feat: prove database-first Leo on private GCP copy
This commit is contained in:
twentyOne2x
parent
6ecc4ac540
commit
9207e1b100
19 changed files with 3511 additions and 178 deletions
|
|
@ -13,20 +13,19 @@ real GCP Leo read/reasoning path without Telegram sends or DB mutation.
|
||||||
|
|
||||||
## Operator Paths
|
## Operator Paths
|
||||||
|
|
||||||
The direct alias is passwordless but firewall-source-dependent:
|
The direct alias is passwordless and was live-verified on 2026-07-14:
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
ssh teleo-gcp-staging
|
ssh teleo-gcp-staging
|
||||||
```
|
```
|
||||||
|
|
||||||
It uses `/Users/user/.ssh/google_compute_engine` for
|
It uses `/Users/user/.ssh/google_compute_engine` for the configured operator,
|
||||||
`billy_livingip_xyz@34.65.143.148`, disables password and keyboard-interactive
|
disables password and keyboard-interactive authentication, and does not store a
|
||||||
authentication, and does not store a Google password. It works only while the
|
Google password. `sudo -n` also works. The route remains
|
||||||
Mac's public egress matches `teleo-prod-allow-ssh-current-ip`. On 2026-07-12 the
|
firewall-source-dependent, so verify `ssh -o BatchMode=yes teleo-gcp-staging true` before a
|
||||||
Mac returned to `99.35.221.133` while the rule still allowed
|
long run instead of assuming retained access is current.
|
||||||
`176.108.138.1/32`, so TCP/22 timed out before authentication.
|
|
||||||
|
|
||||||
The intended durable path is `.github/workflows/gcp-iap-operator.yml`, using
|
The intended secondary path is `.github/workflows/gcp-iap-operator.yml`, using
|
||||||
short-lived GitHub OIDC, IAP, OS Login, and fixed reviewed operations. It is
|
short-lived GitHub OIDC, IAP, OS Login, and fixed reviewed operations. It is
|
||||||
merged but not bootstrapped: workflow run `29208215340` failed at auth with
|
merged but not bootstrapped: workflow run `29208215340` failed at auth with
|
||||||
`invalid_target` because provider `teleo-iap-operator` is absent, disabled, or
|
`invalid_target` because provider `teleo-iap-operator` is absent, disabled, or
|
||||||
|
|
@ -55,39 +54,34 @@ variable, then unset it.
|
||||||
|
|
||||||
Do not describe a passing Hermes memory sync as canonical KB parity.
|
Do not describe a passing Hermes memory sync as canonical KB parity.
|
||||||
|
|
||||||
## Current Verified State - 2026-07-12
|
## Current Verified State - 2026-07-14
|
||||||
|
|
||||||
- GCP `teleo_canonical` matches the captured VPS canonical database across
|
- The newest captured VPS database has `39` tables and `52,167` rows, including
|
||||||
`39/39` tables and `52,164/52,164` rows.
|
claims `1837`, sources `4145`, claim evidence `4670`, claim edges `4916`, and
|
||||||
- Exact high-signal counts are claims `1837`, sources `4145`, claim evidence
|
proposals `29`.
|
||||||
`4670`, claim edges `4916`, and proposals `26`.
|
- A disposable private-TLS GCP clone restored that snapshot with exact
|
||||||
- Rowsets, schemas, columns, constraints, indexes, functions, types, triggers,
|
`39/39`-table and `52,167/52,167`-row parity. Rowsets, schema objects, roles,
|
||||||
views, policies, required roles, extensions, and performance checks have zero
|
extensions, constraints, and performance checks had zero mismatches.
|
||||||
mismatches. `pgcrypto` and `kb_apply` are present.
|
- A real no-send GCP Hermes turn received an ID-free claim challenge, performed
|
||||||
- The GCP gateway remained active/running at PID `148735`, `NRestarts=0`, with
|
`search`, `show`, `evidence`, and `edges`, retrieved the expected claim and
|
||||||
start time `2026-07-09 07:00:04 UTC` throughout restore, swap, and read tests.
|
both source rows, and passed `18/18` runtime checks plus `6/6` reasoning
|
||||||
- The reviewed GCP `teleo-kb` wrapper, Cloud SQL tool, and bridge skill were
|
outcomes. It did not send Telegram or write the DB.
|
||||||
synchronized without a service restart. All six `DC-01` through `DC-06`
|
- `status` and zero-hit search work on a canonical-only clone without the
|
||||||
database-read routes pass.
|
optional `teleo_restore` audit schema. All read commands emit deterministic
|
||||||
- Generated candidate databases and temporary client/operation directories were
|
retrieval receipts.
|
||||||
removed. `teleo_canonical_pre_20260712t1905z` is retained disabled, with zero
|
- The generated clone was deleted. The retained rollback database remains
|
||||||
connections, as the verified pre-swap rollback point.
|
connection-disabled with zero sessions. The GCP gateway remained PID
|
||||||
- A real no-send model replay returned six replies and nominally scored `6/6`,
|
`148735`, `NRestarts=0`, active/running throughout.
|
||||||
but it is rejected as m3taversal-standard proof because `DC-03` and `DC-05`
|
- Persistent GCP `teleo_canonical` remains the older staging copy measured at
|
||||||
printed zero canonical counts. The real database has
|
`52,164` rows and `26` proposals. It has not been promoted or cut over.
|
||||||
`1837/4145/4916/4670/26`.
|
|
||||||
- The harness now enables clone-bound, default-read-only `teleo-kb status`, runs
|
|
||||||
under the Hermes virtualenv, and rejects any printed count that differs from
|
|
||||||
the canonical status receipt. The hardened rerun and clone cleanup wait on
|
|
||||||
the exact operator-access gate below.
|
|
||||||
|
|
||||||
Primary retained proof:
|
Primary retained proof:
|
||||||
|
|
||||||
- `docs/reports/leo-working-state-20260709/gcp-canonical-parity-live-20260712.json`
|
- `docs/reports/leo-working-state-20260709/gcp-db-first-working-leo-20260714.md`
|
||||||
- `docs/reports/leo-working-state-20260709/gcp-cory-model-replay-current.json`
|
- `docs/reports/leo-working-state-20260709/gcp-db-first-restore-current.json`
|
||||||
- `docs/reports/leo-working-state-20260709/gcp-operator-access-blocker-current.json`
|
- `docs/reports/leo-working-state-20260709/gcp-db-first-parity-current.json`
|
||||||
- root task output `outputs/gcp-staging-canonical-parity-20260712T1905Z/`
|
- `docs/reports/leo-working-state-20260709/gcp-db-first-blind-claim-current.json`
|
||||||
- root task output `outputs/gcp-cory-model-replay-20260712T1940Z/`
|
- `docs/reports/leo-working-state-20260709/gcp-db-first-cleanup-current.json`
|
||||||
|
|
||||||
## Required Parity Rows
|
## Required Parity Rows
|
||||||
|
|
||||||
|
|
@ -108,10 +102,16 @@ Use:
|
||||||
|
|
||||||
- `ops/capture_vps_canonical_postgres_snapshot.py` for a single source dump and
|
- `ops/capture_vps_canonical_postgres_snapshot.py` for a single source dump and
|
||||||
manifest;
|
manifest;
|
||||||
|
- `ops/restore_gcp_generated_postgres_snapshot.py restore --execute` for a
|
||||||
|
receipt-bound private-TLS restore into a bounded `teleo_clone_*` database;
|
||||||
|
- `ops/restore_gcp_generated_postgres_snapshot.py cleanup --execute` for exact
|
||||||
|
clone cleanup with live-service and rollback readback;
|
||||||
- `ops/postgres_parity_manifest.sql` for row/catalog/role/performance readback;
|
- `ops/postgres_parity_manifest.sql` for row/catalog/role/performance readback;
|
||||||
- `ops/verify_postgres_parity_manifest.py --scope gcp_staging` for exact parity;
|
- `ops/verify_postgres_parity_manifest.py --scope gcp_staging` for exact parity;
|
||||||
- `scripts/run_gcp_generated_db_direct_claim_suite.py` for the adapter-free,
|
- `scripts/run_gcp_generated_db_direct_claim_suite.py` for the adapter-free,
|
||||||
read-only, no-send six-response replay against a generated `teleo_clone_*`.
|
read-only, no-send six-response replay against a generated `teleo_clone_*`.
|
||||||
|
- `scripts/run_gcp_generated_db_blind_claim_canary.py` for the bounded ID-free
|
||||||
|
claim challenge, source receipt, reasoning, no-write, and cleanup proof.
|
||||||
|
|
||||||
The replay must use the Hermes virtualenv, not system Python:
|
The replay must use the Hermes virtualenv, not system Python:
|
||||||
|
|
||||||
|
|
@ -136,20 +136,14 @@ The strongest accepted claim requires exact DB parity plus real no-send model
|
||||||
replies with truthful counts and cleanup. It still does not prove Telegram
|
replies with truthful counts and cleanup. It still does not prove Telegram
|
||||||
delivery, GCP canonical mutation, ongoing replication, or production cutover.
|
delivery, GCP canonical mutation, ongoing replication, or production cutover.
|
||||||
|
|
||||||
## Exact Current Gate
|
## Current Access And Next Action
|
||||||
|
|
||||||
All autonomous alternatives have been exhausted: privileged local `gcloud`
|
Direct SSH and passwordless sudo are currently working. Local `gcloud` still
|
||||||
requires Google password reauthentication; direct SSH misses the firewall
|
requires account reauthentication for control-plane metadata, so the current
|
||||||
`/32`; the dedicated WIF provider is not bootstrapped; the existing
|
private-IP/TLS proof comes from a live database connection while the public-IP-
|
||||||
`living-ip-github` provider can authenticate only an artifact service account
|
disabled control-plane receipt remains dated 2026-07-12.
|
||||||
that lacks Compute/IAM/Secret Manager/Cloud SQL permissions; no Mullvad or
|
|
||||||
Tailscale route exposes the allowed office ISP address.
|
|
||||||
|
|
||||||
CTA: in Chrome, open the existing tab titled `Google Cloud Platform` for
|
The next production decision is not another restore drill. It is whether to
|
||||||
`billy@livingip.xyz`, enter the current Google password, click `Next`, then tell
|
promote a newly verified snapshot into persistent GCP `teleo_canonical` and
|
||||||
Codex exactly `GCP reauthenticated`. Do not send the password.
|
repoint the production read adapter. Until that decision is explicit, keep GCP
|
||||||
|
classified as staging and do not expose Cloud SQL publicly.
|
||||||
After that, rotate only the SSH `/32`, bootstrap and live-test the IAP operator,
|
|
||||||
run the hardened replay, delete `teleo_clone_cory_20260712t1940z`, remove its
|
|
||||||
run directory, and verify the disabled rollback database still has zero
|
|
||||||
connections.
|
|
||||||
|
|
|
||||||
|
|
@ -24,11 +24,11 @@ Orient the worker before action. Build a current, proof-linked understanding of
|
||||||
- Leo is the operator-facing agent expected to answer in Telegram, remember operator context, reason from canonical KB state, stage concrete KB changes, and support approved changes becoming canonical DB rows with proof.
|
- Leo is the operator-facing agent expected to answer in Telegram, remember operator context, reason from canonical KB state, stage concrete KB changes, and support approved changes becoming canonical DB rows with proof.
|
||||||
- The immediate July 9 issue is not generic bot liveness. It is m3taversal's expectation that approved KB changes move beyond proposal state when appropriate.
|
- The immediate July 9 issue is not generic bot liveness. It is m3taversal's expectation that approved KB changes move beyond proposal state when appropriate.
|
||||||
- The VPS is the currently proven Telegram-visible Leo surface.
|
- The VPS is the currently proven Telegram-visible Leo surface.
|
||||||
- GCP is a separate lane. The live gateway, private Cloud SQL canonical rows,
|
- GCP is a separate lane. Direct passwordless SSH and `sudo -n` work as of
|
||||||
and exact VPS-to-GCP database parity are proven. Direct passwordless SSH was
|
2026-07-14. The newest VPS DB was restored to a disposable private Cloud SQL
|
||||||
proven but is not currently on-demand because its firewall `/32` no longer
|
clone with exact parity, and a real ID-free no-send reasoning turn passed.
|
||||||
matches this Mac's egress, and the dedicated OIDC/IAP path is not bootstrapped.
|
Persistent GCP `teleo_canonical` is still an older staging copy; Telegram
|
||||||
Telegram delivery, GCP canonical mutation, ongoing replication, and cutover
|
delivery, GCP canonical mutation, ongoing replication, promotion, and cutover
|
||||||
remain separate proof rows.
|
remain separate proof rows.
|
||||||
|
|
||||||
## Architecture Boundaries
|
## Architecture Boundaries
|
||||||
|
|
@ -48,16 +48,16 @@ Orient the worker before action. Build a current, proof-linked understanding of
|
||||||
|
|
||||||
From the repo root, read:
|
From the repo root, read:
|
||||||
|
|
||||||
1. `docs/reports/leo-working-state-20260709/working-leo-current-proof-20260712.md`
|
1. `docs/reports/leo-working-state-20260709/current-truth-index.md`
|
||||||
2. `docs/reports/leo-working-state-20260709/current-truth-index.md`
|
2. `docs/reports/leo-working-state-20260709/gcp-db-first-working-leo-20260714.md`
|
||||||
3. `docs/reports/leo-working-state-20260709/operator-surface-map.md`
|
3. `docs/reports/leo-working-state-20260709/gcp-db-first-parity-current.json`
|
||||||
4. `docs/reports/leo-working-state-20260709/working-leo-definition-20260709.md`
|
4. `docs/reports/leo-working-state-20260709/gcp-db-first-blind-claim-current.json`
|
||||||
5. `docs/reports/leo-working-state-20260709/cory-expected-working-leo-outcomes-20260709.md`
|
5. `docs/reports/leo-working-state-20260709/gcp-db-first-cleanup-current.json`
|
||||||
6. `docs/reports/leo-working-state-20260709/approve-claim-clone-canary-current.md`
|
6. `docs/reports/leo-working-state-20260709/operator-surface-map.md`
|
||||||
7. `docs/reports/leo-working-state-20260709/gcp-cloud-sql-t3-live-readonly-current.md`
|
7. `docs/reports/leo-working-state-20260709/working-leo-definition-20260709.md`
|
||||||
8. `docs/reports/leo-working-state-20260709/gcp-canonical-parity-live-20260712.json`
|
8. `.agents/skills/working-leo-m3taversal-outcomes/SKILL.md`
|
||||||
9. `docs/reports/leo-working-state-20260709/gcp-cory-model-replay-current.json`
|
9. `docs/reports/leo-working-state-20260709/approve-claim-clone-canary-current.md`
|
||||||
10. `docs/reports/leo-working-state-20260709/gcp-operator-access-blocker-current.json`
|
10. `docs/reports/leo-working-state-20260709/gcp-cloud-sql-t3-live-readonly-current.md`
|
||||||
|
|
||||||
## Required Status Split
|
## Required Status Split
|
||||||
|
|
||||||
|
|
@ -79,11 +79,11 @@ Do not collapse GCP demo readiness into Telegram completion. Do not collapse pro
|
||||||
- Do not production-apply DB packets unless explicitly authorized.
|
- Do not production-apply DB packets unless explicitly authorized.
|
||||||
- Do not expose secret contents.
|
- Do not expose secret contents.
|
||||||
- Do not treat an old summary as current if a fresh readback is cheap.
|
- Do not treat an old summary as current if a fresh readback is cheap.
|
||||||
- Try `ssh teleo-gcp-staging` for passwordless GCP VM access, but verify the
|
- Use `ssh -o BatchMode=yes teleo-gcp-staging true` to preflight passwordless
|
||||||
current public egress matches the firewall `/32`. If it does not, follow the
|
GCP VM access. If the firewall route drifts, rediscover the authenticated
|
||||||
exact gate in `gcp-operator-access-blocker-current.json`; do not pretend the
|
non-secret route before declaring a blocker. The OIDC/IAP workflow is still
|
||||||
merged OIDC/IAP workflow is bootstrapped. Do not print the Cloud SQL or Google
|
not bootstrapped. Do not print the Cloud SQL or Google password or create
|
||||||
password or create IAM/users inside a read-only lane.
|
IAM/users inside a read-only lane.
|
||||||
- A benchmark score is not sufficient when an answer contradicts the DB receipt.
|
- A benchmark score is not sufficient when an answer contradicts the DB receipt.
|
||||||
Compare every printed count to `teleo-kb status` or the canonical manifest.
|
Compare every printed count to `teleo-kb status` or the canonical manifest.
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -110,37 +110,38 @@ that would change the proof:
|
||||||
|
|
||||||
End no-context answers with exactly one `Next proof-changing follow-up:` line.
|
End no-context answers with exactly one `Next proof-changing follow-up:` line.
|
||||||
|
|
||||||
## Current Verdict - 2026-07-13
|
## Current Verdict - 2026-07-14
|
||||||
|
|
||||||
Use `not fully yet` for the whole m3taversal-standard question until every row below
|
Use `not fully yet` for the whole m3taversal-standard question until every row below
|
||||||
is green at its required tier:
|
is green at its required tier:
|
||||||
|
|
||||||
- VPS runtime and restart survival: proven.
|
- VPS runtime, database-first direct questions, and intentional restart
|
||||||
- VPS no-send `DC-01` through `DC-06`: three post-deploy clean-session trials
|
survival are proven at no-send/runtime tier. The newest captured VPS canonical
|
||||||
strict-score `6/6` (`18/18` replies) with unchanged DB/service state and
|
DB has `39` tables, `52,167` rows, and `29` proposals.
|
||||||
complete temporary-profile cleanup.
|
- One natural ID-free VPS claim challenge now passes the complete bounded chain:
|
||||||
- Telegram-visible open-ended read-only behavior and conversation memory:
|
discover claim, inspect body/evidence/edges, challenge shallow support,
|
||||||
proven for the earlier `OE-01` through `OE-05` suite, but that narrower suite
|
propose candidate claims, and preserve review before any write. This does not
|
||||||
does not establish current broad reliability.
|
erase the older broad 12-prompt failure; broad repeated reliability remains a
|
||||||
- Telegram-visible no-context direct-claim suite: all six prompts/replies are
|
separate benchmark row.
|
||||||
captured with unchanged DB/service state, but the hardened score is `5/6`.
|
- A fresh VPS snapshot was restored into a disposable private GCP Cloud SQL
|
||||||
`DC-05` proposes an incompatible legacy `add_edge` apply target.
|
database with exact `39/39`-table and `52,167/52,167`-row parity, zero catalog
|
||||||
- Canonical apply primitive and approved bundle lifecycle: proven in isolation;
|
mismatches, and unchanged production service state.
|
||||||
broad production packet application is not authorized or executed.
|
- The same GCP ID-free challenge passed `18/18` runtime checks and `6/6`
|
||||||
- Source composition: deterministic fixture proof plus a full-data, no-send,
|
reasoning outcomes through the real Hermes runner. It used four successful
|
||||||
current-VPS clone checkpoint are proven. Arbitrary production document/tweet
|
read-only, receipted calls and retrieved the expected claim plus both source
|
||||||
ingestion is not proven.
|
rows. No Telegram send or database write occurred.
|
||||||
- Broad blind VPS behavior: operationally clean but semantically failed.
|
- The GCP helper now gives deterministic receipts for every read, handles a
|
||||||
Twelve of twelve prompts returned, DB/service state stayed unchanged, and the
|
canonical-only restored DB without the optional audit schema, and returns an
|
||||||
temporary profile was removed; independent strict judges accepted only
|
honest zero-hit result instead of crashing.
|
||||||
`1/12` and `2/12` outright. Failures include invented current schema fields
|
- The disposable GCP database and temporary profiles/processes were removed.
|
||||||
and edge types, handler proof described as Telegram-live, incorrect runtime
|
Persistent GCP `teleo_canonical` remains the older staging copy and has not
|
||||||
memory boundaries, and temporary memory treated as source provenance.
|
been promoted or cut over.
|
||||||
- GCP canonical DB parity and six DB-read routes: proven. A later adapter-free
|
- Earlier Telegram-visible open-ended behavior and conversation memory are
|
||||||
model replay passed `6/6` with exact count consistency and unchanged state.
|
retained proof, but there is no current Telegram-visible run of this full
|
||||||
Durable on-demand operator access and cleanup of the retained replay clone
|
challenge-to-candidate-claims flow.
|
||||||
remain open because the expected operator service accounts are absent and the
|
- Canonical apply primitives are proven in isolation. No proposal from this
|
||||||
privileged Google account requires human password/MFA reauthentication.
|
claim challenge was staged, reviewed, or production-applied, and broad
|
||||||
|
arbitrary document/post reconstruction from original sources remains open.
|
||||||
|
|
||||||
Do not answer `yes` merely because all repo tests pass. The final user-facing
|
Do not answer `yes` merely because all repo tests pass. The final user-facing
|
||||||
proof is a visible Telegram conversation plus truthful canonical row readback.
|
proof is a visible Telegram conversation plus truthful canonical row readback.
|
||||||
|
|
|
||||||
5
.github/workflows/ci.yml
vendored
5
.github/workflows/ci.yml
vendored
|
|
@ -49,11 +49,13 @@ jobs:
|
||||||
ops/check_gcp_service_communications.py \
|
ops/check_gcp_service_communications.py \
|
||||||
ops/plan_gcp_iam_split.py \
|
ops/plan_gcp_iam_split.py \
|
||||||
ops/redact_sqlite_postgres_restore_canary.py \
|
ops/redact_sqlite_postgres_restore_canary.py \
|
||||||
|
ops/restore_gcp_generated_postgres_snapshot.py \
|
||||||
ops/sqlite_to_postgres_dump.py \
|
ops/sqlite_to_postgres_dump.py \
|
||||||
ops/verify_gcp_cloudsql_restore_readback.py \
|
ops/verify_gcp_cloudsql_restore_readback.py \
|
||||||
ops/verify_postgres_parity_manifest.py \
|
ops/verify_postgres_parity_manifest.py \
|
||||||
telegram/approvals.py \
|
telegram/approvals.py \
|
||||||
hermes-agent/leoclean-bin/kb_tool.py \
|
hermes-agent/leoclean-bin/kb_tool.py \
|
||||||
|
hermes-agent/leoclean-bin/cloudsql_memory_tool.py \
|
||||||
scripts/check_crabbox_ci_contract.py \
|
scripts/check_crabbox_ci_contract.py \
|
||||||
scripts/check_llm_refinement_contract.py \
|
scripts/check_llm_refinement_contract.py \
|
||||||
scripts/build_working_leo_m3taversal_outcome_sandbox.py \
|
scripts/build_working_leo_m3taversal_outcome_sandbox.py \
|
||||||
|
|
@ -62,6 +64,7 @@ jobs:
|
||||||
scripts/replay_decision_engine_eval.py \
|
scripts/replay_decision_engine_eval.py \
|
||||||
scripts/prove_phase1b_local.py \
|
scripts/prove_phase1b_local.py \
|
||||||
scripts/run_gcp_generated_db_direct_claim_suite.py \
|
scripts/run_gcp_generated_db_direct_claim_suite.py \
|
||||||
|
scripts/run_gcp_generated_db_blind_claim_canary.py \
|
||||||
scripts/run_leo_direct_claim_handler_suite.py \
|
scripts/run_leo_direct_claim_handler_suite.py \
|
||||||
scripts/run_leo_m3taversal_oos_handler_suite.py \
|
scripts/run_leo_m3taversal_oos_handler_suite.py \
|
||||||
scripts/verify_leo_db_first_oos_canary.py \
|
scripts/verify_leo_db_first_oos_canary.py \
|
||||||
|
|
@ -85,6 +88,7 @@ jobs:
|
||||||
tests/test_gcp_iam_split_plan.py \
|
tests/test_gcp_iam_split_plan.py \
|
||||||
tests/test_gcp_readiness_workflow.py \
|
tests/test_gcp_readiness_workflow.py \
|
||||||
tests/test_gcp_generated_db_direct_claim_suite.py \
|
tests/test_gcp_generated_db_direct_claim_suite.py \
|
||||||
|
tests/test_gcp_generated_db_blind_claim_canary.py \
|
||||||
tests/test_hermes_leoclean_kb_bridge_source.py \
|
tests/test_hermes_leoclean_kb_bridge_source.py \
|
||||||
tests/test_hermes_leoclean_skill_surfaces.py \
|
tests/test_hermes_leoclean_skill_surfaces.py \
|
||||||
tests/test_leo_behavior_manifest.py \
|
tests/test_leo_behavior_manifest.py \
|
||||||
|
|
@ -95,6 +99,7 @@ jobs:
|
||||||
tests/test_working_leo_m3taversal_oos_benchmark.py \
|
tests/test_working_leo_m3taversal_oos_benchmark.py \
|
||||||
tests/test_working_leo_open_ended_benchmark.py \
|
tests/test_working_leo_open_ended_benchmark.py \
|
||||||
tests/test_phase1b_end_to_end.py \
|
tests/test_phase1b_end_to_end.py \
|
||||||
|
tests/test_restore_gcp_generated_postgres_snapshot.py \
|
||||||
tests/test_sqlite_to_postgres_dump.py \
|
tests/test_sqlite_to_postgres_dump.py \
|
||||||
tests/test_sqlite_postgres_restore_canary_capsule.py \
|
tests/test_sqlite_postgres_restore_canary_capsule.py \
|
||||||
tests/test_eval_parse.py \
|
tests/test_eval_parse.py \
|
||||||
|
|
|
||||||
|
|
@ -2,6 +2,33 @@
|
||||||
|
|
||||||
Use this file before making status claims. Prefer fresh VPS/GCP readbacks when cheap; this directory is the retained July 9 evidence snapshot committed to the Teleo infrastructure repo.
|
Use this file before making status claims. Prefer fresh VPS/GCP readbacks when cheap; this directory is the retained July 9 evidence snapshot committed to the Teleo infrastructure repo.
|
||||||
|
|
||||||
|
## GCP Database-First Addendum - 2026-07-14 10:07 UTC
|
||||||
|
|
||||||
|
This addendum supersedes the GCP-pending statements in the earlier July 14
|
||||||
|
section below.
|
||||||
|
|
||||||
|
- The current VPS snapshot (`39` tables, `52,167` rows, `29` proposals) was
|
||||||
|
restored into a disposable private-TLS GCP Cloud SQL database with exact
|
||||||
|
table/row/catalog/role/extension/performance parity.
|
||||||
|
- A real no-send GCP Hermes turn answered an ID-free challenge to a shallow
|
||||||
|
claim. It ran `search`, `show`, `evidence`, and `edges`, retrieved the exact
|
||||||
|
claim plus both expected source rows, passed `18/18` runtime checks and `6/6`
|
||||||
|
reasoning outcomes, made no DB write, and sent no Telegram message.
|
||||||
|
- The disposable clone was deleted. The rollback DB remains disabled with zero
|
||||||
|
connections. The live GCP gateway stayed PID `148735`, `NRestarts=0`.
|
||||||
|
- Persistent GCP `teleo_canonical` is still the older staging copy measured at
|
||||||
|
`52,164` rows and `26` proposals. No promotion or production cutover occurred.
|
||||||
|
- Fast snapshot restore is now proven. Full reconstruction from every original
|
||||||
|
document/post/repository artifact remains incomplete.
