docs: technical memory architecture + landing page clarity by UfukNode · Pull Request #32 · NousResearch/hermes-agent

UfukNode · 2026-02-25T23:32:49Z

No description provided.

…ch#32) - Render ContextBar in chat screen (was imported but never placed) - Pass sessionId to context-usage API for accurate token data - Count all tokens (cached + uncached) for real context window usage - Model-aware max tokens (200k for Claude, 128k for GPT) - Return model name in context-usage response - Remove header border-b (context bar replaces separator) - Remove context bar own border-b for clean look - Change dev server port from 3000 to 3002 Co-authored-by: outsourc-e <eric@outsourc.e>

…h#32) Parses ACTION directives from agent responses and executes PR/issue actions via Claude Code headless sessions with bot identity.

feat(webhook): NousResearch#32 headless CC invocation + routing fixes

) When the WebUI's model picker sets the active provider to "venice" (or "crof", "bankr", "cometapi"), the agent's resolve_provider_client() looked up the slug in PROVIDER_REGISTRY, failed to find it, and raised: "Provider 'venice' is set in config.yaml but no API key was found. Set the VENICE_API_KEY environment variable..." VENICE_API_KEY WAS set in env — the failure was because the agent had no idea which env var or base URL to use for "venice" as a slug. PROVIDER_REGISTRY entries for the other OpenAI-compatible aggregators (Z.AI, MiniMax, Mistral, etc.) already existed; Venice/CrofAI/Bankr/CometAPI just hadn't been added in the upstream code. Adds four api_key-auth entries mirroring the existing OpenAI-compat ones: - venice → https://api.venice.ai/api/v1 + VENICE_API_KEY - crof → https://crof.ai/v1 + CROF_API_KEY - bankr → https://gateway.bankr.bot/v1 + BANKR_API_KEY - cometapi → https://api.cometapi.com/v1 + COMETAPI_API_KEY Companion to the WebUI side (PRs #26/#27/#29/#30/#32/#33) which made these providers discoverable in the model picker with their live /v1/models catalogs. Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

