Files
promptkit/docs/roadmap/invocation-scoped-token-usage.md

437 lines
23 KiB
Markdown
Raw Normal View History

# Invocation-Scoped Execution Observation
Status: agreed direction; default-provider and vLLM scope under discussion;
implementation pending.
## Purpose
Allow consumers to select execution observation once for an application-owned
operation, rather than attach an observer to every PromptKit request. Nested,
concurrent, and multi-engine calls using that operation's context should
participate automatically. Include optional provider-reported cost alongside
token usage, with built-in cost support initially limited to OpenRouter.
The motivating consumer is CommandKit's optional `ckprompt` integration, which
could use this facility to report token usage for an entire command or pipeline.
PromptKit supplies application-neutral observation and aggregation; consumers
choose how to present or use the results.
## Current Baseline
PromptKit v0.24.0 already provides:
- [ExecutionObserver and ComposeObservers](../../observations.go) for synchronous
metadata callbacks and ordered composition.
- [ExecutionGroup](../../execution_group.go) for concurrent collection, detached
snapshots, and aggregation of the first terminal event for each observed run.
- Presence-aware prompt, completion, total, cached, and cache-write token counts,
including aggregate accounting across retries and repairs.
- Explicit selection through `RunRequest.Observer`, retained for prepared
execution, and [CoordinateRequest.Observer](../../coordinate.go) for
coordinator-selected continuation runs.
The missing capabilities are contextual observer selection and provider-reported
cost accounting. Applications currently have to enroll each request explicitly,
and PromptKit does not expose provider charges. The existing
[consumer observation guide](../consumers/pkg-promptkit.md#observe-an-ordinary-run)
describes that workflow.
## Target Public API
Add one public helper:
```go
func WithExecutionObserver(ctx context.Context, observer ExecutionObserver) context.Context
```
The returned context associates the observer with executions using that context
or derived contexts that retain its values. It composes with any observer already
associated with the context; it does not replace the inherited observer. A nil
observer leaves the inherited selection unchanged.
No engine option, process-wide default, or replacement group type is needed.
Extend the existing result, event, and group surfaces with cost metadata as
described below.
The intended consumer workflow is:
```go
var group promptkit.ExecutionGroup
ctx = promptkit.WithExecutionObserver(ctx, group.Observe)
err := runApplicationPipeline(ctx)
// After all application-owned work has finished, including on failure:
summary := group.Snapshot()
```
The consumer owns context propagation, waiting for its work, and using the
snapshot and error. Calls using unrelated contexts are not automatically
enrolled. Group coverage continues to describe observed members, not future
work or overall application progress.
## Observer Selection And Delivery
### Composition
Preserve existing explicit observers. Deliver each event to the explicit request
observer first, then any coordinator observer already composed with it, then
contextual observers in registration order, from inherited to newly added.
Preserve the existing synchronous callback and panic behavior. Concurrent
executions may invoke a shared observer concurrently; consumers remain
responsible for synchronizing their callback state. `ExecutionGroup` already
supports concurrent use.
### Ordinary And Nested Execution
`Run` selects contextual observation from its invocation context. Each execution
has its own observation identity, recorder, and accounting, including a nested
execution using a context passed to an application callback or injected client.
Inherited observer selection is distinct from private execution state. Existing
clearing of an enclosing execution's private state at a public execution boundary
must preserve the contextual observer selection. Inheriting observation does not
reuse an enclosing run's recorder, totals, or lifecycle.
### Prepared Execution
`RunPrepared` selects contextual observation from the context supplied when the
handle is executed. A handle prepared in one scope and executed in another
participates in the execution scope, not the preparation scope.
The explicit `RunRequest.Observer` remains retained by a successfully prepared
handle as today and composes with the execution-time contextual observers.
Preparation itself emits no execution events. Discarded handles and rejected
execution claims retain their existing observation behavior.
### Coordinated Execution
Continuation runs receive contextual observation through their ordinary `Run`
boundary. `CoordinateRequest.Observer` continues to select continuation runs
only. Additional calls made by application callbacks participate when they use
the scoped context, without being automatically selected by the coordinator's
explicit observer.
Contextual observers are incorporated once per execution, rather than being
re-added by coordination or another forwarding layer.
### Duplicate Registration And Accounting
Registering the same callback through multiple explicit or contextual paths may
deliver the same event more than once. Do not attempt to identify or deduplicate
arbitrary Go function values.