|
||||||
|
|
||||||
|
Newest GCP database-first artifacts:
|
||||||
|
|
||||||
|
- `gcp-db-first-working-leo-20260714.md`
|
||||||
|
- `gcp-db-first-restore-current.json`
|
||||||
|
- `gcp-db-first-parity-current.json`
|
||||||
|
- `gcp-db-first-blind-claim-current.json`
|
||||||
|
- `gcp-db-first-cleanup-current.json`
|
||||||
|
|
||||||
## Live Addendum - 2026-07-14
|
## Live Addendum - 2026-07-14
|
||||||
|
|
||||||
The current canonical handoff is
|
The current canonical handoff is
|
||||||
|
|
|
||||||
File diff suppressed because one or more lines are too long
|
|
@ -0,0 +1,40 @@
|
||||||
|
{
|
||||||
|
"artifact": "gcp_generated_postgres_snapshot_cleanup",
|
||||||
|
"database": {
|
||||||
|
"clone_database_remaining": 0,
|
||||||
|
"existed_before": false
|
||||||
|
},
|
||||||
|
"generated_at_utc": "2026-07-14T10:07:17.346308+00:00",
|
||||||
|
"live_service": {
|
||||||
|
"after": {
|
||||||
|
"ActiveState": "active",
|
||||||
|
"ExecMainStartTimestamp": "Thu 2026-07-09 07:00:04 UTC",
|
||||||
|
"MainPID": "148735",
|
||||||
|
"NRestarts": "0",
|
||||||
|
"SubState": "running"
|
||||||
|
},
|
||||||
|
"before": {
|
||||||
|
"ActiveState": "active",
|
||||||
|
"ExecMainStartTimestamp": "Thu 2026-07-09 07:00:04 UTC",
|
||||||
|
"MainPID": "148735",
|
||||||
|
"NRestarts": "0",
|
||||||
|
"SubState": "running"
|
||||||
|
},
|
||||||
|
"unchanged": true
|
||||||
|
},
|
||||||
|
"rollback_database": {
|
||||||
|
"connections": 0,
|
||||||
|
"datallowconn": false,
|
||||||
|
"exists": true
|
||||||
|
},
|
||||||
|
"run_id": "gcp-restore-dbfirst-20260714t090758z",
|
||||||
|
"safety": {
|
||||||
|
"live_database_named": false,
|
||||||
|
"live_profile_modified": false,
|
||||||
|
"live_service_restarted": false,
|
||||||
|
"secret_persisted": false,
|
||||||
|
"telegram_message_sent": false
|
||||||
|
},
|
||||||
|
"status": "pass",
|
||||||
|
"target_database": "teleo_clone_dbfirst_20260714t090758z"
|
||||||
|
}
|
||||||
|
|
@ -0,0 +1,133 @@
|
||||||
|
{
|
||||||
|
"artifact": "canonical_postgres_parity_verification",
|
||||||
|
"details": {
|
||||||
|
"application_role_mismatches": {},
|
||||||
|
"performance": [
|
||||||
|
{
|
||||||
|
"query": "claim_edges_by_claim_id",
|
||||||
|
"source_ms": 0.043,
|
||||||
|
"source_ratio": 0.49000000000000005,
|
||||||
|
"target_ms": 2.45
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"query": "claim_evidence_by_claim_id",
|
||||||
|
"source_ms": 0.062,
|
||||||
|
"source_ratio": 0.1742,
|
||||||
|
"target_ms": 0.871
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"query": "count_claims",
|
||||||
|
"source_ms": 0.23,
|
||||||
|
"source_ratio": 0.09140000000000001,
|
||||||
|
"target_ms": 0.457
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"query": "pending_proposals_latest",
|
||||||
|
"source_ms": 0.015,
|
||||||
|
"source_ratio": 0.0018,
|
||||||
|
"target_ms": 0.009
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"performance_problems": [],
|
||||||
|
"required_extension_mismatches": {},
|
||||||
|
"source_connection": {
|
||||||
|
"database_collation": "en_US.utf8",
|
||||||
|
"database_ctype": "en_US.utf8",
|
||||||
|
"server_address": null,
|
||||||
|
"server_port": null,
|
||||||
|
"ssl": false,
|
||||||
|
"ssl_version": null
|
||||||
|
},
|
||||||
|
"source_database": "teleo",
|
||||||
|
"source_table_count": 39,
|
||||||
|
"source_total_rows": 52167,
|
||||||
|
"structural_hashes": {
|
||||||
|
"columns": {
|
||||||
|
"source": "50b502967aa85b88bd204c7b9035de60bf21a6a6973817e8b8121d0cd9faab81",
|
||||||
|
"target": "50b502967aa85b88bd204c7b9035de60bf21a6a6973817e8b8121d0cd9faab81"
|
||||||
|
},
|
||||||
|
"constraints": {
|
||||||
|
"source": "8b26d26fda56f09325e0603aae48051da08dfc6c35322fa88880acdabb8ad859",
|
||||||
|
"target": "8b26d26fda56f09325e0603aae48051da08dfc6c35322fa88880acdabb8ad859"
|
||||||
|
},
|
||||||
|
"functions": {
|
||||||
|
"source": "4bddee626b3ab62af236493001d2a09f2d56c084beb7e6c69cd082ce4aba155b",
|
||||||
|
"target": "4bddee626b3ab62af236493001d2a09f2d56c084beb7e6c69cd082ce4aba155b"
|
||||||
|
},
|
||||||
|
"indexes": {
|
||||||
|
"source": "5c4f7567e9ad0f25da0ab15f650a1005397ae9c727af1ab41e2675c46a5ebce5",
|
||||||
|
"target": "5c4f7567e9ad0f25da0ab15f650a1005397ae9c727af1ab41e2675c46a5ebce5"
|
||||||
|
},
|
||||||
|
"policies": {
|
||||||
|
"source": "4f53cda18c2baa0c0354bb5f9a3ecbe5ed12ab4d8e11ba873c2f11161202b945",
|
||||||
|
"target": "4f53cda18c2baa0c0354bb5f9a3ecbe5ed12ab4d8e11ba873c2f11161202b945"
|
||||||
|
},
|
||||||
|
"schemas": {
|
||||||
|
"source": "2fdf551b403db2d79813c8fd2869dadfeba261fac2aaa718b355cd7414640979",
|
||||||
|
"target": "2fdf551b403db2d79813c8fd2869dadfeba261fac2aaa718b355cd7414640979"
|
||||||
|
},
|
||||||
|
"sequences": {
|
||||||
|
"source": "4f53cda18c2baa0c0354bb5f9a3ecbe5ed12ab4d8e11ba873c2f11161202b945",
|
||||||
|
"target": "4f53cda18c2baa0c0354bb5f9a3ecbe5ed12ab4d8e11ba873c2f11161202b945"
|
||||||
|
},
|
||||||
|
"triggers": {
|
||||||
|
"source": "4d5f3394480c8410035dac5457e144c7db80fa0820ff49beb93aa819a7282c64",
|
||||||
|
"target": "4d5f3394480c8410035dac5457e144c7db80fa0820ff49beb93aa819a7282c64"
|
||||||
|
},
|
||||||
|
"types": {
|
||||||
|
"source": "365e82ac205319d25d14c8b16026978f0e6023ae0c58767f700d7f2ea659b70b",
|
||||||
|
"target": "365e82ac205319d25d14c8b16026978f0e6023ae0c58767f700d7f2ea659b70b"
|
||||||
|
},
|
||||||
|
"views": {
|
||||||
|
"source": "5c33fa260f25dccffc214f795c66e3dbae89d91d0dbf8a98122ace1dcda46799",
|
||||||
|
"target": "5c33fa260f25dccffc214f795c66e3dbae89d91d0dbf8a98122ace1dcda46799"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"table_mismatches": [],
|
||||||
|
"target_connection": {
|
||||||
|
"database_collation": "en_US.utf8",
|
||||||
|
"database_ctype": "en_US.utf8",
|
||||||
|
"server_address": "10.61.0.3",
|
||||||
|
"server_port": 5432,
|
||||||
|
"ssl": true,
|
||||||
|
"ssl_version": "TLSv1.3"
|
||||||
|
},
|
||||||
|
"target_database": "teleo_clone_dbfirst_20260714t090758z",
|
||||||
|
"target_extra_application_roles": [],
|
||||||
|
"target_table_count": 39,
|
||||||
|
"target_total_rows": 52167
|
||||||
|
},
|
||||||
|
"error": null,
|
||||||
|
"generated_at_utc": "2026-07-14T09:14:02.603285+00:00",
|
||||||
|
"not_proven_by_this_artifact": [
|
||||||
|
"GCP staging Leo composition replay",
|
||||||
|
"ongoing replication after the manifest timestamps",
|
||||||
|
"production cutover"
|
||||||
|
],
|
||||||
|
"private_connectivity": {
|
||||||
|
"path": "/private/tmp/teleo-gcp-dbfirst-proof-20260714/connectivity.json",
|
||||||
|
"proof": {
|
||||||
|
"captured_at_utc": "2026-07-14T09:09:12.241790+00:00",
|
||||||
|
"evidence": {
|
||||||
|
"current_private_tls_manifest": "/private/tmp/teleo-gcp-dbfirst-proof-20260714/target-manifest.jsonl",
|
||||||
|
"current_private_tls_manifest_sha256": "6f834b1486af1e24193a1ded517b4cc9e64e19c68097c028e192dd298986855c",
|
||||||
|
"public_ip_disabled_control_plane_captured_at_utc": "2026-07-12T19:36:50.869980+00:00",
|
||||||
|
"public_ip_disabled_control_plane_receipt": "/Users/user/Documents/Codex/2026-07-09/019f34eb-d297-72d0-b7e2-b222d5515ab9-load/outputs/gcp-staging-canonical-parity-20260712T1905Z/final-connectivity-post-cleanup.json"
|
||||||
|
},
|
||||||
|
"private_connectivity": true,
|
||||||
|
"public_ip_disabled": true,
|
||||||
|
"server_address": "10.61.0.3",
|
||||||
|
"source_compute": "teleo-prod-1",
|
||||||
|
"ssl": true,
|
||||||
|
"ssl_version": "TLSv1.3",
|
||||||
|
"status": "pass",
|
||||||
|
"target_database": "teleo_clone_dbfirst_20260714t090758z"
|
||||||
|
},
|
||||||
|
"required": true
|
||||||
|
},
|
||||||
|
"problems": [],
|
||||||
|
"scope": "gcp_staging",
|
||||||
|
"source_manifest": "/private/tmp/teleo-gcp-dbfirst-source-20260714/source-manifest.jsonl",
|
||||||
|
"status": "pass",
|
||||||
|
"target_manifest": "/private/tmp/teleo-gcp-dbfirst-proof-20260714/target-manifest.jsonl"
|
||||||
|
}
|
||||||
|
|
@ -0,0 +1,182 @@
|
||||||
|
{
|
||||||
|
"artifact": "gcp_generated_postgres_snapshot_restore",
|
||||||
|
"cleanup": {
|
||||||
|
"attempted": false,
|
||||||
|
"clone_database_remaining": 1,
|
||||||
|
"exact_command": "sudo python3 ops/restore_gcp_generated_postgres_snapshot.py cleanup --execute --target-db teleo_clone_dbfirst_20260714t090758z --run-id gcp-restore-dbfirst-20260714t090758z",
|
||||||
|
"required": true
|
||||||
|
},
|
||||||
|
"duration_seconds": 103.83768,
|
||||||
|
"error": null,
|
||||||
|
"generated_at_utc": "2026-07-14T09:09:12.241790+00:00",
|
||||||
|
"live_service": {
|
||||||
|
"after": {
|
||||||
|
"ActiveState": "active",
|
||||||
|
"ExecMainStartTimestamp": "Thu 2026-07-09 07:00:04 UTC",
|
||||||
|
"MainPID": "148735",
|
||||||
|
"NRestarts": "0",
|
||||||
|
"SubState": "running"
|
||||||
|
},
|
||||||
|
"before": {
|
||||||
|
"ActiveState": "active",
|
||||||
|
"ExecMainStartTimestamp": "Thu 2026-07-09 07:00:04 UTC",
|
||||||
|
"MainPID": "148735",
|
||||||
|
"NRestarts": "0",
|
||||||
|
"SubState": "running"
|
||||||
|
},
|
||||||
|
"unchanged": true
|
||||||
|
},
|
||||||
|
"parity": {
|
||||||
|
"details": {
|
||||||
|
"application_role_mismatches": {},
|
||||||
|
"performance": [
|
||||||
|
{
|
||||||
|
"query": "claim_edges_by_claim_id",
|
||||||
|
"source_ms": 0.043,
|
||||||
|
"source_ratio": 0.49000000000000005,
|
||||||
|
"target_ms": 2.45
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"query": "claim_evidence_by_claim_id",
|
||||||
|
"source_ms": 0.062,
|
||||||
|
"source_ratio": 0.1742,
|
||||||
|
"target_ms": 0.871
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"query": "count_claims",
|
||||||
|
"source_ms": 0.23,
|
||||||
|
"source_ratio": 0.09140000000000001,
|
||||||
|
"target_ms": 0.457
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"query": "pending_proposals_latest",
|
||||||
|
"source_ms": 0.015,
|
||||||
|
"source_ratio": 0.0018,
|
||||||
|
"target_ms": 0.009
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"performance_problems": [],
|
||||||
|
"required_extension_mismatches": {},
|
||||||
|
"source_connection": {
|
||||||
|
"database_collation": "en_US.utf8",
|
||||||
|
"database_ctype": "en_US.utf8",
|
||||||
|
"server_address": null,
|
||||||
|
"server_port": null,
|
||||||
|
"ssl": false,
|
||||||
|
"ssl_version": null
|
||||||
|
},
|
||||||
|
"source_database": "teleo",
|
||||||
|
"source_table_count": 39,
|
||||||
|
"source_total_rows": 52167,
|
||||||
|
"structural_hashes": {
|
||||||
|
"columns": {
|
||||||
|
"source": "50b502967aa85b88bd204c7b9035de60bf21a6a6973817e8b8121d0cd9faab81",
|
||||||
|
"target": "50b502967aa85b88bd204c7b9035de60bf21a6a6973817e8b8121d0cd9faab81"
|
||||||
|
},
|
||||||
|
"constraints": {
|
||||||
|
"source": "8b26d26fda56f09325e0603aae48051da08dfc6c35322fa88880acdabb8ad859",
|
||||||
|
"target": "8b26d26fda56f09325e0603aae48051da08dfc6c35322fa88880acdabb8ad859"
|
||||||
|
},
|
||||||
|
"functions": {
|
||||||
|
"source": "4bddee626b3ab62af236493001d2a09f2d56c084beb7e6c69cd082ce4aba155b",
|
||||||
|
"target": "4bddee626b3ab62af236493001d2a09f2d56c084beb7e6c69cd082ce4aba155b"
|
||||||
|
},
|
||||||
|
"indexes": {
|
||||||
|
"source": "5c4f7567e9ad0f25da0ab15f650a1005397ae9c727af1ab41e2675c46a5ebce5",
|
||||||
|
"target": "5c4f7567e9ad0f25da0ab15f650a1005397ae9c727af1ab41e2675c46a5ebce5"
|
||||||
|
},
|
||||||
|
"policies": {
|
||||||
|
"source": "4f53cda18c2baa0c0354bb5f9a3ecbe5ed12ab4d8e11ba873c2f11161202b945",
|
||||||
|
"target": "4f53cda18c2baa0c0354bb5f9a3ecbe5ed12ab4d8e11ba873c2f11161202b945"
|
||||||
|
},
|
||||||
|
"schemas": {
|
||||||
|
"source": "2fdf551b403db2d79813c8fd2869dadfeba261fac2aaa718b355cd7414640979",
|
||||||
|
"target": "2fdf551b403db2d79813c8fd2869dadfeba261fac2aaa718b355cd7414640979"
|
||||||
|
},
|
||||||
|
"sequences": {
|
||||||
|
"source": "4f53cda18c2baa0c0354bb5f9a3ecbe5ed12ab4d8e11ba873c2f11161202b945",
|
||||||
|
"target": "4f53cda18c2baa0c0354bb5f9a3ecbe5ed12ab4d8e11ba873c2f11161202b945"
|
||||||
|
},
|
||||||
|
"triggers": {
|
||||||
|
"source": "4d5f3394480c8410035dac5457e144c7db80fa0820ff49beb93aa819a7282c64",
|
||||||
|
"target": "4d5f3394480c8410035dac5457e144c7db80fa0820ff49beb93aa819a7282c64"
|
||||||
|
},
|
||||||
|
"types": {
|
||||||
|
"source": "365e82ac205319d25d14c8b16026978f0e6023ae0c58767f700d7f2ea659b70b",
|
||||||
|
"target": "365e82ac205319d25d14c8b16026978f0e6023ae0c58767f700d7f2ea659b70b"
|
||||||
|
},
|
||||||
|
"views": {
|
||||||
|
"source": "5c33fa260f25dccffc214f795c66e3dbae89d91d0dbf8a98122ace1dcda46799",
|
||||||
|
"target": "5c33fa260f25dccffc214f795c66e3dbae89d91d0dbf8a98122ace1dcda46799"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"table_mismatches": [],
|
||||||
|
"target_connection": {
|
||||||
|
"database_collation": "en_US.utf8",
|
||||||
|
"database_ctype": "en_US.utf8",
|
||||||
|
"server_address": "10.61.0.3",
|
||||||
|
"server_port": 5432,
|
||||||
|
"ssl": true,
|
||||||
|
"ssl_version": "TLSv1.3"
|
||||||
|
},
|
||||||
|
"target_database": "teleo_clone_dbfirst_20260714t090758z",
|
||||||
|
"target_extra_application_roles": [],
|
||||||
|
"target_table_count": 39,
|
||||||
|
"target_total_rows": 52167
|
||||||
|
},
|
||||||
|
"problems": [],
|
||||||
|
"status": "pass",
|
||||||
|
"verifier": "ops.verify_postgres_parity_manifest.compare_manifests"
|
||||||
|
},
|
||||||
|
"phase": "retained_for_no_send_replay",
|
||||||
|
"rollback_database": {
|
||||||
|
"connections": 0,
|
||||||
|
"datallowconn": false,
|
||||||
|
"exists": true
|
||||||
|
},
|
||||||
|
"run_id": "gcp-restore-dbfirst-20260714t090758z",
|
||||||
|
"safety": {
|
||||||
|
"live_database_named": false,
|
||||||
|
"live_profile_modified": false,
|
||||||
|
"live_service_restarted": false,
|
||||||
|
"secret_persisted": false,
|
||||||
|
"telegram_message_sent": false
|
||||||
|
},
|
||||||
|
"source": {
|
||||||
|
"dump": {
|
||||||
|
"bytes": 13468277,
|
||||||
|
"path": "/home/billy_livingip_xyz/.teleo-gcp-restore-upload-20260714t085320z/source/teleo-canonical.dump",
|
||||||
|
"sha256": "92cc2cafd7575cd38f59745674dd3d18a1f2120d7f87821459b8b38544263f81"
|
||||||
|
},
|
||||||
|
"manifest": {
|
||||||
|
"bytes": 164734,
|
||||||
|
"path": "/home/billy_livingip_xyz/.teleo-gcp-restore-upload-20260714t085320z/source/source-manifest.jsonl",
|
||||||
|
"sha256": "efef2c1d2609879872e70e06758e6d59ce657686eb1e740560e4246fc11ec7c4"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"status": "pass",
|
||||||
|
"target": {
|
||||||
|
"connectivity": {
|
||||||
|
"private_connectivity": true,
|
||||||
|
"server_address": "10.61.0.3",
|
||||||
|
"server_port": 5432,
|
||||||
|
"source_compute": "teleo-prod-1",
|
||||||
|
"ssl": true,
|
||||||
|
"ssl_version": "TLSv1.3",
|
||||||
|
"target_database": "teleo_clone_dbfirst_20260714t090758z",
|
||||||
|
"transaction_read_only": "on"
|
||||||
|
},
|
||||||
|
"manifest_bytes": 164776,
|
||||||
|
"manifest_path": "/var/lib/teleo-gcp-restore-runs/gcp-restore-dbfirst-20260714t090758z/target-manifest.jsonl",
|
||||||
|
"manifest_sha256": "6f834b1486af1e24193a1ded517b4cc9e64e19c68097c028e192dd298986855c",
|
||||||
|
"restore_seconds": 61.761689
|
||||||
|
},
|
||||||
|
"target_database": "teleo_clone_dbfirst_20260714t090758z",
|
||||||
|
"toolchain": {
|
||||||
|
"compatible": true,
|
||||||
|
"pg_restore_bin": "/usr/lib/postgresql/16/bin/pg_restore",
|
||||||
|
"pg_restore_major": 16,
|
||||||
|
"pg_restore_version": "pg_restore (PostgreSQL) 16.14 (Debian 16.14-1.pgdg12+1)",
|
||||||
|
"source_postgres_major": 16
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
@ -0,0 +1,148 @@
|
||||||
|
# GCP Database-First Working Leo Proof - 2026-07-14
|
||||||
|
|
||||||
|
## One-Line Result
|
||||||
|
|
||||||
|
Leo can now take an ID-free challenge to a real claim, find it in a freshly
|
||||||
|
rebuilt private GCP database, inspect its body/evidence/edges, explain why it is
|
||||||
|
shallow, propose better claims, and keep the user in the review loop before any
|
||||||
|
database change. The bounded no-send run passed `18/18` runtime checks and
|
||||||
|
`6/6` reasoning outcomes.
|
||||||
|
|
||||||
|
This is strong GCP no-send handler proof. It is not Telegram delivery, a
|
||||||
|
production knowledge apply, continuous replication, or a GCP production
|
||||||
|
cutover.
|
||||||
|
|
||||||
|
## Problem We Were Solving
|
||||||
|
|
||||||
|
The system mixed several meanings of "Leo learned": conversation history,
|
||||||
|
rendered identity files, deployed instructions, proposal rows, and canonical
|
||||||
|
knowledge. That made it hard to tell whether an answer came from current
|
||||||
|
database facts, stale runtime context, or benchmark-specific training.
|
||||||
|
|
||||||
|
The target is database-first behavior:
|
||||||
|
|
||||||
|
1. A discussion is candidate input, not hidden training.
|
||||||
|
2. Leo retrieves current canonical claims and evidence before asserting KB fact.
|
||||||
|
3. Leo can challenge weak knowledge and draft candidate improvements.
|
||||||
|
4. Candidate changes remain reviewable and replayable before canonical apply.
|
||||||
|
5. Every read and write has a receipt tied to exact database state.
|
||||||
|
6. The database can be copied and verified without retraining Leo.
|
||||||
|
|
||||||
|
## What Makes Leo Leo
|
||||||
|
|
||||||
|
| Layer | Change rate | Role | Canonical knowledge? |
|
||||||
|
| --- | --- | --- | --- |
|
||||||
|
| Base model and Hermes runtime | Slow/versioned | General language and tool-using ability | No |
|
||||||
|
| Deployed skills, tool wrappers, and routing config | Versioned deployment | Tell Leo when and how to query, reason, stage, and apply | No |
|
||||||
|
| Rendered `SOUL.md` and identity/context files | Periodically generated or deployed | Compact runtime context and identity | No; derived/runtime input |
|
||||||
|
| `public.*` in canonical PostgreSQL | Dynamic and durable | Live claims, sources, evidence, edges, personas, beliefs, strategies | Yes |
|
||||||
|
| `kb_stage.*` | Dynamic and review-gated | Candidate proposals, review state, and apply state | No until applied |
|
||||||
|
| Hermes `state.db` and session JSONL | Dynamic runtime continuity | Remembers conversations and operational state | No |
|
||||||
|
| Current message/session context | Ephemeral | Immediate user intent and iteration | No |
|
||||||
|
|
||||||
|
Chat does not update model weights. A conversation can affect the current
|
||||||
|
reply and session continuity, but durable collective learning should become a
|
||||||
|
source-bound proposal and, after review and apply, canonical PostgreSQL rows.
|
||||||
|
|
||||||
|
## What Changed
|
||||||
|
|
||||||
|
### 1. Current VPS knowledge can be rebuilt quickly in GCP
|
||||||
|
|
||||||
|
`ops/restore_gcp_generated_postgres_snapshot.py` now restores a reviewed
|
||||||
|
PostgreSQL 16 custom dump into a bounded `teleo_clone_*` database over private
|
||||||
|
TLS. It verifies the source hash, client version, schema, rows, constraints,
|
||||||
|
roles, extensions, performance, rollback state, and live-service invariants.
|
||||||
|
Failure paths automatically remove partial clones.
|
||||||
|
|
||||||
|
This is a fast exact restore from the current canonical database. It is not yet
|
||||||
|
a full source-of-origin rebuild from every document, URL, post, and repository
|
||||||
|
artifact.
|
||||||
|
|
||||||
|
### 2. GCP retrieval is deterministic and source-bound
|
||||||
|
|
||||||
|
`cloudsql_memory_tool.py` now returns a retrieval receipt containing semantic
|
||||||
|
and artifact-state hashes, database identity, WAL consistency, claim IDs, and
|
||||||
|
source IDs. Receipts cover all read commands, including proposal and
|
||||||
|
decision-matrix reads.
|
||||||
|
|
||||||
|
Clean canonical clones no longer require the optional legacy `teleo_restore`
|
||||||
|
audit schema. `status` works without it, and a zero-hit search returns an honest
|
||||||
|
empty canonical result instead of crashing.
|
||||||
|
|
||||||
|
### 3. The real reasoning path was proved, not inferred
|
||||||
|
|
||||||
|
The exact prompt supplied no row IDs:
|
||||||
|
|
||||||
|
> Our claim that AI sandbagging creates M&A liability feels shallow. Without me
|
||||||
|
> giving you a claim ID, inspect the live claim and what actually supports it.
|
||||||
|
> Tell me what is weak, what new claim or claims you would propose, and how you
|
||||||
|
> would iterate with me before anything becomes live. Do not change the database.
|
||||||
|
|
||||||
|
The GCP Hermes turn performed exactly four successful read-only calls:
|
||||||
|
`search`, `show`, `evidence`, and `edges`. It retrieved claim
|
||||||
|
`2a7ae257-d01d-46f4-b813-63f81bb9c7c7` and both expected source rows, explained
|
||||||
|
why the legal claim was over-bundled and weakly grounded, proposed narrower
|
||||||
|
candidate claims, and asked for review before staging or apply.
|
||||||
|
|
||||||
|
The reply used the exact `m3taversal` handle contract and no forbidden alias.
|
||||||
|
No Telegram message was sent and no DB write was attempted.
|
||||||
|
|
||||||
|
### 4. The experiment cleaned itself up
|
||||||
|
|
||||||
|
The generated clone was deleted. A second cleanup receipt reports zero
|
||||||
|
remaining target databases. The disabled rollback database still has zero
|
||||||
|
connections. The live GCP Leo service remained PID `148735`, active/running,
|
||||||
|
with `NRestarts=0` throughout restore, model replay, and cleanup.
|
||||||
|
|
||||||
|
## VPS Versus GCP
|
||||||
|
|
||||||
|
| Surface | Current result | Meaning |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| VPS production DB | `39` tables, `52,167` rows, `29` proposals at capture | Newest measured canonical source for this run |
|
||||||
|
| GCP persistent `teleo_canonical` | Previously verified at `39` tables, `52,164` rows, `26` proposals | Older staging copy; not promoted or cut over |
|
||||||
|
| Disposable GCP clone | Exact `39/39`, `52,167/52,167`, zero mismatches | Proves current VPS state can be recreated privately in GCP |
|
||||||
|
| GCP Hermes no-send turn | `18/18` checks, `6/6` outcomes | Proves the rebuilt DB works through the real reasoning/tool path |
|
||||||
|
| Disposable clone after test | Absent | Proves lifecycle cleanup; it is not a fourth persistent source of truth |
|
||||||
|
|
||||||
|
This is not three Git branches. The persistent divergence is operational: the
|
||||||
|
VPS canonical DB is newer than the still-staging GCP canonical DB, while the
|
||||||
|
GitHub repository owns the code and deployment instructions. Reconciliation
|
||||||
|
means choosing an authoritative DB snapshot, restoring/verifying GCP from it,
|
||||||
|
then explicitly promoting or cutting over. It does not mean merging database
|
||||||
|
rows as if they were source-code branches.
