superlocalmemory 4.2.2 → 4.2.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude-plugin/marketplace.json +2 -2
- package/CHANGELOG.md +78 -0
- package/README.md +13 -5
- package/antigravity-plugin/_GENERATED.md +1 -1
- package/antigravity-plugin/agents/slm-governance-advisor.md +1 -1
- package/antigravity-plugin/agents/slm-loop-runner.md +1 -1
- package/antigravity-plugin/agents/slm-memory-advisor.md +1 -1
- package/antigravity-plugin/agents/slm-optimize-advisor.md +1 -1
- package/antigravity-plugin/plugin.json +1 -1
- package/antigravity-plugin/skills/slm-bot-memory/SKILL.md +1 -1
- package/antigravity-plugin/skills/slm-cache/SKILL.md +1 -1
- package/antigravity-plugin/skills/slm-compress/SKILL.md +1 -1
- package/antigravity-plugin/skills/slm-getting-started-bot/SKILL.md +1 -1
- package/antigravity-plugin/skills/slm-governance/SKILL.md +1 -1
- package/antigravity-plugin/skills/slm-graph/SKILL.md +1 -1
- package/antigravity-plugin/skills/slm-loop/SKILL.md +4 -3
- package/antigravity-plugin/skills/slm-media/SKILL.md +1 -1
- package/antigravity-plugin/skills/slm-mesh/SKILL.md +1 -1
- package/antigravity-plugin/skills/slm-profile/SKILL.md +1 -1
- package/antigravity-plugin/skills/slm-recall/SKILL.md +1 -1
- package/antigravity-plugin/skills/slm-remember/SKILL.md +1 -1
- package/antigravity-plugin/skills/slm-scope/SKILL.md +1 -1
- package/antigravity-plugin/skills/slm-session/SKILL.md +1 -1
- package/antigravity-plugin/skills/slm-status/SKILL.md +1 -1
- package/codex-plugin/.claude-plugin/plugin.json +1 -1
- package/codex-plugin/.codex-plugin/plugin.json +1 -1
- package/codex-plugin/AGENTS.md +1 -1
- package/codex-plugin/README.md +2 -2
- package/codex-plugin/_GENERATED.md +1 -1
- package/codex-plugin/agents/slm-governance-advisor.md +1 -1
- package/codex-plugin/agents/slm-loop-runner.md +1 -1
- package/codex-plugin/agents/slm-memory-advisor.md +1 -1
- package/codex-plugin/agents/slm-optimize-advisor.md +1 -1
- package/codex-plugin/skills/slm-bot-memory/SKILL.md +1 -1
- package/codex-plugin/skills/slm-cache/SKILL.md +1 -1
- package/codex-plugin/skills/slm-compress/SKILL.md +1 -1
- package/codex-plugin/skills/slm-getting-started-bot/SKILL.md +1 -1
- package/codex-plugin/skills/slm-governance/SKILL.md +1 -1
- package/codex-plugin/skills/slm-graph/SKILL.md +1 -1
- package/codex-plugin/skills/slm-loop/SKILL.md +4 -3
- package/codex-plugin/skills/slm-media/SKILL.md +1 -1
- package/codex-plugin/skills/slm-mesh/SKILL.md +1 -1
- package/codex-plugin/skills/slm-profile/SKILL.md +1 -1
- package/codex-plugin/skills/slm-recall/SKILL.md +1 -1
- package/codex-plugin/skills/slm-remember/SKILL.md +1 -1
- package/codex-plugin/skills/slm-scope/SKILL.md +1 -1
- package/codex-plugin/skills/slm-session/SKILL.md +1 -1
- package/codex-plugin/skills/slm-status/SKILL.md +1 -1
- package/copilot-plugin/.github/agents/slm-governance-advisor.agent.md +2 -2
- package/copilot-plugin/.github/agents/slm-loop-runner.agent.md +2 -2
- package/copilot-plugin/.github/agents/slm-memory-advisor.agent.md +2 -2
- package/copilot-plugin/.github/agents/slm-optimize-advisor.agent.md +2 -2
- package/copilot-plugin/.github/copilot-instructions.md +4 -4
