"Understanding Frontend and Backend Development" matching MCP tools:

• get_benchmark_historyA

  Silicon AnalystsA

  Historical Benchmarks — the bitemporal benchmark-observations ledger behind the Chip Cost Calculator: wafer cost by node/foundry (deflationary curves), defect-density (D0) learning curves per node, advanced-packaging costs incl. the broken-out CoWoS interposer entity, test cost, backend yield, and HBM $/GB. Each observation carries as_of (the date the reading reflects — curated backfill from dated public archives extends history), detected_at (capture time), and full sourcing metadata (source_type taxonomy: foundry_ir | wfe_vendor_earnings | government_filing | press_release | analyst_report | company_announcement | trade_press | public_web; source_url; confidence high/medium/low). grain=month|quarter returns median/min/max rollups per period; grain=raw returns per-source observations. Access tiers: free key → preview, Pro/Enterprise → full ledger, anonymous → none. USE THIS for: "how has TSMC N5 wafer pricing moved over 24 months?", "is our internal D0 ramp tracking the market's learning curve?", "CoWoS interposer cost trend", benchmarking product-lifecycle cost projections. DO NOT USE for: current point values (use get_wafer_pricing / get_packaging_costs); the daily PIT ledger replay (use /api/v1/snapshot-series); margin history (use /api/v1/margin-trends). Filters: benchmark_type (required: wafer_cost|defect_density|packaging_cost|interposer_cost|test_cost|backend_yield|hbm_cost_per_gb), entity_id, foundry, from/to (as_of bounds), grain (raw|month|quarter), limit. Access: a free API key returns a short preview (latest few observations); Pro/Enterprise unlock the full ledger; anonymous callers get none (empty + a get-a-key note). Cite as "Silicon Analysts — Historical Benchmarks".

  ConnectorNo auth

• configure_shareA

  agent4.ioA

  Configure this share — its name and its **appearance** — fields you don't pass stay as they are (server-side partial merge). - `label`: the name at the top of the chat page, and the browser tab's title. **Renaming a share is this call**; you never need to create a replacement and delete the old one. That would mint a new token, so the link already embedded in the client's site would stop working — the visible name and the address are not the same thing. - `theme_color`: the brand colour, `#RGB` or `#RRGGBB`. **This one colour is all you give** — its foregrounds are derived on save. - `highlight_color`: **only if the brand actually has a second colour.** Most don't; leave it out and nothing changes anywhere. When set, it is used where something should be visible without competing with the primary action: the second series in a chart, and citation markers. Buttons, the current storyline step and user bubbles stay on `theme_color` — two colours fighting over the same element is how a two-colour palette goes wrong. Foregrounds are derived from it the same way. Text/foreground colours are derived server-side to WCAG contrast and stored (a light brand colour automatically gets dark text instead of white) — **do not compute a palette yourself and do not try to set text colours**; they would be overridden. - `logo_url`: absolute URL. The header scales by height, any aspect ratio fits; **the collapsed launcher bubble is square**, so only near-square images (aspect 0.74–1.35) are used on the bubble — a wide wordmark falls back to the platform icon there. Want your mark in both places? Provide a square variant too. - `input_mode`: `text` (text box, default) or `voice` (opens in push-to-talk). Requires the platform's voice backend. - `launcher`: hover tooltip text for the bubble. `theme`: `light` / `dark` / empty = follow the visitor. - `custom_css`: the escape hatch for strict brand guidelines — the injected stylesheet can override our CSS variables (`--acc` / `--acc-fg` / `--acc-text-l` / `--acc-text-d` / `--bg` / `--surface` / `--text` / `--border`); write light values under `:root{…}` and dark under `html[data-theme="dark"]{…}`. **Prefer theme_color**: it carries a readability guarantee, with custom_css the contrast is on you. Get the token from `list_shares` first. Full examples in the Cookbook's configure-branding.

  ConnectorNo auth

• verify_brand_attestationA

  droplinkedA

  Resolve the standalone droplinked brand attestation for a single shop slug. Returns `{ brandSlug, verified, since, signer, chain, attestationUid, revokedAt }`. Use this AFTER `find_inventory` to round-trip an `attestationUid` and render the canonical trust row to the buyer before proceeding to checkout. Gracefully degrades to `verified=false` on backend error / missing brand — the response shape is stable so the agent can always cite trust state. Per the droplinked council, the agent IS the verification UX for Stream B.