…ink MCP call — closes D-kr3-st2 Fourth + final mechanical follow-on swap unlocked by K-10 + 0083 (IsoKron PM #32). Same pattern as KR-7 (chain-emit) and KR-8 (scratchpad-write): create_relationlink body replaces `raise RelationLinkWriteNotAvailableError()` with `await mcp_client.invoke('kora__create_relationlink', {...})`, returning the substrate-assigned link_id. ~30 LOC across relationlink.py + tools/iso_link.py + tests + docs. All three KR-3 ST2 substrate blockers are now resolved substrate-side: * actor_kind CHECK extended to include 'kora' via 0083 (prod-applied) * public.kora_create_relationlink SECDEF function exists * kora.relationlink.created event literal in event_log_event_type_check (300th literal in the set post-0083) * kora__create_relationlink Sea MCP tool registered Production-test posture per IsoKron PM #27: * K-10's kora__create_relationlink handler is a notImplementedHandler stub on substrate main; substrate-team's dispatch tier (task NousResearch#395) un-stubs + bridges Layer-A wsk_* auth → Layer-B actor_kind='kora'. * KR-9 code shape is sound; mock tests verify correctness. * Production deploys wait on dispatch tier landing — identical posture to KR-7 / KR-7b / KR-8. Verify-at-first-live-emit per spec § 3: * event_log row with event_type = 'kora.relationlink.created' * event_log.actor_id = 0076-seeded canonical Kora actor (NOT token-UUIDv5) * relationlink row with chain_event_id matching the emitted event + created_by_actor_kind = 'kora' relationlink.py: * create_relationlink body: live call to mcp_client.invoke. K-10 contract output: {'link_id': '<uuid>', 'chain_event_id': '<uuid>'} — projected to a plain str link_id return. * mcp_client param now required (was Optional with deferred-error default). * New rationale_block_id + evidence_block_ids params match K-10's input schema. Legacy `rationale` parameter preserved for one- release back-compat (silently dropped — superseded by rationale_block_id). * Defensive: None mcp_client → ValueError; unexpected response shape → RuntimeError (mirrors KR-7/KR-8 pattern). * RelationLinkWriteNotAvailableError class kept exported tagged [kora.isokron.deprecated] for one release. Original three-blocker message preserved inside the message body for grep stability. tools/iso_link.py:_handle_iso_link_create: * Dropped the deferred-envelope path. Success → {"ok": True, "link_id": <substrate-uuid>}. Substrate failure → {"ok": False, "substrate_error": True, "tool_name", "message"} — same structured signal shape as KR-8's iso_node_create. * Fetches IsoKronMCPClient via get_mcp_client(); MCP-client- unavailable returns {"ok": False, "error": ...} envelope. * Removed unused RelationLinkWriteNotAvailableError import. Tests (7 new + 2 updated): * test_iso_link_tools.py: - test_create_relationlink_raises_deferred_write_error → test_create_relationlink_invokes_kora__create_relationlink: happy path asserts spec-pinned arg shape (workspace_id, from/to entity_id + kind, link_type, evidence_block_ids=[]). - New test_create_relationlink_propagates_mcp_invocation_error (substrate active-edge uniqueness violation surfaces). - New test_create_relationlink_rejects_none_mcp_client. - New test_create_relationlink_rejects_unexpected_response_shape. - New test_create_relationlink_passes_rationale_block_id_when_present (optional args pass-through). - New test_relationlink_write_not_available_error_still_importable_post_kr9 (deprecation runway). - test_iso_link_create_handler_returns_deferred_envelope → _returns_ok_envelope_with_substrate_link_id: success-envelope + verifies spec-pinned tool name in invoke recording. - New test_iso_link_create_handler_surfaces_substrate_error_envelope: IsoKronMCPInvocationError flips to structured envelope. - _FakeMcpClient routes by tool_name (returns link-N for kora__create_relationlink). _FakeProviderConnection gains get_mcp_client(). BUILD_DEVIATIONS: * D-kr3-st2-no-relationlink-write-mcp-tool moved Open → Closed with Rule-5 spec-quote, call-site refactor inventory, production-test posture, all-three-blockers-resolved-substrate-side note, deprecation-runway note, verify-at-first-live-emit step. README "Operator pitfalls": * "Deferred-surface summary" table replaced with "All BUILD_DEVIATIONS closed code-side as of KR-9 (parallel-merged with KR-7b + KR-8)" note. All 5 deferral closures listed under Recently closed. * Individual "iso_link_create writes are blocked" pitfall rewritten as "RelationLink writes route via kora__create_relationlink (KR-9)" with success/failure envelope shapes + operator grep pointer. Parallel-mergeability note: KR-7b + KR-8 + KR-9 modify disjoint files (KR-7b: capability_matrix_mirror.py + provider.initialize; KR-8: scratchpad.py + provider sync_turn/on_memory_write; KR-9: relationlink.py + tools/iso_link.py). Merge interleaves; each PR narrows its E2E assertions to its own surface so test fixture counts don't fight. PM handles README + BUILD_DEVIATIONS final reconciliation on merge order. Local gates: * ty check — 7,337 diagnostics, zero-delta vs KR-7 baseline. * pytest tests/plugins/memory/ — 357/357 passing. * Full suite via xdist (-n auto): 24,629 / 181 failed / 12 errors / 129 skipped. Same tests/tools/* xdist isolation noise as documented across prior PRs; none touch isokron. After KR-9 + KR-7b + KR-8 merge, all four BUILD_DEVIATIONS are closed code-side. Standing-by state becomes dispatch-tier-gated (waiting on substrate-team task NousResearch#395 + service-token mint for production deploys). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

