Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions docs/ROADMAP.md
Original file line number Diff line number Diff line change
Expand Up @@ -410,18 +410,18 @@ Each task flips only its own row here and in TRACKING.md.
| M9.3 | Journeys and metrics: steps, pass criteria, events, metric query definitions, source refs; `diff` blocks removing or weakening without approval; `run` through a pinned runner; all-green-at-baseline refused | M9.0 | `plugin/mission/journeys.py`, `schemas/journey.json`, `scripts/test/mission-journeys.test.py`, `plugin/mission/_runner.py` | yes | done: `mission-journeys.test.py` (7 checks: self-replacement, pinned replacements, hand-set status, runner script pins, unreported values) |
| M9.4 | Ethics: review per mission and goal, three tiers, gray consent bound to the goal's sha256, hard line never unlocked | M9.0 | `plugin/mission/ethics.py`, `schemas/ethics.json`, `scripts/test/mission-ethics.test.py` | yes | open |
| M9.5 | Judges: rubric setup check and an agreement verdict from recorded runs | M9.0 | `plugin/mission/judge.py`, `schemas/rubric.json`, `scripts/test/mission-judge.test.py` | yes | open |
| M9.6 | Telemetry (GA4): opt-in consent, Admin API setup, Measurement Protocol debug hit, fixed Data API reports (+ realtime), minimum-sample rule, static emit check; network faked in tests | M9.0 | `plugin/mission/telemetry.py`, `schemas/telemetry.json`, `scripts/test/mission-telemetry.test.py`, `scripts/test/fixtures/fake-ga.py` | yes | open |
| M9.6 | Telemetry (GA4): opt-in consent, Admin API setup, Measurement Protocol debug hit, fixed Data API reports (+ realtime), minimum-sample rule, static emit check; network faked in tests | M9.0 | `plugin/mission/telemetry.py`, `schemas/telemetry.json`, `scripts/test/mission-telemetry.test.py`, `scripts/test/fixtures/fake-ga.py` | yes | done: `mission-telemetry.test.py` (13 checks, fake GA); consent counts only `role=human` events, so its provenance rides M9.17 |
| M9.7 | Principles in two variants with tension pairs; `principles show --mode`, hashed and injected into goals | M9.0 | `plugin/mission/principles.{md,py}`, `scripts/test/mission-principles.test.py` | yes | open |
| M9.8 | Loop: `tick` (the state machine above), `due` (zero-token cadence check), `cron` (host routine or crontab line), budget caps from the token ledger | M9.0 | `plugin/mission/{tick,due,cron}.py`, `scripts/test/mission-tick.test.py` | yes | open |
| M9.9 | Roles and wiring: the six personas, hook matchers, model routes, host install, eval suites, role counts in docs; `gate-mission-scope` (role path guards) and `gate-mission-artifact` (a role's artifact passes its check at stop) | M9.0 | `plugin/agents/` (6 new files), `plugin/hooks/hooks.json`, `plugin/hosts/`, `plugin/evals/`, `plugin/bin/gate-mission-*`, role counts in README / OVERVIEW / plugin docs | yes (the only track touching shared lists) | open |
| M9.10 | Assess and evaluate: the State Assessor's report (numbers only, from pinned scripts) and the Evaluator's gap list against the baseline and rivals, with `goal_met` | M9.2, M9.3, M9.5 | `plugin/mission/{assess,evaluate}.py`, `schemas/{state,eval}.json`, `scripts/test/mission-evaluate.test.py` | after its needs | done: `mission-evaluate.test.py` (6 checks); judged metrics come from `judge.verdict(cwd, rubric, journey_id)` (M9.5) and stay pending until a pass or fail verdict. Open: rival values keyed per benchmark in the baseline, so the gap list compares against rivals (review finding) |
| M9.11 | Goals and the Aladdin handoff: top gaps → a goal → intents (`intent` source `mission`), ethics and principles applied, mode → autonomy; `events trace` reaches goal → mission | M9.4, M9.7, M9.10 | `plugin/mission/goal.py`, `schemas/goal.json`, `plugin/bin/intent` (source list), `plugin/bin/events` (trace) | after its needs | blocked |
| M9.12 | The `/aloop:mission` skill: the supervisor's playbook for the tick loop | M9.8, M9.9 | `plugin/skills/mission/` | after its needs | blocked |
| M9.13 | End to end: an offline scripted to-do-app mission (mission → baseline → eval → goal → intent, zero tokens), then a live `make e2e-mission YES=1` | M9.10–M9.12 | `scripts/test/mission-e2e.test.py`, `scripts/smoke/e2e-mission.sh` | after its needs | blocked |
| M9.14 | GA4 live on the owner's account (one Google sign-in) | M9.6 | — | — | needs the owner |
| M9.14 | GA4 live on the owner's account (one Google sign-in) | M9.6 | — | — | needs the owner: `aloop mission telemetry auth` prints the steps, then `init`, `consent`, `setup`, `debug-hit` |
| M9.15 | Native voice mode | the owner's scope (spec cut off) | — | — | open question |
| M9.16 | Docs: OVERVIEW, README, CHANGELOG, site | M9.13 | shared docs | — | blocked |
| M9.17 | Approval provenance: an approval names the captured human prompt (the UserPromptSubmit log), so a supervisor cannot approve its own mission change; the same for a well-formed row appended to `ledger.jsonl` (the chain catches edits, removals and backdating, not a forged append). Reason: found while building M9.0 and in the M9.2/M9.3 review, an approval is only as strong as `--by` | M9.0 | `plugin/bin/_mission.py` (`approve`), its test | yes | open |
