nsaspy/prolog-rlm
1
0
Fork 0
Code Issues 83 Pull requests 10 Projects Releases Packages Wiki Activity Actions

[P1] Add configurable error and agent-loop detector registry #130

New issue
Closed
opened 2026-08-19 16:55:53 +00:00 by lost-rob0t · 1 comment
lost-rob0t commented 2026-08-19 16:55:53 +00:00 (Migrated from github.com)
Copy link

Parent: #126
Depends on: #127 and #128. Integrates with existing recursion guards, traces, conversation/agent events, verification and repair APIs.

Goal

Create a detector registry where trusted config.prolog may define/register executable Prolog detectors for structured errors, repetition, agent loops, and lack of progress.

The runtime should not force every detector into a static built-in catalog. The user's XDG config is a programmable extension environment. Trusted project config may register project-scoped detectors only after project trust.

Detector contract

Each registration has stable id/schema/version, supported observation kinds, bounded state requirements, priority/scope, config-generation ownership, sanitized metadata, and a trusted Prolog predicate.

Detector inputs are structured runtime observations/events. Outputs are structured decisions such as clear, suspected, detected, or indeterminate, with reason/evidence/confidence and a bounded recommended response class.

A detector may compute arbitrary trusted Prolog logic, but it does not by itself bypass the runtime that owns cancellation, repair, authority, effects, capabilities, or verification.

Initial loop/non-progress coverage

  • duplicate recursive subproblem fingerprints, while preserving #42 as an open correctness defect;
  • repeated equivalent tool calls/arguments;
  • repeated model -> same tool -> same result cycles;
  • repeated failed repair attempts without a meaningful plan/spec change;
  • repeated materially equivalent assistant outputs;
  • turn/step trajectories with no measured progress for configured windows;
  • repeated provider/transient failures where further retry is low-value;
  • user/project-defined detector predicates over structured observations.

Error detection/classification

Support trusted classifiers for provider, parsing/structured-output, tool, authority, effect, verification, project/source, and agent-runtime failures. Preserve original structured errors and provenance; classification augments rather than replaces evidence.

Acceptance

  • XDG config.prolog can define and register a detector predicate.
  • Trusted project config can register project-scoped detectors only after project trust.
  • Untrusted project/model data cannot register executable detector code.
  • Detector catalog exposes sanitized metadata, not callable terms.
  • Config enables/disables/tunes registered detectors by id.
  • Tests cover repeated-tool and non-progress loops beyond recursion-only fingerprints.
  • False-positive controls/window/budget semantics are deterministic.
  • #42 remains tracked until its fingerprint bug is actually fixed.
  • Detector outputs are structured, traceable and provenance-carrying.
  • Detector recommendations cannot directly bypass authority/effects/capabilities.
  • Reload removes stale config-generation detectors deterministically.
Parent: #126 Depends on: #127 and #128. Integrates with existing recursion guards, traces, conversation/agent events, verification and repair APIs. ## Goal Create a detector registry where trusted `config.prolog` may define/register executable Prolog detectors for structured errors, repetition, agent loops, and lack of progress. The runtime should not force every detector into a static built-in catalog. The user's XDG config is a programmable extension environment. Trusted project config may register project-scoped detectors only after project trust. ## Detector contract Each registration has stable id/schema/version, supported observation kinds, bounded state requirements, priority/scope, config-generation ownership, sanitized metadata, and a trusted Prolog predicate. Detector inputs are structured runtime observations/events. Outputs are structured decisions such as `clear`, `suspected`, `detected`, or `indeterminate`, with reason/evidence/confidence and a bounded recommended response class. A detector may compute arbitrary trusted Prolog logic, but it does not by itself bypass the runtime that owns cancellation, repair, authority, effects, capabilities, or verification. ## Initial loop/non-progress coverage - duplicate recursive subproblem fingerprints, while preserving #42 as an open correctness defect; - repeated equivalent tool calls/arguments; - repeated model -> same tool -> same result cycles; - repeated failed repair attempts without a meaningful plan/spec change; - repeated materially equivalent assistant outputs; - turn/step trajectories with no measured progress for configured windows; - repeated provider/transient failures where further retry is low-value; - user/project-defined detector predicates over structured observations. ## Error detection/classification Support trusted classifiers for provider, parsing/structured-output, tool, authority, effect, verification, project/source, and agent-runtime failures. Preserve original structured errors and provenance; classification augments rather than replaces evidence. ## Acceptance - [ ] XDG `config.prolog` can define and register a detector predicate. - [ ] Trusted project config can register project-scoped detectors only after project trust. - [ ] Untrusted project/model data cannot register executable detector code. - [ ] Detector catalog exposes sanitized metadata, not callable terms. - [ ] Config enables/disables/tunes registered detectors by id. - [ ] Tests cover repeated-tool and non-progress loops beyond recursion-only fingerprints. - [ ] False-positive controls/window/budget semantics are deterministic. - [ ] #42 remains tracked until its fingerprint bug is actually fixed. - [ ] Detector outputs are structured, traceable and provenance-carrying. - [ ] Detector recommendations cannot directly bypass authority/effects/capabilities. - [ ] Reload removes stale config-generation detectors deterministically.
nsaspy commented 2026-09-02 17:26:01 +00:00
Owner
Copy link