- package/copilot-plugin/.github/prompts/slm-bot-memory.prompt.md +2 -2
- package/copilot-plugin/.github/prompts/slm-cache.prompt.md +2 -2
- package/copilot-plugin/.github/prompts/slm-compress.prompt.md +2 -2
- package/copilot-plugin/.github/prompts/slm-getting-started-bot.prompt.md +2 -2
- package/copilot-plugin/.github/prompts/slm-governance.prompt.md +2 -2
- package/copilot-plugin/.github/prompts/slm-graph.prompt.md +2 -2
- package/copilot-plugin/.github/prompts/slm-loop.prompt.md +5 -4
- package/copilot-plugin/.github/prompts/slm-media.prompt.md +2 -2
- package/copilot-plugin/.github/prompts/slm-mesh.prompt.md +2 -2
- package/copilot-plugin/.github/prompts/slm-profile.prompt.md +2 -2
- package/copilot-plugin/.github/prompts/slm-recall.prompt.md +2 -2
- package/copilot-plugin/.github/prompts/slm-remember.prompt.md +2 -2
- package/copilot-plugin/.github/prompts/slm-scope.prompt.md +2 -2
- package/copilot-plugin/.github/prompts/slm-session.prompt.md +2 -2
- package/copilot-plugin/.github/prompts/slm-status.prompt.md +2 -2
- package/copilot-plugin/.github/prompts/slm-web-access.prompt.md +1 -1
- package/copilot-plugin/README.md +2 -2
- package/copilot-plugin/_GENERATED.md +1 -1
- package/hermes-plugin/__init__.py +5 -2
- package/hermes-plugin/agents/slm-governance-advisor.md +1 -1
- package/hermes-plugin/agents/slm-loop-runner.md +1 -1
- package/hermes-plugin/agents/slm-memory-advisor.md +1 -1
- package/hermes-plugin/agents/slm-optimize-advisor.md +1 -1
- package/hermes-plugin/plugin.yaml +1 -1
- package/hermes-plugin/skills/slm-bot-memory/SKILL.md +1 -1
- package/hermes-plugin/skills/slm-cache/SKILL.md +1 -1
- package/hermes-plugin/skills/slm-compress/SKILL.md +1 -1
- package/hermes-plugin/skills/slm-getting-started-bot/SKILL.md +1 -1
- package/hermes-plugin/skills/slm-governance/SKILL.md +1 -1
- package/hermes-plugin/skills/slm-graph/SKILL.md +1 -1
- package/hermes-plugin/skills/slm-loop/SKILL.md +4 -3
- package/hermes-plugin/skills/slm-media/SKILL.md +1 -1
- package/hermes-plugin/skills/slm-mesh/SKILL.md +1 -1
- package/hermes-plugin/skills/slm-profile/SKILL.md +1 -1
- package/hermes-plugin/skills/slm-recall/SKILL.md +1 -1
- package/hermes-plugin/skills/slm-remember/SKILL.md +1 -1
- package/hermes-plugin/skills/slm-scope/SKILL.md +1 -1
- package/hermes-plugin/skills/slm-session/SKILL.md +1 -1
- package/hermes-plugin/skills/slm-status/SKILL.md +1 -1
- package/package.json +1 -1
- package/plugin/.claude-plugin/plugin.json +1 -1
- package/plugin/.cursor-plugin/plugin.json +1 -1
- package/plugin/CLAUDE.md +3 -3
- package/plugin/agents/slm-governance-advisor.md +1 -1
- package/plugin/agents/slm-loop-runner.md +1 -1
- package/plugin/agents/slm-memory-advisor.md +1 -1
- package/plugin/agents/slm-optimize-advisor.md +1 -1
- package/plugin/cursor-skills/slm-bot-memory/SKILL.md +1 -1
- package/plugin/cursor-skills/slm-getting-started-bot/SKILL.md +1 -1
- package/plugin/cursor-skills/slm-recall/SKILL.md +1 -1
- package/plugin/cursor-skills/slm-remember/SKILL.md +1 -1
- package/plugin/cursor-skills/slm-scope/SKILL.md +1 -1
- package/plugin/cursor-skills/slm-session/SKILL.md +1 -1
- package/plugin/mcp.cursor.json +1 -1
- package/plugin/requirements.txt +1 -1