- path-to-regexp: 0.1.12 → 0.1.13 (CVE-2026-4867, GHSA-37ch-88jc-xwx2) - picomatch: 2.3.1 → 2.3.2 (CVE-2026-33671, GHSA-c2c7-rcm5-vvqj) - undici: 7.23.0 → 7.27.1 (CVE-2026-1526/CVE-2026-2229/CVE-2026-1528) - serialize-javascript: 6.0.2 → 7.0.3 (GHSA-5c6j-r48x-rmvq, via overrides) Fixes Dependabot alerts #37, #34, #33, #32, #29, #27

Adds two new completion gates that fire alongside the Part 1/2 gates. Closes hermes-jarvis#63 (PR-existence verification) Closes hermes-jarvis#32 (doc-drift check) Context: hermes-jarvis#61 (bootstrap-paradox case study) ## NousResearch#63 — verify_pr_urls_exist When a verdict result or summary contains a GitHub PR URL pattern, the dispatcher runs `gh pr view <url> --json number` to verify each URL resolves. Phantom URLs (404 with "Not Found" / "Could not resolve" / "no pull request" in stderr) reject the completion. Indeterminate cases (gh missing, network error, unauthenticated) fall open — workers can still complete in offline / broken-gh envs without being trapped. Catches the 2026-06-09 Tchalla case (hermes-jarvis#61): release-gate reviewer blocked with "cannot run gh pr diff 42" on PR NousResearch#42 that didn't exist. With this gate, his completion would have surfaced the phantom URL specifically, prompting him to surface the real cause. Opt-out: `metadata.x_phantom_pr_ok` with ≥20-char string reason. ## NousResearch#32 — verify_doc_drift For tasks whose tenant slug encodes a version (`marvel-swarm-vN-N-test`), the gate scans `README.md` / `README` in the workspace for older `vX.Y` mentions outside a history-style heading (`## History`, `## Older versions`, `## Previous versions`, `## Archive`). Stale mentions reject the completion. CHANGELOG.md is intentionally skipped — older versions are expected there by definition. Catches the 2026-06-09 agent-dashboard PR #1 case (hermes-jarvis#61): README still said "v6.2 Marvel swarm test target" while the chain was v6.6. No reviewer flagged it. Opt-out: `metadata.x_doc_drift_ok` with ≥20-char string reason. ## Tests 19 new tests added to `test_kanban_completion_gates.py`: - TestPRExistence (8) — no PR URL skipped, real passes, phantom rejects, mixed real+phantom flags only phantom, indeterminate falls open, summary scanned, dedup, opt-out - TestDocDrift (10) — non-versioned tenant skips, no README skips, stale README rejects, current README passes, History section excused, CHANGELOG file excused, higher version not stale, scratch skipped, opt-out 83 passed in test_kanban_completion_gates.py (up from 64). Zero regressions on adjacent paths. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

…earch#32) - `verify_pr_urls_exist` (closes hermes-jarvis#63) — scans verdict text + summary for GitHub PR URLs and runs `gh pr view` per URL. Phantom URLs (404) reject; indeterminate (gh missing / network) falls open. Strict 404 classification excludes DNS/network token patterns so "could not resolve host" stays indeterminate. - `verify_doc_drift` (closes hermes-jarvis#32) — for tasks whose tenant slug encodes a version (marvel-swarm-vN-N-test), scans README.md/README for older vX.Y mentions outside a history section. Depth-aware section-tracking so `## History\n### v6.2 details` correctly excuses the subsection. Opt-outs: x_phantom_pr_ok / x_doc_drift_ok (≥20-char string reasons). Context: hermes-jarvis#61. 90 tests pass after two self-review passes. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