| M9.17 | Approval provenance: an approval names the captured human prompt (the UserPromptSubmit log), so a supervisor cannot approve its own mission change; the same for a well-formed row appended to `ledger.jsonl` (the chain catches edits, removals and backdating, not a forged append). Reason: found while building M9.0 and in the M9.2/M9.3 review, an approval is only as strong as `--by`; telemetry consent (M9.6) inherits the same gap | M9.0 | `plugin/bin/_mission.py` (`approve`), its test | yes | open |

**Parallel tracks** (one thread each, from M9.0 on master): (1) Research + Judges, M9.1 + M9.5;
(2) Baseline + Journeys → Assess/Evaluate, M9.2 + M9.3 → M9.10; (3) Ethics + Principles → Goals,
Expand Down
2 changes: 1 addition & 1 deletion docs/TRACKING.md
Original file line number Diff line number Diff line change
Expand Up @@ -65,7 +65,7 @@ Status of every requirement in [ROADMAP.md](ROADMAP.md), in the four states §8
| M9.3 | Journeys and metrics: events per step, query definitions, no removal or weakening without approval | IMPLEMENTED_TESTED | `scripts/test/mission-journeys.test.py` |
| M9.4 | Ethics: three tiers; gray consent bound to the goal; hard line never unlocked | NOT_IMPLEMENTED | §4.12 |
| M9.5 | LLM judges: pinned model, hashed rubric, several runs, agreement threshold | NOT_IMPLEMENTED | §4.12 |
| M9.6 | Telemetry (GA4): opt-in, Admin API setup, debug hit, fixed reports, minimum sample; never a gate | NOT_IMPLEMENTED | §4.12 |
| M9.6 | Telemetry (GA4): opt-in, Admin API setup, debug hit, fixed reports, minimum sample; never a gate | IMPLEMENTED_TESTED | `scripts/test/mission-telemetry.test.py` |
| M9.7 | Standing principles in two variants (autonomous, spoon-fed) | NOT_IMPLEMENTED | §4.12 |
| M9.8 | Mission loop: `tick` from facts, zero-token `due`, cron, budget caps | NOT_IMPLEMENTED | §4.12 |
| M9.9 | Six fixed mission roles, wired; role path guards; artifact check at stop | NOT_IMPLEMENTED | §4.12 |
Expand Down
76 changes: 76 additions & 0 deletions plugin/mission/schemas/telemetry.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,76 @@
{
"title": "telemetry — the opt-in GA4 usage record (ROADMAP §4.12, M9.6): docs/agents/mission/telemetry/<telemetry_id>.json",
"type": "object",
"required": ["telemetry_id", "status", "created_at", "provider", "terms", "settings", "property", "acknowledged", "stream", "secret", "key_events", "debug_hit"],
"additionalProperties": false,
"properties": {
"telemetry_id": {"type": "string", "pattern": "^tlm_"},
"status": {"enum": ["off", "consented", "configured", "revoked"]},
"created_at": {"type": "string", "minLength": 1},
"provider": {"const": "ga4"},
"mission_id": {"type": ["string", "null"]},
"terms": {
"type": "object",
"required": ["uri", "purpose", "collects", "agents_see", "acknowledgement", "credential", "scopes", "others"],
"additionalProperties": false,
"properties": {
"uri": {"type": "string", "pattern": "^https?://[^\\s/]+"},
"purpose": {"type": "string", "minLength": 1},
"collects": {"type": "array", "minItems": 1, "items": {"type": "string", "minLength": 1}},
"agents_see": {"type": "string", "minLength": 1},
"acknowledgement": {"type": "string", "minLength": 1},
"credential": {"type": "string", "minLength": 1},
"scopes": {"type": "array", "minItems": 1, "items": {"type": "string", "pattern": "^https://www\\.googleapis\\.com/auth/analytics"}},
"others": {"type": "string", "minLength": 1}
}
},
"settings": {
"type": "object",
"required": ["display_name", "time_zone", "currency"],
"additionalProperties": false,
"properties": {
"display_name": {"type": "string", "minLength": 1},
"time_zone": {"type": "string", "minLength": 1},
"currency": {"type": "string", "pattern": "^[A-Z]{3}$"}
}
},
"account": {"type": ["string", "null"], "pattern": "^accounts/[0-9]+$"},
"property": {"type": ["string", "null"], "pattern": "^properties/[0-9]+$"},
"acknowledged": {"type": "boolean"},
"stream": {
"type": ["object", "null"],
"required": ["name", "measurement_id", "default_uri"],
"additionalProperties": false,
"properties": {
"name": {"type": "string", "pattern": "^properties/[0-9]+/dataStreams/[0-9]+$"},
"measurement_id": {"type": "string", "pattern": "^G-[A-Z0-9]+$"},
"default_uri": {"type": "string", "minLength": 1}
}
},
"secret": {
"type": ["object", "null"],
"required": ["name", "display_name"],
"additionalProperties": false,
"properties": {
"name": {"type": "string", "pattern": "/measurementProtocolSecrets/"},
"display_name": {"type": "string"}
}
},
"key_events": {"type": "array", "items": {"type": "string", "pattern": "^[A-Za-z][A-Za-z0-9_]{0,39}$"}},
"debug_hit": {
"type": ["object", "null"],
"required": ["at", "ok", "measurement_id", "events_sha256", "events", "messages"],
"additionalProperties": false,
"properties": {
"at": {"type": "string", "minLength": 1},
"ok": {"type": "boolean"},
"measurement_id": {"type": "string", "pattern": "^G-"},
"events_sha256": {"type": "string", "pattern": "^[0-9a-f]{64}$"},
"events": {"type": "integer", "minimum": 1},
"messages": {"type": "array", "items": {"type": "object"}}
}
},
"approval": {"type": "object"},
"sha256": {"type": "string", "pattern": "^[0-9a-f]{64}$"}
}
}
Loading
Loading