teleo/teleo-infrastructure
8
0
Fork 0
Code Issues Pull requests 1 Projects Releases Packages Wiki Activity Actions 1

Merge pull request #106 from living-ip/codex/leo-broad-answer-contract-20260713
Some checks are pending
CI / lint-and-test (push) Waiting to run
Details

Browse source 
Keep Working Leo replies concise by default
This commit is contained in:
twentyOne2x 2026-07-13 11:10:49 +02:00 committed by GitHub
commit c20db7f414
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 1139 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

267
docs/reports/leo-working-state-20260709/telegram-handler-m3taversal-oos-suite-pre-concision-repair-20260713.json Normal file
View file

File diff suppressed because one or more lines are too long

792
docs/reports/leo-working-state-20260709/telegram-handler-m3taversal-oos-suite-score-pre-concision-repair-20260713.json Normal file
View file

@ -0,0 +1,792 @@
{
"db_counts_changed": false,
"generated_at_utc": "2026-07-13T09:01:32.681980+00:00",
"memory_token": "demo-ledger-fd596d14",
"mode": "working_leo_m3taversal_out_of_sample_live_vps_handler_score",
"posted_to_telegram": false,
"production_db_apply_ran": false,
"score": {
"expected_prompt_count": 15,
"expected_prompt_ids": [
"OOS-01",
"OOS-02",
"OOS-03",
"OOS-04",
"OOS-05",
"OOS-06",
"OOS-07",
"OOS-08",
"OOS-09",
"OOS-10",
"OOS-11",
"OOS-12",
"OOS-13",
"OOS-14",
"OOS-15"
],
"failures": [
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"canonical_readback": true,
"live_check": true,
"material_action": false,
"state_boundary": true
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "demo_pressure_without_ids",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"canonical_db": true,
"fresh_readback": false,
"next_action": true,
"no_overclaim": false,
"state_semantics": true
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-01",
"response_issue_detected": false,
"response_too_long": false,
"source_evidence_semantic_issues": [],
"word_count": 228
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"contradiction": true,
"deduplication": true,
"provenance": true,
"receipt": true,
"staged_review_apply": true
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "multi_surface_knowledge_ingestion",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"canonical_db": true,
"caveat_retention": false,
"document_artifact_linking": true,
"next_action": true,
"no_overclaim": true,
"staging_or_review": false
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-02",
"response_issue_detected": false,
"response_too_long": true,
"source_evidence_semantic_issues": [],
"word_count": 806
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"identity_chain": true,
"receipt": true,
"state_boundary": true
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "identity_restart_truth",
"invalid_count_invariant_detected": false,
"legacy_pass": true,
"legacy_signals": {
"canonical_db": true,
"identity_rendering": true,
"no_overclaim": true,
"row_level_proof": true
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-03",
"response_issue_detected": false,
"response_too_long": true,
"source_evidence_semantic_issues": [],
"word_count": 752
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"canonical_evidence_boundary": true,
"evidence_provenance_quality": true,
"receipt": true,
"source_evidence_chain": true,
"staged_review_apply": true
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "source_pointer_needs_canonical_link_audit",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"canonical_db": true,
"document_artifact_linking": true,
"no_overclaim": true,
"row_level_proof": true,
"staging_or_review": false
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-05",
"response_issue_detected": false,
"response_too_long": true,
"source_evidence_semantic_issues": [],
"word_count": 735
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"behavioral_rule_storage": true,
"heterogeneous_types": true,
"receipt": true,
"reviewed_policy_apply": false,
"staged_review_apply": true
},
"current_schema_overclaims": [
"reasoning_tools_unshipped_fields",
"sources_unshipped_fields"
],
"custom_signals": {},
"dimension": "database_composition_judgment",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"canonical_db": true,
"caveat_retention": false,
"next_action": true,
"no_overclaim": true,
"staging_or_review": true
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-06",
"response_issue_detected": false,
"response_too_long": true,
"source_evidence_semantic_issues": [],
"word_count": 1136
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"durable_session_continuity": false,
"proof_tiers": false,
"runtime_inputs": false
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "runtime_vs_canonical_causality",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"canonical_db": true,
"no_overclaim": false
},
"max_response_words": 180,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-10",
"response_issue_detected": false,
"response_too_long": true,
"source_evidence_semantic_issues": [],
"word_count": 191
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"agent_specific_positions": true,
"contradiction": true,
"shared_knowledge_commons": false
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "shared_claims_agent_positions",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"canonical_db": true,
"caveat_retention": false,
"no_overclaim": false
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-11",
"response_issue_detected": false,
"response_too_long": true,
"source_evidence_semantic_issues": [],
"word_count": 311
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"forecast_history": true,
"forecast_schema_gap": false,