|
||||||
|
|
||||||
|
## Proof Receipts
|
||||||
|
|
||||||
|
| Receipt | SHA-256 | What it proves |
|
||||||
|
| --- | --- | --- |
|
||||||
|
| `gcp-db-first-restore-current.json` | `06591cb97c7108f7932d042912e2dcad9eb54bbca5cde72ad53642beb79aa89c` | Private restore completed and live service stayed unchanged |
|
||||||
|
| `gcp-db-first-parity-current.json` | `0173ee6707016e8412e6dd4326d61f71b6ef862bbc5b819079d62680676729f2` | Schema, row, role, extension, and performance parity passed |
|
||||||
|
| `gcp-db-first-blind-claim-current.json` | `8a7cc3c1814eb385e858f12ef7579cd4524f37886c03fc6d9c61624b6aff2a52` | Real GCP Hermes reasoning passed with source-bound read receipts |
|
||||||
|
| `gcp-db-first-cleanup-current.json` | `cac7e34f45653fabb696d911b6ccc921d3f291bf8cbe05a429d757e717dcafb4` | Clone absent, rollback disabled, service unchanged |
|
||||||
|
|
||||||
|
## What This Unlocks
|
||||||
|
|
||||||
|
- We can test database changes by rebuilding a disposable copy instead of
|
||||||
|
repeatedly changing Leo's prompt or session memory.
|
||||||
|
- We can compare answers against exact claim/evidence/source rows and detect
|
||||||
|
when a response came from unsupported runtime context.
|
||||||
|
- We can move the same database-first behavior from VPS to GCP without exposing
|
||||||
|
Cloud SQL publicly.
|
||||||
|
- We have a bounded path for future out-of-sample benchmarks: vague question,
|
||||||
|
fresh retrieval, claim challenge, candidate proposal, user iteration, guarded
|
||||||
|
apply, and row-level postflight.
|
||||||
|
|
||||||
|
## Still Not Proven
|
||||||
|
|
||||||
|
1. The same full challenge is visible in a current Telegram conversation.
|
||||||
|
2. A real user-approved candidate from this reasoning loop is staged, reviewed,
|
||||||
|
applied, and read back end to end on production.
|
||||||
|
3. The entire canonical DB can be reconstructed from original source documents
|
||||||
|
and repository artifacts rather than restored from a database snapshot.
|
||||||
|
4. VPS changes continuously replicate to GCP or GCP has been formally promoted.
|
||||||
|
5. Broad reliability across many unseen claim domains and repeated trials.
|
||||||
|
|
||||||
|
The next product-level proof is one natural Telegram challenge that reaches
|
||||||
|
the same database-grounded reasoning, followed by one explicitly approved
|
||||||
|
proposal lifecycle with exact source/claim/evidence/edge receipts. Those are
|
||||||
|
separate authorization and production-mutation steps; neither occurred here.
|
||||||
|
|
@ -10,6 +10,7 @@ shadow schema in Cloud SQL. Proposal commands write staged review records into
|
||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
|
|
||||||
import argparse
|
import argparse
|
||||||
|
import hashlib
|
||||||
import json
|
import json
|
||||||
import os
|
import os
|
||||||
import re
|
import re
|
||||||
|
|
@ -17,14 +18,76 @@ import subprocess
|
||||||
from typing import Any
|
from typing import Any
|
||||||
|
|
||||||
STOPWORDS = {
|
STOPWORDS = {
|
||||||
"a", "about", "after", "all", "an", "and", "are", "as", "at", "be", "before",
|
"a",
|
||||||
"by", "can", "cloud", "context", "do", "does", "for", "from", "gcp", "give",
|
"about",
|
||||||
"how", "i", "in", "into", "is", "it", "leo", "me", "memory", "of", "on", "or",
|
"after",
|
||||||
"our", "production", "should", "source", "that", "the", "their", "this", "to",
|
"all",
|
||||||
"using", "what", "when", "where", "which", "who", "why", "with", "you", "your",
|
"an",
|
||||||
|
"and",
|
||||||
|
"are",
|
||||||
|
"as",
|
||||||
|
"at",
|
||||||
|
"be",
|
||||||
|
"before",
|
||||||
|
"by",
|
||||||
|
"can",
|
||||||
|
"cloud",
|
||||||
|
"context",
|
||||||
|
"do",
|
||||||
|
"does",
|
||||||
|
"for",
|
||||||
|
"from",
|
||||||
|
"gcp",
|
||||||
|
"give",
|
||||||
|
"how",
|
||||||
|
"i",
|
||||||
|
"in",
|
||||||
|
"into",
|
||||||
|
"is",
|
||||||
|
"it",
|
||||||
|
"leo",
|
||||||
|
"me",
|
||||||
|
"memory",
|
||||||
|
"of",
|
||||||
|
"on",
|
||||||
|
"or",
|
||||||
|
"our",
|
||||||
|
"production",
|
||||||
|
"should",
|
||||||
|
"source",
|
||||||
|
"that",
|
||||||
|
"the",
|
||||||
|
"their",
|
||||||
|
"this",
|
||||||
|
"to",
|
||||||
|
"using",
|
||||||
|
"what",
|
||||||
|
"when",
|
||||||
|
"where",
|
||||||
|
"which",
|
||||||
|
"who",
|
||||||
|
"why",
|
||||||
|
"with",
|
||||||
|
"you",
|
||||||
|
"your",
|
||||||
}
|
}
|
||||||
|
|
||||||
DEFAULT_CLAIM_BASE_URL = "https://leo.livingip.xyz"
|
DEFAULT_CLAIM_BASE_URL = "https://leo.livingip.xyz"
|
||||||
|
RETRIEVAL_RECEIPT_SCHEMA = "livingip.teleoKbRetrievalReceipt.v1"
|
||||||
|
RECEIPTED_READ_COMMANDS = frozenset(
|
||||||
|
{
|
||||||
|
"search",
|
||||||
|
"context",
|
||||||
|
"show",
|
||||||
|
"evidence",
|
||||||
|
"edges",
|
||||||
|
"status",
|
||||||
|
"list-proposals",
|
||||||
|
"search-proposals",
|
||||||
|
"show-proposal",
|
||||||
|
"decision-matrix-status",
|
||||||
|
}
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
def parse_args() -> argparse.Namespace:
|
def parse_args() -> argparse.Namespace:
|
||||||
|
|
@ -54,38 +117,52 @@ def parse_args() -> argparse.Namespace:
|
||||||
search = sub.add_parser("search", help="Search restored Cloud SQL memory rows.")
|
search = sub.add_parser("search", help="Search restored Cloud SQL memory rows.")
|
||||||
search.add_argument("query")
|
search.add_argument("query")
|
||||||
search.add_argument("--limit", type=int, default=8)
|
search.add_argument("--limit", type=int, default=8)
|
||||||
search.add_argument("--context-limit", type=int, default=argparse.SUPPRESS, help="Accepted for teleo-kb compatibility; ignored.")
|
search.add_argument(
|
||||||
|
"--context-limit", type=int, default=argparse.SUPPRESS, help="Accepted for teleo-kb compatibility; ignored."
|
||||||
|
)
|
||||||
search.add_argument("--format", choices=["markdown", "json"], default=argparse.SUPPRESS)
|
search.add_argument("--format", choices=["markdown", "json"], default=argparse.SUPPRESS)
|
||||||
search.add_argument("--redacted", action="store_true", default=argparse.SUPPRESS)
|
search.add_argument("--redacted", action="store_true", default=argparse.SUPPRESS)
|
||||||
search.add_argument("--include-excerpts", "--raw-ok", dest="include_excerpts", action="store_true", default=argparse.SUPPRESS)
|
search.add_argument(
|
||||||
|
"--include-excerpts", "--raw-ok", dest="include_excerpts", action="store_true", default=argparse.SUPPRESS
|
||||||
|
)
|
||||||
|
|
||||||
context = sub.add_parser("context", help="Build an agent-ready memory context bundle.")
|
context = sub.add_parser("context", help="Build an agent-ready memory context bundle.")
|
||||||
context.add_argument("query")
|
context.add_argument("query")
|
||||||
context.add_argument("--limit", type=int, default=8)
|
context.add_argument("--limit", type=int, default=8)
|
||||||
context.add_argument("--context-limit", type=int, default=argparse.SUPPRESS, help="Accepted for teleo-kb compatibility; ignored.")
|
context.add_argument(
|
||||||
|
"--context-limit", type=int, default=argparse.SUPPRESS, help="Accepted for teleo-kb compatibility; ignored."
|
||||||
|
)
|
||||||
context.add_argument("--format", choices=["markdown", "json"], default=argparse.SUPPRESS)
|
context.add_argument("--format", choices=["markdown", "json"], default=argparse.SUPPRESS)
|
||||||
context.add_argument("--redacted", action="store_true", default=argparse.SUPPRESS)
|
context.add_argument("--redacted", action="store_true", default=argparse.SUPPRESS)
|
||||||
context.add_argument("--include-excerpts", "--raw-ok", dest="include_excerpts", action="store_true", default=argparse.SUPPRESS)
|
context.add_argument(
|
||||||
|
"--include-excerpts", "--raw-ok", dest="include_excerpts", action="store_true", default=argparse.SUPPRESS
|
||||||
|
)
|
||||||
|
|
||||||
show = sub.add_parser("show", help="Show one canonical claim with evidence and edges.")
|
show = sub.add_parser("show", help="Show one canonical claim with evidence and edges.")
|
||||||
show.add_argument("claim_id")
|
show.add_argument("claim_id")
|
||||||
show.add_argument("--format", choices=["markdown", "json"], default=argparse.SUPPRESS)
|
show.add_argument("--format", choices=["markdown", "json"], default=argparse.SUPPRESS)
|
||||||
show.add_argument("--redacted", action="store_true", default=argparse.SUPPRESS)
|
show.add_argument("--redacted", action="store_true", default=argparse.SUPPRESS)
|
||||||
show.add_argument("--include-excerpts", "--raw-ok", dest="include_excerpts", action="store_true", default=argparse.SUPPRESS)
|
show.add_argument(
|
||||||
|
"--include-excerpts", "--raw-ok", dest="include_excerpts", action="store_true", default=argparse.SUPPRESS
|
||||||
|
)
|
||||||
|
|
||||||
evidence = sub.add_parser("evidence", help="Show canonical evidence rows for one claim.")
|
evidence = sub.add_parser("evidence", help="Show canonical evidence rows for one claim.")
|
||||||
evidence.add_argument("claim_id")
|
evidence.add_argument("claim_id")
|
||||||
evidence.add_argument("--limit", type=int, default=8)
|
evidence.add_argument("--limit", type=int, default=8)
|
||||||
evidence.add_argument("--format", choices=["markdown", "json"], default=argparse.SUPPRESS)
|
evidence.add_argument("--format", choices=["markdown", "json"], default=argparse.SUPPRESS)
|
||||||
evidence.add_argument("--redacted", action="store_true", default=argparse.SUPPRESS)
|
evidence.add_argument("--redacted", action="store_true", default=argparse.SUPPRESS)
|
||||||
evidence.add_argument("--include-excerpts", "--raw-ok", dest="include_excerpts", action="store_true", default=argparse.SUPPRESS)
|
evidence.add_argument(
|
||||||
|
"--include-excerpts", "--raw-ok", dest="include_excerpts", action="store_true", default=argparse.SUPPRESS
|
||||||
|
)
|
||||||
|
|
||||||
edges = sub.add_parser("edges", help="Show canonical graph edges for one claim.")
|
edges = sub.add_parser("edges", help="Show canonical graph edges for one claim.")
|
||||||
edges.add_argument("claim_id")
|
edges.add_argument("claim_id")
|
||||||
edges.add_argument("--limit", type=int, default=12)
|
edges.add_argument("--limit", type=int, default=12)
|
||||||
edges.add_argument("--format", choices=["markdown", "json"], default=argparse.SUPPRESS)
|
edges.add_argument("--format", choices=["markdown", "json"], default=argparse.SUPPRESS)
|
||||||
edges.add_argument("--redacted", action="store_true", default=argparse.SUPPRESS)
|
edges.add_argument("--redacted", action="store_true", default=argparse.SUPPRESS)
|
||||||
edges.add_argument("--include-excerpts", "--raw-ok", dest="include_excerpts", action="store_true", default=argparse.SUPPRESS)
|
edges.add_argument(
|
||||||
|
"--include-excerpts", "--raw-ok", dest="include_excerpts", action="store_true", default=argparse.SUPPRESS
|
||||||
|
)
|
||||||
|
|
||||||
status = sub.add_parser("status", help="Read back Cloud SQL memory backend status.")
|
status = sub.add_parser("status", help="Read back Cloud SQL memory backend status.")
|
||||||
status.add_argument("--format", choices=["markdown", "json"], default=argparse.SUPPRESS)
|
status.add_argument("--format", choices=["markdown", "json"], default=argparse.SUPPRESS)
|
||||||
|
|
@ -96,8 +173,14 @@ def parse_args() -> argparse.Namespace:
|
||||||
help="Stage a review-gated canonical KB change instead of writing core truth to runtime memory.",
|
help="Stage a review-gated canonical KB change instead of writing core truth to runtime memory.",
|
||||||
)
|
)
|
||||||
propose.add_argument("--proposal-type", choices=["revise_claim", "revise_strategy"], required=True)
|
propose.add_argument("--proposal-type", choices=["revise_claim", "revise_strategy"], required=True)
|
||||||
propose.add_argument("--target-kind", choices=["claim", "belief", "strategy", "identity", "role", "telos", "framework", "reasoning_tool", "other"], required=True)
|
propose.add_argument(
|
||||||
propose.add_argument("--target-ref", required=True, help="Claim id, strategy id/name, or unresolved target description.")
|
"--target-kind",
|
||||||
|
choices=["claim", "belief", "strategy", "identity", "role", "telos", "framework", "reasoning_tool", "other"],
|
||||||
|
required=True,
|
||||||
|
)
|
||||||
|
propose.add_argument(
|
||||||
|
"--target-ref", required=True, help="Claim id, strategy id/name, or unresolved target description."
|
||||||
|
)
|
||||||
propose.add_argument("--current", default="", help="Current/old claim or state, if known.")
|
propose.add_argument("--current", default="", help="Current/old claim or state, if known.")
|
||||||
propose.add_argument("--proposed", required=True, help="Proposed replacement or correction.")
|
propose.add_argument("--proposed", required=True, help="Proposed replacement or correction.")
|
||||||
propose.add_argument("--evidence", action="append", default=[], help="Evidence/source pointer. Can be repeated.")
|
propose.add_argument("--evidence", action="append", default=[], help="Evidence/source pointer. Can be repeated.")
|
||||||
|
|
@ -124,7 +207,9 @@ def parse_args() -> argparse.Namespace:
|
||||||
list_proposals.add_argument("--limit", type=int, default=10)
|
list_proposals.add_argument("--limit", type=int, default=10)
|
||||||
list_proposals.add_argument("--format", choices=["markdown", "json"], default=argparse.SUPPRESS)
|
list_proposals.add_argument("--format", choices=["markdown", "json"], default=argparse.SUPPRESS)
|
||||||
|
|
||||||
search_proposals = sub.add_parser("search-proposals", help="Search staged KB proposals across statuses from Cloud SQL.")
|
search_proposals = sub.add_parser(
|
||||||
|
"search-proposals", help="Search staged KB proposals across statuses from Cloud SQL."
|
||||||
|
)
|
||||||
search_proposals.add_argument("query")
|
search_proposals.add_argument("query")
|
||||||
search_proposals.add_argument("--status", default="all")
|
search_proposals.add_argument("--status", default="all")
|
||||||
search_proposals.add_argument("--limit", type=int, default=10)
|
search_proposals.add_argument("--limit", type=int, default=10)
|
||||||
|
|
@ -201,7 +286,7 @@ def password(args: argparse.Namespace) -> str:
|
||||||
check=False,
|
check=False,
|
||||||
)
|
)
|
||||||
if result.returncode != 0:
|
if result.returncode != 0:
|
||||||
raise SystemExit(f"Secret access failed: {result.stderr.strip()}")
|
raise SystemExit(f"Secret access failed: {result.stderr.strip()}")
|
||||||
return result.stdout.strip()
|
return result.stdout.strip()
|
||||||
|
|
||||||
|
|
||||||
|
|
@ -233,6 +318,157 @@ def psql_json_lines(args: argparse.Namespace, sql: str, db: str | None = None) -
|
||||||
return rows
|
return rows
|
||||||
|
|
||||||
|
|
||||||
|
def canonical_json_sha256(value: Any) -> str:
|
||||||
|
encoded = json.dumps(value, sort_keys=True, separators=(",", ":"), ensure_ascii=True).encode()
|
||||||
|
return hashlib.sha256(encoded).hexdigest()
|
||||||
|
|
||||||
|
|
||||||
|
def database_read_marker(args: argparse.Namespace) -> dict[str, Any]:
|
||||||
|
sql = """
|
||||||
|
select jsonb_build_object(
|
||||||
|
'database', current_database(),
|
||||||
|
'database_user', current_user,
|
||||||
|
'system_identifier', (select system_identifier::text from pg_control_system()),
|
||||||
|
'wal_lsn', pg_current_wal_lsn()::text
|
||||||
|
)::text;
|
||||||
|
"""
|
||||||
|
rows = psql_json_lines(args, sql, db=args.canonical_db)
|
||||||
|
if len(rows) != 1:
|
||||||
|
raise SystemExit("Canonical database read marker returned an invalid row count.")
|
||||||
|
return rows[0]
|
||||||
|
|
||||||
|
|
||||||
|
def _read_marker_stable(before: dict[str, Any], after: dict[str, Any]) -> bool:
|
||||||
|
return all(
|
||||||
|
before.get(key) == after.get(key) for key in ("database", "database_user", "system_identifier", "wal_lsn")
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def _stable_receipt_value(value: Any) -> Any:
|
||||||
|
if isinstance(value, dict):
|
||||||
|
return {
|
||||||
|
key: _stable_receipt_value(item)
|
||||||
|
for key, item in sorted(value.items())
|
||||||
|
if key not in {"claim_url", "connected_url", "retrieval_receipt"}
|
||||||
|
}
|
||||||
|
if isinstance(value, list):
|
||||||
|
return [_stable_receipt_value(item) for item in value]
|
||||||
|
return value
|
||||||
|
|
||||||
|
|
||||||
|
def _retrieved_claim_ids(data: dict[str, Any]) -> list[str]:
|
||||||
|
values = []
|
||||||
|
if data.get("claim_id"):
|
||||||
|
values.append(str(data["claim_id"]))
|
||||||
|
claim = data.get("claim") or {}
|
||||||
|
if claim.get("id"):
|
||||||
|
values.append(str(claim["id"]))
|
||||||
|
values.extend(str(row["id"]) for row in data.get("claims", []) if row.get("id"))
|
||||||
|
return sorted(set(values))
|
||||||
|
|
||||||
|
|
||||||
|
def _retrieved_evidence(data: dict[str, Any]) -> list[dict[str, Any]]:
|
||||||
|
rows = [row for row in data.get("evidence", []) if isinstance(row, dict)]
|
||||||
|
for claim in data.get("claims", []):
|
||||||
|
rows.extend(row for row in claim.get("evidence", []) if isinstance(row, dict))
|
||||||
|
return rows
|
||||||
|
|
||||||
|
|
||||||
|
def build_retrieval_receipt(
|
||||||
|
data: dict[str, Any],
|
||||||
|
*,
|
||||||
|
query_descriptor: dict[str, Any],
|
||||||
|
before: dict[str, Any],
|
||||||
|
after: dict[str, Any],
|
||||||
|
attempts: int,
|
||||||
|
consistency_status: str,
|
||||||
|
) -> dict[str, Any]:
|
||||||
|
evidence = _retrieved_evidence(data)
|
||||||
|
artifact_states = sorted(
|
||||||
|
(
|
||||||
|
{
|
||||||
|
"source_id": row.get("source_id"),
|
||||||
|
"source_hash": row.get("source_hash"),
|
||||||
|
"storage_path": row.get("storage_path"),
|
||||||
|
}
|
||||||
|
for row in evidence
|
||||||
|
),
|
||||||
|
key=lambda row: (str(row.get("source_id") or ""), str(row.get("storage_path") or "")),
|
||||||
|
)
|
||||||
|
return {
|
||||||
|
"schema": RETRIEVAL_RECEIPT_SCHEMA,
|
||||||
|
"query_sha256": canonical_json_sha256(query_descriptor),
|
||||||
|
"semantic_context_sha256": canonical_json_sha256(_stable_receipt_value(data)),
|
||||||
|
"artifact_state_sha256": canonical_json_sha256(artifact_states),
|
||||||
|
"claim_ids": _retrieved_claim_ids(data),
|
||||||
|
"source_ids": sorted({str(row["source_id"]) for row in evidence if row.get("source_id")}),
|
||||||
|
"counts": {
|
||||||
|
"claims": len(_retrieved_claim_ids(data)),
|
||||||
|
"evidence_rows": len(evidence),
|
||||||
|
"edge_rows": len(data.get("edges", []))
|
||||||
|
+ sum(len(claim.get("edges", [])) for claim in data.get("claims", [])),
|
||||||
|
},
|
||||||
|
"read_consistency": {
|
||||||
|
"status": consistency_status,
|
||||||
|
"attempts": attempts,
|
||||||
|
"database": before.get("database"),
|
||||||
|
"database_user": before.get("database_user"),
|
||||||
|
"system_identifier": before.get("system_identifier"),
|
||||||
|
"wal_lsn_before": before.get("wal_lsn"),
|
||||||
|
"wal_lsn_after": after.get("wal_lsn"),
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
def receipt_query_descriptor(args: argparse.Namespace) -> dict[str, Any]:
|
||||||
|
return {
|
||||||
|
"command": args.command,
|
||||||
|
"query": getattr(args, "query", None),
|
||||||
|
"claim_id": getattr(args, "claim_id", None),
|
||||||
|
"limit": getattr(args, "limit", None),
|
||||||
|
"context_limit": getattr(args, "context_limit", None),
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
def read_with_retrieval_receipt(args: argparse.Namespace, loader: Any) -> dict[str, Any]:
|
||||||
|
try:
|
||||||
|
max_attempts = max(1, min(int(os.environ.get("TELEO_KB_READ_ATTEMPTS", "3")), 5))
|
||||||
|
except ValueError as exc:
|
||||||
|
raise SystemExit("TELEO_KB_READ_ATTEMPTS must be an integer") from exc
|
||||||
|
previous_semantic_sha256: str | None = None
|
||||||
|
last_markers: tuple[dict[str, Any], dict[str, Any]] | None = None
|
||||||
|
descriptor = receipt_query_descriptor(args)
|
||||||
|
for attempt in range(1, max_attempts + 1):
|
||||||
|
before = database_read_marker(args)
|
||||||
|
data = loader()
|
||||||
|
after = database_read_marker(args)
|
||||||
|
last_markers = (before, after)
|
||||||
|
consistency_status = "stable_wal_marker" if _read_marker_stable(before, after) else "wal_changed_during_read"
|
||||||
|
receipt = build_retrieval_receipt(
|
||||||
|
data,
|
||||||
|
query_descriptor=descriptor,
|
||||||
|
before=before,
|
||||||
|
after=after,
|
||||||
|
attempts=attempt,
|
||||||
|
consistency_status=consistency_status,
|
||||||
|
)
|
||||||
|
if consistency_status == "stable_wal_marker":
|
||||||
|
data["retrieval_receipt"] = receipt
|
||||||
|
return data
|
||||||
|
semantic_sha256 = receipt["semantic_context_sha256"]
|
||||||
|
if previous_semantic_sha256 == semantic_sha256:
|
||||||
|
receipt["read_consistency"]["status"] = "stable_content_across_wal_change_retry"
|
||||||
|
data["retrieval_receipt"] = receipt
|
||||||
|
return data
|
||||||
|
previous_semantic_sha256 = semantic_sha256
|
||||||
|
assert last_markers is not None
|
||||||
|
before, after = last_markers
|
||||||
|
raise SystemExit(
|
||||||
|
"Canonical DB changed during retrieval and no identical retry was observed "
|
||||||
|
f"(wal_lsn {before.get('wal_lsn')} -> {after.get('wal_lsn')})."