  ConnectorNo auth

• verify_methodologyA

  droplinkedA

  Look up a lender's underwriting methodology by lenderId. When called without `methodologyHash`, returns the lender's currently-ACTIVE methodology (the one new Schema B mints reference). When called WITH `methodologyHash`, returns the specific version cited on an existing Schema B attestation — possibly ACTIVE, SUPERSEDED, or REVOKED. Returns `{ found, lenderId, version, methodologyHash, documentUrl, displayName, status, effectiveAt, supersededAt }`. Forensic workflow: read the cited methodologyHash from the on-chain Schema B payload, call this tool with that hash, download the documentUrl, hash it yourself, and compare. Any divergence flags methodology tampering. Pair with verify_lender + verify_credit_risk for the full forensic chain. Graceful clean-slate envelope on missing / backend error.

  ConnectorNo auth

• what_changedA

  Drupal Code QueryA

  Answer "what changed in the core API between two core versions": symbols added, deprecated and removed, as ranked groups with counts. One symbol: lookup_core_symbol. Human write-ups: list_change_records. Every row of one bucket: flat=true with bucket, paged. Every row of the whole diff: the result's bulk block, with attach and sql for the published catalog. Write those rows to a file, so they stay out of the context window. - Bounds are inclusive. Forms: 11.2, 11.2.x, 11.2.0, 11, 11.x. The same version twice is one minor. Upgrading 11.2 → 11.4 means from=11.3. Buckets are independent. - Grouped (default): a head entry is a symbol group; grouped_by is change_record, name_prefix or singleton. head: groups, up to 5. count: symbols. group_count: groups. members: up to 3 per group, highest usage first. Group fields appear only when every member agrees. Rank: max_projects_using desc, then member_count magnitude, tier, count, key; ranked_by states it. When head_covers_all_callers is false, narrow with kind or min_projects_using, or page with offset. - Flat (flat=true, bucket=added, deprecated, removed): rows by projects_using then fqn. Each row: fqn, kind, subsystem, stamp, projects_using, removal_in, removal_kind, replacement when the catalog lists one, change_record_nids. count: public symbols in the bucket after filters. limit ≤ 100. next_offset is absent on the last page. - Filters apply to every count. internal_excluded and test_theme_excluded are counted apart and left out. unplaceable_symbols have no minor in their stamp. - Usage: contrib development branches only, from the evidence rollup as of usage_evidence_built_at. 0 means no caller observed. - change_record_nids: for get_change_record. removal_kind observed: gone. removal_kind scheduled: promised and still present; say "scheduled for removal in 13.0".

  ConnectorNo auth

• list_class_relationsA

  Drupal Code QueryA

  List the contrib classes that extend, implement or use a core class, interface or trait, one row per edge with file and line, paged. Example: "who subclasses FormBase". Call-site counts: list_symbol_users. The symbol's status: lookup_core_symbol. - target: with or without the leading backslash. An unknown target is refused with a pointer at lookup_core_symbol; a fragment there lists candidates. rel_kind: one of extends, implements, uses_trait. project: one machine name. - Development branches only. edge_count: every edge. project_count: projects. count: edges after the per_project cap. project_edges on each row: the project's full count. per_project=50 with project= lists one project in full. - Rows are ordered by project installs, project, source_fqn. Each row: project, branch, installs, source_fqn, rel_kind, file, line, project_edges. limit ≤ 100. next_offset is absent on the last page.

  ConnectorNo auth

• get_standardsA

  TsehaA

  Returns the organization's development standards: coding conventions, project structure, and framework-specific rules. Read-only. Call it before writing or reviewing code, so the result follows this organization's rules rather than general defaults. Call it first without a section to get an index of available sections, each with a note on what it covers, then call again with one section id copied from that index; inventing a section id returns a not-found error naming that step. Request only the sections a task needs - the full content of one section can be long. The framework argument is deprecated: use section with the "framework:" prefix instead. It returns prose rules, not data - use get_style_tokens for visual values and get_component for component APIs.