…te (NousResearch#32) * fix(gateway): add OutboundGuard to prevent cross-channel Slack misroute Production incident (2026-06-19 11:20:58–11:22:32 UTC): Inbound from C0AH3RY3DK6 (WorldArchitect) at 11:20:58. Orphan reply 1781868147.039389 posted to C0AJQ5M0A0Y (home channel) at 11:22:27 — 5 seconds BEFORE the correct reply to C0AH3RY3DK6. No thread_ts on the orphan because the inbound had no parent in C0AJQ5M0A0Y. Root cause class: the gateway's outbound path used a chat_id that was NOT derived from the inbound that triggered the response. This change adds OutboundGuard (gateway/outbound_guard.py) — a task-local contextvar that pins the inbound chat_id for the lifetime of _handle_message_with_agent. Any adapter.send call whose chat_id mismatches the active inbound is logged as a WARNING and recorded in violations for the regression test. Wiring: - Pin source.chat_id at handler entry (gateway/run.py:6943). - Reset in the existing finally block (gateway/run.py:7953) so the next handler's verify_send() checks are not contaminated. Regression test (tests/hermes_cli/test_outbound_guard.py): - 8 tests cover pin/verify round-trip, exact incident repro pattern (pin A, send to B, send to A → exactly one violation), task-local isolation across concurrent asyncio tasks, allowed_extra_destinations opt-out for home-channel startup/shutdown notifications, and the unrestricted case where no chat_id is pinned. - All 8 tests pass. * fix(gateway): wire OutboundGuard into real send paths; per-instance ContextVar; None-block - outbound_guard.py: move _active_chat_id ContextVar into __post_init__ so each OutboundGuard instance has its own per-instance ContextVar (regression for CR major on the dataclass mutable-default smell). Treat verify_send(None) while inbound is pinned as a violation rather than a silent bypass (regression for codex-connector P1 and CR major). Add module-level singleton _global_guard with pin_inbound/unpin_inbound/verify_outbound helpers so production call sites that don't hold a guard reference still see the handler's pin. - run.py: route the per-handler pin through both the per-instance guard AND the module-level singleton; unpin both in the finally block. - platforms/slack.py: SlackAdapter.send calls verify_outbound(chat_id) before chat_postMessage; returns a failed SendResult when misaligned. - delivery.py: DeliveryRouter._deliver_to_platform calls verify_outbound(target.chat_id) before adapter.send; raises ValueError on misalignment (cron deliveries outside a handler still pass through because the guard has no pinned inbound). - stream_consumer.py: replace every self.adapter.send call with a new _guarded_send helper that wraps verify_outbound around the send; on violation returns a fake failed SendResult without invoking the underlying adapter. - tests/hermes_cli/test_outbound_guard.py: add test_none_chat_id_while_inbound_pinned_records_violation, test_module_level_singleton_pins_and_verifies, test_per_instance_contextvar_is_not_shared_between_guards, test_real_slack_send_with_aligned_chat_id_succeeds, and test_real_slack_send_with_misaligned_chat_id_is_refused. Apply the CR nitpicks: f-string assertion keys + shared guard instance in the task-locality test. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(gateway): sentinel for no-active-inbound; guard all slack write paths Three CR Major findings on the previous commit (234aafe6b1) addressed: 1. chat_id=None was bypassing the guard while inbound was pinned. The guard had no way to distinguish 'no handler active' from 'handler active with missing inbound chat_id' — both states collapsed to None via the Optional[str] ContextVar. Introduced _NO_ACTIVE_INBOUND sentinel object so verify_send can refuse sends through a handler that has no idea what channel to target (incident class includes no-destination sends when upstream code forgot to thread source.chat_id through). 2. The CR Major asked to extract the verify_outbound guard logic into a reusable helper and call it from every Slack write path. Added module-level _slack_guard_check() in slack.py and wired it into all 11 write methods: send, send_private_notice, _upload_file, send_multiple_images, send_image_file, send_image, send_voice, send_video, send_document, send_exec_approval, send_slash_confirm. 3. _send_draft_frame in stream_consumer.py uses adapter.send_draft (not adapter.send), so it slipped through the previous _guarded_send wiring. Added verify_outbound check at the top of _send_draft_frame that disables draft streaming on a misroute. Tests: 13 existing tests pass + 3 new tests covering the sentinel: - test_pin_none_marks_handler_active_and_refuses_sends - test_pin_none_also_blocks_via_module_singleton - test_active_chat_id_distinguishes_inactive_from_pin_none Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(gateway): bound OutboundGuard.violations retention with deque(maxlen) CR Major (review 4546711137) flagged the violations list as growing unbounded for the lifetime of the _global_guard singleton — a misbehaving handler spinning in a loop could exhaust process memory. Replaced List[dict] with collections.deque(maxlen=MAX_VIOLATION_HISTORY=256). Retains the most recent 256 violations for diagnostics while bounding memory at a fixed cost. Added violation_count property for clean test assertions (avoids deque/list equality noise). Added 2 regression tests: - test_violations_list_is_bounded — verifies retention cap - test_violations_clear_works_with_bounded_deque — verifies clear_violations Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