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
def include_excerpts(args: argparse.Namespace) -> bool:
|
def include_excerpts(args: argparse.Namespace) -> bool:
|
||||||
return bool(getattr(args, "include_excerpts", False)) and not bool(getattr(args, "redacted", False))
|
return bool(getattr(args, "include_excerpts", False)) and not bool(getattr(args, "redacted", False))
|
||||||
|
|
||||||
|
|
@ -394,11 +630,13 @@ select jsonb_build_object(
|
||||||
evidence_sql = f"""
|
evidence_sql = f"""
|
||||||
with ranked as (
|
with ranked as (
|
||||||
select ce.claim_id,
|
select ce.claim_id,
|
||||||
|
s.id as source_id,
|
||||||
ce.role::text as role,
|
ce.role::text as role,
|
||||||
ce.weight,
|
ce.weight,
|
||||||
s.source_type,
|
s.source_type,
|
||||||
s.url,
|
s.url,
|
||||||
s.storage_path,
|
s.storage_path,
|
||||||
|
s.hash as source_hash,
|
||||||
left(coalesce(s.excerpt, ''), 800) as excerpt,
|
left(coalesce(s.excerpt, ''), 800) as excerpt,
|
||||||
row_number() over (
|
row_number() over (
|
||||||
partition by ce.claim_id
|
partition by ce.claim_id
|
||||||
|
|
@ -413,11 +651,13 @@ with ranked as (
|
||||||
)
|
)
|
||||||
select jsonb_build_object(
|
select jsonb_build_object(
|
||||||
'claim_id', claim_id::text,
|
'claim_id', claim_id::text,
|
||||||
|
'source_id', source_id::text,
|
||||||
'role', role,
|
'role', role,
|
||||||
'weight', weight,
|
'weight', weight,
|
||||||
'source_type', source_type,
|
'source_type', source_type,
|
||||||
'url', url,
|
'url', url,
|
||||||
'storage_path', storage_path,
|
'storage_path', storage_path,
|
||||||
|
'source_hash', source_hash,
|
||||||
'excerpt', excerpt
|
'excerpt', excerpt
|
||||||
)::text
|
)::text
|
||||||
from ranked
|
from ranked
|
||||||
|
|
@ -501,7 +741,8 @@ select jsonb_build_object(
|
||||||
"excerpt": claim.get("text"),
|
"excerpt": claim.get("text"),
|
||||||
}
|
}
|
||||||
for claim in claims
|
for claim in claims
|
||||||
] + [
|
]
|
||||||
|
+ [
|
||||||
{
|
{
|
||||||
"source_table": f"public.{row['source']}",
|
"source_table": f"public.{row['source']}",
|
||||||
"row_id": f"{row['owner']}:{row['title']}",
|
"row_id": f"{row['owner']}:{row['title']}",
|
||||||
|
|
@ -524,9 +765,13 @@ select jsonb_build_object(
|
||||||
row.pop("body", None)
|
row.pop("body", None)
|
||||||
for hit in result["hits"]:
|
for hit in result["hits"]:
|
||||||
hit.pop("excerpt", None)
|
hit.pop("excerpt", None)
|
||||||
result["privacy"] = "redacted proof mode: raw body used only inside SQL matching; output has counts, hashes, canonical table, row id, timestamps, and evidence links"
|
result["privacy"] = (
|
||||||
|
"redacted proof mode: raw body used only inside SQL matching; output has counts, hashes, canonical table, row id, timestamps, and evidence links"
|
||||||
|
)
|
||||||
else:
|
else:
|
||||||
result["privacy"] = "private agent context mode: short excerpts included; do not retain or paste raw output into public artifacts"
|
result["privacy"] = (
|
||||||
|
"private agent context mode: short excerpts included; do not retain or paste raw output into public artifacts"
|
||||||
|
)
|
||||||
return result
|
return result
|
||||||
|
|
||||||
|
|
||||||
|
|
@ -609,9 +854,13 @@ select json_build_object(
|
||||||
if not include_excerpts(args):
|
if not include_excerpts(args):
|
||||||
for hit in result["hits"]:
|
for hit in result["hits"]:
|
||||||
hit.pop("excerpt", None)
|
hit.pop("excerpt", None)
|
||||||
result["privacy"] = "redacted proof mode: raw body used only inside SQL matching; output has counts, hashes, source table, row id, and timestamps"
|
result["privacy"] = (
|
||||||
|
"redacted proof mode: raw body used only inside SQL matching; output has counts, hashes, source table, row id, and timestamps"
|
||||||
|
)
|
||||||
else:
|
else:
|
||||||
result["privacy"] = "private agent context mode: short excerpts included; do not retain or paste raw output into public artifacts"
|
result["privacy"] = (
|
||||||
|
"private agent context mode: short excerpts included; do not retain or paste raw output into public artifacts"
|
||||||
|
)
|
||||||
return result
|
return result
|
||||||
|
|
||||||
|
|
||||||
|
|
@ -619,6 +868,11 @@ def query_rows(args: argparse.Namespace, query: str, limit: int) -> dict[str, An
|
||||||
canonical = query_canonical_rows(args, query, limit)
|
canonical = query_canonical_rows(args, query, limit)
|
||||||
if canonical.get("hit_count_total", 0) or canonical.get("hits"):
|
if canonical.get("hit_count_total", 0) or canonical.get("hits"):
|
||||||
return canonical
|
return canonical
|
||||||
|
if not audit_restore_available(args):
|
||||||
|
canonical["canonical_fallback_reason"] = (
|
||||||
|
"no matching canonical public/persona/strategy/belief rows; teleo_restore audit fallback unavailable"
|
||||||
|
)
|
||||||
|
return canonical
|
||||||
audit = query_audit_rows(args, query, limit)
|
audit = query_audit_rows(args, query, limit)
|
||||||
audit["canonical_fallback_reason"] = "no matching canonical public/persona/strategy/belief rows"
|
audit["canonical_fallback_reason"] = "no matching canonical public/persona/strategy/belief rows"
|
||||||
return audit
|
return audit
|
||||||
|
|
@ -652,11 +906,13 @@ def canonical_evidence(args: argparse.Namespace, claim_id: str, limit: int) -> l
|
||||||
sql = f"""
|
sql = f"""
|
||||||
with ranked as (
|
with ranked as (
|
||||||
select ce.claim_id,
|
select ce.claim_id,
|
||||||
|
s.id as source_id,
|
||||||
ce.role::text as role,
|
ce.role::text as role,
|
||||||
ce.weight,
|
ce.weight,
|
||||||
s.source_type,
|
s.source_type,
|
||||||
s.url,
|
s.url,
|
||||||
s.storage_path,
|
s.storage_path,
|
||||||
|
s.hash as source_hash,
|
||||||
left(coalesce(s.excerpt, ''), 800) as excerpt,
|
left(coalesce(s.excerpt, ''), 800) as excerpt,
|
||||||
row_number() over (
|
row_number() over (
|
||||||
partition by ce.claim_id
|
partition by ce.claim_id
|
||||||
|
|
@ -671,11 +927,13 @@ with ranked as (
|
||||||
)
|
)
|
||||||
select jsonb_build_object(
|
select jsonb_build_object(
|
||||||
'claim_id', claim_id::text,
|
'claim_id', claim_id::text,
|
||||||
|
'source_id', source_id::text,
|
||||||
'role', role,
|
'role', role,
|
||||||
'weight', weight,
|
'weight', weight,
|
||||||
'source_type', source_type,
|
'source_type', source_type,
|
||||||
'url', url,
|
'url', url,
|
||||||
'storage_path', storage_path,
|
'storage_path', storage_path,
|
||||||
|
'source_hash', source_hash,
|
||||||
'excerpt', excerpt
|
'excerpt', excerpt
|
||||||
)::text
|
)::text
|
||||||
from ranked
|
from ranked
|
||||||
|
|
@ -1106,6 +1364,23 @@ select jsonb_build_object(
|
||||||
return result
|
return result
|
||||||
|
|
||||||
|
|
||||||
|
def audit_restore_available(args: argparse.Namespace) -> bool:
|
||||||
|
sql = """
|
||||||
|
select bool_and(to_regclass(table_name) is not null)
|
||||||
|
from (values
|
||||||
|
('teleo_restore.response_audit'),
|
||||||
|
('teleo_restore.sources'),
|
||||||
|
('teleo_restore.agent_research_runs'),
|
||||||
|
('teleo_restore.agent_tool_invocations'),
|
||||||
|
('teleo_restore.audit_log'),
|
||||||
|
('teleo_restore.metrics_snapshots'),
|
||||||
|
('teleo_restore.prs'),
|
||||||
|
('teleo_restore.review_records')
|
||||||
|
) required(table_name);
|
||||||
|
"""
|
||||||
|
return run_psql(args, sql).strip().lower() in {"t", "true"}
|
||||||
|
|
||||||
|
|
||||||
def status(args: argparse.Namespace) -> dict[str, Any]:
|
def status(args: argparse.Namespace) -> dict[str, Any]:
|
||||||
canonical_sql = """
|
canonical_sql = """
|
||||||
select json_build_object(
|
select json_build_object(
|
||||||
|
|
@ -1158,10 +1433,24 @@ select json_build_object(
|
||||||
)
|
)
|
||||||
)::text;
|
)::text;
|
||||||
"""
|
"""
|
||||||
result = json.loads(run_psql(args, audit_sql).strip())
|
canonical = json.loads(run_psql(args, canonical_sql, db=args.canonical_db).strip())
|
||||||
result["canonical"] = json.loads(run_psql(args, canonical_sql, db=args.canonical_db).strip())
|
audit_available = audit_restore_available(args)
|
||||||
|
if audit_available:
|
||||||
|
result = json.loads(run_psql(args, audit_sql).strip())
|
||||||
|
else:
|
||||||
|
result = {
|
||||||
|
"db_identity": canonical["db_identity"],
|
||||||
|
"extensions": canonical.get("extensions") or [],
|
||||||
|
"teleo_restore_tables": 0,
|
||||||
|
"total_rows": 0,
|
||||||
|
"high_signal_rows": {},
|
||||||
|
}
|
||||||
|
result["canonical"] = canonical
|
||||||
|
result["audit_fallback_available"] = audit_available
|
||||||
result["artifact"] = "teleo_cloudsql_memory_status"
|
result["artifact"] = "teleo_cloudsql_memory_status"
|
||||||
result["backend"] = f"cloudsql:teleo-pgvector-standby/{args.canonical_db}/public+kb_stage primary; {args.db}/teleo_restore fallback"
|
result["backend"] = f"cloudsql:teleo-pgvector-standby/{args.canonical_db}/public+kb_stage primary; " + (
|
||||||
|
f"{args.db}/teleo_restore fallback" if audit_available else "teleo_restore fallback unavailable"
|
||||||
|
)
|
||||||
return result
|
return result
|
||||||
|
|
||||||
|
|
||||||
|
|
@ -1170,6 +1459,15 @@ def emit_json(value: dict[str, Any]) -> None:
|
||||||
|
|
||||||
|
|
||||||
def emit_markdown(value: dict[str, Any]) -> None:
|
def emit_markdown(value: dict[str, Any]) -> None:
|
||||||
|
receipt = value.get("retrieval_receipt") or {}
|
||||||
|
if receipt:
|
||||||
|
consistency = receipt.get("read_consistency") or {}
|
||||||
|
print("# Teleo KB Retrieval Receipt\n")
|
||||||
|
print(f"- schema: `{receipt.get('schema')}`")
|
||||||
|
print(f"- semantic context SHA-256: `{receipt.get('semantic_context_sha256')}`")
|
||||||
|
print(f"- artifact state SHA-256: `{receipt.get('artifact_state_sha256')}`")
|
||||||
|
print(f"- DB read consistency: `{consistency.get('status')}`; attempts: `{consistency.get('attempts')}`\n")
|
||||||
|
|
||||||
if value["artifact"] == "teleo_cloudsql_memory_status":
|
if value["artifact"] == "teleo_cloudsql_memory_status":
|
||||||
print("# Teleo Cloud SQL Memory Status\n")
|
print("# Teleo Cloud SQL Memory Status\n")
|
||||||
print(f"- Backend: `{value['backend']}`")
|
print(f"- Backend: `{value['backend']}`")
|
||||||
|
|
@ -1180,10 +1478,7 @@ def emit_markdown(value: dict[str, Any]) -> None:
|
||||||
print(f"- Canonical tables: `{json.dumps(canonical.get('schema_tables'), sort_keys=True)}`")
|
print(f"- Canonical tables: `{json.dumps(canonical.get('schema_tables'), sort_keys=True)}`")
|
||||||
print(f"- Canonical high-signal rows: `{json.dumps(canonical.get('high_signal_rows'), sort_keys=True)}`")
|
print(f"- Canonical high-signal rows: `{json.dumps(canonical.get('high_signal_rows'), sort_keys=True)}`")
|
||||||
counts = canonical.get("high_signal_rows") or {}
|
counts = canonical.get("high_signal_rows") or {}
|
||||||
if all(
|
if all(key in counts for key in ("claims", "sources", "claim_edges", "claim_evidence", "kb_proposals")):
|
||||||
key in counts
|
|
||||||
for key in ("claims", "sources", "claim_edges", "claim_evidence", "kb_proposals")
|
|
||||||
):
|
|
||||||
print(
|
print(
|
||||||
f"\nDB readback: claims: `{counts['claims']}`; sources: `{counts['sources']}`; "
|
f"\nDB readback: claims: `{counts['claims']}`; sources: `{counts['sources']}`; "
|
||||||
f"claim_edges: `{counts['claim_edges']}`; claim_evidence: `{counts['claim_evidence']}`; "
|
f"claim_edges: `{counts['claim_edges']}`; claim_evidence: `{counts['claim_evidence']}`; "
|
||||||
|
|
@ -1218,7 +1513,9 @@ def emit_markdown(value: dict[str, Any]) -> None:
|
||||||
print(f"### {i}. {markdown_claim_link(claim['id'], claim_label[:140])}\n")
|
print(f"### {i}. {markdown_claim_link(claim['id'], claim_label[:140])}\n")
|
||||||
print(f"- claim id: {markdown_claim_link(claim['id'], claim['id'])}")
|
print(f"- claim id: {markdown_claim_link(claim['id'], claim['id'])}")
|
||||||
print(f"- open full claim/body/edges: {markdown_claim_link(claim['id'], 'claim page')}")
|
print(f"- open full claim/body/edges: {markdown_claim_link(claim['id'], 'claim page')}")
|
||||||
print(f"- type: `{claim.get('type')}`; confidence: `{claim.get('confidence')}`; score: `{claim.get('score')}`")
|
print(
|
||||||
|
f"- type: `{claim.get('type')}`; confidence: `{claim.get('confidence')}`; score: `{claim.get('score')}`"
|
||||||
|
)
|
||||||
print(f"- tags: `{', '.join(claim.get('tags') or [])}`")
|
print(f"- tags: `{', '.join(claim.get('tags') or [])}`")
|
||||||
print(f"- evidence rows: `{claim.get('evidence_count', len(claim.get('evidence', [])))}`")
|
print(f"- evidence rows: `{claim.get('evidence_count', len(claim.get('evidence', [])))}`")
|
||||||
print(f"- edge rows: `{claim.get('edge_count', len(claim.get('edges', [])))}`")
|
print(f"- edge rows: `{claim.get('edge_count', len(claim.get('edges', [])))}`")
|
||||||
|
|
@ -1246,7 +1543,9 @@ def emit_markdown(value: dict[str, Any]) -> None:
|
||||||
print(f"- Backend: `{value['backend']}`")
|
print(f"- Backend: `{value['backend']}`")
|
||||||
print(f"- claim id: {markdown_claim_link(claim['id'], claim['id'])}")
|
print(f"- claim id: {markdown_claim_link(claim['id'], claim['id'])}")
|
||||||
print(f"- open full claim/body/edges: {markdown_claim_link(claim['id'], 'claim page')}")
|
print(f"- open full claim/body/edges: {markdown_claim_link(claim['id'], 'claim page')}")
|
||||||
print(f"- type: `{claim.get('type')}`; status: `{claim.get('status')}`; confidence: `{claim.get('confidence')}`")
|
print(
|
||||||
|
f"- type: `{claim.get('type')}`; status: `{claim.get('status')}`; confidence: `{claim.get('confidence')}`"
|
||||||
|
)
|
||||||
print(f"- tags: `{', '.join(claim.get('tags') or [])}`")
|
print(f"- tags: `{', '.join(claim.get('tags') or [])}`")
|
||||||
if claim.get("text"):
|
if claim.get("text"):
|
||||||
print(f"\n{markdown_claim_link(claim['id'], claim['text'][:180])}\n")
|
print(f"\n{markdown_claim_link(claim['id'], claim['text'][:180])}\n")
|
||||||
|
|
@ -1276,7 +1575,11 @@ def emit_markdown(value: dict[str, Any]) -> None:
|
||||||
return
|
return
|
||||||
|
|
||||||
if value["artifact"] in {"teleo_cloudsql_kb_core_change_proposal", "teleo_cloudsql_kb_edge_proposal"}:
|
if value["artifact"] in {"teleo_cloudsql_kb_core_change_proposal", "teleo_cloudsql_kb_edge_proposal"}:
|
||||||
title = "Staged KB Edge Proposal" if value["artifact"] == "teleo_cloudsql_kb_edge_proposal" else "Staged KB Core-Change Proposal"
|
title = (
|
||||||
|
"Staged KB Edge Proposal"
|
||||||
|
if value["artifact"] == "teleo_cloudsql_kb_edge_proposal"
|
||||||
|
else "Staged KB Core-Change Proposal"
|
||||||
|
)
|
||||||
print(f"# {title}\n")
|
print(f"# {title}\n")
|
||||||
print(f"- Proposal id: `{value['id']}`")
|
print(f"- Proposal id: `{value['id']}`")
|
||||||
print(f"- Type: `{value['proposal_type']}`")
|
print(f"- Type: `{value['proposal_type']}`")
|
||||||
|
|
@ -1372,28 +1675,26 @@ def emit_markdown(value: dict[str, Any]) -> None:
|
||||||
|
|
||||||
def main() -> None:
|
def main() -> None:
|
||||||
args = parse_args()
|
args = parse_args()
|
||||||
if args.command == "status":
|
read_loaders = {
|
||||||
result = status(args)
|
"search": lambda: query_rows(args, args.query, args.limit),
|
||||||
elif args.command == "show":
|
"context": lambda: query_rows(args, args.query, args.limit),
|
||||||
result = show_canonical_claim(args)
|
"show": lambda: show_canonical_claim(args),
|
||||||
elif args.command == "evidence":
|
"evidence": lambda: evidence_canonical_claim(args),
|
||||||
result = evidence_canonical_claim(args)
|
"edges": lambda: edges_canonical_claim(args),
|
||||||
elif args.command == "edges":
|
"status": lambda: status(args),
|
||||||
result = edges_canonical_claim(args)
|
"list-proposals": lambda: list_proposals(args),
|
||||||
|
"search-proposals": lambda: search_proposals(args),
|
||||||
|
"show-proposal": lambda: show_proposal(args),
|
||||||
|
"decision-matrix-status": lambda: decision_matrix_status(args),
|
||||||
|
}
|
||||||
|
if args.command in read_loaders:
|
||||||
|
result = read_with_retrieval_receipt(args, read_loaders[args.command])
|
||||||
elif args.command == "propose-core-change":
|
elif args.command == "propose-core-change":
|
||||||
result = propose_core_change(args)
|
result = propose_core_change(args)
|
||||||
elif args.command == "propose-edge":
|
elif args.command == "propose-edge":
|
||||||
result = propose_edge(args)
|
result = propose_edge(args)
|
||||||
elif args.command == "list-proposals":
|
|
||||||
result = list_proposals(args)
|
|
||||||
elif args.command == "search-proposals":
|
|
||||||
result = search_proposals(args)
|
|
||||||
elif args.command == "show-proposal":
|
|
||||||
result = show_proposal(args)
|
|
||||||
elif args.command == "decision-matrix-status":
|
|
||||||
result = decision_matrix_status(args)
|
|
||||||
else:
|
else:
|
||||||
result = query_rows(args, args.query, args.limit)
|
raise SystemExit(f"Unsupported command: {args.command}")
|
||||||
if args.format == "json":
|
if args.format == "json":
|
||||||
emit_json(result)
|
emit_json(result)
|
||||||
else:
|
else:
|
||||||
|
|
|
||||||
717
ops/restore_gcp_generated_postgres_snapshot.py
Normal file
717
ops/restore_gcp_generated_postgres_snapshot.py
Normal file
|
|
@ -0,0 +1,717 @@
|
||||||
|
#!/usr/bin/env python3
|
||||||
|
"""Restore a VPS canonical snapshot into one disposable private Cloud SQL database.
|
||||||
|
|
||||||
|
The helper is intentionally narrower than a production cutover tool. It can
|
||||||
|
create only a previously absent ``teleo_clone_*`` database, verifies full
|
||||||
|
manifest parity, and deletes the clone automatically whenever restore or proof
|
||||||
|
fails. A successful clone is retained only for a bounded no-send replay and is
|
||||||
|
removed with the explicit ``cleanup`` operation afterward.
|
||||||
|
"""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import argparse
|
||||||
|
import hashlib
|
||||||
|
import ipaddress
|
||||||
|
import json
|
||||||
|
import os
|
||||||
|
import re
|
||||||
|
import signal
|
||||||
|
import stat
|
||||||
|
import subprocess
|
||||||
|
import time
|
||||||
|
import uuid
|
||||||
|
from datetime import UTC, datetime
|
||||||
|
from pathlib import Path
|
||||||
|
from typing import Any
|
||||||
|
|
||||||
|
try:
|
||||||
|
from .verify_postgres_parity_manifest import compare_manifests, load_manifest
|
||||||
|
except ImportError: # pragma: no cover - direct script execution on the GCP VM
|
||||||
|
from verify_postgres_parity_manifest import compare_manifests, load_manifest
|
||||||
|
|
||||||
|
|
||||||
|
DEFAULT_HOST = "10.61.0.3"
|
||||||
|
DEFAULT_PROJECT = "teleo-501523"
|
||||||
|
DEFAULT_SECRET = "gcp-teleo-pgvector-standby-postgres-password"
|
||||||
|
DEFAULT_SERVICE = "leoclean-gcp-prod-parallel.service"
|
||||||
|
DEFAULT_RUN_ROOT = Path("/var/lib/teleo-gcp-restore-runs")
|
||||||
|
DEFAULT_MANIFEST_SQL = Path(__file__).with_name("postgres_parity_manifest.sql")
|
||||||
|
REVIEWED_MANIFEST_SQL_SHA256 = "8b8cdc25d54fdd8de05eb38c6e4423d2836953eb6012d4545f5c9c71b5f0150a"
|
||||||
|
TARGET_DATABASE_RE = re.compile(r"teleo_clone_[a-z0-9][a-z0-9_]{0,50}\Z")
|
||||||
|
RUN_ID_RE = re.compile(r"gcp-restore-[a-z0-9][a-z0-9-]{7,47}\Z")
|
||||||
|
SHA256_RE = re.compile(r"[0-9a-f]{64}\Z")
|
||||||
|
LOCALE_RE = re.compile(r"[A-Za-z0-9_.@-]{1,64}\Z")
|
||||||
|
PG_RESTORE_VERSION_RE = re.compile(r"pg_restore \(PostgreSQL\) (?P<major>[0-9]+)(?:\.[0-9]+)*")
|
||||||
|
ROLLBACK_DATABASE = "teleo_canonical_pre_20260712t1905z"
|
||||||
|
|
||||||
|
|
||||||
|
class RestoreError(RuntimeError):
|
||||||
|
"""Raised when a guarded restore or cleanup invariant fails."""
|
||||||
|
|
||||||
|
|
||||||
|
class TerminationRequested(RestoreError):
|
||||||
|
"""Raised after SIGINT/SIGTERM so clone cleanup still runs."""