- package/plugin/skills/slm-bot-memory/SKILL.md +1 -1
- package/plugin/skills/slm-cache/SKILL.md +1 -1
- package/plugin/skills/slm-compress/SKILL.md +1 -1
- package/plugin/skills/slm-getting-started-bot/SKILL.md +1 -1
- package/plugin/skills/slm-governance/SKILL.md +1 -1
- package/plugin/skills/slm-graph/SKILL.md +1 -1
- package/plugin/skills/slm-loop/SKILL.md +4 -3
- package/plugin/skills/slm-media/SKILL.md +1 -1
- package/plugin/skills/slm-mesh/SKILL.md +1 -1
- package/plugin/skills/slm-profile/SKILL.md +1 -1
- package/plugin/skills/slm-recall/SKILL.md +1 -1
- package/plugin/skills/slm-remember/SKILL.md +1 -1
- package/plugin/skills/slm-scope/SKILL.md +1 -1
- package/plugin/skills/slm-session/SKILL.md +1 -1
- package/plugin/skills/slm-status/SKILL.md +1 -1
- package/plugin-src/agents/slm-governance-advisor.md +1 -1
- package/plugin-src/agents/slm-loop-runner.md +1 -1
- package/plugin-src/agents/slm-memory-advisor.md +1 -1
- package/plugin-src/agents/slm-optimize-advisor.md +1 -1
- package/plugin-src/rules/AGENTS.md +1 -1
- package/plugin-src/rules/CLAUDE.md.fragment +3 -3
- package/plugin-src/skills/slm-bot-memory/SKILL.md +1 -1
- package/plugin-src/skills/slm-cache/SKILL.md +1 -1
- package/plugin-src/skills/slm-compress/SKILL.md +1 -1
- package/plugin-src/skills/slm-getting-started-bot/SKILL.md +1 -1
- package/plugin-src/skills/slm-governance/SKILL.md +1 -1
- package/plugin-src/skills/slm-graph/SKILL.md +1 -1
- package/plugin-src/skills/slm-loop/SKILL.md +4 -3
- package/plugin-src/skills/slm-media/SKILL.md +1 -1
- package/plugin-src/skills/slm-mesh/SKILL.md +1 -1
- package/plugin-src/skills/slm-profile/SKILL.md +1 -1
- package/plugin-src/skills/slm-recall/SKILL.md +1 -1
- package/plugin-src/skills/slm-remember/SKILL.md +1 -1
- package/plugin-src/skills/slm-scope/SKILL.md +1 -1
- package/plugin-src/skills/slm-session/SKILL.md +1 -1
- package/plugin-src/skills/slm-status/SKILL.md +1 -1
package/plugin/mcp.cursor.json
CHANGED
package/plugin/requirements.txt
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
superlocalmemory==4.2.
|
|
1
|
+
superlocalmemory==4.2.4
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: slm-loop
|
|
3
|
-
description: Gate-verified bounded loops with SuperLocalMemory as the durable ledger. Use when a task has a checkable acceptance condition and you must iterate until an INDEPENDENT gate passes — never stopping because the agent believes it is done. `slm_loop_run` (MCP) waits, under hard bounds, for
|
|
3
|
+
description: Gate-verified bounded loops with SuperLocalMemory as the durable ledger. Use when a task has a checkable acceptance condition and you must iterate until an INDEPENDENT gate passes — never stopping because the agent believes it is done. `slm_loop_run` (MCP) waits, under hard bounds, for an independently executed check registered by the operator to pass; `slm loop demo` shows the control flow keyless; `slm loop history` and `slm loop show <run_id>` (or `slm_loop_history` / `slm_loop_show`) inspect past runs, whose every lap is stored as queryable SLM memory (tag `loop:<name>`). Terminal statuses are DONE / HALT / PAUSE / KILLED / ERROR — report them exactly, never converting HALT/PAUSE/ERROR into success.