Child of #126; closed with the epic under the restored canonical boundary (#141, 2026-08-31): AgentProlog product configuration/UX belongs to lost-rob0t/agentProlog, and this is not a current prolog-rlm gap blocking a coding agent. Re-file in the product repo if still wanted.

Child of #126; closed with the epic under the restored canonical boundary (#141, 2026-08-31): AgentProlog product configuration/UX belongs to lost-rob0t/agentProlog, and this is not a current prolog-rlm gap blocking a coding agent. Re-file in the product repo if still wanted.
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
feat/prolog-rlm-language
codex/claude-api-provider
codex/symbolic-experts
codex/openai-api-provider
feat/zai-provider-protocols
hardening/project-semantic-20260911
hardening/ws7-nix-ci-pinning
chore/track-prolog
rage/98-semantic-project-knowledge
fix/339-agent-zero-skill-graph
ci/tree-sitter-runner-labels
issue-293
research/text-streaming
docs/agent-editor-handoff
icon-add
hydra/fleet-jobs-20260904
rage/355-d6-11-plan-native-dispatch
cd/nix-installer-action-url
issue-355
rage/97-query-capture-apis
research/expert-direct-tool-projection
rage/96-versioned-syntax-facts
fix/direct-deadline-typing
dogfood/auto-dig-native-tools
feature/rage-feature-freeze
fix/323-native-batch-cardinality
fix/328-direct-user-namespace-text-string
fix/transient-provider-retry-2026-09-01
fix/openrouter-dotted-tool-result-name
rage/325-native-call-isolation
fix/316-original-batch-effect-isolation
fix/313-per-call-preflight
fix/312-peek-schema-contract
docs/agents-worktree-rule
fix/child-native-capability-narrowing
test/paid-lane-glm-53-flash
docs/spec-seeded-symbolic-plans
rage/290-spec-plan-authority
fix/304-context-peek-selector-contract
fix/298-native-any-json-schema
rage/288-spec-plan-graph-executor
feat/spec-plan-flow-api
prolog-rlm-v1
gpt-5-6-sol-high/questions-for-rlm-prolog-and-lambda-rlm
rage/277-planner-protocol-context
research-approval/rlm-research-026-task-deadlines-20260827135838
research-approval/rlm-research-025-lem-ui-20260827135751
rage/183-live-operator-behavior
agent/127-agentprolog-config
recovery/132-agentprolog-monorepo
rage/223-durable-context-mount-recovery
rage/223-constraint-benchmark-recovery
research-approval/rlm-research-011-managed-context-tool-discovery-20260827054019
feat/research-approval-schema
agent/rrlm-control-plane-research
docs/219-adrrd-review
salvage/231-runtime-status
salvage/231-runtime-status-run
tmp
tmp2
tmp3
rage/245-planner-structural-retry
rage/168-skill-selection-eval
rage/250-skill-catalog-graph
rage/56-result-acceptance
rage/172-parent-resume-replan
rage/175-deadline-policy-recovery
rage/257-provider-tool-choice-normalization
agent/tool-result-projection-presets
fix/234-numeric-schema-bounds
feature/231-rlm-cli-reference-harness
feature/223-durable-context-mounts
feature/223-real-constraint-benchmark
feature/223-real-constraint-benchmark-clean
feature/223-real-constraint-benchmark-final
feature/223-real-constraint-benchmark-impl
feature/223-real-constraint-benchmark-now
feature/223-real-constraint-benchmark-tdd
feature/223-real-constraint-benchmark-work
rage/176-root-planner-tool-projection
rage/172-typed-delegation-policy
rage/175-subagent-deadline-policy
rage/206-prompt-command-runtime
rage/203-subagent-skill-role-provenance
rage/200-permanent-rlm-context
fix/190-cli-help-success
archive/pr-132-agentprolog-config-20260827
feature/117-prolog-skill-activation-linear
feature/117-prolog-skill-activation
fix/194-completion-budget-usage
fix/191-capability-filtered-tool-schemas
fix/185-reasoning-effort