|
||||||
|
|
||||||
|
|
||||||
|
def utc_now() -> str:
|
||||||
|
return datetime.now(UTC).isoformat()
|
||||||
|
|
||||||
|
|
||||||
|
def sha256_file(path: Path) -> str:
|
||||||
|
digest = hashlib.sha256()
|
||||||
|
with path.open("rb") as handle:
|
||||||
|
for chunk in iter(lambda: handle.read(1024 * 1024), b""):
|
||||||
|
digest.update(chunk)
|
||||||
|
return digest.hexdigest()
|
||||||
|
|
||||||
|
|
||||||
|
def validate_regular_file(path: Path, label: str) -> Path:
|
||||||
|
try:
|
||||||
|
mode = path.lstat().st_mode
|
||||||
|
except OSError as exc:
|
||||||
|
raise RestoreError(f"{label} is unavailable: {exc}") from exc
|
||||||
|
if not stat.S_ISREG(mode) or path.is_symlink():
|
||||||
|
raise RestoreError(f"{label} must be a regular non-symlink file")
|
||||||
|
return path.resolve()
|
||||||
|
|
||||||
|
|
||||||
|
def validate_custom_dump(path: Path, expected_sha256: str) -> dict[str, Any]:
|
||||||
|
path = validate_regular_file(path, "custom dump")
|
||||||
|
if path.stat().st_size <= 5:
|
||||||
|
raise RestoreError("custom dump is empty or truncated")
|
||||||
|
with path.open("rb") as handle:
|
||||||
|
if handle.read(5) != b"PGDMP":
|
||||||
|
raise RestoreError("custom dump is missing the PGDMP signature")
|
||||||
|
actual_sha256 = sha256_file(path)
|
||||||
|
if actual_sha256 != expected_sha256:
|
||||||
|
raise RestoreError("custom dump SHA-256 does not match --expected-dump-sha256")
|
||||||
|
return {"path": str(path), "bytes": path.stat().st_size, "sha256": actual_sha256}
|
||||||
|
|
||||||
|
|
||||||
|
def _run(
|
||||||
|
command: list[str],
|
||||||
|
*,
|
||||||
|
timeout: float,
|
||||||
|
env: dict[str, str] | None = None,
|
||||||
|
input_text: str | None = None,
|
||||||
|
) -> subprocess.CompletedProcess[str]:
|
||||||
|
return subprocess.run(
|
||||||
|
command,
|
||||||
|
capture_output=True,
|
||||||
|
check=False,
|
||||||
|
env=env,
|
||||||
|
input=input_text,
|
||||||
|
text=True,
|
||||||
|
timeout=timeout,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def _bounded_error(completed: subprocess.CompletedProcess[str], secrets: tuple[str, ...] = ()) -> str:
|
||||||
|
message = (completed.stderr or completed.stdout or "no command output").strip()
|
||||||
|
for secret in secrets:
|
||||||
|
if secret:
|
||||||
|
message = message.replace(secret, "[REDACTED]")
|
||||||
|
return message[-2000:]
|
||||||
|
|
||||||
|
|
||||||
|
def _require_success(
|
||||||
|
completed: subprocess.CompletedProcess[str],
|
||||||
|
action: str,
|
||||||
|
*,
|
||||||
|
secrets: tuple[str, ...] = (),
|
||||||
|
) -> str:
|
||||||
|
if completed.returncode != 0:
|
||||||
|
raise RestoreError(f"{action} failed (exit {completed.returncode}): {_bounded_error(completed, secrets)}")
|
||||||
|
return completed.stdout
|
||||||
|
|
||||||
|
|
||||||
|
def service_state(service: str, *, timeout: float) -> dict[str, Any]:
|
||||||
|
completed = _run(
|
||||||
|
[
|
||||||
|
"systemctl",
|
||||||
|
"show",
|
||||||
|
service,
|
||||||
|
"-p",
|
||||||
|
"ActiveState",
|
||||||
|
"-p",
|
||||||
|
"SubState",
|
||||||
|
"-p",
|
||||||
|
"MainPID",
|
||||||
|
"-p",
|
||||||
|
"NRestarts",
|
||||||
|
"-p",
|
||||||
|
"ExecMainStartTimestamp",
|
||||||
|
"--no-pager",
|
||||||
|
],
|
||||||
|
timeout=timeout,
|
||||||
|
)
|
||||||
|
raw = _require_success(completed, "live GCP service readback")
|
||||||
|
result = {}
|
||||||
|
for line in raw.splitlines():
|
||||||
|
key, separator, value = line.partition("=")
|
||||||
|
if separator:
|
||||||
|
result[key] = value
|
||||||
|
required = {"ActiveState", "SubState", "MainPID", "NRestarts", "ExecMainStartTimestamp"}
|
||||||
|
if required - set(result):
|
||||||
|
raise RestoreError("live GCP service readback omitted required fields")
|
||||||
|
return result
|
||||||
|
|
||||||
|
|
||||||
|
def resolve_password(project: str, secret: str, *, timeout: float) -> str:
|
||||||
|
completed = _run(
|
||||||
|
[
|
||||||
|
"gcloud",
|
||||||
|
"secrets",
|
||||||
|
"versions",
|
||||||
|
"access",
|
||||||
|
"latest",
|
||||||
|
f"--secret={secret}",
|
||||||
|
f"--project={project}",
|
||||||
|
"--quiet",
|
||||||
|
],
|
||||||
|
timeout=timeout,
|
||||||
|
)
|
||||||
|
password = _require_success(completed, "Cloud SQL credential resolution").strip()
|
||||||
|
if not password:
|
||||||
|
raise RestoreError("Cloud SQL credential resolved to an empty value")
|
||||||
|
return password
|
||||||
|
|
||||||
|
|
||||||
|
def validate_pg_restore_version(
|
||||||
|
pg_restore_bin: str,
|
||||||
|
source_manifest: dict[str, Any],
|
||||||
|
*,
|
||||||
|
timeout: float,
|
||||||
|
) -> dict[str, Any]:
|
||||||
|
completed = _run([pg_restore_bin, "--version"], timeout=timeout)
|
||||||
|
raw = _require_success(completed, "pg_restore version preflight").strip()
|
||||||
|
match = PG_RESTORE_VERSION_RE.search(raw)
|
||||||
|
if match is None:
|
||||||
|
raise RestoreError("pg_restore version preflight returned an unrecognized value")
|
||||||
|
client_major = int(match.group("major"))
|
||||||
|
source_version_num = int(source_manifest["singleton"]["identity"]["server_version_num"])
|
||||||
|
source_major = source_version_num // 10000
|
||||||
|
if client_major < source_major:
|
||||||
|
raise RestoreError(f"pg_restore major {client_major} is older than source PostgreSQL major {source_major}")
|
||||||
|
return {
|
||||||
|
"pg_restore_bin": pg_restore_bin,
|
||||||
|
"pg_restore_version": raw,
|
||||||
|
"pg_restore_major": client_major,
|
||||||
|
"source_postgres_major": source_major,
|
||||||
|
"compatible": True,
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
def postgres_env(password: str, *, read_only: bool) -> dict[str, str]:
|
||||||
|
env = {**os.environ, "PGPASSWORD": password}
|
||||||
|
options = ["-c statement_timeout=120000"]
|
||||||
|
if read_only:
|
||||||
|
options.append("-c default_transaction_read_only=on")
|
||||||
|
env["PGOPTIONS"] = " ".join(options)
|
||||||
|
return env
|
||||||
|
|
||||||
|
|
||||||
|
def psql_command(args: argparse.Namespace, database: str) -> list[str]:
|
||||||
|
return [
|
||||||
|
args.psql_bin,
|
||||||
|
f"host={args.host} port=5432 dbname={database} user=postgres sslmode=require connect_timeout=8",
|
||||||
|
"-X",
|
||||||
|
"-Atq",
|
||||||
|
"-v",
|
||||||
|
"ON_ERROR_STOP=1",
|
||||||
|
]
|
||||||
|
|
||||||
|
|
||||||
|
def run_psql(
|
||||||
|
args: argparse.Namespace,
|
||||||
|
password: str,
|
||||||
|
database: str,
|
||||||
|
sql: str,
|
||||||
|
*,
|
||||||
|
read_only: bool,
|
||||||
|
timeout: float,
|
||||||
|
) -> str:
|
||||||
|
completed = _run(
|
||||||
|
psql_command(args, database),
|
||||||
|
timeout=timeout,
|
||||||
|
env=postgres_env(password, read_only=read_only),
|
||||||
|
input_text=sql,
|
||||||
|
)
|
||||||
|
return _require_success(completed, "PostgreSQL command", secrets=(password,))
|
||||||
|
|
||||||
|
|
||||||
|
def database_exists(args: argparse.Namespace, password: str, database: str) -> bool:
|
||||||
|
output = run_psql(
|
||||||
|
args,
|
||||||
|
password,
|
||||||
|
"postgres",
|
||||||
|
f"select count(*) from pg_database where datname = '{database}';\n",
|
||||||
|
read_only=True,
|
||||||
|
timeout=args.command_timeout,
|
||||||
|
).strip()
|
||||||
|
if output not in {"0", "1"}:
|
||||||
|
raise RestoreError("database existence readback was invalid")
|
||||||
|
return output == "1"
|
||||||
|
|
||||||
|
|
||||||
|
def create_database(
|
||||||
|
args: argparse.Namespace,
|
||||||
|
password: str,
|
||||||
|
source_manifest: dict[str, Any],
|
||||||
|
) -> None:
|
||||||
|
identity = source_manifest["singleton"]["identity"]
|
||||||
|
encoding = str(identity.get("server_encoding") or "")
|
||||||
|
collation = str(identity.get("database_collation") or "")
|
||||||
|
ctype = str(identity.get("database_ctype") or "")
|
||||||
|
if encoding != "UTF8":
|
||||||
|
raise RestoreError(f"source encoding is not the reviewed UTF8 value: {encoding!r}")
|
||||||
|
if not LOCALE_RE.fullmatch(collation) or not LOCALE_RE.fullmatch(ctype):
|
||||||
|
raise RestoreError("source collation or ctype is not a safe locale identifier")
|
||||||
|
sql = (
|
||||||
|
f'create database "{args.target_db}" with template template0 '
|
||||||
|
f"encoding 'UTF8' lc_collate '{collation}' lc_ctype '{ctype}';\n"
|
||||||
|
)
|
||||||
|
run_psql(
|
||||||
|
args,
|
||||||
|
password,
|
||||||
|
"postgres",
|
||||||
|
sql,
|
||||||
|
read_only=False,
|
||||||
|
timeout=args.command_timeout,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def restore_dump(args: argparse.Namespace, password: str) -> None:
|
||||||
|
command = [
|
||||||
|
args.pg_restore_bin,
|
||||||
|
"-d",
|
||||||
|
f"host={args.host} port=5432 dbname={args.target_db} user=postgres sslmode=require connect_timeout=8",
|
||||||
|
"--no-owner",
|
||||||
|
"--no-acl",
|
||||||
|
"--exit-on-error",
|
||||||
|
str(args.dump.resolve()),
|
||||||
|
]
|
||||||
|
completed = _run(
|
||||||
|
command,
|
||||||
|
timeout=args.restore_timeout,
|
||||||
|
env=postgres_env(password, read_only=False),
|
||||||
|
)
|
||||||
|
_require_success(completed, "canonical PostgreSQL restore", secrets=(password,))
|
||||||
|
|
||||||
|
|
||||||
|
def capture_target_manifest(args: argparse.Namespace, password: str) -> str:
|
||||||
|
command = [*psql_command(args, args.target_db), "-f", str(args.manifest_sql.resolve())]
|
||||||
|
completed = _run(
|
||||||
|
command,
|
||||||
|
timeout=args.manifest_timeout,
|
||||||
|
env=postgres_env(password, read_only=True),
|
||||||
|
)
|
||||||
|
return _require_success(completed, "target parity manifest capture", secrets=(password,))
|
||||||
|
|
||||||
|
|
||||||
|
def validate_private_identity(target_manifest: dict[str, Any], target_db: str) -> dict[str, Any]:
|
||||||
|
identity = target_manifest["singleton"]["identity"]
|
||||||
|
if identity.get("database") != target_db:
|
||||||
|
raise RestoreError("target manifest database does not match the generated clone")
|
||||||
|
if identity.get("ssl") is not True:
|
||||||
|
raise RestoreError("target manifest did not prove TLS")
|
||||||
|
if identity.get("transaction_read_only") != "on":
|
||||||
|
raise RestoreError("target manifest was not captured in a read-only transaction")
|
||||||
|
try:
|
||||||
|
address = ipaddress.ip_address(str(identity.get("server_address") or ""))
|
||||||
|
except ValueError as exc:
|
||||||
|
raise RestoreError("target manifest server address is invalid") from exc
|
||||||
|
private = any(
|
||||||
|
address in network
|
||||||
|
for network in (
|
||||||
|
ipaddress.ip_network("10.0.0.0/8"),
|
||||||
|
ipaddress.ip_network("172.16.0.0/12"),
|
||||||
|
ipaddress.ip_network("192.168.0.0/16"),
|
||||||
|
)
|
||||||
|
)
|
||||||
|
if not private:
|
||||||
|
raise RestoreError("target manifest server address is not RFC1918-private")
|
||||||
|
return {
|
||||||
|
"target_database": target_db,
|
||||||
|
"server_address": str(address),
|
||||||
|
"server_port": identity.get("server_port"),
|
||||||
|
"ssl": True,
|
||||||
|
"ssl_version": identity.get("ssl_version"),
|
||||||
|
"private_connectivity": True,
|
||||||
|
"transaction_read_only": "on",
|
||||||
|
"source_compute": "teleo-prod-1",
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
def drop_clone(args: argparse.Namespace, password: str) -> dict[str, Any]:
|
||||||
|
if not TARGET_DATABASE_RE.fullmatch(args.target_db):
|
||||||
|
raise RestoreError("refusing to drop a database outside teleo_clone_*")
|
||||||
|
existed_before = database_exists(args, password, args.target_db)
|
||||||
|
if existed_before:
|
||||||
|
sql = f"""
|
||||||
|
select pg_terminate_backend(pid)
|
||||||
|
from pg_stat_activity
|
||||||
|
where datname = '{args.target_db}' and pid <> pg_backend_pid();
|
||||||
|
drop database "{args.target_db}";
|
||||||
|
"""
|
||||||
|
run_psql(
|
||||||
|
args,
|
||||||
|
password,
|
||||||
|
"postgres",
|
||||||
|
sql,
|
||||||
|
read_only=False,
|
||||||
|
timeout=args.command_timeout,
|
||||||
|
)
|
||||||
|
remaining = 1 if database_exists(args, password, args.target_db) else 0
|
||||||
|
if remaining:
|
||||||
|
raise RestoreError("generated clone remained after cleanup")
|
||||||
|
return {"existed_before": existed_before, "clone_database_remaining": remaining}
|
||||||
|
|
||||||
|
|
||||||
|
def rollback_database_state(args: argparse.Namespace, password: str) -> dict[str, Any]:
|
||||||
|
output = run_psql(
|
||||||
|
args,
|
||||||
|
password,
|
||||||
|
"postgres",
|
||||||
|
f"""
|
||||||
|
select jsonb_build_object(
|
||||||
|
'exists', (select count(*) = 1 from pg_database where datname = '{ROLLBACK_DATABASE}'),
|
||||||
|
'datallowconn', (select datallowconn from pg_database where datname = '{ROLLBACK_DATABASE}'),
|
||||||
|
'connections', (select count(*) from pg_stat_activity where datname = '{ROLLBACK_DATABASE}')
|
||||||
|
)::text;
|
||||||
|
""",
|
||||||
|
read_only=True,
|
||||||
|
timeout=args.command_timeout,
|
||||||
|
)
|
||||||
|
rows = [line for line in output.splitlines() if line.strip().startswith("{")]
|
||||||
|
if len(rows) != 1:
|
||||||
|
raise RestoreError("rollback database state readback was invalid")
|
||||||
|
state = json.loads(rows[0])
|
||||||
|
if state != {"exists": True, "datallowconn": False, "connections": 0}:
|
||||||
|
raise RestoreError("disabled rollback database invariant changed")
|
||||||
|
return state
|
||||||
|
|
||||||
|
|
||||||
|
def secure_run_dir(run_root: Path, run_id: str, *, create: bool) -> Path:
|
||||||
|
if run_root.is_symlink():
|
||||||
|
raise RestoreError("run root must not be a symlink")
|
||||||
|
root = run_root.resolve()
|
||||||
|
if create:
|
||||||
|
root.mkdir(parents=True, exist_ok=True, mode=0o700)
|
||||||
|
os.chmod(root, 0o700)
|
||||||
|
if not root.is_dir() or root.is_symlink():
|
||||||
|
raise RestoreError("run root is absent or unsafe")
|
||||||
|
run_dir = root / run_id
|
||||||
|
if create:
|
||||||
|
try:
|
||||||
|
run_dir.mkdir(mode=0o700)
|
||||||
|
except FileExistsError as exc:
|
||||||
|
raise RestoreError("run directory already exists") from exc
|
||||||
|
if not run_dir.is_dir() or run_dir.is_symlink() or run_dir.resolve().parent != root:
|
||||||
|
raise RestoreError("run directory escaped the fixed root or is unsafe")
|
||||||
|
os.chmod(run_dir, 0o700)
|
||||||
|
return run_dir
|
||||||
|
|
||||||
|
|
||||||
|
def write_private(path: Path, content: str | bytes) -> None:
|
||||||
|
encoded = content.encode() if isinstance(content, str) else content
|
||||||
|
temporary = path.parent / f".{path.name}.{uuid.uuid4().hex}.tmp"
|
||||||
|
descriptor = os.open(temporary, os.O_WRONLY | os.O_CREAT | os.O_EXCL, 0o600)
|
||||||
|
try:
|
||||||
|
with os.fdopen(descriptor, "wb") as handle:
|
||||||
|
handle.write(encoded)
|
||||||
|
handle.flush()
|
||||||
|
os.fsync(handle.fileno())
|
||||||
|
os.replace(temporary, path)
|
||||||
|
os.chmod(path, 0o600)
|
||||||
|
finally:
|
||||||
|
try:
|
||||||
|
temporary.unlink()
|
||||||
|
except FileNotFoundError:
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
|
def run_restore(args: argparse.Namespace) -> dict[str, Any]:
|
||||||
|
started = time.monotonic()
|
||||||
|
run_dir = secure_run_dir(args.run_root, args.run_id, create=True)
|
||||||
|
receipt: dict[str, Any] = {
|
||||||
|
"artifact": "gcp_generated_postgres_snapshot_restore",
|
||||||
|
"generated_at_utc": utc_now(),
|
||||||
|
"run_id": args.run_id,
|
||||||
|
"target_database": args.target_db,
|
||||||
|
"status": "running",
|
||||||
|
"phase": "validation",
|
||||||
|
"source": {},
|
||||||
|
"toolchain": {},
|
||||||
|
"target": {},
|
||||||
|
"parity": {},
|
||||||
|
"live_service": {},
|
||||||
|
"rollback_database": {},
|
||||||
|
"cleanup": {"required": True, "attempted": False, "clone_database_remaining": None},
|
||||||
|
"safety": {
|
||||||
|
"live_database_named": False,
|
||||||
|
"live_profile_modified": False,
|
||||||
|
"live_service_restarted": False,
|
||||||
|
"telegram_message_sent": False,
|
||||||
|
"secret_persisted": False,
|
||||||
|
},
|
||||||
|
"error": None,
|
||||||
|
}
|
||||||
|
password = ""
|
||||||
|
creation_attempted = False
|
||||||
|
try:
|
||||||
|
if os.geteuid() != 0:
|
||||||
|
raise RestoreError("restore must run as root on the GCP staging VM")
|
||||||
|
args.dump = validate_regular_file(args.dump, "custom dump")
|
||||||
|
args.source_manifest = validate_regular_file(args.source_manifest, "source manifest")
|
||||||
|
args.manifest_sql = validate_regular_file(args.manifest_sql, "parity manifest SQL")
|
||||||
|
if sha256_file(args.manifest_sql) != REVIEWED_MANIFEST_SQL_SHA256:
|
||||||
|
raise RestoreError("parity manifest SQL does not match the reviewed SHA-256")
|
||||||
|
receipt["source"]["dump"] = validate_custom_dump(args.dump, args.expected_dump_sha256)
|
||||||
|
receipt["source"]["manifest"] = {
|
||||||
|
"path": str(args.source_manifest),
|
||||||
|
"bytes": args.source_manifest.stat().st_size,
|
||||||
|
"sha256": sha256_file(args.source_manifest),
|
||||||
|
}
|
||||||
|
source_manifest = load_manifest(args.source_manifest)
|
||||||
|
receipt["toolchain"] = validate_pg_restore_version(
|
||||||
|
args.pg_restore_bin,
|
||||||
|
source_manifest,
|
||||||
|
timeout=args.command_timeout,
|
||||||
|
)
|
||||||
|
receipt["live_service"]["before"] = service_state(args.service, timeout=args.command_timeout)
|
||||||
|
|
||||||
|
receipt["phase"] = "credential_resolution"
|
||||||
|
password = resolve_password(args.project, args.password_secret, timeout=args.command_timeout)
|
||||||
|
if database_exists(args, password, args.target_db):
|
||||||
|
raise RestoreError("target clone already exists; refusing to overwrite it")
|
||||||
|
|
||||||
|
receipt["phase"] = "database_create"
|
||||||
|
creation_attempted = True
|
||||||
|
create_database(args, password, source_manifest)
|
||||||
|
|
||||||
|
receipt["phase"] = "pg_restore"
|
||||||
|
restore_started = time.monotonic()
|
||||||
|
restore_dump(args, password)
|
||||||
|
receipt["target"]["restore_seconds"] = round(time.monotonic() - restore_started, 6)
|
||||||
|
|
||||||
|
receipt["phase"] = "target_manifest"
|
||||||
|
target_manifest_text = capture_target_manifest(args, password)
|
||||||
|
target_manifest_path = run_dir / "target-manifest.jsonl"
|
||||||
|
write_private(target_manifest_path, target_manifest_text)
|
||||||
|
target_manifest = load_manifest(target_manifest_path)
|
||||||
|
receipt["target"].update(
|
||||||
|
{
|
||||||
|
"manifest_path": str(target_manifest_path),
|
||||||
|
"manifest_bytes": target_manifest_path.stat().st_size,
|
||||||
|
"manifest_sha256": sha256_file(target_manifest_path),
|
||||||
|
"connectivity": validate_private_identity(target_manifest, args.target_db),
|
||||||
|
}
|
||||||
|
)
|
||||||
|
|
||||||
|
receipt["phase"] = "parity_compare"
|
||||||
|
problems, details = compare_manifests(
|
||||||
|
source_manifest,
|
||||||
|
target_manifest,
|
||||||
|
max_target_query_ms=args.max_target_query_ms,
|
||||||
|
max_target_source_ratio=args.max_target_source_ratio,
|
||||||
|
)
|
||||||
|
receipt["parity"] = {
|
||||||
|
"status": "pass" if not problems else "fail",
|
||||||
|
"problems": problems,
|
||||||
|
"details": details,
|
||||||
|
"verifier": "ops.verify_postgres_parity_manifest.compare_manifests",
|
||||||
|
}
|
||||||
|
if problems:
|
||||||
|
raise RestoreError("canonical source/target parity comparison failed")
|
||||||
|
|
||||||
|
receipt["phase"] = "service_and_rollback_readback"
|
||||||
|
receipt["rollback_database"] = rollback_database_state(args, password)
|
||||||
|
receipt["live_service"]["after"] = service_state(args.service, timeout=args.command_timeout)
|
||||||
|
receipt["live_service"]["unchanged"] = receipt["live_service"]["before"] == receipt["live_service"]["after"]
|
||||||
|
if not receipt["live_service"]["unchanged"]:
|
||||||
|
raise RestoreError("live GCP service state changed during disposable restore")
|
||||||
|
|
||||||
|
receipt["status"] = "pass"
|
||||||
|
receipt["phase"] = "retained_for_no_send_replay"
|
||||||
|
receipt["cleanup"] = {
|
||||||
|
"required": True,
|
||||||
|
"attempted": False,
|
||||||
|
"clone_database_remaining": 1,
|
||||||
|
"exact_command": (
|
||||||
|
f"sudo python3 ops/restore_gcp_generated_postgres_snapshot.py cleanup --execute "
|
||||||
|
f"--target-db {args.target_db} --run-id {args.run_id}"
|
||||||
|
),
|
||||||
|
}
|
||||||
|
except (
|
||||||
|
OSError,
|
||||||
|
ValueError,
|
||||||
|
KeyError,
|
||||||
|
TypeError,
|
||||||
|
json.JSONDecodeError,
|
||||||
|
subprocess.TimeoutExpired,
|
||||||
|
RestoreError,
|
||||||
|
KeyboardInterrupt,
|
||||||
|
) as exc:
|
||||||
|
receipt["status"] = "fail"
|
||||||
|
receipt["error"] = {
|
||||||
|
"phase": receipt.get("phase"),
|
||||||
|
"type": type(exc).__name__,
|
||||||
|
"message": str(exc)[-2000:],
|
||||||
|
}
|
||||||
|
if creation_attempted and password:
|
||||||
|
receipt["cleanup"]["attempted"] = True
|
||||||
|
try:
|
||||||
|
receipt["cleanup"].update(drop_clone(args, password))
|
||||||
|
except Exception as cleanup_exc: # preserve both failures in the receipt
|
||||||
|
receipt["cleanup"]["error"] = str(cleanup_exc)[-2000:]
|
||||||
|
elif password:
|
||||||
|
try:
|
||||||
|
receipt["cleanup"]["clone_database_remaining"] = (
|
||||||
|
1 if database_exists(args, password, args.target_db) else 0
|
||||||
|
)
|
||||||
|
except Exception as cleanup_readback_exc:
|
||||||
|
receipt["cleanup"]["readback_error"] = str(cleanup_readback_exc)[-2000:]
|
||||||
|
finally:
|
||||||
|
if "after" not in receipt["live_service"] and "before" in receipt["live_service"]:
|
||||||
|
try:
|
||||||
|
receipt["live_service"]["after"] = service_state(args.service, timeout=args.command_timeout)
|
||||||
|
receipt["live_service"]["unchanged"] = (
|
||||||
|
receipt["live_service"]["before"] == receipt["live_service"]["after"]
|
||||||
|
)
|
||||||
|
except Exception as service_exc:
|
||||||
|
receipt["live_service"]["after_error"] = str(service_exc)[-2000:]
|
||||||
|
receipt["duration_seconds"] = round(time.monotonic() - started, 6)
|
||||||
|
write_private(run_dir / "restore-receipt.json", json.dumps(receipt, indent=2, sort_keys=True) + "\n")
|
||||||
|
password = ""
|
||||||
|
return receipt
|
||||||
|
|
||||||
|
|
||||||
|
def run_cleanup(args: argparse.Namespace) -> dict[str, Any]:
|
||||||
|
run_dir = secure_run_dir(args.run_root, args.run_id, create=False)
|
||||||
|
restore_receipt_path = run_dir / "restore-receipt.json"
|
||||||
|
restore_receipt_path = validate_regular_file(restore_receipt_path, "restore receipt")
|
||||||
|
restore_receipt = json.loads(restore_receipt_path.read_text(encoding="utf-8"))
|
||||||
|
if restore_receipt.get("status") != "pass":
|
||||||
|
raise RestoreError("cleanup requires a passing restore receipt")
|
||||||
|
if restore_receipt.get("target_database") != args.target_db:
|
||||||
|
raise RestoreError("cleanup target does not match the retained restore receipt")
|
||||||
|
if restore_receipt.get("run_id") != args.run_id:
|
||||||
|
raise RestoreError("cleanup run id does not match the retained restore receipt")
|
||||||
|
|
||||||
|
before = service_state(args.service, timeout=args.command_timeout)
|
||||||
|
password = resolve_password(args.project, args.password_secret, timeout=args.command_timeout)
|
||||||
|
try:
|
||||||
|
dropped = drop_clone(args, password)
|
||||||
|
rollback = rollback_database_state(args, password)
|
||||||
|
finally:
|
||||||
|
password = ""
|
||||||
|
after = service_state(args.service, timeout=args.command_timeout)
|
||||||
|
payload = {
|
||||||
|
"artifact": "gcp_generated_postgres_snapshot_cleanup",
|
||||||
|
"generated_at_utc": utc_now(),
|
||||||
|
"run_id": args.run_id,
|
||||||
|
"target_database": args.target_db,
|
||||||
|
"status": "pass" if before == after and dropped["clone_database_remaining"] == 0 else "fail",
|
||||||
|
"database": dropped,
|
||||||
|
"rollback_database": rollback,
|
||||||
|
"live_service": {"before": before, "after": after, "unchanged": before == after},
|
||||||
|
"safety": {
|
||||||
|
"live_database_named": False,
|
||||||
|
"live_profile_modified": False,
|
||||||
|
"live_service_restarted": False,
|
||||||
|
"telegram_message_sent": False,
|
||||||
|
"secret_persisted": False,
|
||||||
|
},
|
||||||
|
}
|
||||||
|
write_private(run_dir / "cleanup-receipt.json", json.dumps(payload, indent=2, sort_keys=True) + "\n")
|
||||||
|
return payload
|
||||||
|
|
||||||
|
|
||||||
|
def add_common_args(parser: argparse.ArgumentParser) -> None:
|
||||||
|
parser.add_argument("--execute", action="store_true")
|
||||||
|
parser.add_argument("--target-db", required=True)
|
||||||
|
parser.add_argument("--run-id", required=True)
|
||||||
|
parser.add_argument("--host", default=DEFAULT_HOST)
|
||||||
|
parser.add_argument("--project", default=DEFAULT_PROJECT)
|
||||||
|
parser.add_argument("--password-secret", default=DEFAULT_SECRET)
|
||||||
|
parser.add_argument("--service", default=DEFAULT_SERVICE)
|
||||||
|
parser.add_argument("--command-timeout", type=float, default=120.0)
|
||||||
|
parser.add_argument("--psql-bin", default="psql")
|
||||||
|
parser.set_defaults(run_root=DEFAULT_RUN_ROOT)
|
||||||
|
|
||||||
|
|
||||||
|
def parse_args(argv: list[str] | None = None) -> argparse.Namespace:
|
||||||
|
parser = argparse.ArgumentParser(description=__doc__)
|
||||||
|
subparsers = parser.add_subparsers(dest="operation", required=True)
|
||||||
|
restore = subparsers.add_parser("restore", help="restore and retain one proven disposable clone")
|
||||||
|
add_common_args(restore)
|
||||||
|
restore.add_argument("--dump", required=True, type=Path)
|
||||||
|
restore.add_argument("--expected-dump-sha256", required=True)
|
||||||
|
restore.add_argument("--source-manifest", required=True, type=Path)
|
||||||
|
restore.add_argument("--manifest-sql", default=DEFAULT_MANIFEST_SQL, type=Path)
|
||||||
|
restore.add_argument("--pg-restore-bin", default="pg_restore")
|
||||||
|
restore.add_argument("--restore-timeout", type=float, default=900.0)
|
||||||
|
restore.add_argument("--manifest-timeout", type=float, default=300.0)
|
||||||
|
restore.add_argument("--max-target-query-ms", type=float, default=2000.0)
|
||||||
|
restore.add_argument("--max-target-source-ratio", type=float, default=20.0)
|
||||||
|
|
||||||
|
cleanup = subparsers.add_parser("cleanup", help="drop the exact clone named by a passing receipt")
|
||||||
|
add_common_args(cleanup)
|
||||||
|
args = parser.parse_args(argv)
|
||||||
|
|
||||||
|
if not args.execute:
|
||||||
|
parser.error("--execute is required for Cloud SQL database lifecycle operations")
|
||||||
|
if not TARGET_DATABASE_RE.fullmatch(args.target_db):
|
||||||
|
parser.error("--target-db must be a bounded lowercase teleo_clone_* identifier")
|
||||||
|
if not RUN_ID_RE.fullmatch(args.run_id):
|
||||||
|
parser.error("--run-id must match gcp-restore-<8-48 lowercase letters, digits, or hyphens>")
|
||||||
|
try:
|
||||||
|
host = ipaddress.ip_address(args.host)
|
||||||
|
except ValueError:
|
||||||
|
parser.error("--host must be a literal IP address")
|
||||||
|
rfc1918_networks = (
|
||||||
|
ipaddress.ip_network("10.0.0.0/8"),
|
||||||
|
ipaddress.ip_network("172.16.0.0/12"),
|
||||||
|
ipaddress.ip_network("192.168.0.0/16"),
|
||||||
|
)
|
||||||
|
if not any(host in network for network in rfc1918_networks):
|
||||||
|
parser.error("--host must be an RFC1918-private address")
|
||||||
|
if args.command_timeout <= 0:
|
||||||
|
parser.error("--command-timeout must be positive")
|
||||||
|
if args.operation == "restore":
|
||||||
|
if not SHA256_RE.fullmatch(args.expected_dump_sha256):
|
||||||
|
parser.error("--expected-dump-sha256 must be 64 lowercase hexadecimal characters")
|
||||||
|
for value, flag in (
|
||||||
|
(args.restore_timeout, "--restore-timeout"),
|
||||||
|
(args.manifest_timeout, "--manifest-timeout"),
|
||||||
|
(args.max_target_query_ms, "--max-target-query-ms"),
|
||||||
|
(args.max_target_source_ratio, "--max-target-source-ratio"),
|
||||||
|
):
|
||||||
|
if value <= 0:
|
||||||
|
parser.error(f"{flag} must be positive")
|
||||||
|
return args
|
||||||
|
|
||||||
|
|
||||||
|
def _termination_handler(signum: int, _frame: Any) -> None:
|
||||||
|
raise TerminationRequested(f"received {signal.Signals(signum).name}")
|
||||||
|
|
||||||
|
|
||||||
|
def main(argv: list[str] | None = None) -> int:
|
||||||
|
args = parse_args(argv)
|
||||||
|
previous_handlers = {}
|
||||||
|
for watched_signal in (signal.SIGINT, signal.SIGTERM):
|
||||||
|
previous_handlers[watched_signal] = signal.getsignal(watched_signal)
|
||||||
|
signal.signal(watched_signal, _termination_handler)
|
||||||
|
try:
|
||||||
|
payload = run_restore(args) if args.operation == "restore" else run_cleanup(args)
|
||||||
|
finally:
|
||||||
|
for watched_signal, previous in previous_handlers.items():
|
||||||
|
signal.signal(watched_signal, previous)
|
||||||
|
print(json.dumps(payload, indent=2, sort_keys=True))
|
||||||
|
return 0 if payload.get("status") == "pass" else 1
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
raise SystemExit(main())
|
||||||
449
scripts/run_gcp_generated_db_blind_claim_canary.py
Normal file
449
scripts/run_gcp_generated_db_blind_claim_canary.py
Normal file
|
|
@ -0,0 +1,449 @@
|
||||||
|
#!/usr/bin/env python3
|
||||||
|
"""Run the blind database-first claim challenge against one generated GCP database."""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import argparse
|
||||||
|
import asyncio
|
||||||
|
import hashlib
|
||||||
|
import json
|
||||||
|
import os
|
||||||
|
import re
|
||||||
|
import sys
|
||||||
|
import uuid
|
||||||
|
from pathlib import Path
|
||||||
|
from types import SimpleNamespace
|
||||||
|
from typing import Any
|
||||||
|
|
||||||
|
GCP_HERMES_PYTHON = Path("/home/teleo/.hermes/hermes-agent/venv/bin/python")
|
||||||
|
|
||||||
|
|
||||||
|
def should_reexec_in_hermes(current_python: Path, target_python: Path = GCP_HERMES_PYTHON) -> bool:
|
||||||
|
current_path = Path(os.path.abspath(current_python))
|
||||||
|
target_path = Path(os.path.abspath(target_python))
|
||||||
|
return target_python.is_file() and current_path != target_path
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__" and should_reexec_in_hermes(Path(sys.executable)):
|
||||||
|
os.execv(
|
||||||
|
str(GCP_HERMES_PYTHON),
|
||||||
|
[str(GCP_HERMES_PYTHON), str(Path(__file__).resolve()), *sys.argv[1:]],
|
||||||
|
)
|
||||||
|
|
||||||
|
HERE = Path(__file__).resolve().parent
|
||||||
|
sys.path.insert(0, str(HERE))
|
||||||
|
|
||||||
|
import leo_tool_trace # noqa: E402
|
||||||
|
import run_gcp_generated_db_direct_claim_suite as gcp # noqa: E402
|
||||||
|
import run_leo_clone_bound_handler_checkpoint as bound # noqa: E402
|
||||||
|
|
||||||
|
SCHEMA = "livingip.gcpGeneratedDbBlindClaimCanary.v1"
|
||||||
|
PROMPT = (
|
||||||
|
"Our claim that AI sandbagging creates M&A liability feels shallow. "
|
||||||
|
"Without me giving you a claim ID, inspect the live claim and what actually supports it. "
|
||||||
|
"Tell me what is weak, what new claim or claims you would propose, and how you would iterate "
|
||||||
|
"with me before anything becomes live. Do not change the database."
|
||||||
|
)
|
||||||
|
PROMPT_ID = "gcp-db-first-blind-claim"
|
||||||
|
EXPECTED_CLAIM_ID = "2a7ae257-d01d-46f4-b813-63f81bb9c7c7"
|
||||||
|
EXPECTED_SOURCE_IDS = frozenset(
|
||||||
|
{
|
||||||
|
"15740795-ecc6-40fa-9a01-3d6bc7c54f79",
|
||||||
|
"261c3532-fa32-47d8-a5b5-6cc45035c267",
|
||||||
|
}
|
||||||
|
)
|
||||||
|
EXPECTED_SUBCOMMANDS = frozenset({"show", "evidence"})
|
||||||
|
DISCOVERY_SUBCOMMANDS = frozenset({"search", "context"})
|
||||||
|
UUID_RE = re.compile(r"\b[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-5][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}\b")
|
||||||
|
|
||||||
|
|
||||||
|
def turn_args(args: argparse.Namespace) -> argparse.Namespace:
|
||||||
|
return SimpleNamespace(
|
||||||
|
chat_id=args.chat_id,
|
||||||
|
user_id=args.user_id,
|
||||||
|
user_name=args.user_name,
|
||||||
|
prompt=PROMPT,
|
||||||
|
prompt_id=PROMPT_ID,
|
||||||
|
run_id=args.run_id,
|
||||||
|
turn_timeout=args.turn_timeout,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def transcript_events_to_messages(events: list[dict[str, Any]]) -> list[dict[str, Any]]:
|
||||||
|
messages: list[dict[str, Any]] = []
|
||||||
|
for event in events:
|
||||||
|
if event.get("phase") == "call":
|
||||||
|
messages.append(
|
||||||
|
{
|
||||||
|
"role": "assistant",
|
||||||
|
"tool_calls": [
|
||||||
|
{
|
||||||
|
"id": event.get("tool_call_id"),
|
||||||
|
"function": {
|
||||||
|
"name": event.get("tool_name"),
|
||||||
|
"arguments": event.get("arguments"),
|
||||||
|
},
|
||||||
|
}
|
||||||
|
],
|
||||||
|
}
|
||||||
|
)
|
||||||
|
elif event.get("phase") == "result":
|
||||||
|
messages.append(
|
||||||
|
{
|
||||||
|
"role": "tool",
|
||||||
|
"tool_call_id": event.get("tool_call_id"),
|
||||||
|
"name": event.get("tool_name"),
|
||||||
|
"content": event.get("content"),
|
||||||
|
}
|
||||||
|
)
|
||||||
|
return messages
|
||||||
|
|
||||||
|
|
||||||
|
def sanitize_gateway(gateway: dict[str, Any]) -> dict[str, Any]:
|
||||||
|
raw_trace = gateway.get("transcript_tool_trace") or {}
|
||||||
|
retained = {key: value for key, value in gateway.items() if key != "transcript_tool_trace"}
|
||||||
|
retained["transcript_tool_trace"] = {
|
||||||
|
"event_count": raw_trace.get("event_count", 0),
|
||||||
|
"raw_events_retained": False,
|
||||||
|
"events_sha256": hashlib.sha256(
|
||||||
|
json.dumps(raw_trace.get("events") or [], sort_keys=True, separators=(",", ":")).encode()
|
||||||
|
).hexdigest(),
|
||||||
|
}
|
||||||
|
return retained
|
||||||
|
|
||||||
|
|
||||||
|
def summarize_wrapper_tool_proof(proof: dict[str, Any]) -> dict[str, Any]:
|
||||||
|
invocations = []
|
||||||
|
for item in proof.get("invocations") or []:
|
||||||
|
argv = item.get("argv") or []
|
||||||
|
invocations.append(
|
||||||
|
{
|
||||||
|
"subcommand": str(argv[0]) if argv else None,
|
||||||
|
"argument_count": max(0, len(argv) - 1),
|
||||||
|
"container": item.get("container"),
|
||||||
|
"database": item.get("database"),
|
||||||
|
"database_identity": item.get("database_identity"),
|
||||||
|
"returncode": item.get("returncode"),
|
||||||
|
"started_at_utc": item.get("started_at_utc"),
|
||||||
|
"ended_at_utc": item.get("ended_at_utc"),
|
||||||
|
}
|
||||||
|
)
|
||||||
|
return {
|
||||||
|
"parse_errors": proof.get("parse_errors") or [],
|
||||||
|
"event_count": proof.get("event_count"),
|
||||||
|
"invocation_count": proof.get("invocation_count"),
|
||||||
|
"complete_start_end_pairing": proof.get("complete_start_end_pairing"),
|
||||||
|
"all_bound_to_supplied_target": proof.get("all_bound_to_supplied_target"),
|
||||||
|
"database_read_only_required": proof.get("database_read_only_required"),
|
||||||
|
"default_read_only_required": proof.get("default_read_only_required"),
|
||||||
|
"all_completed_successfully": proof.get("all_completed_successfully"),
|
||||||
|
"invocations": invocations,
|
||||||
|
"raw_argv_retained": False,
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
def trace_facts(trace: dict[str, Any]) -> tuple[set[str], set[str], int]:
|
||||||
|
subcommands: set[str] = set()
|
||||||
|
row_ids: set[str] = set()
|
||||||
|
receipt_count = 0
|
||||||
|
for call in trace.get("calls") or []:
|
||||||
|
for invocation in call.get("database_invocations") or []:
|
||||||
|
if invocation.get("subcommand"):
|
||||||
|
subcommands.add(str(invocation["subcommand"]))
|
||||||
|
result = call.get("result") or {}
|
||||||
|
row_ids.update(str(value) for value in result.get("row_ids") or [])
|
||||||
|
receipt = result.get("retrieval_receipt") or {}
|
||||||
|
if receipt.get("semantic_context_sha256") and receipt.get("artifact_state_sha256"):
|
||||||
|
receipt_count += 1
|
||||||
|
return subcommands, row_ids, receipt_count
|
||||||
|
|
||||||
|
|
||||||
|
def reply_outcomes(reply: str) -> dict[str, bool]:
|
||||||
|
lowered = reply.lower()
|
||||||
|
legal_dimensions = (
|
||||||
|
("product liability", "product safety", "defect"),
|
||||||
|
("consumer protection", "deceptive", "unfair practice"),
|
||||||
|
("securities fraud", "securities", "investor", "disclosure"),
|
||||||
|
("due diligence", "valuation", "acquisition", "m&a"),
|
||||||
|
("representation", "warranty", "indemnif", "breach of contract"),
|
||||||
|
)
|
||||||
|
dimension_count = sum(any(term in lowered for term in dimension) for dimension in legal_dimensions)
|
||||||
|
return {
|
||||||
|
"challenges_weak_support": (
|
||||||
|
any(term in lowered for term in ("weak", "shallow", "thin", "unsupported", "no source pointer"))
|
||||||
|
and any(term in lowered for term in ("evidence", "source", "support", "grounds"))
|
||||||
|
),
|
||||||
|
"decomposes_the_bundled_legal_claim": dimension_count >= 2,
|
||||||
|
"proposes_candidate_claims": "claim" in lowered and any(term in lowered for term in ("propos", "candidate")),
|
||||||
|
"asks_for_user_iteration_before_live": (
|
||||||
|
any(term in lowered for term in ("send", "provide", "confirm", "choose", "review", "url", "file"))
|
||||||
|
and any(term in lowered for term in ("before", "live", "apply", "write"))
|
||||||
|
),
|
||||||
|
"does_not_claim_a_database_change": not any(
|
||||||
|
term in lowered for term in ("i updated the database", "i changed the database", "now live in the database")
|
||||||
|
),
|
||||||
|
"uses_only_m3taversal_handle": re.search(r"\b(?:cory|m3ta)\b", lowered) is None,
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
async def run_canary(args: argparse.Namespace) -> dict[str, Any]:
|
||||||
|
report: dict[str, Any] = {
|
||||||
|
"schema": SCHEMA,
|
||||||
|
"generated_at_utc": bound.utc_now(),
|
||||||
|
"mode": "gcp_generated_db_gatewayrunner_blind_claim_no_send",
|
||||||
|
"source_compute": gcp.SOURCE_COMPUTE,
|
||||||
|
"target_database": args.target_db,
|
||||||
|
"prompt": PROMPT,
|
||||||
|
"posted_to_telegram": False,
|
||||||
|
"database_write_attempted": False,
|
||||||
|
"production_service_restart_attempted": False,
|
||||||
|
"errors": [],
|
||||||
|
}
|
||||||
|
before_service: dict[str, Any] = {}
|
||||||
|
before_hashes: dict[str, Any] = {}
|
||||||
|
before_identity: dict[str, Any] = {}
|
||||||
|
before_fingerprint: dict[str, Any] = {}
|
||||||
|
before_status: dict[str, Any] = {}
|
||||||
|
temp_profile: Path | None = None
|
||||||
|
bridge: dict[str, Any] = {}
|
||||||
|
provider_environment: dict[str, str] = {}
|
||||||
|
provider_secrets: tuple[str, ...] = ()
|
||||||
|
raw_gateway: dict[str, Any] = {}
|
||||||
|
database_trace: dict[str, Any] = {}
|
||||||
|
wrapper_proof: dict[str, Any] = {}
|
||||||
|
termination: bound.TerminationRequested | None = None
|
||||||
|
try:
|
||||||
|
report["reviewed_inputs"] = {
|
||||||
|
"cloudsql_tool_sha256": gcp.validate_reviewed_file(
|
||||||
|
args.cloudsql_tool,
|
||||||
|
gcp.REVIEWED_CLOUDSQL_TOOL_SHA256,
|
||||||
|
"Cloud SQL bridge helper",
|
||||||
|
),
|
||||||
|
"manifest_sql_sha256": gcp.validate_reviewed_file(
|
||||||
|
args.manifest_sql,
|
||||||
|
gcp.REVIEWED_MANIFEST_SQL_SHA256,
|
||||||
|
"Postgres parity manifest",
|
||||||
|
),
|
||||||
|
}
|
||||||
|
report["parity_receipt"] = gcp.validate_parity_receipt(args.parity_receipt, args.target_db)
|
||||||
|
before_service = gcp.service_state(args.service)
|
||||||
|
before_hashes = gcp.profile_hashes(args.live_profile)
|
||||||
|
before_identity = gcp.database_identity(args)
|
||||||
|
gcp.validate_database_identity(before_identity, args.target_db)
|
||||||
|
before_fingerprint = gcp.database_fingerprint(args)
|
||||||
|
before_status = gcp.canonical_status(args)
|
||||||
|
report["service_before"] = before_service
|
||||||
|
report["live_profile_hashes_before"] = before_hashes
|
||||||
|
report["database_identity_before"] = before_identity
|
||||||
|
report["database_fingerprint_before"] = before_fingerprint
|
||||||
|
report["canonical_status_before"] = before_status
|
||||||
|
|
||||||
|
temp_profile, copy_audit = bound.copy_profile(
|
||||||
|
run_id=args.run_id,
|
||||||
|
prompt_id=PROMPT_ID,
|
||||||
|
live_profile=args.live_profile,
|
||||||
|
)
|
||||||
|
report["temporary_profile_copy_audit"] = copy_audit
|
||||||
|
report["model_auth_binding"] = bound.copy_ephemeral_model_auth(
|
||||||
|
temp_profile,
|
||||||
|
live_profile=args.live_profile,
|
||||||
|
)
|
||||||
|
provider_environment, environment_audit = bound.load_ephemeral_provider_environment(temp_profile)
|
||||||
|
provider_secrets = tuple(provider_environment.values())
|
||||||
|
report["model_auth_binding"]["environment_binding"] = environment_audit
|
||||||
|
bridge = gcp.patch_temp_bridge(args, temp_profile)
|
||||||
|
report["temporary_bridge"] = bridge
|
||||||
|
|
||||||
|
raw_gateway = await bound.invoke_gateway_subprocess(
|
||||||
|
turn_args(args),
|
||||||
|
temp_profile,
|
||||||
|
provider_environment=provider_environment,
|
||||||
|
)
|
||||||
|
raw_events = (raw_gateway.get("transcript_tool_trace") or {}).get("events") or []
|
||||||
|
database_trace = leo_tool_trace.extract_kb_tool_trace(transcript_events_to_messages(raw_events))
|
||||||
|
raw_tool_proof = bound.read_tool_proof(
|
||||||
|
Path(bridge["tool_log_path"]),
|
||||||
|
gcp.SOURCE_COMPUTE,
|
||||||
|
args.target_db,
|
||||||
|
run_nonce=bridge["run_nonce"],
|
||||||
|
database_identity=before_identity,
|
||||||
|
require_database_read_only=True,
|
||||||
|
require_default_read_only=True,
|
||||||
|
)
|
||||||
|
wrapper_proof = summarize_wrapper_tool_proof(raw_tool_proof)
|
||||||
|
report["result"] = {
|
||||||
|
"prompt": PROMPT,
|
||||||
|
"reply": str(raw_gateway.get("reply") or ""),
|
||||||
|
"database_tool_trace": database_trace,
|
||||||
|
"gateway": sanitize_gateway(raw_gateway),
|
||||||
|
}
|
||||||
|
report["wrapper_tool_proof"] = wrapper_proof
|
||||||
|
except bound.TerminationRequested as exc:
|
||||||
|
termination = exc
|
||||||
|
report["errors"].append({"phase": "execution", "type": type(exc).__name__, "message": f"signal={exc.signum}"})
|
||||||
|
except Exception as exc:
|
||||||
|
report["errors"].append(
|
||||||
|
{"phase": "execution", "type": type(exc).__name__, "message": bound.redact_text(str(exc))}
|
||||||
|
)
|
||||||
|
finally:
|
||||||
|
provider_environment.clear()
|
||||||
|
report["gateway_child_cleanup"] = bound.cleanup_active_gateway_children()
|
||||||
|
temp_root = temp_profile.parent if temp_profile else None
|
||||||
|
report["temp_profile_removed"] = bound.remove_tree(temp_root) if not bound._ACTIVE_GATEWAY_CHILDREN else False
|
||||||
|
report["temp_profile_absent"] = bound.temp_path_absent(temp_root)
|
||||||
|
postflight = {
|
||||||
|
"service_after": lambda: gcp.service_state(args.service),
|
||||||
|
"live_profile_hashes_after": lambda: gcp.profile_hashes(args.live_profile),
|
||||||
|
}
|
||||||
|
if before_identity:
|
||||||
|
postflight["database_identity_after"] = lambda: gcp.database_identity(args)
|
||||||
|
postflight["canonical_status_after"] = lambda: gcp.canonical_status(args)
|
||||||
|
if before_fingerprint:
|
||||||
|
postflight["database_fingerprint_after"] = lambda: gcp.database_fingerprint(args)
|
||||||
|
for key, capture in postflight.items():
|
||||||
|
try:
|
||||||
|
report[key] = capture()
|
||||||
|
except BaseException as exc:
|
||||||
|
if isinstance(exc, bound.TerminationRequested) and termination is None:
|
||||||
|
termination = exc
|
||||||
|
report["errors"].append(
|
||||||
|
{"phase": key, "type": type(exc).__name__, "message": bound.redact_text(str(exc))}
|
||||||
|
)
|
||||||
|
report[key] = None
|
||||||
|
|
||||||
|
after_service = report.get("service_after") or {}
|
||||||
|
after_hashes = report.get("live_profile_hashes_after") or {}
|
||||||
|
after_identity = report.get("database_identity_after") or {}
|
||||||
|
after_fingerprint = report.get("database_fingerprint_after") or {}
|
||||||
|
after_status = report.get("canonical_status_after") or {}
|
||||||
|
reply = str((report.get("result") or {}).get("reply") or "")
|
||||||
|
subcommands, row_ids, receipt_count = trace_facts(database_trace)
|
||||||
|
outcomes = reply_outcomes(reply)
|
||||||
|
gateway_receipt = (report.get("result") or {}).get("gateway") or {}
|
||||||
|
child = gateway_receipt.get("child_process") or {}
|
||||||
|
report["checks"] = {
|
||||||
|
"exact_blind_prompt_without_ids": report.get("prompt") == PROMPT and UUID_RE.search(PROMPT) is None,
|
||||||
|
"parity_receipt_validated": bool(report.get("parity_receipt")),
|
||||||
|
"private_tls_read_only_target": (
|
||||||
|
before_identity.get("ssl") is True
|
||||||
|
and before_identity.get("transaction_read_only") == "on"
|
||||||
|
and before_identity.get("default_transaction_read_only") == "on"
|
||||||
|
),
|
||||||
|
"one_nonempty_reply": bool(reply.strip()) and raw_gateway.get("handler_error") is None,
|
||||||
|
"discovery_show_evidence_completed": (
|
||||||
|
database_trace.get("database_tool_completed_count", 0) >= 3
|
||||||
|
and subcommands >= EXPECTED_SUBCOMMANDS
|
||||||
|
and bool(subcommands & DISCOVERY_SUBCOMMANDS)
|
||||||
|
),
|
||||||
|
"retrieval_receipts_proven": (
|
||||||
|
database_trace.get("database_retrieval_receipt_proven") is True and receipt_count >= 3
|
||||||
|
),
|
||||||
|
"database_calls_read_only": database_trace.get("database_tool_calls_read_only") is True,
|
||||||
|
"claim_and_sources_retrieved": EXPECTED_CLAIM_ID in row_ids and row_ids >= EXPECTED_SOURCE_IDS,
|
||||||
|
"wrapper_calls_bound_and_successful": (
|
||||||
|
int(wrapper_proof.get("invocation_count") or 0) >= 3
|
||||||
|
and wrapper_proof.get("all_bound_to_supplied_target") is True
|
||||||
|
and wrapper_proof.get("all_completed_successfully") is True
|
||||||
|
and wrapper_proof.get("default_read_only_required") is True
|
||||||
|
),
|
||||||
|
"generated_database_unchanged": bool(before_fingerprint) and before_fingerprint == after_fingerprint,
|
||||||
|
"canonical_counts_unchanged": bool(before_status) and before_status == after_status,
|
||||||
|
"database_identity_unchanged": bool(before_identity) and before_identity == after_identity,
|
||||||
|
"live_service_unchanged": bool(before_service) and before_service == after_service,
|
||||||
|
"live_profile_unchanged": any(before_hashes.values()) and before_hashes == after_hashes,
|
||||||
|
"gateway_child_exited": (
|
||||||
|
child.get("alive_after_readback") is False and child.get("process_group_alive_after_readback") is False
|
||||||
|
),
|
||||||
|
"temporary_profile_removed": report.get("temp_profile_removed") is True
|
||||||
|
and report.get("temp_profile_absent") is True,
|
||||||
|
"no_telegram_send": raw_gateway.get("posted_to_telegram") is False
|
||||||
|
and report.get("posted_to_telegram") is False,
|
||||||
|
"no_database_write": report.get("database_write_attempted") is False,
|
||||||
|
}
|
||||||
|
report["outcomes"] = outcomes
|
||||||
|
report["status"] = (
|
||||||
|
"pass" if not report["errors"] and all(report["checks"].values()) and all(outcomes.values()) else "fail"
|
||||||
|
)
|
||||||
|
report["claim_ceiling"] = {
|
||||||
|
"proven": (
|
||||||
|
"One fresh no-send GCP GatewayRunner turn found the claim without a supplied ID, completed "
|
||||||
|
"read-only discovery/show/evidence calls against an exact generated Cloud SQL copy, challenged its "
|
||||||
|
"support, proposed candidate claims, and preserved user review before any live change."
|
||||||
|
),
|
||||||
|
"not_proven": [
|
||||||
|
"Telegram-visible delivery",
|
||||||
|
"canonical proposal apply",
|
||||||
|
"continuous VPS-to-GCP replication",
|
||||||
|
"production cutover to Cloud SQL",
|
||||||
|
],
|
||||||
|
}
|
||||||
|
report["completed_at_utc"] = bound.utc_now()
|
||||||
|
bound.write_report(args.output, report, secret_values=provider_secrets)
|
||||||
|
if termination is not None:
|
||||||
|
raise termination
|
||||||
|
return report
|
||||||
|
|
||||||
|
|
||||||
|
def parse_args(argv: list[str] | None = None) -> argparse.Namespace:
|
||||||
|
parser = argparse.ArgumentParser(description=__doc__)
|
||||||
|
parser.add_argument("--execute", action="store_true")
|
||||||
|
parser.add_argument("--target-db", required=True)
|
||||||
|
parser.add_argument("--cloudsql-tool", required=True, type=Path)
|
||||||
|
parser.add_argument("--manifest-sql", default=gcp.DEFAULT_MANIFEST_SQL, type=Path)
|
||||||
|
parser.add_argument("--parity-receipt", required=True, type=Path)
|
||||||
|
parser.add_argument("--output", required=True, type=Path)
|
||||||
|
parser.add_argument("--host", default=gcp.DEFAULT_HOST)
|
||||||
|
parser.add_argument("--project", default=gcp.DEFAULT_PROJECT)
|
||||||
|
parser.add_argument("--password-secret", default=gcp.DEFAULT_SECRET)
|
||||||
|
parser.add_argument("--service", default=gcp.DEFAULT_SERVICE)
|
||||||
|
parser.add_argument("--live-profile", default=bound.LIVE_PROFILE, type=Path)
|
||||||
|
parser.add_argument("--chat-id", default=bound.DEFAULT_CHAT_ID)
|
||||||
|
parser.add_argument("--user-id", default=bound.DEFAULT_USER_ID)
|
||||||
|
parser.add_argument("--user-name", default="codex GCP blind claim canary")
|
||||||
|
parser.add_argument("--run-id", default="gcp-blind-claim-" + uuid.uuid4().hex[:12])
|
||||||
|
parser.add_argument("--turn-timeout", default=300, type=int)
|
||||||
|
args = parser.parse_args(argv)
|
||||||
|
if not args.execute:
|
||||||
|
parser.error("--execute is required because this runs a paid no-send model call")
|
||||||
|
if not bound.SAFE_DB_NAME_RE.fullmatch(args.target_db) or not args.target_db.startswith("teleo_clone_"):
|
||||||
|
parser.error("--target-db must be a safe disposable teleo_clone_* database")
|
||||||
|
for path, flag in (
|
||||||
|
(args.cloudsql_tool, "--cloudsql-tool"),
|
||||||
|
(args.manifest_sql, "--manifest-sql"),
|
||||||
|
(args.parity_receipt, "--parity-receipt"),
|
||||||
|
):
|
||||||
|
if not path.is_file():
|
||||||
|
parser.error(f"{flag} must exist")
|
||||||
|
if not args.live_profile.is_dir():
|
||||||
|
parser.error("--live-profile must exist")
|
||||||
|
if args.turn_timeout <= 0:
|
||||||
|
parser.error("--turn-timeout must be positive")
|
||||||
|
try:
|
||||||
|
args.output = bound.validate_private_output_path(args.output)
|
||||||
|
except bound.CheckpointError as exc:
|
||||||
|
parser.error(str(exc))
|
||||||
|
return args
|
||||||
|
|
||||||
|
|
||||||
|
def main(argv: list[str] | None = None) -> int:
|
||||||
|
args = parse_args(argv)
|
||||||
|
with bound.termination_cleanup_handlers():
|
||||||
|
report = asyncio.run(run_canary(args))
|
||||||
|
print(
|
||||||
|
json.dumps(
|
||||||
|
{
|
||||||
|
"status": report.get("status"),
|
||||||
|
"checks_passed": sum(bool(value) for value in report.get("checks", {}).values()),
|
||||||
|
"checks_total": len(report.get("checks", {})),
|
||||||
|
"outcomes_passed": sum(bool(value) for value in report.get("outcomes", {}).values()),
|
||||||
|
"outcomes_total": len(report.get("outcomes", {})),
|
||||||
|
"output": str(args.output),
|
||||||
|
},
|
||||||
|
sort_keys=True,
|
||||||
|
)
|
||||||
|
)
|
||||||
|
return 0 if report.get("status") == "pass" else 1
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
raise SystemExit(main())
|
||||||
|
|
@ -23,7 +23,9 @@ GCP_HERMES_PYTHON = Path("/home/teleo/.hermes/hermes-agent/venv/bin/python")
|
||||||
|
|
||||||
|
|
||||||
def should_reexec_in_hermes(current_python: Path, target_python: Path = GCP_HERMES_PYTHON) -> bool:
|
def should_reexec_in_hermes(current_python: Path, target_python: Path = GCP_HERMES_PYTHON) -> bool:
|
||||||
return target_python.is_file() and current_python.resolve() != target_python.resolve()
|
current_path = Path(os.path.abspath(current_python))
|
||||||
|
target_path = Path(os.path.abspath(target_python))
|
||||||
|
return target_python.is_file() and current_path != target_path
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__" and should_reexec_in_hermes(Path(sys.executable)):
|
if __name__ == "__main__" and should_reexec_in_hermes(Path(sys.executable)):
|
||||||
|
|
@ -45,7 +47,7 @@ DEFAULT_HOST = "10.61.0.3"
|
||||||
DEFAULT_PROJECT = "teleo-501523"
|
DEFAULT_PROJECT = "teleo-501523"
|
||||||
DEFAULT_SECRET = "gcp-teleo-pgvector-standby-postgres-password"
|
DEFAULT_SECRET = "gcp-teleo-pgvector-standby-postgres-password"
|
||||||
DEFAULT_MANIFEST_SQL = HERE.parent / "ops" / "postgres_parity_manifest.sql"
|
DEFAULT_MANIFEST_SQL = HERE.parent / "ops" / "postgres_parity_manifest.sql"
|
||||||
REVIEWED_CLOUDSQL_TOOL_SHA256 = "f4396298405b1cbc92590e148b6272c66bb0e8461178edc3ffcfd02bfed69ab4"
|
REVIEWED_CLOUDSQL_TOOL_SHA256 = "7d2074a0fc5f0d48fbf8f7905a72ead8f2696c86a041fa43e078fff5500baa51"
|
||||||
REVIEWED_MANIFEST_SQL_SHA256 = "8b8cdc25d54fdd8de05eb38c6e4423d2836953eb6012d4545f5c9c71b5f0150a"
|
REVIEWED_MANIFEST_SQL_SHA256 = "8b8cdc25d54fdd8de05eb38c6e4423d2836953eb6012d4545f5c9c71b5f0150a"
|
||||||
COUNT_READBACK_RE = re.compile(
|
COUNT_READBACK_RE = re.compile(
|
||||||
r"DB readback:\s*claims:\s*`?(?P<claims>\d+)`?;\s*"
|
r"DB readback:\s*claims:\s*`?(?P<claims>\d+)`?;\s*"
|
||||||
|
|
@ -441,6 +443,11 @@ exit "$STATUS"
|
||||||
"""
|
"""
|
||||||
|
|
||||||
|
|
||||||
|
def normalize_stakeholder_labels(text: str) -> str:
|
||||||
|
text = re.sub(r"\bCory-style\b", "m3taversal-style", text, flags=re.IGNORECASE)
|
||||||
|
return re.sub(r"\bCory\b", "m3taversal", text, flags=re.IGNORECASE)
|
||||||
|
|
||||||
|
|
||||||
def patch_temp_bridge(args: argparse.Namespace, temp_profile: Path) -> dict[str, Any]:
|
def patch_temp_bridge(args: argparse.Namespace, temp_profile: Path) -> dict[str, Any]:
|
||||||
wrapper = temp_profile / "bin" / "teleo-kb"
|
wrapper = temp_profile / "bin" / "teleo-kb"
|
||||||
target_tool = temp_profile / "bin" / "cloudsql_memory_tool.py"
|
target_tool = temp_profile / "bin" / "cloudsql_memory_tool.py"
|
||||||
|
|
@ -487,8 +494,13 @@ but has no applied timestamp, say that approval is not application and that
|
||||||
explicit operator authorization is required before apply. When discussing the
|
explicit operator authorization is required before apply. When discussing the
|
||||||
matrix, say the conclusion comes from the fresh schema readback. When discussing
|
matrix, say the conclusion comes from the fresh schema readback. When discussing
|
||||||
identity, name the DB rows/readback needed in addition to the rendered file.
|
identity, name the DB rows/readback needed in addition to the rendered file.
|
||||||
|
|
||||||
|
For a single blind claim challenge, use at most four KB reads: one search or
|
||||||
|
context discovery, one show, one evidence, and optionally one edges call. Do not
|
||||||
|
inspect proposals or unrelated neighboring claim bodies unless the operator asks.
|
||||||
|
After those reads, answer from the retrieved rows and clearly name missing proof.
|
||||||
"""
|
"""
|
||||||
skill_text = skill.read_text(encoding="utf-8")
|
skill_text = normalize_stakeholder_labels(skill.read_text(encoding="utf-8"))
|
||||||
for live_wrapper in {
|
for live_wrapper in {
|
||||||
"/home/teleo/.hermes/profiles/leoclean/bin/teleo-kb",
|
"/home/teleo/.hermes/profiles/leoclean/bin/teleo-kb",
|
||||||
str(args.live_profile / "bin" / "teleo-kb"),
|
str(args.live_profile / "bin" / "teleo-kb"),
|
||||||
|
|
@ -668,9 +680,7 @@ async def run_suite(args: argparse.Namespace) -> dict[str, Any]:
|
||||||
)
|
)
|
||||||
except bound.TerminationRequested as exc:
|
except bound.TerminationRequested as exc:
|
||||||
termination = exc
|
termination = exc
|
||||||
report["errors"].append(
|
report["errors"].append({"phase": "execution", "type": type(exc).__name__, "message": f"signal={exc.signum}"})
|
||||||
{"phase": "execution", "type": type(exc).__name__, "message": f"signal={exc.signum}"}
|
|
||||||
)
|
|
||||||
except Exception as exc:
|
except Exception as exc:
|
||||||
report["errors"].append(
|
report["errors"].append(
|
||||||
{"phase": "execution", "type": type(exc).__name__, "message": bound.redact_text(str(exc))}
|
{"phase": "execution", "type": type(exc).__name__, "message": bound.redact_text(str(exc))}
|
||||||
|
|
@ -726,7 +736,9 @@ async def run_suite(args: argparse.Namespace) -> dict[str, Any]:
|
||||||
"gateway_adapters_absent": bool(gateways)
|
"gateway_adapters_absent": bool(gateways)
|
||||||
and all((gateway.get("tool_surface") or {}).get("gateway_adapter_count") == 0 for gateway in gateways),
|
and all((gateway.get("tool_surface") or {}).get("gateway_adapter_count") == 0 for gateway in gateways),
|
||||||
"send_message_tool_absent": bool(gateways)
|
"send_message_tool_absent": bool(gateways)
|
||||||
and all((gateway.get("tool_surface") or {}).get("send_message_tool_enabled") is False for gateway in gateways),
|
and all(
|
||||||
|
(gateway.get("tool_surface") or {}).get("send_message_tool_enabled") is False for gateway in gateways
|
||||||
|
),
|
||||||
"tool_registry_allowlisted": bool(gateways)
|
"tool_registry_allowlisted": bool(gateways)
|
||||||
and all(
|
and all(
|
||||||
set((gateway.get("tool_surface") or {}).get("actual_registry_tools") or []) == allowed_tools
|
set((gateway.get("tool_surface") or {}).get("actual_registry_tools") or []) == allowed_tools
|
||||||
|
|
@ -738,8 +750,7 @@ async def run_suite(args: argparse.Namespace) -> dict[str, Any]:
|
||||||
and (gateway.get("child_process") or {}).get("process_group_alive_after_readback") is False
|
and (gateway.get("child_process") or {}).get("process_group_alive_after_readback") is False
|
||||||
for gateway in gateways
|
for gateway in gateways
|
||||||
),
|
),
|
||||||
"generated_database_unchanged": bool(before_fingerprint)
|
"generated_database_unchanged": bool(before_fingerprint) and before_fingerprint == after_fingerprint,
|
||||||
and before_fingerprint == after_fingerprint,
|
|
||||||
"database_identity_unchanged": bool(before_identity) and before_identity == after_identity,
|
"database_identity_unchanged": bool(before_identity) and before_identity == after_identity,
|
||||||
"live_service_unchanged": bool(before_service) and before_service == after_service,
|
"live_service_unchanged": bool(before_service) and before_service == after_service,
|
||||||
"live_profile_unchanged": any(before_hashes.values()) and before_hashes == after_hashes,
|
"live_profile_unchanged": any(before_hashes.values()) and before_hashes == after_hashes,
|
||||||
|
|
|
||||||
162
tests/test_gcp_generated_db_blind_claim_canary.py
Normal file
162
tests/test_gcp_generated_db_blind_claim_canary.py
Normal file
|
|
@ -0,0 +1,162 @@
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
from scripts import leo_tool_trace
|
||||||
|
from scripts.run_gcp_generated_db_blind_claim_canary import (
|
||||||
|
DISCOVERY_SUBCOMMANDS,
|
||||||
|
EXPECTED_CLAIM_ID,
|
||||||
|
EXPECTED_SOURCE_IDS,
|
||||||
|
EXPECTED_SUBCOMMANDS,
|
||||||
|
PROMPT,
|
||||||
|
reply_outcomes,
|
||||||
|
sanitize_gateway,
|
||||||
|
should_reexec_in_hermes,
|
||||||
|
summarize_wrapper_tool_proof,
|
||||||
|
trace_facts,
|
||||||
|
transcript_events_to_messages,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def retrieval_content(*row_ids: str) -> str:
|
||||||
|
return "\n".join(
|
||||||
|
[
|
||||||
|
"schema: livingip.teleoKbRetrievalReceipt.v1",
|
||||||
|
f"semantic context SHA-256: `{'1' * 64}`",
|
||||||
|
f"artifact state SHA-256: `{'2' * 64}`",
|
||||||
|
"DB read consistency: `stable_wal_marker`",
|
||||||
|
*row_ids,
|
||||||
|
]
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def test_blind_prompt_contains_no_row_identifier() -> None:
|
||||||
|
assert EXPECTED_CLAIM_ID not in PROMPT
|
||||||
|
assert not EXPECTED_SOURCE_IDS.intersection(PROMPT.split())
|
||||||
|
|
||||||
|
|
||||||
|
def test_blind_runner_reexecs_when_venv_python_symlinks_to_system_python(tmp_path) -> None:
|
||||||
|
system_python = tmp_path / "system-python"
|
||||||
|
system_python.touch()
|
||||||
|
hermes_python = tmp_path / "hermes-python"
|
||||||
|
hermes_python.symlink_to(system_python)
|
||||||
|
|
||||||
|
assert should_reexec_in_hermes(system_python, hermes_python) is True
|
||||||
|
assert should_reexec_in_hermes(hermes_python, hermes_python) is False
|
||||||
|
|
||||||
|
|
||||||
|
def test_transcript_proves_three_receipted_read_calls_and_expected_rows() -> None:
|
||||||
|
source_ids = sorted(EXPECTED_SOURCE_IDS)
|
||||||
|
events = []
|
||||||
|
for index, (subcommand, content) in enumerate(
|
||||||
|
(
|
||||||
|
("search", retrieval_content(EXPECTED_CLAIM_ID)),
|
||||||
|
("show", retrieval_content(EXPECTED_CLAIM_ID)),
|
||||||
|
("evidence", retrieval_content(EXPECTED_CLAIM_ID, *source_ids)),
|
||||||
|
)
|
||||||
|
):
|
||||||
|
call_id = f"call-{index}"
|
||||||
|
events.extend(
|
||||||
|
[
|
||||||
|
{
|
||||||
|
"phase": "call",
|
||||||
|
"tool_call_id": call_id,
|
||||||
|
"tool_name": "terminal",
|
||||||
|
"arguments": {"command": f"teleo-kb {subcommand} query"},
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"phase": "result",
|
||||||
|
"tool_call_id": call_id,
|
||||||
|
"tool_name": "terminal",
|
||||||
|
"content": content,
|
||||||
|
},
|
||||||
|
]
|
||||||
|
)
|
||||||
|
|
||||||
|
trace = leo_tool_trace.extract_kb_tool_trace(transcript_events_to_messages(events))
|
||||||
|
subcommands, row_ids, receipt_count = trace_facts(trace)
|
||||||
|
|
||||||
|
assert subcommands >= EXPECTED_SUBCOMMANDS
|
||||||
|
assert subcommands & DISCOVERY_SUBCOMMANDS
|
||||||
|
assert EXPECTED_CLAIM_ID in row_ids
|
||||||
|
assert row_ids >= EXPECTED_SOURCE_IDS
|
||||||
|
assert receipt_count == 3
|
||||||
|
assert trace["database_tool_calls_read_only"] is True
|
||||||
|
|
||||||
|
|
||||||
|
def test_gateway_sanitization_hashes_events_without_retaining_them() -> None:
|
||||||
|
secret = "raw-secret-that-must-not-survive"
|
||||||
|
sanitized = sanitize_gateway(
|
||||||
|
{
|
||||||
|
"reply": "safe reply",
|
||||||
|
"transcript_tool_trace": {
|
||||||
|
"event_count": 1,
|
||||||
|
"events": [{"content": secret}],
|
||||||
|
},
|
||||||
|
}
|
||||||
|
)
|
||||||
|
|
||||||
|
assert sanitized["reply"] == "safe reply"
|
||||||
|
assert sanitized["transcript_tool_trace"]["event_count"] == 1
|
||||||
|
assert sanitized["transcript_tool_trace"]["raw_events_retained"] is False
|
||||||
|
assert len(sanitized["transcript_tool_trace"]["events_sha256"]) == 64
|
||||||
|
assert secret not in str(sanitized)
|
||||||
|
|
||||||
|
|
||||||
|
def test_wrapper_summary_drops_raw_arguments_but_keeps_database_binding() -> None:
|
||||||
|
secret_argument = "do-not-retain-this-query"
|
||||||
|
summarized = summarize_wrapper_tool_proof(
|
||||||
|
{
|
||||||
|
"event_count": 2,
|
||||||
|
"invocation_count": 1,
|
||||||
|
"complete_start_end_pairing": True,
|
||||||
|
"all_bound_to_supplied_target": True,
|
||||||
|
"database_read_only_required": True,
|
||||||
|
"default_read_only_required": True,
|
||||||
|
"all_completed_successfully": True,
|
||||||
|
"invocations": [
|
||||||
|
{
|
||||||
|
"argv": ["search", secret_argument],
|
||||||
|
"container": "teleo-prod-1",
|
||||||
|
"database": "teleo_clone_test",
|
||||||
|
"database_identity": {"ssl": True},
|
||||||
|
"returncode": 0,
|
||||||
|
}
|
||||||
|
],
|
||||||
|
}
|
||||||
|
)
|
||||||
|
|
||||||
|
assert summarized["invocations"][0]["subcommand"] == "search"
|
||||||
|
assert summarized["invocations"][0]["argument_count"] == 1
|
||||||
|
assert summarized["invocations"][0]["database"] == "teleo_clone_test"
|
||||||
|
assert summarized["raw_argv_retained"] is False
|
||||||
|
assert secret_argument not in str(summarized)
|
||||||
|
|
||||||
|
|
||||||
|
def test_reply_outcomes_accepts_reasoned_alternative_decomposition() -> None:
|
||||||
|
reply = """
|
||||||
|
The support is thin: the two sources do not establish the full legal conclusion.
|
||||||
|
I would split it into candidate claims about acquisition due diligence and valuation risk,
|
||||||
|
plus a separate representations and warranties claim. Please provide the filing or URL,
|
||||||
|
then review and confirm the candidates before any apply step or database write goes live.
|
||||||
|
"""
|
||||||
|
|
||||||
|
assert all(reply_outcomes(reply).values())
|
||||||
|
|
||||||
|
|
||||||
|
def test_reply_outcomes_rejects_assertion_without_decomposition_or_iteration() -> None:
|
||||||
|
reply = "The claim is weak. I propose a better claim."
|
||||||
|
|
||||||
|
outcomes = reply_outcomes(reply)
|
||||||
|
|
||||||
|
assert outcomes["challenges_weak_support"] is False
|
||||||
|
assert outcomes["decomposes_the_bundled_legal_claim"] is False
|
||||||
|
assert outcomes["asks_for_user_iteration_before_live"] is False
|
||||||
|
|
||||||
|
|
||||||
|
def test_reply_outcomes_rejects_forbidden_stakeholder_alias() -> None:
|
||||||
|
otherwise_valid = """
|
||||||
|
The evidence is thin. I propose candidate claims about acquisition due diligence and
|
||||||
|
representations and warranties. Please review the source URL before any apply step goes live.
|
||||||
|
Next Cory-style follow-up: choose the claim framing.
|
||||||
|
"""
|
||||||
|
|
||||||
|
assert reply_outcomes(otherwise_valid)["uses_only_m3taversal_handle"] is False
|
||||||
|
|
@ -16,6 +16,7 @@ from scripts.run_gcp_generated_db_direct_claim_suite import (
|
||||||
database_fingerprint,
|
database_fingerprint,
|
||||||
direct_prompts,
|
direct_prompts,
|
||||||
normalize_database_manifest_rows,
|
normalize_database_manifest_rows,
|
||||||
|
normalize_stakeholder_labels,
|
||||||
run_suite,
|
run_suite,
|
||||||
should_reexec_in_hermes,
|
should_reexec_in_hermes,
|
||||||
validate_database_identity,
|
validate_database_identity,
|
||||||
|
|
@ -49,6 +50,25 @@ def test_gcp_runner_reexecs_from_system_python_into_hermes_venv(tmp_path: Path)
|
||||||
assert str(GCP_HERMES_PYTHON) == "/home/teleo/.hermes/hermes-agent/venv/bin/python"
|
assert str(GCP_HERMES_PYTHON) == "/home/teleo/.hermes/hermes-agent/venv/bin/python"
|
||||||
|
|
||||||
|
|
||||||
|
def test_gcp_runner_reexecs_when_venv_python_symlinks_to_system_python(tmp_path: Path) -> None:
|
||||||
|
system_python = tmp_path / "system-python"
|
||||||
|
system_python.touch()
|
||||||
|
hermes_python = tmp_path / "hermes-python"
|
||||||
|
hermes_python.symlink_to(system_python)
|
||||||
|
|
||||||
|
assert should_reexec_in_hermes(system_python, hermes_python) is True
|
||||||
|
assert should_reexec_in_hermes(hermes_python, hermes_python) is False
|
||||||
|
|
||||||
|
|
||||||
|
def test_temporary_gcp_profile_removes_forbidden_stakeholder_alias() -> None:
|
||||||
|
original = "For Cory use Next Cory-style follow-up."
|
||||||
|
|
||||||
|
normalized = normalize_stakeholder_labels(original)
|
||||||
|
|
||||||
|
assert normalized == "For m3taversal use Next m3taversal-style follow-up."
|
||||||
|
assert "Cory" not in normalized
|
||||||
|
|
||||||
|
|
||||||
def test_structured_count_readback_audit_rejects_plausible_but_false_counts() -> None:
|
def test_structured_count_readback_audit_rejects_plausible_but_false_counts() -> None:
|
||||||
status = {
|
status = {
|
||||||
"high_signal_rows": {
|
"high_signal_rows": {
|
||||||
|
|
@ -63,8 +83,7 @@ def test_structured_count_readback_audit_rejects_plausible_but_false_counts() ->
|
||||||
{
|
{
|
||||||
"prompt_id": "DC-03",
|
"prompt_id": "DC-03",
|
||||||
"reply": (
|
"reply": (
|
||||||
"DB readback: claims: `0`; sources: `0`; claim_edges: `0`; "
|
"DB readback: claims: `0`; sources: `0`; claim_edges: `0`; claim_evidence: `0`; kb_proposals: `26`."
|
||||||
"claim_evidence: `0`; kb_proposals: `26`."
|
|
||||||
),
|
),
|
||||||
}
|
}
|
||||||
]
|
]
|
||||||
|
|
@ -138,12 +157,12 @@ def test_database_identity_requires_private_tls_and_read_only_target() -> None:
|
||||||
def test_manifest_normalization_excludes_nondeterministic_timing() -> None:
|
def test_manifest_normalization_excludes_nondeterministic_timing() -> None:
|
||||||
output = "\n".join(
|
output = "\n".join(
|
||||||
[
|
[
|
||||||
'BEGIN',
|
"BEGIN",
|
||||||
'{"kind":"identity","database":"teleo_clone_test","captured_at":"2026-07-12T00:00:00Z"}',
|
'{"kind":"identity","database":"teleo_clone_test","captured_at":"2026-07-12T00:00:00Z"}',
|
||||||
'{"kind":"schemas","items":["kb_stage","public"]}',
|
'{"kind":"schemas","items":["kb_stage","public"]}',
|
||||||
'{"kind":"table","schema":"public","table":"claims","row_count":2,"rowset_md5":"abc"}',
|
'{"kind":"table","schema":"public","table":"claims","row_count":2,"rowset_md5":"abc"}',
|
||||||
'{"kind":"performance","query":"count_claims","elapsed_ms":1.2,"observed_rows":2}',
|
'{"kind":"performance","query":"count_claims","elapsed_ms":1.2,"observed_rows":2}',
|
||||||
'ROLLBACK',
|
"ROLLBACK",
|
||||||
]
|
]
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
@ -191,7 +210,10 @@ def test_reviewed_helper_hashes_match_repo_files() -> None:
|
||||||
hashlib.sha256(Path("hermes-agent/leoclean-bin/cloudsql_memory_tool.py").read_bytes()).hexdigest()
|
hashlib.sha256(Path("hermes-agent/leoclean-bin/cloudsql_memory_tool.py").read_bytes()).hexdigest()
|
||||||
== REVIEWED_CLOUDSQL_TOOL_SHA256
|
== REVIEWED_CLOUDSQL_TOOL_SHA256
|
||||||
)
|
)
|
||||||
assert hashlib.sha256(Path("ops/postgres_parity_manifest.sql").read_bytes()).hexdigest() == REVIEWED_MANIFEST_SQL_SHA256
|
assert (
|
||||||
|
hashlib.sha256(Path("ops/postgres_parity_manifest.sql").read_bytes()).hexdigest()
|
||||||
|
== REVIEWED_MANIFEST_SQL_SHA256
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
def parity_payload(target_db: str = "teleo_clone_test") -> dict[str, object]:
|
def parity_payload(target_db: str = "teleo_clone_test") -> dict[str, object]:
|
||||||
|
|
@ -237,9 +259,9 @@ def test_generated_wrapper_executes_only_clone_bound_default_read_only_tool(tmp_
|
||||||
psql = fake_bin / "psql"
|
psql = fake_bin / "psql"
|
||||||
psql.write_text(
|
psql.write_text(
|
||||||
"#!/bin/sh\ncat >/dev/null\nprintf '%s\\n' "
|
"#!/bin/sh\ncat >/dev/null\nprintf '%s\\n' "
|
||||||
"'{\"current_database\":\"teleo_clone_test\",\"system_identifier\":\"system-1\","
|
'\'{"current_database":"teleo_clone_test","system_identifier":"system-1",'
|
||||||
"\"server_address\":\"10.61.0.3\",\"ssl\":true,\"transaction_read_only\":\"on\","
|
'"server_address":"10.61.0.3","ssl":true,"transaction_read_only":"on",'
|
||||||
"\"default_transaction_read_only\":\"on\"}'\n"
|
'"default_transaction_read_only":"on"}\'\n'
|
||||||
)
|
)
|
||||||
psql.chmod(0o700)
|
psql.chmod(0o700)
|
||||||
tool = tmp_path / "tool.py"
|
tool = tmp_path / "tool.py"
|
||||||
|
|
@ -313,7 +335,9 @@ def test_generated_wrapper_executes_only_clone_bound_default_read_only_tool(tmp_
|
||||||
assert unsafe_proof["all_bound_to_supplied_target"] is False
|
assert unsafe_proof["all_bound_to_supplied_target"] is False
|
||||||
|
|
||||||
|
|
||||||
def test_run_suite_retains_failure_report_when_postflight_fails(monkeypatch: pytest.MonkeyPatch, tmp_path: Path) -> None:
|
def test_run_suite_retains_failure_report_when_postflight_fails(
|
||||||
|
monkeypatch: pytest.MonkeyPatch, tmp_path: Path
|
||||||
|
) -> None:
|
||||||
output = tmp_path / "report.json"
|
output = tmp_path / "report.json"
|
||||||
placeholder = tmp_path / "placeholder"
|
placeholder = tmp_path / "placeholder"
|
||||||
placeholder.write_text("x")
|
placeholder.write_text("x")
|
||||||
|
|
|
||||||
|
|
@ -100,6 +100,175 @@ def _load_module(path: Path):
|
||||||
return module
|
return module
|
||||||
|
|
||||||
|
|
||||||
|
def test_cloudsql_reads_emit_stable_source_bound_retrieval_receipts(
|
||||||
|
monkeypatch: pytest.MonkeyPatch,
|
||||||
|
) -> None:
|
||||||
|
module = _load_module(BRIDGE_DIR / "cloudsql_memory_tool.py")
|
||||||
|
args = SimpleNamespace(
|
||||||
|
command="search",
|
||||||
|
query="AI sandbagging M&A liability",
|
||||||
|
claim_id=None,
|
||||||
|
limit=5,
|
||||||
|
context_limit=5,
|
||||||
|
)
|
||||||
|
marker = {
|
||||||
|
"database": "teleo_clone_test",
|
||||||
|
"database_user": "postgres",
|
||||||
|
"system_identifier": "system-1",
|
||||||
|
"wal_lsn": "0/123",
|
||||||
|
}
|
||||||
|
monkeypatch.setattr(module, "database_read_marker", lambda _args: dict(marker))
|
||||||
|
payload = {
|
||||||
|
"artifact": "teleo_cloudsql_canonical_kb_context",
|
||||||
|
"query": args.query,
|
||||||
|
"claims": [
|
||||||
|
{
|
||||||
|
"id": "2a7ae257-d01d-46f4-b813-63f81bb9c7c7",
|
||||||
|
"evidence": [
|
||||||
|
{
|
||||||
|
"source_id": "15740795-ecc6-40fa-9a01-3d6bc7c54f79",
|
||||||
|
"source_hash": "abc123",
|
||||||
|
"storage_path": "inbox/archive/source.md",
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"edges": [],
|
||||||
|
}
|
||||||
|
],
|
||||||
|
}
|
||||||
|
|
||||||
|
result = module.read_with_retrieval_receipt(args, lambda: json.loads(json.dumps(payload)))
|
||||||
|
receipt = result["retrieval_receipt"]
|
||||||
|
|
||||||
|
assert receipt["schema"] == "livingip.teleoKbRetrievalReceipt.v1"
|
||||||
|
assert receipt["claim_ids"] == ["2a7ae257-d01d-46f4-b813-63f81bb9c7c7"]
|
||||||
|
assert receipt["source_ids"] == ["15740795-ecc6-40fa-9a01-3d6bc7c54f79"]
|
||||||
|
assert receipt["read_consistency"]["status"] == "stable_wal_marker"
|
||||||
|
rebuilt = module.build_retrieval_receipt(
|
||||||
|
payload,
|
||||||
|
query_descriptor=module.receipt_query_descriptor(args),
|
||||||
|
before=marker,
|
||||||
|
after=marker,
|
||||||
|
attempts=1,
|
||||||
|
consistency_status="stable_wal_marker",
|
||||||
|
)
|
||||||
|
assert rebuilt["semantic_context_sha256"] == receipt["semantic_context_sha256"]
|
||||||
|
assert rebuilt["artifact_state_sha256"] == receipt["artifact_state_sha256"]
|
||||||
|
|
||||||
|
|
||||||
|
def test_cloudsql_evidence_rows_include_source_identity_and_hash(
|
||||||
|
monkeypatch: pytest.MonkeyPatch,
|
||||||
|
) -> None:
|
||||||
|
module = _load_module(BRIDGE_DIR / "cloudsql_memory_tool.py")
|
||||||
|
captured = {}
|
||||||
|
|
||||||
|
def fake_query(_args, sql, db=None):
|
||||||
|
captured.update(sql=sql, db=db)
|
||||||
|
return []
|
||||||
|
|
||||||
|
monkeypatch.setattr(module, "psql_json_lines", fake_query)
|
||||||
|
args = SimpleNamespace(canonical_db="teleo_clone_test", include_excerpts=False, redacted=False)
|
||||||
|
|
||||||
|
assert module.canonical_evidence(args, "2a7ae257-d01d-46f4-b813-63f81bb9c7c7", 8) == []
|
||||||
|
assert "s.id as source_id" in captured["sql"]
|
||||||
|
assert "s.hash as source_hash" in captured["sql"]
|
||||||
|
assert "'source_id', source_id::text" in captured["sql"]
|
||||||
|
assert "'source_hash', source_hash" in captured["sql"]
|
||||||
|
assert captured["db"] == "teleo_clone_test"
|
||||||
|
|
||||||
|
|
||||||
|
def test_cloudsql_markdown_prints_retrieval_receipt_before_claim_context() -> None:
|
||||||
|
module = _load_module(BRIDGE_DIR / "cloudsql_memory_tool.py")
|
||||||
|
value = {
|
||||||
|
"artifact": "teleo_cloudsql_canonical_kb_context",
|
||||||
|
"backend": "cloudsql:test",
|
||||||
|
"query": "test",
|
||||||
|
"terms": ["test"],
|
||||||
|
"privacy": "redacted",
|
||||||
|
"claims": [],
|
||||||
|
"context_rows": [],
|
||||||
|
"retrieval_receipt": {
|
||||||
|
"schema": "livingip.teleoKbRetrievalReceipt.v1",
|
||||||
|
"semantic_context_sha256": "a" * 64,
|
||||||
|
"artifact_state_sha256": "b" * 64,
|
||||||
|
"read_consistency": {"status": "stable_wal_marker", "attempts": 1},
|
||||||
|
},
|
||||||
|
}
|
||||||
|
output = io.StringIO()
|
||||||
|
|
||||||
|
with contextlib.redirect_stdout(output):
|
||||||
|
module.emit_markdown(value)
|
||||||
|
|
||||||
|
text = output.getvalue()
|
||||||
|
assert text.index("# Teleo KB Retrieval Receipt") < text.index("# Teleo KB Context")
|
||||||
|
assert "semantic context SHA-256" in text
|
||||||
|
assert "artifact state SHA-256" in text
|
||||||
|
assert "DB read consistency: `stable_wal_marker`" in text
|
||||||
|
|
||||||
|
|
||||||
|
def test_cloudsql_all_read_commands_are_receipted() -> None:
|
||||||
|
module = _load_module(BRIDGE_DIR / "cloudsql_memory_tool.py")
|
||||||
|
|
||||||
|
expected = {
|
||||||
|
"search",
|
||||||
|
"context",
|
||||||
|
"show",
|
||||||
|
"evidence",
|
||||||
|
"edges",
|
||||||
|
"status",
|
||||||
|
"list-proposals",
|
||||||
|
"search-proposals",
|
||||||
|
"show-proposal",
|
||||||
|
"decision-matrix-status",
|
||||||
|
}
|
||||||
|
assert expected == module.RECEIPTED_READ_COMMANDS
|
||||||
|
|
||||||
|
|
||||||
|
def test_cloudsql_status_works_without_optional_audit_fallback(monkeypatch) -> None:
|
||||||
|
module = _load_module(BRIDGE_DIR / "cloudsql_memory_tool.py")
|
||||||
|
canonical = {
|
||||||
|
"db_identity": "teleo_clone_test|postgres",
|
||||||
|
"extensions": ["plpgsql"],
|
||||||
|
"schema_tables": {"kb_stage": 15, "public": 32},
|
||||||
|
"high_signal_rows": {"claims": 1837, "sources": 4145, "kb_proposals": 29},
|
||||||
|
}
|
||||||
|
calls = []
|
||||||
|
|
||||||
|
def fake_run_psql(_args, sql, db=None):
|
||||||
|
calls.append((sql, db))
|
||||||
|
if "json_build_object" in sql:
|
||||||
|
return json.dumps(canonical)
|
||||||
|
if "to_regclass" in sql:
|
||||||
|
return "f\n"
|
||||||
|
raise AssertionError(sql)
|
||||||
|
|
||||||
|
monkeypatch.setattr(module, "run_psql", fake_run_psql)
|
||||||
|
args = SimpleNamespace(db="teleo_clone_test", canonical_db="teleo_clone_test")
|
||||||
|
|
||||||
|
result = module.status(args)
|
||||||
|
|
||||||
|
assert result["canonical"] == canonical
|
||||||
|
assert result["audit_fallback_available"] is False
|
||||||
|
assert result["teleo_restore_tables"] == 0
|
||||||
|
assert all("teleo_restore.response_audit" not in sql or "to_regclass" in sql for sql, _db in calls)
|
||||||
|
|
||||||
|
|
||||||
|
def test_cloudsql_zero_hit_search_stays_canonical_when_audit_is_unavailable(monkeypatch) -> None:
|
||||||
|
module = _load_module(BRIDGE_DIR / "cloudsql_memory_tool.py")
|
||||||
|
canonical = {"artifact": "teleo_cloudsql_canonical_kb_context", "hit_count_total": 0, "hits": []}
|
||||||
|
monkeypatch.setattr(module, "query_canonical_rows", lambda *_args: canonical.copy())
|
||||||
|
monkeypatch.setattr(module, "audit_restore_available", lambda _args: False)
|
||||||
|
monkeypatch.setattr(
|
||||||
|
module,
|
||||||
|
"query_audit_rows",
|
||||||
|
lambda *_args: (_ for _ in ()).throw(AssertionError("audit fallback must not run")),
|
||||||
|
)
|
||||||
|
|
||||||
|
result = module.query_rows(SimpleNamespace(), "unseen query", 8)
|
||||||
|
|
||||||
|
assert result["hits"] == []
|
||||||
|
assert "audit fallback unavailable" in result["canonical_fallback_reason"]
|
||||||
|
|
||||||
|
|
||||||
def test_vps_bridge_verifies_relative_source_artifact_against_canonical_hash(tmp_path: Path) -> None:
|
def test_vps_bridge_verifies_relative_source_artifact_against_canonical_hash(tmp_path: Path) -> None:
|
||||||
module = _load_module(BRIDGE_DIR / "kb_tool.py")
|
module = _load_module(BRIDGE_DIR / "kb_tool.py")
|
||||||
root = tmp_path / "workspace"
|
root = tmp_path / "workspace"
|
||||||
|
|
|
||||||
|
|
@ -9,9 +9,7 @@ MANIFEST = REPORT_DIR / "skill-pack-manifest.json"
|
||||||
|
|
||||||
|
|
||||||
def _skill(name: str) -> str:
|
def _skill(name: str) -> str:
|
||||||
return (ROOT / ".agents" / "skills" / name / "SKILL.md").read_text(
|
return (ROOT / ".agents" / "skills" / name / "SKILL.md").read_text(encoding="utf-8")
|
||||||
encoding="utf-8"
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
def test_manifest_indexes_valid_repo_native_skills() -> None:
|
def test_manifest_indexes_valid_repo_native_skills() -> None:
|
||||||
|
|
@ -72,16 +70,19 @@ def test_gcp_skill_uses_current_operator_access_and_parity_truth() -> None:
|
||||||
"PostgreSQL 16.14",
|
"PostgreSQL 16.14",
|
||||||
"public IP disabled",
|
"public IP disabled",
|
||||||
"39/39",
|
"39/39",
|
||||||
"52,164/52,164",
|
"52,167/52,167",
|
||||||
"PID `148735`",
|
"`148735`, `NRestarts=0`",
|
||||||
"NRestarts=0",
|
"NRestarts=0",
|
||||||
"state.db",
|
"state.db",
|
||||||
"leoclean-cloudsql-memory-sync.service",
|
"leoclean-cloudsql-memory-sync.service",
|
||||||
"gcp-canonical-parity-live-20260712.json",
|
"gcp-db-first-restore-current.json",
|
||||||
"gcp-cory-model-replay-current.json",
|
"gcp-db-first-parity-current.json",
|
||||||
"gcp-operator-access-blocker-current.json",
|
"gcp-db-first-blind-claim-current.json",
|
||||||
|
"gcp-db-first-cleanup-current.json",
|
||||||
|
"18/18",
|
||||||
|
"6/6",
|
||||||
"invalid_target",
|
"invalid_target",
|
||||||
"rejected",
|
"older staging copy",
|
||||||
):
|
):
|
||||||
assert required in text
|
assert required in text
|
||||||
|
|
||||||
|
|
@ -105,10 +106,11 @@ def test_vps_onboarding_and_m3taversal_skills_point_to_current_proof() -> None:
|
||||||
assert "/opt/teleo-eval/.last-deploy-sha" in provenance
|
assert "/opt/teleo-eval/.last-deploy-sha" in provenance
|
||||||
assert "does not prove a gateway restart" in " ".join(provenance.split())
|
assert "does not prove a gateway restart" in " ".join(provenance.split())
|
||||||
assert "gcp-cloud-sql-t3-live-readonly-current.md" in onboarding
|
assert "gcp-cloud-sql-t3-live-readonly-current.md" in onboarding
|
||||||
assert "gcp-canonical-parity-live-20260712.json" in onboarding
|
assert "gcp-db-first-working-leo-20260714.md" in onboarding
|
||||||
assert "gcp-cory-model-replay-current.json" in onboarding
|
assert "gcp-db-first-parity-current.json" in onboarding
|
||||||
assert "working-leo-current-proof-20260712.md" in onboarding
|
assert "gcp-db-first-blind-claim-current.json" in onboarding
|
||||||
assert "ssh teleo-gcp-staging" in onboarding
|
assert "gcp-db-first-cleanup-current.json" in onboarding
|
||||||
|
assert "ssh -o BatchMode=yes teleo-gcp-staging true" in onboarding
|
||||||
assert "37/37" in outcomes
|
assert "37/37" in outcomes
|
||||||
assert "Approved is not the same as applied" in outcomes
|
assert "Approved is not the same as applied" in outcomes
|
||||||
assert "Address `@m3taversal` only as `m3taversal`, exactly" in outcomes
|
assert "Address `@m3taversal` only as `m3taversal`, exactly" in outcomes
|
||||||
|
|
|
||||||
374
tests/test_restore_gcp_generated_postgres_snapshot.py
Normal file
374
tests/test_restore_gcp_generated_postgres_snapshot.py
Normal file
|
|
@ -0,0 +1,374 @@
|
||||||
|
import argparse
|
||||||
|
import hashlib
|
||||||
|
import json
|
||||||
|
import subprocess
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
import pytest
|
||||||
|
|
||||||
|
from ops import restore_gcp_generated_postgres_snapshot as restore
|
||||||
|
|
||||||
|
SERVICE_STATE = {
|
||||||
|
"ActiveState": "active",
|
||||||
|
"SubState": "running",
|
||||||
|
"MainPID": "148735",
|
||||||
|
"NRestarts": "0",
|
||||||
|
"ExecMainStartTimestamp": "Thu 2026-07-09 07:00:04 UTC",
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
def manifest_rows(database: str, *, target: bool, row_count: int = 1) -> list[dict]:
|
||||||
|
identity = {
|
||||||
|
"kind": "identity",
|
||||||
|
"database": database,
|
||||||
|
"server_version_num": 160014,
|
||||||
|
"transaction_read_only": "on",
|
||||||
|
"server_address": "10.61.0.3" if target else None,
|
||||||
|
"server_port": 5432 if target else None,
|
||||||
|
"ssl": target,
|
||||||
|
"ssl_version": "TLSv1.3" if target else None,
|
||||||
|
"database_collation": "en_US.UTF8" if target else "en_US.utf8",
|
||||||
|
"database_ctype": "en_US.UTF8" if target else "en_US.utf8",
|
||||||
|
"server_encoding": "UTF8",
|
||||||
|
}
|
||||||
|
rows = [
|
||||||
|
identity,
|
||||||
|
{"kind": "schemas", "items": ["kb_stage", "public"]},
|
||||||
|
{"kind": "extensions", "items": [{"name": "pgcrypto", "version": "1.3"}]},
|
||||||
|
{
|
||||||
|
"kind": "application_roles",
|
||||||
|
"items": [
|
||||||
|
{
|
||||||
|
"name": "kb_apply",
|
||||||
|
"can_login": True,
|
||||||
|
"superuser": False,
|
||||||
|
"create_db": False,
|
||||||
|
"create_role": False,
|
||||||
|
"inherit": True,
|
||||||
|
"replication": False,
|
||||||
|
"bypass_rls": False,
|
||||||
|
}
|
||||||
|
],
|
||||||
|
},
|
||||||
|
]
|
||||||
|
rows.extend(
|
||||||
|
{"kind": kind, "items": []}
|
||||||
|
for kind in (
|
||||||
|
"columns",
|
||||||
|
"constraints",
|
||||||
|
"indexes",
|
||||||
|
"sequences",
|
||||||
|
"views",
|
||||||
|
"functions",
|
||||||
|
"triggers",
|
||||||
|
"types",
|
||||||
|
"policies",
|
||||||
|
)
|
||||||
|
)
|
||||||
|
rows.extend(
|
||||||
|
[
|
||||||
|
{
|
||||||
|
"kind": "table",
|
||||||
|
"schema": "public",
|
||||||
|
"table": "claims",
|
||||||
|
"row_count": row_count,
|
||||||
|
"rowset_md5": "same" if row_count == 1 else "different",
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"kind": "performance",
|
||||||
|
"query": "count_claims",
|
||||||
|
"elapsed_ms": 1.0,
|
||||||
|
"observed_rows": row_count,
|
||||||
|
},
|
||||||
|
]
|
||||||
|
)
|
||||||
|
return rows
|
||||||
|
|
||||||
|
|
||||||
|
def manifest_text(database: str, *, target: bool, row_count: int = 1) -> str:
|
||||||
|
return "".join(json.dumps(row) + "\n" for row in manifest_rows(database, target=target, row_count=row_count))
|
||||||
|
|
||||||
|
|
||||||
|
def args_for(tmp_path: Path, **overrides) -> argparse.Namespace:
|
||||||
|
dump = tmp_path / "teleo-canonical.dump"
|
||||||
|
dump.write_bytes(b"PGDMPfixture")
|
||||||
|
source_manifest = tmp_path / "source-manifest.jsonl"
|
||||||
|
source_manifest.write_text(manifest_text("teleo", target=False), encoding="utf-8")
|
||||||
|
values = {
|
||||||
|
"operation": "restore",
|
||||||
|
"execute": True,
|
||||||
|
"target_db": "teleo_clone_dbfirst_test",
|
||||||
|
"run_id": "gcp-restore-test12345",
|
||||||
|
"host": restore.DEFAULT_HOST,
|
||||||
|
"project": restore.DEFAULT_PROJECT,
|
||||||
|
"password_secret": restore.DEFAULT_SECRET,
|
||||||
|
"service": restore.DEFAULT_SERVICE,
|
||||||
|
"command_timeout": 2.0,
|
||||||
|
"psql_bin": "psql",
|
||||||
|
"run_root": tmp_path / "runs",
|
||||||
|
"dump": dump,
|
||||||
|
"expected_dump_sha256": hashlib.sha256(dump.read_bytes()).hexdigest(),
|
||||||
|
"source_manifest": source_manifest,
|
||||||
|
"manifest_sql": Path("ops/postgres_parity_manifest.sql").resolve(),
|
||||||
|
"pg_restore_bin": "pg_restore",
|
||||||
|
"restore_timeout": 5.0,
|
||||||
|
"manifest_timeout": 5.0,
|
||||||
|
"max_target_query_ms": 2000.0,
|
||||||
|
"max_target_source_ratio": 20.0,
|
||||||
|
}
|
||||||
|
values.update(overrides)
|
||||||
|
return argparse.Namespace(**values)
|
||||||
|
|
||||||
|
|
||||||
|
def install_restore_fakes(
|
||||||
|
monkeypatch: pytest.MonkeyPatch,
|
||||||
|
*,
|
||||||
|
target_manifest: str,
|
||||||
|
) -> dict[str, bool]:
|
||||||
|
state = {"exists": False, "dropped": False}
|
||||||
|
monkeypatch.setattr(restore.os, "geteuid", lambda: 0)
|
||||||
|
monkeypatch.setattr(restore, "service_state", lambda *_args, **_kwargs: dict(SERVICE_STATE))
|
||||||
|
monkeypatch.setattr(restore, "resolve_password", lambda *_args, **_kwargs: "private-password")
|
||||||
|
monkeypatch.setattr(
|
||||||
|
restore,
|
||||||
|
"validate_pg_restore_version",
|
||||||
|
lambda *_args, **_kwargs: {
|
||||||
|
"pg_restore_bin": "pg_restore",
|
||||||
|
"pg_restore_version": "pg_restore (PostgreSQL) 16.14",
|
||||||
|
"pg_restore_major": 16,
|
||||||
|
"source_postgres_major": 16,
|
||||||
|
"compatible": True,
|
||||||
|
},
|
||||||
|
)
|
||||||
|
monkeypatch.setattr(restore, "database_exists", lambda *_args, **_kwargs: state["exists"])
|
||||||
|
|
||||||
|
def fake_create(*_args, **_kwargs):
|
||||||
|
state["exists"] = True
|
||||||
|
|
||||||
|
def fake_drop(*_args, **_kwargs):
|
||||||
|
existed = state["exists"]
|
||||||
|
state["exists"] = False
|
||||||
|
state["dropped"] = True
|
||||||
|
return {"existed_before": existed, "clone_database_remaining": 0}
|
||||||
|
|
||||||
|
monkeypatch.setattr(restore, "create_database", fake_create)
|
||||||
|
monkeypatch.setattr(restore, "restore_dump", lambda *_args, **_kwargs: None)
|
||||||
|
monkeypatch.setattr(restore, "capture_target_manifest", lambda *_args, **_kwargs: target_manifest)
|
||||||
|
monkeypatch.setattr(
|
||||||
|
restore,
|
||||||
|
"rollback_database_state",
|
||||||
|
lambda *_args, **_kwargs: {"exists": True, "datallowconn": False, "connections": 0},
|
||||||
|
)
|
||||||
|
monkeypatch.setattr(restore, "drop_clone", fake_drop)
|
||||||
|
return state
|
||||||
|
|
||||||
|
|
||||||
|
def test_restore_success_retains_only_exact_parity_clone(
|
||||||
|
tmp_path: Path,
|
||||||
|
monkeypatch: pytest.MonkeyPatch,
|
||||||
|
) -> None:
|
||||||
|
args = args_for(tmp_path)
|
||||||
|
state = install_restore_fakes(
|
||||||
|
monkeypatch,
|
||||||
|
target_manifest=manifest_text(args.target_db, target=True),
|
||||||
|
)
|
||||||
|
|
||||||
|
result = restore.run_restore(args)
|
||||||
|
|
||||||
|
assert result["status"] == "pass"
|
||||||
|
assert result["phase"] == "retained_for_no_send_replay"
|
||||||
|
assert result["parity"]["problems"] == []
|
||||||
|
assert result["parity"]["details"]["source_total_rows"] == 1
|
||||||
|
assert result["target"]["connectivity"]["private_connectivity"] is True
|
||||||
|
assert result["target"]["connectivity"]["ssl"] is True
|
||||||
|
assert result["live_service"]["unchanged"] is True
|
||||||
|
assert result["cleanup"]["clone_database_remaining"] == 1
|
||||||
|
assert state == {"exists": True, "dropped": False}
|
||||||
|
run_dir = args.run_root / args.run_id
|
||||||
|
assert (run_dir / "target-manifest.jsonl").stat().st_mode & 0o777 == 0o600
|
||||||
|
assert (run_dir / "restore-receipt.json").stat().st_mode & 0o777 == 0o600
|
||||||
|
|
||||||
|
|
||||||
|
def test_parity_failure_drops_generated_clone_and_receipts_both_failures(
|
||||||
|
tmp_path: Path,
|
||||||
|
monkeypatch: pytest.MonkeyPatch,
|
||||||
|
) -> None:
|
||||||
|
args = args_for(tmp_path)
|
||||||
|
state = install_restore_fakes(
|
||||||
|
monkeypatch,
|
||||||
|
target_manifest=manifest_text(args.target_db, target=True, row_count=2),
|
||||||
|
)
|
||||||
|
|
||||||
|
result = restore.run_restore(args)
|
||||||
|
|
||||||
|
assert result["status"] == "fail"
|
||||||
|
assert result["error"]["phase"] == "parity_compare"
|
||||||
|
assert result["parity"]["problems"] == ["table_content_mismatches=1"]
|
||||||
|
assert result["cleanup"]["attempted"] is True
|
||||||
|
assert result["cleanup"]["clone_database_remaining"] == 0
|
||||||
|
assert state == {"exists": False, "dropped": True}
|
||||||
|
|
||||||
|
|
||||||
|
def test_create_command_failure_still_drops_a_committed_clone(
|
||||||
|
tmp_path: Path,
|
||||||
|
monkeypatch: pytest.MonkeyPatch,
|
||||||
|
) -> None:
|
||||||
|
args = args_for(tmp_path)
|
||||||
|
state = install_restore_fakes(
|
||||||
|
monkeypatch,
|
||||||
|
target_manifest=manifest_text(args.target_db, target=True),
|
||||||
|
)
|
||||||
|
|
||||||
|
def committed_then_failed(*_args, **_kwargs):
|
||||||
|
state["exists"] = True
|
||||||
|
raise restore.RestoreError("connection dropped after create committed")
|
||||||
|
|
||||||
|
monkeypatch.setattr(restore, "create_database", committed_then_failed)
|
||||||
|
|
||||||
|
result = restore.run_restore(args)
|
||||||
|
|
||||||
|
assert result["status"] == "fail"
|
||||||
|
assert result["error"]["phase"] == "database_create"
|
||||||
|
assert result["cleanup"]["attempted"] is True
|
||||||
|
assert result["cleanup"]["clone_database_remaining"] == 0
|
||||||
|
assert state == {"exists": False, "dropped": True}
|
||||||
|
|
||||||
|
|
||||||
|
def test_changed_live_service_turns_successful_restore_into_cleanup(
|
||||||
|
tmp_path: Path,
|
||||||
|
monkeypatch: pytest.MonkeyPatch,
|
||||||
|
) -> None:
|
||||||
|
args = args_for(tmp_path)
|
||||||
|
state = install_restore_fakes(
|
||||||
|
monkeypatch,
|
||||||
|
target_manifest=manifest_text(args.target_db, target=True),
|
||||||
|
)
|
||||||
|
calls = 0
|
||||||
|
|
||||||
|
def changing_service(*_args, **_kwargs):
|
||||||
|
nonlocal calls
|
||||||
|
calls += 1
|
||||||
|
result = dict(SERVICE_STATE)
|
||||||
|
if calls > 1:
|
||||||
|
result["NRestarts"] = "1"
|
||||||
|
return result
|
||||||
|
|
||||||
|
monkeypatch.setattr(restore, "service_state", changing_service)
|
||||||
|
|
||||||
|
result = restore.run_restore(args)
|
||||||
|
|
||||||
|
assert result["status"] == "fail"
|
||||||
|
assert result["error"]["phase"] == "service_and_rollback_readback"
|
||||||
|
assert result["live_service"]["unchanged"] is False
|
||||||
|
assert result["cleanup"]["clone_database_remaining"] == 0
|
||||||
|
assert state["dropped"] is True
|
||||||
|
|
||||||
|
|
||||||
|
def test_cleanup_is_bound_to_passing_restore_receipt(
|
||||||
|
tmp_path: Path,
|
||||||
|
monkeypatch: pytest.MonkeyPatch,
|
||||||
|
) -> None:
|
||||||
|
args = args_for(tmp_path)
|
||||||
|
state = install_restore_fakes(
|
||||||
|
monkeypatch,
|
||||||
|
target_manifest=manifest_text(args.target_db, target=True),
|
||||||
|
)
|
||||||
|
assert restore.run_restore(args)["status"] == "pass"
|
||||||
|
|
||||||
|
cleanup_args = argparse.Namespace(
|
||||||
|
**{
|
||||||
|
key: getattr(args, key)
|
||||||
|
for key in (
|
||||||
|
"target_db",
|
||||||
|
"run_id",
|
||||||
|
"host",
|
||||||
|
"project",
|
||||||
|
"password_secret",
|
||||||
|
"service",
|
||||||
|
"command_timeout",
|
||||||
|
"psql_bin",
|
||||||
|
"run_root",
|
||||||
|
)
|
||||||
|
},
|
||||||
|
operation="cleanup",
|
||||||
|
execute=True,
|
||||||
|
)
|
||||||
|
result = restore.run_cleanup(cleanup_args)
|
||||||
|
|
||||||
|
assert result["status"] == "pass"
|
||||||
|
assert result["database"] == {"existed_before": True, "clone_database_remaining": 0}
|
||||||
|
assert result["rollback_database"] == {"exists": True, "datallowconn": False, "connections": 0}
|
||||||
|
assert result["live_service"]["unchanged"] is True
|
||||||
|
assert state == {"exists": False, "dropped": True}
|
||||||
|
|
||||||
|
|
||||||
|
def test_restore_dump_uses_tls_no_owner_no_acl_and_keeps_secret_out_of_argv(
|
||||||
|
tmp_path: Path,
|
||||||
|
monkeypatch: pytest.MonkeyPatch,
|
||||||
|
) -> None:
|
||||||
|
args = args_for(tmp_path)
|
||||||
|
captured = {}
|
||||||
|
|
||||||
|
def fake_run(command, *, timeout, env=None, input_text=None):
|
||||||
|
captured.update(command=command, timeout=timeout, env=env, input_text=input_text)
|
||||||
|
return subprocess.CompletedProcess(command, 0, "", "")
|
||||||
|
|
||||||
|
monkeypatch.setattr(restore, "_run", fake_run)
|
||||||
|
restore.restore_dump(args, "private-password")
|
||||||
|
|
||||||
|
assert captured["command"][0] == "pg_restore"
|
||||||
|
assert captured["command"][1] == "-d"
|
||||||
|
assert "sslmode=require" in captured["command"][2]
|
||||||
|
assert "--no-owner" in captured["command"]
|
||||||
|
assert "--no-acl" in captured["command"]
|
||||||
|
assert "--exit-on-error" in captured["command"]
|
||||||
|
assert all("private-password" not in argument for argument in captured["command"])
|
||||||
|
assert captured["env"]["PGPASSWORD"] == "private-password"
|
||||||
|
|
||||||
|
|
||||||
|
def test_pg_restore_preflight_rejects_client_older_than_snapshot(
|
||||||
|
tmp_path: Path,
|
||||||
|
monkeypatch: pytest.MonkeyPatch,
|
||||||
|
) -> None:
|
||||||
|
manifest_path = tmp_path / "source.jsonl"
|
||||||
|
manifest_path.write_text(manifest_text("teleo", target=False), encoding="utf-8")
|
||||||
|
source_manifest = restore.load_manifest(manifest_path)
|
||||||
|
|
||||||
|
def fake_run(command, *, timeout, env=None, input_text=None):
|
||||||
|
assert command == ["pg_restore", "--version"]
|
||||||
|
assert timeout > 0
|
||||||
|
assert env is None
|
||||||
|
assert input_text is None
|
||||||
|
return subprocess.CompletedProcess(command, 0, "pg_restore (PostgreSQL) 15.18\n", "")
|
||||||
|
|
||||||
|
monkeypatch.setattr(restore, "_run", fake_run)
|
||||||
|
with pytest.raises(restore.RestoreError, match="major 15 is older than source PostgreSQL major 16"):
|
||||||
|
restore.validate_pg_restore_version("pg_restore", source_manifest, timeout=2.0)
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.parametrize("target", ["teleo_canonical", "teleo_clone_UPPER", "other_clone_test"])
|
||||||
|
def test_parse_args_rejects_non_disposable_target(target: str) -> None:
|
||||||
|
with pytest.raises(SystemExit):
|
||||||
|
restore.parse_args(
|
||||||
|
[
|
||||||
|
"cleanup",
|
||||||
|
"--execute",
|
||||||
|
"--target-db",
|
||||||
|
target,
|
||||||
|
"--run-id",
|
||||||
|
"gcp-restore-test12345",
|
||||||
|
]
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def test_parse_args_requires_explicit_execute() -> None:
|
||||||
|
with pytest.raises(SystemExit):
|
||||||
|
restore.parse_args(
|
||||||
|
[
|
||||||
|
"cleanup",
|
||||||
|
"--target-db",
|
||||||
|
"teleo_clone_test",
|
||||||
|
"--run-id",
|
||||||
|
"gcp-restore-test12345",
|
||||||
|
]
|
||||||
|
)
|
||||||
Loading…
Reference in a new issue