  ConnectorNo auth

• springroll.approval.submitA

  SpringRollA

  Submits an approval request of any supported type: UAT_PROMOTION, UAT_SIGN_OFF, PRODUCTION_PROMOTION, VISIBILITY_CHANGE, OWNERSHIP_TRANSFER, RETIREMENT, DOMAIN_CHANGE, or ROLLBACK. **An agent may submit but never decide**: SpringRoll requires a human approver, and an agent token cannot approve its own request. Confirm with the user before calling this. It creates review work for named people. Type-specific behaviour: • `PRODUCTION_PROMOTION`: this does NOT deploy. It asks. `releaseId` defaults to the application's latest release, and `targetEnvironmentType` to 'production'. Once approved, call springroll.deploy.promote. • `UAT_PROMOTION`: `targetEnvironmentType` is required, 'uat' (or 'development' where Development needs approval). An approval only unlocks the environment it names. • `UAT_SIGN_OFF`: `targetEnvironmentType` defaults to 'uat'. • `ROLLBACK`: `justification` and `targetEnvironmentType` (the environment to roll back) are required. Put the deployment to restore in `payload.targetDeploymentId`; it defaults to the last successful one. • `RETIREMENT`: `justification` is required. • Every other type takes no `targetEnvironmentType`.

  ConnectorNo auth

• historyA

  recordariA

  Return memories ordered chronologically. Default (important_only=false) includes all memories ordered by COALESCE(occurred_at, created_at) ASC. Set important_only=true to return only memories with occurred_at set (the curated decision timeline). Pass memory_id instead of domain to scope the timeline to a single memory's neighbourhood (depth 2 by default, domain-clipped) — useful for understanding how a specific workstream evolved. memory_id takes precedence if both domain and memory_id are supplied. Optional from/to date filters apply to the effective date. Optional tags filter uses whole-word matching. Optional node_kind filter (space-separated union) restricts timeline entries to matching kinds. For importance analysis beyond the timeline, use significance. Returns lean results only — id, label, and a truncated why_matters excerpt; call recall(id) for full content. When a list or section has 2 or more results, each is rendered as a single compact text line — "[id] label — excerpt (domain, node_kind)" — instead of a JSON object; exactly one result is returned as a full object. Each line also carries the memory's effective date.

  ConnectorAPI key

• explain_transactionA

  cleartraceA

  Classify a single transaction against the attribution engine: which frontend or router originated the trade and by which evidence, the pools it touched, any fee recipients, and whether it was sandwiched. Confidence is per-vector and is reported per result -- a calldata suffix is strong evidence a specific frontend tagged the swap, while a fee recipient is indirect evidence and is never rated high. Pass that qualification through instead of stating the frontend flatly. `estimated_volume_usd` (only with price=true) is a best-effort spot price on the dominant leg. It is an approximation for orientation and must never be quoted as a settlement figure. Fee amounts are exact raw token integers with no decimals or pricing applied. deep=true costs more upstream credits; leave it off unless a shallow classification came back unattributed.

  ConnectorNo auth

• find_continuationsA

  vuln-intelA

  When you're STUCK mid-hunt: describe your POSITION — the attacker state/capabilities you hold, stripped of product names — and get the CONTINUATIONS that worked from positions like it, matched against the full disclosed-report BODIES (the concrete step/payload/precondition), not just the distilled card. This is the "I have a messy pile of capabilities, what are my legal moves?" layer. position: a product-free statement of what you can already do, e.g. "a backend fetches a user-supplied URL during import/webhook and I can't read the response (blind)", or "I hold a low-priv token and can store config that is later rendered to an admin". The richer/sharper the position, the better — vague positions retrieve generic moves. Optional program: restrict to one program's reports (substring match on handle); limit (default 10) caps the moves. Returns concrete 'move_step' techniques from real reports — including non-obvious cross-class moves the by-card layer can't surface (e.g. credential-leak-on-redirect, request-smuggling desync). HARD CONTRACT: every result is status=UNVERIFIED — a LEGAL MOVE, never a confirmed bug. Each carries a 'decisive_check' you must verify against the target (read its code / fire a test) before claiming anything; the corpus generates the move, the TARGET decides if it survives. Complements find_attack_approaches (by-card mechanism) — this is the by-step, full-body layer.

  ConnectorNo auth

• add_custom_domainA

  GrigoraB

  Connect the owner's custom hostname and return the DNS records they must configure. Requires project administrator access. Pass a unique idempotency_key for this connection attempt; reuse it for retries, and use a new one after cancel/re-add. Call get_custom_domain first. Do not replace an existing domain implicitly. A root domain defaults to www as the primary hostname. Set use_www=False only when the owner explicitly requests the root hostname as primary. Present the returned DNS records exactly. The backend checks DNS automatically and enables SSL; the owner never needs to click Verify or call a validate API.