|
|
4
4
|
when_to_use: "run a bounded loop, gate-verified task, iterate until tests pass, verify against an independent gate, don't trust the agent's own done claim, slm loop, convergence loop, loop until green, loop ledger, wait for another agent's result"
|
|
5
5
|
allowed-tools: slm_loop_run, slm_loop_history, slm_loop_show, recall, report_outcome, get_soft_prompts, skill_health, skill_lineage, evolve_skill, observe_bounded_loop_evidence, Bash
|
|
6
6
|
---
|
|
@@ -26,7 +26,7 @@ subprocess or sandbox machinery. What each surface gives you:
|
|
|
26
26
|
|
|
27
27
|
| Surface | What it does |
|
|
28
28
|
|---|---|
|
|
29
|
-
| `slm_loop_run` (MCP) | A *watcher
|
|
29
|
+
| `slm_loop_run` (MCP) | A *watcher* for a registered check. DONE needs `gate_contract={"job_id": ...}`: a job the operator registered with `superlocalmemory.loops.receipt_jobs.register_job` and executed with `run_registered_check`. Each lap's recall of `gate_query` only locates context; a matching memory alone never passes. Without a registered job the run ends HALT ("operator-registered job_id required"), which is the correct, honest outcome. |
|
|
30
30
|
| `slm loop demo` (CLI) | A keyless convergence demo: a stub proposer, a deterministic gate that passes on lap 3, every lap recorded. Proves the engine and ledger work end to end. |
|
|
31
31
|
| `slm loop history`, `slm loop show` / `slm_loop_history`, `slm_loop_show` | Read the ledger of past runs. |
|
|
32
32
|
| `superlocalmemory.loops.run_bounded_loop` (Python) | The engine itself, for code that supplies its own runner and gate callables. |
|
|
@@ -62,6 +62,7 @@ slm_loop_run(
|
|
|
62
62
|
max_tokens: int = 0, # optional token budget; 0 disables
|
|
63
63
|
no_progress_window: int = 0, # halt after N no-change laps; leave 0 for a watcher
|
|
64
64
|
require_support: bool = False,# pass only if the answer check ran and judged it sufficient
|
|
65
|
+
gate_contract: dict | None = None, # {"job_id": <operator registration>}; required for DONE
|
|
65
66
|
)
|
|
66
67
|
```
|
|
67
68
|
|
|
@@ -170,4 +171,4 @@ Guides: `docs/skill-evolution.md`, `docs/bounded-loops-bridge.md`.
|
|
|
170
171
|
|
|
171
172
|
---
|
|
172
173
|
|
|
173
|
-
SuperLocalMemory v4.2.
|
|
174
|
+
SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later
|
|
@@ -81,4 +81,4 @@ slm-scope · slm-governance · slm-profile · slm-remember · slm-recall · slm-
|
|
|
81
81
|
# What NOT to do
|
|
82
82
|
Never session_init twice; never forget without dry-run preview; never run `slm gdpr erase --yes` unasked; never store secrets; never bypass role checks; never claim an erasure succeeded without verifying via recall.
|
|
83
83
|
|
|
84
|
-
SuperLocalMemory v4.2.
|
|
84
|
+
SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later
|
|
@@ -51,4 +51,4 @@ slm-recall · slm-remember · slm-session · slm-scope · slm-profile · slm-gov
|
|
|
51
51
|
# What NOT to do
|
|
52
52
|
Never session_init twice; never forget dry_run=False without reporting preview; never switch the active profile unasked; never dump a whole file into remember; never invent a memory; never claim "saved" without success:true / clean CLI exit; never bypass scope or governance restrictions.
|
|
53
53
|
|
|
54
|
-
SuperLocalMemory v4.2.
|
|
54
|
+
SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later
|
|
@@ -41,4 +41,4 @@ slm-compress · slm-cache · slm-status · slm-profile
|
|
|
41
41
|
# What NOT to do
|
|
42
42
|
Never compress code-for-edit/JSON-to-parse/<500 chars; never store secrets/ccr_ids; never let optimize failure block/alter the task; never claim a specific savings %; never hand a ccr_id to another agent.
|
|
43
43
|
|
|
44
|
-
SuperLocalMemory v4.2.
|
|
44
|
+
SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later
|
|
@@ -187,4 +187,4 @@ Using this memory from a web assistant or another computer: see the slm-web-acce
|
|
|
187
187
|
- **slm-governance-advisor** — scope/role compliance, retention and lifecycle, GDPR
|
|
188
188
|
- **slm-loop-runner** — bounded, gate-verified loops (the `/slm-loop` command delegates to it)
|
|
189
189
|
|
|
190
|
-
SuperLocalMemory v4.2.
|
|
190
|
+
SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later
|
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
<!-- BEGIN SuperLocalMemory v4.2.