…ion preflight + cost-aware gate (build stage, gate pending) ATTEMPTED: - NousResearch#32 first-order candidate source: pipeline.firstorder_questions (one naive raw_chat asking for the K best clarifying questions, numbered-parse -> tagged family="First-order semantics", lens="firstorder"); infogain.run() round-1 merge gated on the families-block key "firstorder" (default "off"); --firstorder / INFOGAIN_FIRSTORDER plumbing + families_cfg(firstorder=...); dry-run STAGE 1c. Scored by the normal pipeline; formula frozen. - NousResearch#33 discrimination preflight (audit A7): validate_evsi.discrimination_preflight -- 8 static forced-choice fixtures (one-token semantic flips + cosmetic rewording), score <6/8 -> exit 2; --strict-preflight flag on validate_evsi + outcome_eval (default off, 8 calls/model). - Cost-aware gate instrumentation (Part 0b): outcome_eval.analyze() prints per-arm mean wall/tokens/calls (missing usage -> "--"); zeroshot/prompt-evsi arms now carry meta.usage; new gate arms nbq-firstorder / nbq-firstorder-behavior. - Bank +6 agentic tasks (AGENTIC 8->14, gate n 28->34), each combining a first-order + a lens-class ambiguity, reference-passes/misreading-fails verified. - New docs-only nbq-improve skill (the self-improving REVIEW->RESEARCH->PLAN->BUILD->EVALUATE-> JOURNAL->LOOP protocol) with preregistration template, verdict rubric (incl. this commit-message contract), and a research-populated backlog; next-best-questions README §5 meta-lessons + §7 + SKILL/evals cross-links. WHY: - P4 gap hypothesis (from the NousResearch#28 verdict): the residual gap over the zeroshot arm is generation altitude, not the value judge -- so expose first-order semantic unknowns AT GENERATION and let the frozen formula dispose. Institutionalize the research -> pre-registered experiment -> mechanical verdict -> journal loop as a documented skill, now cost-aware (Δtokens/Δwall measured alongside Δresult). - NousResearch#33: today's emptiness preflight passes a model that answers but judges randomly; verify actual better-vs-worse discrimination before trusting realized-value judgments. RESULT: - NousResearch#32: build stage, gate pending. Offline: 206 tests green (inert-by-default pin holds -- a cfg from DEFAULTS makes no firstorder call and emits no firstorder lens). Live smoke (rate-limiting prompt, --firstorder on): 3 firstorder-lens candidates scored through the pipeline, 2 surviving at value ~0.69. Pre-registered gate (arms baseline/nbq/nbq-firstorder/nbq-firstorder-behavior/ zeroshot, both banks n=34, K=3, all-deepseek, --strict-preflight) + ADOPT rule to run next; verdict commit to follow. - NousResearch#33: PASS -- discrimination_preflight scores fast 8/8, deepseek 8/8 (both eval-duty models discriminate perfectly on the fixtures). Instrument adopted; no elicitation change, so no gate. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

