOCH capture timing before spawn in create_session.sh to prevent epoch race
- Update reconcile.sh for hermes drift-C multi-candidate and sibling claimed exclusion
- Add Hermes contract, epoch filtering, and C-ambiguous unit tests (140 passed)
- Add agent evaluation report and final review reports for Hermes support
- Remove dead agent_identities read path and PyYAML import from workspace_uuid.py
- Defer eager PyYAML import in verify_session.py to lazy YAML fallback branch
- Simplify UUID resolution to 2-tier model (tier-1 own row ID -> tier-2 adapter scan)
- Clean up unused Drift D and ghost cache clearing in reconcile.sh and stop_session.sh
- Add 3 regression guards in tests/test_tier1_unit.py (266/266 PASS)
- Update IMPROVEMENTS.md, VERSIONS.md, and SKILL.md files
- Option B / C-3b: Deprecate isolation.root and remove its 4 legacy consumers in lib.sh, workspace_uuid.py, verify_session.py, and stop_session.sh.
- M2~M7 Migration: Implement artifact_path, verify_artifact, purge_artifacts, spawn_spec, resume_spec, auth_ok, discover, ready_tokens, exit_key, and delegate_agent_key across BaseAgentAdapter and all 4 adapters (Claude, Agy, Hermes, Cline).
- Migrate shell duplications in lib.sh, create_session.sh, resume_session.sh, stop_session.sh, and reconcile.sh to python -m lib_py.agents facts.
- Hardening & Corrections: Fix Cline resume_spec flag to '-i --id', apply shlex.quote across all facts variables with MAM_ prefix, add safe fallback in wait_for_tui_ready.
- Add comprehensive contract tests in tests/test_a4_adapter_contract.py and sync IMPROVEMENTS.md / LOG.md.
- Verified: 100% PASS across unit, component, contract, and integration tests.
- Update .agents/MULTI_AGENT_RULES.md & .ko.md to align with TMUX concepts
- Add .agents/INSTALL.md guide for MAM setup and workflows
- Clean up legacy markdown reports under .agents/reports/
- Refactor MAM scripts in .agents/skills/ (rename resolve_herdr_session to resolve_herdr_workspace)
- Improve workspace pane splitting/re-use logic in lib.sh
- Reduce paste safety sleep in send_keys_safe and support linking ~/.claude.json
- Modify reconcile.sh mutation logic to clear delegate_job_id instead of calling tmux kill-session on 'completed' events
- Retain process termination behavior on 'error' events for safety
- Extract load_state_json centralized helper inside lib.sh to unify state querying
- Refactor status, resume, stop, and monitor scripts to fetch state via MAM_STATE_JSON env var to avoid stdin pipeline collisions
- Restructure delegate-job to provision .mam/jobs/<job_id>/brief.md and direct agents to it, minimizing token size and preventing TUI paste freezes
- Harden send_keys_safe submission loop with was_popup state capture and edge case guards, preventing timing spin false-positives
- Passed cross-verification approved PASS from Planner Claude session
- OP-1: Implement reactive _wait_session_gone in lib.sh and stop_session.sh with set -e || true guard
- OP-2: Event-driven MQTT subscribe handshake with sub_pid liveness in delegate-job
- OP-3: Replace CPU time.sleep(0.5) spin with threading.Event wait in reconcile.sh
- OP-4: Define mam_tmux dispatcher targeting resolved _REAL_TMUX_PATH to prevent recursion
- OP-6 & OP-7: Add token variables and bash version source check in lib.sh
- Integrate approved optimization plan and PASS review reports from all agents
- lib.sh: update atomic_dump_yaml to sync with YAML on any active session status change; set reader timeouts to 60.0s
- create_session.sh: add exit trap cleanup_tmux_on_error to rollback spawned tmux sessions on initialization failures
- reconcile.sh, update_yaml_resumed.sh, status.sh, stop_session.sh: align SQLite connection timeout values to 60.0s