|
|
1
|
+
<!-- BEGIN SuperLocalMemory v4.2.4 -->
|
|
2
2
|
|
|
3
3
|
## SuperLocalMemory (SLM) — Agent Rules
|
|
4
4
|
|
|
@@ -51,6 +51,6 @@ slm-recall · slm-remember · slm-session · slm-status · slm-cache · slm-comp
|
|
|
51
51
|
### Subagents
|
|
52
52
|
slm-memory-advisor (memory decisions, session hygiene, scope/profile guidance) · slm-optimize-advisor (context compression + KV cache) · slm-governance-advisor (scope/roles/compliance/GDPR) · slm-loop-runner (bounded, gate-verified loops)
|
|
53
53
|
|
|
54
|
-
<!-- END SuperLocalMemory v4.2.
|
|
54
|
+
<!-- END SuperLocalMemory v4.2.4 -->
|
|
55
55
|
|
|
56
|
-
SuperLocalMemory v4.2.
|
|
56
|
+
SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: slm-loop
|
|
3
|
-
description: Gate-verified bounded loops with SuperLocalMemory as the durable ledger. Use when a task has a checkable acceptance condition and you must iterate until an INDEPENDENT gate passes — never stopping because the agent believes it is done. `slm_loop_run` (MCP) waits, under hard bounds, for
|
|
3
|
+
description: Gate-verified bounded loops with SuperLocalMemory as the durable ledger. Use when a task has a checkable acceptance condition and you must iterate until an INDEPENDENT gate passes — never stopping because the agent believes it is done. `slm_loop_run` (MCP) waits, under hard bounds, for an independently executed check registered by the operator to pass; `slm loop demo` shows the control flow keyless; `slm loop history` and `slm loop show <run_id>` (or `slm_loop_history` / `slm_loop_show`) inspect past runs, whose every lap is stored as queryable SLM memory (tag `loop:<name>`). Terminal statuses are DONE / HALT / PAUSE / KILLED / ERROR — report them exactly, never converting HALT/PAUSE/ERROR into success.
|
|
4
4
|
when_to_use: "run a bounded loop, gate-verified task, iterate until tests pass, verify against an independent gate, don't trust the agent's own done claim, slm loop, convergence loop, loop until green, loop ledger, wait for another agent's result"
|
|
5
5
|
allowed-tools: slm_loop_run, slm_loop_history, slm_loop_show, recall, report_outcome, get_soft_prompts, skill_health, skill_lineage, evolve_skill, observe_bounded_loop_evidence, Bash
|
|
6
6
|
---
|
|
@@ -26,7 +26,7 @@ subprocess or sandbox machinery. What each surface gives you:
|
|
|
26
26
|
|
|
27
27
|
| Surface | What it does |
|
|
28
28
|
|---|---|
|
|
29
|
-
| `slm_loop_run` (MCP) | A *watcher
|
|
29
|
+
| `slm_loop_run` (MCP) | A *watcher* for a registered check. DONE needs `gate_contract={"job_id": ...}`: a job the operator registered with `superlocalmemory.loops.receipt_jobs.register_job` and executed with `run_registered_check`. Each lap's recall of `gate_query` only locates context; a matching memory alone never passes. Without a registered job the run ends HALT ("operator-registered job_id required"), which is the correct, honest outcome. |
|
|
30
30
|
| `slm loop demo` (CLI) | A keyless convergence demo: a stub proposer, a deterministic gate that passes on lap 3, every lap recorded. Proves the engine and ledger work end to end. |
|
|
31
31
|
| `slm loop history`, `slm loop show` / `slm_loop_history`, `slm_loop_show` | Read the ledger of past runs. |
|
|
32
32
|
| `superlocalmemory.loops.run_bounded_loop` (Python) | The engine itself, for code that supplies its own runner and gate callables. |
|
|
@@ -62,6 +62,7 @@ slm_loop_run(
|
|
|
62
62
|
max_tokens: int = 0, # optional token budget; 0 disables
|
|
63
63
|
no_progress_window: int = 0, # halt after N no-change laps; leave 0 for a watcher
|
|
64
64
|
require_support: bool = False,# pass only if the answer check ran and judged it sufficient
|
|
65
|
+
gate_contract: dict | None = None, # {"job_id": <operator registration>}; required for DONE
|
|
65
66
|
)
|
|
66
67
|
```
|
|
67
68
|
|
|
@@ -170,4 +171,4 @@ Guides: `docs/skill-evolution.md`, `docs/bounded-loops-bridge.md`.
|
|
|
170
171
|
|
|
171
172
|
---
|
|
172
173
|
|
|
173
|
-
SuperLocalMemory v4.2.
|
|
174
|
+
SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later
|