…h#33 adopted; journal + v1.3.4 ATTEMPTED: - Ran the pre-registered NousResearch#32 gate (objective outcome harness, n=34 = 20 micro + 14 agentic, K=3, all-deepseek, --max-rounds 1, --strict-preflight; 170 cells / 52 min; raw ~/.hermes/outcome_eval_32.json) and applied the ADOPT rule mechanically. Journaled the verdict both ways across README §6, design-decisions (§First-order candidate source NousResearch#32 + §Discrimination preflight NousResearch#33), evsi-validation-findings (pre-registered rule quoted verbatim, incl. the efficiency ceiling), and the nbq-improve backlog. Bumped nbq 1.3.3 -> 1.3.4 (negative result, no default flip). WHY: - NousResearch#32 tested the NousResearch#28 successor hypothesis: the residual P4 gap over the naive zeroshot arm is generation altitude, not the value judge. First cost-aware gate: efficiency (wall/tokens/calls) measured alongside Δresult, with a pre-registered 10%-added-wall ceiling that vetoes even a result win. RESULT: - NousResearch#32: NO ADOPT. Per-arm pass vs baseline 0.460 -- nbq +0.083 (9W/4L, un 74%, 25.0s/20221tok/38.3c); nbq-firstorder +0.132 (7W/3L, un 78%, 29.2s/23944tok/45.4c); zeroshot +0.274 (15W/1L, p=0.0005, un 31%, 5.9s/154tok/1c). Paired nbq-firstorder vs nbq: Δ+0.049 > 0 but 6W/6L/22-tie (broad-win guard fails); unanswerable 77% (>50%); lens-payoff regression (log-clean 0.67->0.33); +16.8% wall (>10% ceiling). All four adopt conditions fail. Altitude has signal (mean beat plain nbq) but did NOT close the gap -- zeroshot still dominates at ~1/5 wall, ~1/150 tokens; the residual gap is ANSWERABILITY. firstorder stays built, off-by-default. NousResearch#30 answerability weighting re-opened (its condition, unanswerable >50%, is now met). - NousResearch#33: PASS/adopted as opt-in instrument -- discrimination_preflight fast 8/8, deepseek 8/8. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

…retro probe ATTEMPTED: First real use of the nbq-improve protocol (iteration two) — a conditional full lap. Built a zero-model-call retro probe (evals/probe_answerability.py + 5 tests) to gate whether to build NousResearch#30 answerability weighting, testing NousResearch#30's premise against the existing objective corpus (outcome_eval_32.json: per-question EVSI meta.q_values, answerability qa[].revealed, outcome frac). WHY: NousResearch#32 pinned the residual P4 gap on answerability (unanswerable 77% > 50%), re-opening NousResearch#30. Rather than build first, probe the premise for free: do kept high-EVSI *unanswerable* questions cause objective failure? The cheapest falsifying test uses data we already have — zero new model calls. RESULT: PARK (premise NOT supported, n=34). top1_unans x fail r=+0.052, SE=0.177, does not clear SE (no association); any_unans x fail r=-0.112, base rate 0.971 => DEGENERATE (near-universal unanswerability => no answerable-question contrast to steer toward) + wrong-direction; tertiary n_unans x frac r=-0.219 (weak whiff only). Delta-result: none (no NousResearch#30 build; conditional gate honored in commit order). Delta-cost: zero (probe is offline). Verdict per the pre-registered rule (quoted verbatim in evsi-validation-findings.md): PARK. NousResearch#30 re-open now requires a higher-contrast corpus (candidate 2/3) plus a non-self-rated mechanism (batched strict-simulator answer/refuse probe, designed + parked in prereg-iteration-two.md item B, unbuilt). Methodology banked: cost is multi-dimensional — verdict-rubric.md now requires a per-axis ceiling (wall, tokens, calls), any bust vetoing a result win. Suite 206 -> 211 green. next-best-questions 1.3.4 -> 1.3.5; nbq-improve 1.0.0 -> 1.0.1. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Upstream TS 6 migration (3bfbb3f) introduced unresolved type errors in web/src/ (ChatSidebar, PairingPage, PluginsPage, etc.) that cause tsc -b to fail with exit code 2. vite build uses esbuild and does not type-check, so the production bundle is unaffected. This unblocks the GHCR fork build (runs NousResearch#31/NousResearch#32 both failed).