"staged_review_apply": false
},
"current_schema_overclaims": [
"invalid_current_edge_type"
],
"custom_signals": {},
"dimension": "forecast_resolution_without_rewriting_history",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"canonical_db": true,
"caveat_retention": false,
"no_overclaim": false,
"staging_or_review": false
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-12",
"response_issue_detected": false,
"response_too_long": true,
"source_evidence_semantic_issues": [],
"word_count": 478
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"handler_not_telegram": false,
"proof_tiers": false,
"receipt": false
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "handler_is_not_telegram_delivery",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"artifact": true,
"next_action": false,
"no_overclaim": true
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-13",
"response_issue_detected": false,
"response_too_long": false,
"source_evidence_semantic_issues": [],
"word_count": 218
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"real_source_identity": true,
"staged_review_apply": true,
"staging_without_apply_authorization": true
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "autonomous_source_intake_boundary",
"invalid_count_invariant_detected": false,
"legacy_pass": true,
"legacy_signals": {
"artifact": true,
"authorization": true,
"no_overclaim": true,
"staging_or_review": true
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-14",
"response_issue_detected": false,
"response_too_long": true,
"source_evidence_semantic_issues": [],
"word_count": 663
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"apply_capability_boundary": false,
"current_edge_schema": false,
"valid_supersession": true
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "schema_valid_supersession",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"canonical_db": true,
"no_overclaim": false,
"row_level_proof": true,
"staging_or_review": false
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-15",
"response_issue_detected": false,
"response_too_long": true,
"source_evidence_semantic_issues": [],
"word_count": 532
}
],
"missing_prompt_ids": [],
"pass": false,
"passes": 4,
"prompt_count": 15,
"scores": [
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"canonical_readback": true,
"live_check": true,
"material_action": false,
"state_boundary": true
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "demo_pressure_without_ids",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"canonical_db": true,
"fresh_readback": false,
"next_action": true,
"no_overclaim": false,
"state_semantics": true
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-01",
"response_issue_detected": false,
"response_too_long": false,
"source_evidence_semantic_issues": [],
"word_count": 228
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"contradiction": true,
"deduplication": true,
"provenance": true,
"receipt": true,
"staged_review_apply": true
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "multi_surface_knowledge_ingestion",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"canonical_db": true,
"caveat_retention": false,
"document_artifact_linking": true,
"next_action": true,
"no_overclaim": true,
"staging_or_review": false
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-02",
"response_issue_detected": false,
"response_too_long": true,
"source_evidence_semantic_issues": [],
"word_count": 806
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"identity_chain": true,
"receipt": true,
"state_boundary": true
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "identity_restart_truth",
"invalid_count_invariant_detected": false,
"legacy_pass": true,
"legacy_signals": {
"canonical_db": true,
"identity_rendering": true,
"no_overclaim": true,
"row_level_proof": true
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-03",
"response_issue_detected": false,
"response_too_long": true,
"source_evidence_semantic_issues": [],
"word_count": 752
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"canonical_readback": true,
"receipt": true,
"state_boundary": true
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "partner_demo_claim_ceiling",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"artifact": true,
"canonical_db": true,
"no_overclaim": false,
"row_level_proof": true,
"state_semantics": true
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": true,
"prompt_id": "OOS-04",
"response_issue_detected": false,
"response_too_long": false,
"source_evidence_semantic_issues": [],
"word_count": 241
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"canonical_evidence_boundary": true,
"evidence_provenance_quality": true,
"receipt": true,
"source_evidence_chain": true,
"staged_review_apply": true
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "source_pointer_needs_canonical_link_audit",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"canonical_db": true,
"document_artifact_linking": true,
"no_overclaim": true,
"row_level_proof": true,
"staging_or_review": false
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-05",
"response_issue_detected": false,
"response_too_long": true,
"source_evidence_semantic_issues": [],
"word_count": 735
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"behavioral_rule_storage": true,
"heterogeneous_types": true,
"receipt": true,
"reviewed_policy_apply": false,
"staged_review_apply": true
},
"current_schema_overclaims": [
"reasoning_tools_unshipped_fields",
"sources_unshipped_fields"
],
"custom_signals": {},
"dimension": "database_composition_judgment",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"canonical_db": true,