ci/report-workflow-failures-20260825
cleanup/186-remove-legacy-harnesses
fix/185-reasoning-routing
agent/evolution-async-evaluator
rage/181-binding-replay-race
agent/124-deepseek-harness-prolog
rage/144-fallback-closure
rage/164-conversation-metadata
agent/subagent-supervised-call-conformance
fix/160-context-adapter-closed-data
codex/move-agent-zero-adaptor
codex/sol-high-integration
fix/151-plunit-gate
fix/165-evolution-closed-data
fix/162-async-control-exceptions
fix/158-prompt-compiler-closed-dicts
fix/151-plunit-main-ownership
fix/156-registry-destroy-hooks
fix/154-anonymous-dict-canonicalization
fix/flake-lock-reproducibility
agent/issue-142-evolution-kernel
agent/141-flake-runtime-package
agent/rlm-subagent-runtime
agent/144-subagent-fallback-a
agent/107-bound-adapter-metadata
validation/clean-pack-install
fix/45-authoritative-nested-model-events
fix/46-router-safe-live-streaming
agent/prompt-context-compiler
agent/42-canonical-recursive-fingerprints
agent/136-static-load-errors-fail-ci
agent/44-completion-error-usage
fix/67-loader-registry-cleanup
agent/opentui-solid-reference-client-current
agent/95-project-source-registry
feature/issue-117-prolog-skill-compiler
backlog/roadmap-86-merged
agent/opentui-solid-reference-client
79-tool-effect-boundary
agent/prolog-agent-ui-research
agent/conversation-cold-context
agent/94-tree-sitter-ffi
agent/conversation-warm-context
111-opentui-solid-reference-client
109-prolog-agent-ui-v1
agent/conversation-runtime
agent/spec-mode-language
agent/spec-verify-foundation
agent/prompt-compiler-research
reconcile-backlog-postmerge
reconcile-backlog-issues
agent/prolog-agent-roadmap
feature/issue-84-effect-store-migration
fix/issue-80-effect-substrate-adversarial-hardening
feature/issue-57-effect-identity
agent/mcp-declaration-security
agent/external-tool-category-boundary
feature/issue-53-authority-pending-async
feature/issue-54-agent-graph-canonical-async
feature/issue-54-tools-mcp-canonical-async
feature/issue-54-async-canonical-runtime
agent/dual-sync-async-runtime
agent/reconcile-todo-status
feature/issue-20-deep-recursion-experiments
feature/issue-19-cli-demo-trace
feature/issue-18-benchmark-conformance
feature/issue-17-adaptive-recursion
feature/issue-16-durable-artifacts
feature/issue-15-mcp-2026-dual-version
feature/issue-14-mcp-2025-11-25
hotfix/live-tool-native-openrouter
feature/issue-13-chain-runtime
fix/stable-live-repair-gate
fix/live-repair-strategy-parser
feature/issue-12-durable-graph
feature/issue-11-agent-supervision
feature/issue-10-structured-outcomes-repair
feature/issue-9-rlm-completion
feature/issue-8-capability-tools
feature/issue-7-typed-plan-runtime
feature/issue-6-context-store
fix/openrouter-reasoning-response
fix/live-openrouter-smoke-stability
feature/issue-5-openrouter-provider
feature/issue-4-swi-bootstrap
agent/agentic-harness-research
agent/prolog-rlm-foundation
No results found.
Labels
Clear labels   
bug
Something isn't working

  
documentation
Improvements or additions to documentation

  
duplicate
This issue or pull request already exists

  
enhancement
New feature or request

  
good first issue
Good for newcomers

  
help wanted
Extra attention is needed

  
invalid
This doesn't seem right

  
question
Further information is requested

  
wontfix
This will not be worked on

No labels
bug
documentation
duplicate
enhancement
good first issue
help wanted
invalid
question
wontfix
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
2 participants
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
nsaspy/prolog-rlm#130
No description provided.