…y (§1) (NousResearch#32) * fix(artifact-actions): confirmation prompt leads with trusted intent name; codify entity-ref rule (§0) Two pre-merge security fixes identified in the V2 spec review (§0): §0.1 — _build_confirmation_prompt now leads with the server-resolved intent name rather than the artifact-authored label. A declaration labelled "Refresh" bound to artifact.entity.tombstone previously produced a dialog the user could confirm thinking they were refreshing; it now reads "artifact.entity.tombstone — ..." so the real operation is unambiguous. Artifact label appears as secondary text when it differs. Two tests assert the invariant: one that the first line starts with the intent name, one that a mismatched label ("Refresh" → tombstone) still appears downstream. §0.2 — Module docstring now codifies the entity-ref resolution rule: handlers must treat entity_ref as a lookup key into pinned artifact content and must extract external IDs from stored entity fields, never from the raw client string. Wrong-vs-right example included. Built-in handlers already conform; the rule is now the stated contract for plugin authors. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(artifacts): plugin action loader — ~/.hermes/plugins/actions/*.py (§1) Adds a plugin system for Tier-1 artifact action handlers so per-deployment integrations (e.g. linear.issue.delete) don't require forking core. Design: - Plugins live in ~/.hermes/plugins/actions/*.py. Each file calls register_handler("name", fn) at load time. - Authorship/activation split: the loader resolves the real path and hard-fails (not warns) if the plugins dir sits under any registered agent workspace root. This makes the reload trigger safe to expose publicly — agent tools/CLI/RPC can trigger reload, but only the human can author what activates. - Reload is explicit only (actions.reload RPC). No file-watching; silent auto-reload would turn agent file-write tools into a code-injection path if the workspace-root check were ever misconfigured. - Staged swap: all plugin files execute against a staging registry; any parse/exec error aborts the swap and leaves the last-good handlers live. The traceback is returned to the caller. - Registry diff (added/changed/removed) logged on every reload with file list. Pairs with the invocation ledger (§2) to answer "what code ran". - Built-in handlers (artifact.refresh, artifact.entity.tombstone) survive reload; a plugin can deliberately override a built-in by name. - initial_load() called at gateway startup before gateway.ready fires. New: tui_gateway/artifact_plugin_loader.py — loader, staged swap, diff tests/gateway/test_artifact_plugin_loader.py — 11 tests Modified: tui_gateway/server.py — actions.reload RPC (error 5218); artifact.action.reload in gateway.capabilities tui_gateway/entry.py — initial_load() at startup Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

…ference (NousResearch#34) Fulfills the docs follow-up from NousResearch#32 (§1 plugin loader) — the module docstring in artifact_actions.py already points at docs/plugins/actions.md for the entity-ref wrong-vs-right example; this adds the file. Covers: - Where plugins live, handler signature, register_handler contract - Explicit reload (RPC / chat / startup), staged swap semantics, registry diff + ledger pairing - The authorship/activation split and why reload is never file-watched - The mandatory entity-ref resolution rule with wrong-vs-right code - Destructive role declaration and the challenge flow - Full reference plugin: linear.issue.delete — lookup from pinned content, linear_id from stored row fields, env-var credential, GraphQL error surfacing - Artifact binding declaration + inline HTML marker wiring - Iteration loop and built-in override behavior Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

…PR#31 review) (NousResearch#32)

… Sprint NousResearch#30 evidence: none verified: - zentao story list --product=11 → 4 stories (NousResearch#117-120) - zentao task list --execution=30 → 13 tasks (NousResearch#45-57) - http://pm.test.com/zentao/story-browse-117.html Changed: - .zentao/mapping.json: winpeek#6 → peeka数字机器人NousResearch#11, SCRUM NousResearch#29, Sprint NousResearch#30 - tasks/mim-chat-v1-*: updated zentao IDs NousResearch#32-44 → NousResearch#45-57 - tasks/README.md + CLAUDE-module.md: zentao URLs/commands Co-Authored-By: Claude <noreply@anthropic.com>