Retain one execution lifecycle per run and reuse `ExecutionGroup`'s existing
terminal-event deduplication. Selecting the same group through multiple paths
must not inflate its totals. Terminal usage is an aggregate, not an additional
contribution to be added to attempt usage. These rules apply to cost as well as
token counts.
## Backend Provider Selection
Add an optional backend `provider` field identifying the API implementation
whose conventions PromptKit should use. It identifies the service contacted,
not the organization that trained the selected model. Backend IDs remain resource
identities; names, namespaces, and endpoint hostnames do not select provider
behavior.
```yaml
promptkit:
backends:
- id: research-router
provider: openrouter
endpoint: https://openrouter.ai/api/v1
api_key_env: OPENROUTER_API_KEY
```
Normalize the final effective provider value by trimming whitespace and
lowercasing. Omitted, null, empty, and whitespace-only values are equivalent.
Reject an unsupported nonempty normalized value as an ordinary configuration
error rather than silently using generic behavior. `openrouter` selects the
OpenRouter conventions described here.
The current generic fallback retains ordinary OpenAI-compatible behavior without
provider-specific defaults or metadata interpretation. Before finalizing this
roadmap, discuss making this fallback an explicit lowest-common-denominator
provider and adding a `vllm` selection. Their names, supported conventions, and
final scope remain to be settled; this document does not yet select a vLLM
contract.
Resolve the field through ordinary ConfigKit composition and inheritance. Carry
the selected value through configuration capture and prepared execution, expose
it in backend inspection, and declare it in the bundled OpenRouter backend.
It is PromptKit metadata, not an outbound `extra_params` entry. Selecting a
provider does not choose a model or alter the configured endpoint. An endpoint
override retains the provider selection.
### Smoke-Test Defaults And Explicit Overrides
When an authentication smoke test is explicitly requested, the selected provider
supplies its default probe convention. `provider: openrouter` supplies the
existing `openrouter_key` convention. Preserve explicit
`smoke_tests.authentication.kind` and `smoke_tests.authentication.endpoint`
settings as overrides:
- A supplied kind selects the diagnostic adapter instead of the provider default.
`kind: none` continues to declare authentication testing inapplicable.
- An omitted/null kind uses the provider default, if available. This permits an
endpoint override without repeating the provider's default kind.
- A supplied endpoint overrides the selected adapter's default destination.
An omitted/null endpoint uses that adapter's existing endpoint fallback.
An absent/null authentication block likewise leaves selection to the provider
default. Clearing the block removes its explicit overrides; `kind: none` is the
explicit way to declare authentication inapplicable despite a provider default.
Without a provider default or explicit adapter, retain existing unsupported
diagnostic behavior. Existing explicit adapters continue to work without a
provider declaration. Reachability and inference-default settings keep their
existing behavior.
These are conventions for explicitly requested diagnostics. Loading a backend,
constructing an engine, and ordinary generation do not initiate probes.
Resolve provider-supplied diagnostic defaults at the provider boundary without
writing them into the loaded configuration or recording them as explicit source
values. Configuration inspection preserves the distinction between configured
overrides and provider-supplied fallbacks, including their existing source
provenance.
### Diagnostic Migration
This changes the current authentication metadata contract: an authentication
object currently requires `kind`, and clearing the object removes its configured
adapter. Under this roadmap, endpoint-only overrides become valid, and clearing
the object restores any selected provider's default. `kind: none` suppresses
that default. Explain these changes in the framework format documentation and
release notes, alongside the new provider field.
### Provider Behavior Ownership
Centralize provider-specific behavior within `internal/llm`, which already owns
OpenAI-compatible transport and OpenRouter authentication-response recognition.
Keep common request construction, credentials, HTTP execution, framing, and
common response fields shared. Provider-specific code owns additional response
metadata interpretation and authentication-probe conventions.
Use one provider-selection mechanism inside that package. Generation,
observation, and smoke-test coordination consume provider-neutral facts or invoke
generic diagnostic operations rather than repeating provider dispatch and
response interpretation. Explicit diagnostic adapter selection remains supported
at this boundary. Update the current OpenRouter-specific diagnostic collaborator
method to a generic operation as part of this consolidation.
Provider-specific files and straightforward dispatch are sufficient initially.
No new `internal/providers` package, registration framework, or broad interface
requiring every provider to implement every capability is needed.
This is configurable selection among PromptKit-supported provider implementations,
not a public API for downstream registration of additional implementations.
## Optional Provider-Reported Cost
### Initial Provider Support
Capture OpenRouter Chat Completions' top-level `usage.cost`, which OpenRouter
defines as the amount charged to the account, denominated in USD. See its
[usage accounting reference](https://openrouter.ai/docs/cookbook/administration/usage-accounting)
and [USD cost explanation](https://openrouter.ai/blog/insights/cost-vs-quality-tradeoff-framework-for-agent-models/).