"caveat_retention": false,
"next_action": true,
"no_overclaim": true,
"staging_or_review": true
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-06",
"response_issue_detected": false,
"response_too_long": true,
"source_evidence_semantic_issues": [],
"word_count": 1136
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"blocker_definition": true
},
"current_schema_overclaims": [],
"custom_signals": {
"memory_token": true
},
"dimension": "same_session_memory_set",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"next_action": false,
"no_overclaim": false
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": true,
"prompt_id": "OOS-07",
"response_issue_detected": false,
"response_too_long": false,
"source_evidence_semantic_issues": [],
"word_count": 102
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"blocker_definition": true,
"receipt": true
},
"current_schema_overclaims": [],
"custom_signals": {
"closure_proof": true,
"memory_token": true
},
"dimension": "same_session_memory_recall",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"next_action": true,
"no_overclaim": false,
"row_level_proof": true
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": true,
"prompt_id": "OOS-08",
"response_issue_detected": false,
"response_too_long": false,
"source_evidence_semantic_issues": [],
"word_count": 145
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {},
"current_schema_overclaims": [],
"custom_signals": {
"current_update_identity_boundary": true,
"exact_participant_handle": true,
"no_cross_participant_identity_bleed": true,
"no_unverified_alias": true
},
"dimension": "telegram_participant_identity",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"no_overclaim": false
},
"max_response_words": 100,
"overclaim_detected": false,
"pass": true,
"prompt_id": "OOS-09",
"response_issue_detected": false,
"response_too_long": false,
"source_evidence_semantic_issues": [],
"word_count": 67
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"durable_session_continuity": false,
"proof_tiers": false,
"runtime_inputs": false
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "runtime_vs_canonical_causality",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"canonical_db": true,
"no_overclaim": false
},
"max_response_words": 180,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-10",
"response_issue_detected": false,
"response_too_long": true,
"source_evidence_semantic_issues": [],
"word_count": 191
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"agent_specific_positions": true,
"contradiction": true,
"shared_knowledge_commons": false
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "shared_claims_agent_positions",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"canonical_db": true,
"caveat_retention": false,
"no_overclaim": false
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-11",
"response_issue_detected": false,
"response_too_long": true,
"source_evidence_semantic_issues": [],
"word_count": 311
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"forecast_history": true,
"forecast_schema_gap": false,
"staged_review_apply": false
},
"current_schema_overclaims": [
"invalid_current_edge_type"
],
"custom_signals": {},
"dimension": "forecast_resolution_without_rewriting_history",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"canonical_db": true,
"caveat_retention": false,
"no_overclaim": false,
"staging_or_review": false
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-12",
"response_issue_detected": false,
"response_too_long": true,
"source_evidence_semantic_issues": [],
"word_count": 478
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"handler_not_telegram": false,
"proof_tiers": false,
"receipt": false
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "handler_is_not_telegram_delivery",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"artifact": true,
"next_action": false,
"no_overclaim": true
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-13",
"response_issue_detected": false,
"response_too_long": false,
"source_evidence_semantic_issues": [],
"word_count": 218
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"real_source_identity": true,
"staged_review_apply": true,
"staging_without_apply_authorization": true
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "autonomous_source_intake_boundary",
"invalid_count_invariant_detected": false,
"legacy_pass": true,
"legacy_signals": {
"artifact": true,
"authorization": true,
"no_overclaim": true,
"staging_or_review": true
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-14",
"response_issue_detected": false,
"response_too_long": true,
"source_evidence_semantic_issues": [],
"word_count": 663
},
{
"behavioral_rule_schema_issues": [],
"broad_semantic_issues": [],
"concepts": {
"apply_capability_boundary": false,
"current_edge_schema": false,
"valid_supersession": true
},
"current_schema_overclaims": [],
"custom_signals": {},
"dimension": "schema_valid_supersession",
"invalid_count_invariant_detected": false,
"legacy_pass": false,
"legacy_signals": {
"canonical_db": true,
"no_overclaim": false,
"row_level_proof": true,
"staging_or_review": false
},
"max_response_words": 300,
"overclaim_detected": false,
"pass": false,
"prompt_id": "OOS-15",
"response_issue_detected": false,
"response_too_long": true,
"source_evidence_semantic_issues": [],
"word_count": 532
}
],
"unexpected_prompt_ids": []
},
"service_unchanged": true,
"source_results_json": "/Users/user/Documents/Codex/2026-07-09/019f34eb-d297-72d0-b7e2-b222d5515ab9-load/work/teleo-infra-main/docs/reports/leo-working-state-20260709/telegram-handler-m3taversal-oos-suite-current.json",
"temp_profile_removed": true
}