Dep-inventory items #26/#27/#32: three copies of the same uv - pip - ensurepip strategy grew independently, and lazy_deps' docstring admitted being a mirror of tools_config's. Copies drift: the lazy copy had learned that a uv resolver failure must be final (falling to pip discards exclude-newer and can install a quarantined release) while the setup-hook copy still fell through, and only one of them hid console windows on Windows. installation/pip_ladder.py now owns the mechanics, stdlib-only under the same run-dont-parse audit as the rest of the package (the ladder exists precisely for venvs that are missing pip). The policy choices that used to be baked into each copy are arguments: * uv_bin - the caller decides what acquiring uv is worth. Setup hooks pass ensure_uv() (downloading uv is in scope during setup); lazy installs pass resolve_uv() (a download as a side effect of an optional import is not). * uv_resolver_failure_is_final - the lazy policy above. Availability failures (binary vanished, could not exec) always fall through: uv never evaluated the requirements, so pip is not a second opinion. * target/constraints - the durable overlay mode sealed installs use. tools_config._pip_install and lazy_deps._venv_pip_install are now thin policy wrappers; agent/lsp/install.py already delegated to the former, so the third copy collapses transitively. A structural test walks both wrappers' AST (code, not docstrings) and fails if either regrows a private ladder. The 5 failing tests in test_lazy_deps.py fail identically without this change (verified by stash round-trip): pre-existing on the branch, not introduced here.

docs: technical memory architecture + landing page clarity

b406c03

UfukNode closed this Feb 26, 2026

UfukNode deleted the docs/technical-memory-architecture branch February 26, 2026 03:11

claude-bot-maiixu Bot added a commit to maiixu/hermes-agent that referenced this pull request Apr 13, 2026

Merge pull request #9 from maiixu/claude/implement-32-headless-cc

31fb533

feat(webhook): NousResearch#32 headless CC invocation + routing fixes

ashneil12 mentioned this pull request May 18, 2026

fix(auth): register Venice/Crof/Bankr/CometAPI in PROVIDER_REGISTRY ashneil12/vanilla-hermes-agent#16

Merged

3 tasks

rafe-walker mentioned this pull request May 20, 2026

feat(KR-9): swap relationlink-create defer for kora__create_relationlink MCP call — closes D-kr3-st2 rafe-walker/kora#17

Merged

11 tasks

dizhaky mentioned this pull request Jun 4, 2026

fix(deps): resolve HIGH severity npm vulnerabilities in website dizhaky/hermes-agent#3

Merged

gabiar-maker mentioned this pull request Jun 8, 2026

feat(jb_outbound): plugin « rien ne part sans accord » (Jean-Billie) gabiar-maker/hermes-fork#1

Merged

This was referenced Jun 9, 2026

v6.7 Tranche 1: kanban_complete verification gates (#28, #62, #64) #43104

Closed

v6.7 Tranche 1: kanban_complete verification gates (#28, #62, #64) 1Team-Engineering/hermes-agent#11

Merged

Soju06 added a commit to Soju06/hermes-agent that referenced this pull request Jul 16, 2026

docs(patches): register search-slow-query-log (patch NousResearch#32)

6bd2583

Meraniya pushed a commit to Meraniya/hermes-agent that referenced this pull request Aug 6, 2026

fix(memgw): catch ValueError on malformed URL in is_available (Codex …

d47f218

…PR#31 review) (NousResearch#32)

yshen92 mentioned this pull request Aug 14, 2026

Phase 10.2B: planned-stop runtime correction (stdlib-only marker protocol + H3 standalone stop) yshen92/hermes-agent#2

Closed

kaecer68 mentioned this pull request Aug 22, 2026

feat(runtime): Plan F 護欄 + Plan B runtime toolset + 軟警告 + 競爭 SOP #91951

Open

6 tasks

Navigation Menu

Uh oh!

docs: technical memory architecture + landing page clarity - #32

docs: technical memory architecture + landing page clarity#32
UfukNode wants to merge 1 commit into
NousResearch:mainfrom
UfukNode:docs/technical-memory-architecture

UfukNode commented Feb 25, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

UfukNode commented Feb 25, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants