18 — Coverage and gap map
Coverage map for quota, multimodal input, latency, fleets, portability, literature, governance, and online quality.
Summary
The core techniques chapters cover text-token economics, caching, retrieval, output discipline, routing, provider features, infrastructure, composition, and validation. This map identifies the decision axes that need separate treatment: subscription quota, multimodal input, latency and human time, fleet behavior, portability, current literature, and runtime governance.
The strongest correction is conceptual: a subscriber constrained by a usage cap should optimize tasks per cap, not API dollars per task. Multimodal input is another distinct token class rather than a footnote to text context. Latency and quality also need explicit accounting because a cheaper token path can still be slower or less reliable.
Question and scope
Which independent cost and quality axes are already covered, and where do material evidence gaps remain?
Method
Coverage was assessed against six independent axes rather than the dossier table of contents:
| Axis | Decision dimension |
|---|---|
| Cost metric | dollars, subscription quota, wall-clock time, human attention |
| Token class | fresh input, cache write, cache read, visible output, thinking, image, document |
| Emission surface | system prefix, tools, message history, model output, media tool results |
| Lever | style, tokenizer, context architecture, caching, retrieval, routing, infrastructure, governance |
| Scope | turn, session, cross-session, capsule, fleet, organization |
| Delivery | instruction, configuration, hook, orchestrator, provider feature |
The existing chapters were checked for absent, incidental, partial, or decision-complete treatment. A topic remains a gap when the corpus mentions it but does not supply the measurement or decision rule required to choose an action.
Findings
Current coverage map
| Topic | Current assessment | Decision stake | Detailed chapter |
|---|---|---|---|
| Subscription and quota economics | Dollar economics are mature; cap accounting remains partly provider-opaque | Cache-heavy levers can rank differently under quota than under API prices | 19 — Subscription and quota economics |
| Multimodal input | Separate measurement required for images, screenshots, and PDFs | A screenshot can be cheaper or much more expensive than structured text | 20 — Multimodal token economics |
| Latency and human time | Token and dollar models do not decide the time tradeoff | Fan-out, fast modes, and compression hops can exchange tokens for elapsed time | 21 — Latency and time economics |
| Fleet and multi-tenant caching | Self-host mechanisms are covered; hosted cache scope is not fully observable | Spawn timing, dynamic prefixes, and quota attribution change fleet efficiency | 22 — Fleet and multi-tenant cache |
| Cross-agent portability | Individual mechanisms are documented, but support differs by runtime | A stack tied to one hook or provider is fragile | 23 — Portability matrix |
| Literature and product surface | Provider features and research continue to change | New mechanisms can strengthen, qualify, or leave existing decisions unchanged | 24 — Literature and market scan |
| Governance and online quality | Offline validation exists; runtime budget and drift controls are thinner | Savings are invalid if measurement overhead or quality regressions erase them | 25 — Governance and online quality |
| Unresolved mechanisms | Several ideas remain conditional or provider-blocked | Frontier ideas need feasibility gates before entering a stack | 26 — Frontier mechanisms |
| Combined verdict | Layer interactions and metric choice need one synthesis | Composition must count overlap, cache effects, recovery, and quality | 27 — Stack verdict |
| Volatile claims | Provider-sensitive claims require an explicit verification contract | A current decision must expose its cutoff and uncertainty | 28 — Provider-sensitive claim verification |
Headline findings
- Quota is a separate objective. Provider caps are not transparently convertible to API dollars, so quota-sensitive conclusions are explicitly bounded where the denominator is unpublished.
- Media must be measured in its native representation. Image and PDF cost depends on dimensions, preprocessing, page handling, and provider rules; text-token intuition is insufficient.
- Latency is not a token subclass. It belongs beside token and quality metrics in the acceptance function.
- Fleet behavior is cache behavior plus orchestration. Prefix identity, dynamic sections, start timing, and provider cache scope determine whether nominally identical agents share work.
- Portability follows the interception boundary. Instruction-only techniques travel widely; provider betas, proprietary hooks, and runtime-specific storage do not.
- Governance is part of net savings. Measurement, recovery, retries, and quality monitoring consume resources and must be charged to the technique.
Implications for jackin❯
For jackin❯, the coverage and gap map evidence identifies which mechanisms are safe to adopt directly and which still require workload-specific validation.
Limitations and unknowns
Evidence boundaries
The chapters use the measurement conventions in 01 — Economics and measurement and the acceptance harness in 16 — Validation harness. Provider-sensitive facts follow the verification contract. Where providers do not publish quota weights, cache scope, or internal token accounting, the result stays bounded rather than inferred.
The dossier's measured heavy-session profile remains a comparison fixture, not a universal workload. Reach must be remeasured for each capsule because a docs-heavy task dominated by native reads presents different optimization opportunities from a shell-heavy code task.
Sources
Evidence and repository references are cited inline beside the claims they support.