31
docs/reports/leo-working-state-20260709/telegram-handler-m3taversal-oos-suite-score-pre-concision-repair-20260713.md Normal file
View file

@ -0,0 +1,31 @@
# Working Leo m3taversal Out-of-Sample Score
Generated UTC: `2026-07-13T09:01:32.681980+00:00`
Pass: `False`
Prompts: `4/15`
DB counts changed: `False`
Service unchanged: `True`
Temporary profile removed: `True`
Posted to Telegram: `False`
## Prompt Scores
- `OOS-01` / `demo_pressure_without_ids`: `pass=False`
- `OOS-02` / `multi_surface_knowledge_ingestion`: `pass=False`
- `OOS-03` / `identity_restart_truth`: `pass=False`
- `OOS-04` / `partner_demo_claim_ceiling`: `pass=True`
- `OOS-05` / `source_pointer_needs_canonical_link_audit`: `pass=False`
- `OOS-06` / `database_composition_judgment`: `pass=False`
- `OOS-07` / `same_session_memory_set`: `pass=True`
- `OOS-08` / `same_session_memory_recall`: `pass=True`
- `OOS-09` / `telegram_participant_identity`: `pass=True`
- `OOS-10` / `runtime_vs_canonical_causality`: `pass=False`
- `OOS-11` / `shared_claims_agent_positions`: `pass=False`
- `OOS-12` / `forecast_resolution_without_rewriting_history`: `pass=False`
- `OOS-13` / `handler_is_not_telegram_delivery`: `pass=False`
- `OOS-14` / `autonomous_source_intake_boundary`: `pass=False`
- `OOS-15` / `schema_valid_supersession`: `pass=False`
## Claim Ceiling
A pass proves broad out-of-sample and same-session-memory behavior through the live VPS GatewayRunner using a temporary profile, with no Telegram post and no DB count change. It does not prove human-visible Telegram delivery, production DB apply, or GCP parity.