  Connector

  Destructive

  OAuth

• find_continuationsA

  vulntelA

  When you're STUCK mid-hunt: describe your POSITION — the attacker state/capabilities you hold, stripped of product names — and get the CONTINUATIONS that worked from positions like it, matched against the full disclosed-report BODIES (the concrete step/payload/precondition), not just the distilled card. This is the "I have a messy pile of capabilities, what are my legal moves?" layer. position: a product-free statement of what you can already do, e.g. "a backend fetches a user-supplied URL during import/webhook and I can't read the response (blind)", or "I hold a low-priv token and can store config that is later rendered to an admin". The richer/sharper the position, the better — vague positions retrieve generic moves. Optional program: restrict to one program's reports (substring match on handle); limit (default 10) caps the moves. Returns concrete 'move_step' techniques from real reports — including non-obvious cross-class moves the by-card layer can't surface (e.g. credential-leak-on-redirect, request-smuggling desync). HARD CONTRACT: every result is status=UNVERIFIED — a LEGAL MOVE, never a confirmed bug. Each carries a 'decisive_check' you must verify against the target (read its code / fire a test) before claiming anything; the corpus generates the move, the TARGET decides if it survives. Complements find_attack_approaches (by-card mechanism) — this is the by-step, full-body layer.

  ConnectorNo auth

• set_user_regionA

  My wineA

  Change the user's marketplace region (profile country). This overwrites the country saved on the user's My Wine account, so the change applies across My Wine, not only to this conversation. It can be undone by calling this again with the previous country, which the result reports. Only call this on the user's EXPLICIT request to change their region — never as part of the normal sommelier flow, and never on your own initiative. If unsure of the exact spelling, call list_available_regions first. If the named country isn't one the backend allows in a user profile, this refuses and does not change anything. Args: country: Country name, as returned by list_available_regions (case-insensitive).

  Connector

  Destructive

  API key

• springroll.approval.submitA

  SpringRollA

  Submits an approval request of any supported type: UAT_PROMOTION, UAT_SIGN_OFF, PRODUCTION_PROMOTION, VISIBILITY_CHANGE, OWNERSHIP_TRANSFER, RETIREMENT, DOMAIN_CHANGE, or ROLLBACK. **An agent may submit but never decide**: SpringRoll requires a human approver, and an agent token cannot approve its own request. Confirm with the user before calling this. It creates review work for named people. Type-specific behaviour: • `PRODUCTION_PROMOTION`: this does NOT deploy. It asks. `releaseId` defaults to the application's latest release, and `targetEnvironmentType` to 'production'. Once approved, call springroll.deploy.promote. • `UAT_PROMOTION`: `targetEnvironmentType` is required, 'uat' (or 'development' where Development needs approval). An approval only unlocks the environment it names. • `UAT_SIGN_OFF`: `targetEnvironmentType` defaults to 'uat'. • `ROLLBACK`: `justification` and `targetEnvironmentType` (the environment to roll back) are required. Put the deployment to restore in `payload.targetDeploymentId`; it defaults to the last successful one. • `RETIREMENT`: `justification` is required. • Every other type takes no `targetEnvironmentType`.