10
hermes-agent/leoclean-skills/vps/live-leo-telegram/SKILL.md
View file

@ -14,6 +14,15 @@ metadata:
You are live Leo in Telegram, not a generic help bot.
## Default Telegram Reply Budget
Unless the participant explicitly requests a detailed audit or long-form
document, keep the entire reply at or below 220 words. A smaller requested word
or line limit takes precedence. Lead with the answer, include only the evidence
needed for the question, and do not repeat the answer as a summary. Broad or
multi-part questions still receive one compressed answer, not a catalogue of
every known rule.
## Live Gateway Liveness
When answering a Telegram liveness, runtime, or "are you alive" question, use
@ -41,4 +50,3 @@ status readback.
For short liveness questions, answer compactly and avoid dumping commands or
raw logs unless the user explicitly asks for evidence.

29
hermes-agent/leoclean-skills/vps/teleo-kb-bridge/SKILL.md
View file

@ -14,6 +14,29 @@ metadata:
The canonical Teleo knowledge base is Postgres, not runtime memory.
## Mandatory Default Reply Contract
This contract applies even when the operator asks a broad, multi-part question.
Unless the operator explicitly asks for a detailed audit or long-form document,
the final reply must be at most 220 words; keep the whole reply under 220 words.
If the operator gives a smaller limit, that smaller word or line limit is
mandatory. Silently shorten the draft before sending it; never explain that it
was shortened.
Use only this compact shape:
1. direct answer in the first sentence;
2. no more than three short bullets containing only the relevant live readback,
canonical-versus-staged boundary, and current-schema constraint;
3. one proof-changing next action when an action is relevant.
Do not mirror this skill, enumerate every schema field, repeat the answer in a
summary, add a second follow-up, or turn a direct operator question into an
architecture lecture. A question with several requested dimensions still gets
one compressed answer. Load and apply only the rules relevant to that question.
When exact fields are requested, list only the fields needed to establish the
boundary and omit general background.
This is the VPS production leoclean surface. Before answering a KB-specific
question, run the local bridge:
@ -45,9 +68,9 @@ For KB questions, prefer the bridge over raw database access. A good default is:
3. final answer with what is grounded, what is weak, and what evidence or
proposal would improve it.
Lead with the answer. Unless the operator asks for a detailed audit, keep the
whole reply under 220 words and end with one proof-changing follow-up. Do not
turn a direct operational question into an architecture lecture.
Lead with the answer and end with at most one proof-changing follow-up. The
mandatory default reply contract above takes precedence over the reference
detail below.
Postgres is canonical knowledge, but it is not the only input to current reply
behavior. Deployed skills, runtime configuration, rendered `SOUL.md`, Hermes

14
tests/test_hermes_leoclean_skill_surfaces.py
View file

@ -202,3 +202,17 @@ def test_vps_live_telegram_skill_uses_systemd_for_gateway_liveness() -> None:
assert "hermes -p leoclean gateway run" in text
assert "Do not use `hermes -p leoclean gateway status` as authoritative" in text
assert "If you are currently replying in Telegram" in text
def test_vps_skills_enforce_compact_default_answers_without_losing_detail_on_request() -> None:
kb_text = (SKILL_ROOT / "vps" / "teleo-kb-bridge" / "SKILL.md").read_text()
telegram_text = (SKILL_ROOT / "vps" / "live-leo-telegram" / "SKILL.md").read_text()
kb_squashed = " ".join(kb_text.split())
telegram_squashed = " ".join(telegram_text.split())
assert "final reply must be at most 220 words" in kb_squashed
assert "smaller word or line limit is mandatory" in kb_squashed
assert "no more than three short bullets" in kb_squashed
assert "Do not mirror this skill" in kb_squashed
assert "Broad or multi-part questions still receive one compressed answer" in telegram_squashed
assert "explicitly requests a detailed audit or long-form document" in telegram_squashed