  ConnectorNo auth

• design.validateA

  AI Design BlueprintA

  Pro/Teams: first-pass surface-craft review of a FRONTEND artefact (component, screen, or flow) against the 8 laws of the Experience Design Blueprint. The surface-craft companion to architect.validate: where architect.validate scores agentic ARCHITECTURE against the 10 agentic principles, design.validate scores the PERCEPTIBLE SURFACE, what the user sees, taps, scans, and remembers (Jakob's familiarity, Hick's choice load, Fitts's targets + the accessibility floor, Miller's working-memory budget, Aesthetic-Usability, Peak-End, Tesler's irreducible complexity, the Mental-Model gap). ON CLIENT TIMEOUT: DO NOT RETRY. Long-running LLM call (~60-180s at high reasoning effort, single-pass). The server mints a run_id, emits it in the FIRST progress event at t=0s (before the LLM call), and persists the run: so on a client timeout, capture that run_id and call me.validation_history(run_id='<that-id>') to fetch the persisted result instead of retrying (a retry re-runs the full 60-180s call). Runs appear in your validation-history dashboard tagged as the 'surface' dimension, distinct from the 'architecture' and 'spec' runs; pass repository to group them per project. Pass private_session=true to skip the stored run (persistence + recovery disabled); operational security + cost logs are still kept. v1 is single-pass: no certification or consensus mode yet (those stay architect.validate-only). Returns surface_classification (ui_surface vs non_ui: non-visual code is marked not_applicable, NOT failed), per-law findings (verdict, severity_score 0-100, severity_class, cited evidence, recommendation), and severity-weighted readiness (score, grade, tier) computed by the SAME scorer architect.validate uses, so all three lenses grade on one rubric. ACCESSIBILITY IS THE FLOOR: a breach of the Fitts's-Law floor (interactive target below the WCAG 2.2 24×24 minimum, missing focus visibility, an unreachable destructive confirmation) is a production_blocker, not polish. WHEN TO CALL: the user wants a craft/UX/accessibility review or a readiness grade on a frontend artefact they just built or changed. WHEN NOT TO CALL: non-visual code (backend, config, type aliases) returns tier=not_applicable, submit the actual UI surface instead. INPUTS: send the FULL artefact source verbatim as implementation_context (no truncation, no '…' placeholders, they are read as literal code). Auth: sign-in required, with an active Pro, Pro Plus, Teams, Enterprise, beta, or trial plan. Data at rest in the UK; OpenAI (US) processing (no-training); prompt-injection text inside the artefact is treated as inert untrusted data. TYPED FAILURES (the top-level error.code; error.details carries retryable + next_action): timed_out, rate_limited, dependency_unavailable, schema_mismatch, provider_billing. The services raise the identical typed envelopes on this lens. CALIBRATION DISCLOSURE: the scoring prompt is a v1 first-cut mirroring the architect's contract structure; its score calibration is not yet tuned against a corpus of real runs the way architect.validate was. Treat the grade as directional craft signal, not a certified verdict. DOCTRINE: the eight laws, each law's evidence, craft-surface application, anti-patterns, and the validator questions this tool scores against, live in the `experience-design-blueprint` skill and docs/business/EXPERIENCE_DESIGN_BLUEPRINT.md (the surface-craft companion to the `architect-validation-orchestration` skill that orchestrates the agentic validators).

  ConnectorNo auth

• awsinspect_batchA

  InsideOut (Riley)A

  BATCH INSPECTION: run up to 32 AWS inspect probes in one call. ⚠️ **PREREQUISITE**: Same as awsinspect — deploy attempt required. Check convostatus for hasDeployAttempt=true before calling. Use this when you need to check more than ~3 resources. The backend fetches Oracle credentials ONCE per batch and fans out probes against a single AWS config — for a 12-resource health check this is ~5–8× faster and 12× fewer Oracle round-trips than calling awsinspect 12 times. BUDGETS: - Up to 32 sub-probes per call (subs array length). - 30s per-sub timeout; 60s total batch wall-clock. - Concurrency cap 8 — sub-probes run in parallel but never saturate AWS. - 512 KB response cap: subs past the cap keep their envelope (index/service/action/ok) but have result replaced with truncated=true. PARTIAL FAILURE IS EXPECTED. The response is an ordered results array; each entry has {index, service, action, ok, result, error}. Inspect each result — do NOT abort on the first error. A credential fetch failure leaves cred-less probes (list-actions, list-metrics) succeeding anyway. REQUIRES: session_id from convoopen response (format: sess_v2_...). Supported services: account, acm, alb, apigateway, apprunner, backup, bedrock, cloudfront, cloudwatchlogs, cognito, cost-explorer, dynamodb, ebs, ec2, ecs, eks, elasticache, kms, lambda, msk, opensearch, rds, route53, s3, sagemaker, secretsmanager, sqs, vpc, waf For a specific service's actions, use awsinspect (singular) with action="list-actions" — batch is not the place for discovery. Batch responses are always summarized (no detail/raw per-sub); use singular awsinspect when you need full metadata or raw API output for one resource. EXAMPLES: - awsinspect_batch(session_id=..., subs=[ {"service":"ec2","action":"describe-instances"}, {"service":"rds","action":"describe-db-instances"}, {"service":"vpc","action":"describe-vpcs"}, {"service":"s3","action":"list-buckets"}]) - awsinspect_batch(session_id=..., subs=[ {"service":"ec2","action":"get-metrics","filters":"{\"hours\":6}"}, {"service":"rds","action":"get-metrics","filters":"{\"hours\":6}"}])

  ConnectorNo auth

• gcpinspect_batchA

  InsideOut (Riley)A

  BATCH INSPECTION: run up to 32 GCP inspect probes in one call. ⚠️ **PREREQUISITE**: Same as gcpinspect — deploy attempt required. Check convostatus for hasDeployAttempt=true before calling. Use this when you need to check more than ~3 resources. The backend fetches Oracle credentials ONCE per batch and fans out probes against a single GCP credentials blob — a 12-resource health check is ~5–8× faster and 12× fewer Oracle round-trips than calling gcpinspect 12 times. BUDGETS: - Up to 32 sub-probes per call (subs array length). - 30s per-sub timeout; 60s total batch wall-clock. - Concurrency cap 8. - 512 KB response cap: subs past the cap keep their envelope (index/service/action/ok) but have result replaced with truncated=true. PARTIAL FAILURE IS EXPECTED. The response is an ordered results array; each entry has {index, service, action, ok, result, error}. Inspect each result — do NOT abort on the first error. A credential fetch failure leaves cred-less probes (list-actions, list-metrics) succeeding anyway. REQUIRES: session_id from convoopen response (format: sess_v2_...). Supported services: apigateway, bastion, billing, certificatemanager, cloudarmor, cloudbuild, cloudcdn, clouddeploy, clouddns, cloudfunctions, cloudkms, cloudlogging, cloudmonitoring, cloudrun, cloudsql, compute, firestore, gcs, gke, iam, identityplatform, loadbalancer, memorystore, pubsub, secretmanager, vertexai, vpc For a specific service's actions, use gcpinspect (singular) with action="list-actions" — batch is not the place for discovery. Batch responses are always summarized (no detail/raw per-sub); use singular gcpinspect when you need full metadata or raw API output for one resource. EXAMPLES: - gcpinspect_batch(session_id=..., subs=[ {"service":"compute","action":"list-instances"}, {"service":"gke","action":"list-clusters"}, {"service":"cloudsql","action":"list-instances"}]) - gcpinspect_batch(session_id=..., subs=[ {"service":"compute","action":"get-metrics","filters":"{\"hours\":6}"}, {"service":"cloudrun","action":"get-metrics","filters":"{\"hours\":6}"}])

  ConnectorNo auth

• get_fab_capacityA

  Silicon AnalystsA

  Fab Capacity — Silicon Analysts' per-fab, per-tech-node-class capacity ESTIMATES from the fabs + fab_capacity_snapshots time-series (100+ fab and advanced-packaging sites: TSMC, Samsung, Intel, SMIC, GlobalFoundries, SK hynix, Micron and more; Frontend in kwspm, Backend advanced-packaging in k units/month). Current readings are Silicon Analysts estimates (source_type analyst_report, source_name Silicon Analysts; each entry's capacity_basis = 'sa_estimate'), not company figures (TSMC, Samsung and Intel do not disclose per-fab capacity) — describe them as Silicon Analysts estimates when quoting them. The foundry_ir / wfe_vendor_earnings / government_filing source types are for future dated observations (capacity_basis 'cited_source'). Default mode returns the LATEST state per (fab, node class) at/before as_of, joined with fab metadata (name, foundry, country, status) and availability_status — OUR allocation tier for the fab (fully_booked = our tightest tier, down to available; availability_basis 'sa_estimate'), not a statement by the company. For evidence-graded supply questions (who said a component is allocated or tight, and when) use get_bottlenecks. series=true returns the full dated series — node conversions appear as capacity shifting between node-class rows across effective_dates (e.g. 28nm shrinking while 7nm grows). Every reading carries its source columns (source_type + citation + confidence, where confidence says whether the fab RECORD is company-confirmed, not whether its capacity is disclosed) and period_relation (past / current / future vs as_of; filter on this, not is_projection, which is the stored flag and is also true on every reading of a fab whose record is still an estimate). Latest state does not carry forward an annual series that ended before the dataset's latest year at/before as_of (e.g. a fab that was sold or closed); meta.corrections lists the published corrections to the fabs the query matched. Latest state: all tiers (incl. anonymous). series=true: free key → preview, Pro/Enterprise → full series. USE THIS for: "what is TSMC's 3nm-class installed capacity by fab?", "which fabs sit in our tightest allocation tier (our estimate)?", "how is Fab 14's mature-node capacity being converted over time?", country-level capacity aggregation. DO NOT USE for: node-level annual wafer starts (use get_wafer_pricing's foundry context or /api/v1/foundry endpoints — different granularity, deliberately separate); allocation/lead-time status per node (use get_foundry_allocation). Filters: fab_id, foundry, country, tech_node_class, as_of (latest-state cutoff), series (bool), limit (max entries returned: fab·class rows in latest state, newest readings with series=true). Access: latest state is free for all tiers (incl. anonymous); series=true returns a preview on a free key and the full series for Pro/Enterprise (anonymous gets an empty series + a get-a-key note). Cite as "Silicon Analysts — Fab Capacity".

  ConnectorNo auth

• send_messageA

  AlmuredA

  Post a message on a consultation thread (scope negotiation, delivery, extension, dispute). WHEN TO USE - You are a responder submitting a scope proposal (kind='scope_proposal'). Must include metadata.no_conflict_affirmed=true. - You are the asker accepting a proposal (kind='scope_accepted') — provide responder_agent_id and the system stamps deliverable_type on the consultation. - Either party requesting or accepting an extension (kind='extension_request' / 'extension_response'). - Delivering a draft or final output (kind='draft_delivery', 'final_delivery'). - Free-form back-and-forth during engagement (kind='freeform'). WHEN NOT TO USE - For submitting a full response — use POST /api/v1/consultations/{id}/responses (REST API). - For rating a response — use rate_response. BEHAVIOR - Mutating. Auth required: agent API key. Rate-limited to 10 writes/min. - scope_proposal gate: metadata.no_conflict_affirmed must be true or the call returns an error. - scope_accepted: backend stamps consultations.deliverable_type from the accepted proposal's metadata, and snapshots agent pricing at that moment. - extension_response with metadata.accepted=true: backend updates consultations.expires_at from the most recent extension_request in the thread. - Tier-based per-thread message cap: Tier 0 (<100 lifetime interactions): 100 msgs/thread; Tier 1 (100–999): 250; Tier 2 (≥1000): 5000. - Audit log entry created for scope_proposal, scope_accepted, scope_clarification, dispute_raised. WORKFLOW - Responder: send scope_proposal → asker reviews → asker sends scope_accepted → continue with progress_update, draft_delivery, final_delivery. - Use read_messages to check the full thread history before replying.

  ConnectorNo auth

• awsinspect_batchA

  InsideOut (Riley)A

  BATCH INSPECTION: run up to 32 AWS inspect probes in one call. ⚠️ **PREREQUISITE**: Same as awsinspect — deploy attempt required. Check convostatus for hasDeployAttempt=true before calling. Use this when you need to check more than ~3 resources. The backend fetches Oracle credentials ONCE per batch and fans out probes against a single AWS config — for a 12-resource health check this is ~5–8× faster and 12× fewer Oracle round-trips than calling awsinspect 12 times. BUDGETS: - Up to 32 sub-probes per call (subs array length). - 30s per-sub timeout; 60s total batch wall-clock. - Concurrency cap 8 — sub-probes run in parallel but never saturate AWS. - 512 KB response cap: subs past the cap keep their envelope (index/service/action/ok) but have result replaced with truncated=true. PARTIAL FAILURE IS EXPECTED. The response is an ordered results array; each entry has {index, service, action, ok, result, error}. Inspect each result — do NOT abort on the first error. A credential fetch failure leaves cred-less probes (list-actions, list-metrics) succeeding anyway. REQUIRES: session_id from convoopen response (format: sess_v2_...). Supported services: account, acm, alb, apigateway, apprunner, backup, bedrock, cloudfront, cloudwatchlogs, cognito, cost-explorer, dynamodb, ebs, ec2, ecs, eks, elasticache, kms, lambda, msk, opensearch, rds, route53, s3, sagemaker, secretsmanager, sqs, vpc, waf For a specific service's actions, use awsinspect (singular) with action="list-actions" — batch is not the place for discovery. Batch responses are always summarized (no detail/raw per-sub); use singular awsinspect when you need full metadata or raw API output for one resource. EXAMPLES: - awsinspect_batch(session_id=..., subs=[ {"service":"ec2","action":"describe-instances"}, {"service":"rds","action":"describe-db-instances"}, {"service":"vpc","action":"describe-vpcs"}, {"service":"s3","action":"list-buckets"}]) - awsinspect_batch(session_id=..., subs=[ {"service":"ec2","action":"get-metrics","filters":"{\"hours\":6}"}, {"service":"rds","action":"get-metrics","filters":"{\"hours\":6}"}])

  ConnectorNo auth