Do not add `cost_details` breakdowns or combine upstream inference cost with the
top-level charge; those describe different facts and could double-count cost.
For the built-in client, select this interpretation through `provider: openrouter`,
regardless of backend identity or namespace. Do not infer USD semantics from an
arbitrary backend's field named `cost`, or add endpoint discovery or verification.
Without an OpenRouter provider selection, built-in cost is unknown initially.
No separate cost-reporting selector is needed.
Use the cost included in the normal completion response. No additional usage
lookup, pricing request, or opt-in provider request parameter is needed.
### Monetary Representation
Use `float64` amounts in USD. Make the unit explicit in public field names such
as `CostUSD`, rather than introducing a generic amount with an implicit currency.
At the individual model-client response boundary, use an optional amount
(`*float64`): nil means unknown, and a pointer to zero means reported zero.
Injected clients may supply the same optional USD value without needing an
OpenRouter backend; no provider-specific interface is needed.
Expose cost separately from `TokenUsage` and `TokenUsagePresence`, whose fields
remain token counts. For run results, execution events, and group summaries,
use a small presence-aware cost value with `Value float64`, `Known bool`, and
`Complete bool`, following the existing observed-count conventions. Successful
run results should expose cost even when no observer was registered; observers
also provide per-attempt and terminal cost, including available facts on failure.
Binary floating point is sufficient for operational telemetry and keeps decoding,
addition, and the public API lightweight. Do not round to cents or another fixed
scale during capture or aggregation; consumers choose display precision.
Decimal strings or a decimal arithmetic dependency would be appropriate for
exact financial ledgers, while fixed-scale integers would require a selected
precision and rounding policy. Neither is warranted for this reporting feature.
The API does not promise exact decimal arithmetic or invoice reconciliation.
### Presence, Aggregation, And Failures
- An absent or null cost is unknown. Explicit numeric zero is known zero.
A backend that reports no cost remains unknown even when a consumer knows it
has no external charge.
- On a dispatched attempt, a usable reported cost is known and complete for
that attempt. Cost completeness is independent of token-field completeness.
- Sum known costs across dispatched attempts, including initial generations,
retries, and repairs. `Known` means at least one attempt reported cost;
`Complete` means every dispatched attempt did. Unknown values contribute no
amount, but make the total incomplete. With no dispatched attempts, follow
the existing known, complete zero convention.
- Group summaries reuse existing terminal-only aggregation and deduplication:
sum known terminal values, OR their `Known` flags, and AND their `Complete`
flags. Retain existing empty-group and terminal-coverage semantics. A subtotal
from OpenRouter mixed with unreported local-backend cost is incomplete.
- Keep valid cost observed from a decoded successful envelope when a later
choice/content check fails, as with token usage. Invalid framing and non-2xx
error bodies continue to supply no usage. Cancellation or failure may leave
incomplete reporting even when billable upstream work occurred.
- Treat an unusable optional cost value, including a nonnumeric value or one
not representable as a finite `float64`, as unknown rather than making an
otherwise valid generation fail. This does not relax existing response framing
or content validation. An injected client likewise cannot supply a nonfinite
usable cost.
Completeness describes coverage of reported values, not verification of the
provider's billing. Preserve reported usable amounts without pricing inference
or reconciliation.
For a successful run, result cost and terminal-event cost describe the same
dispatched attempts and must agree on value, presence, and completeness. Result
cost must also be the same with observation enabled or disabled. For example,
an unreported failed attempt followed by a successful attempt reporting USD
0.002 yields `Value: 0.002`, `Known: true`, and `Complete: false`. Apply the same
accounting through repairs and ordinary or prepared execution.
Group cost completeness concerns the terminal observations included in its
subtotal. If two completed runs reported all their costs but a third observed
run has no terminal event, the subtotal may have `Complete: true` while
`TerminalCoverageComplete` is false. Preserve this distinction using the existing
coverage field; no additional completion flag or group lifecycle is needed.
## Accounting And Responsibility Boundaries
Reuse existing events, token presence/completeness, and group summaries, extending
them with the cost facts above. Available usage remains observable after an error
or cancellation under the existing execution-observation behavior; this does not
promise that upstream providers report usage for every attempt.
PromptKit owns observer selection, event generation, and aggregation. CommandKit
and other consumers own invocation lifecycle, CLI flags, presentation, output
delivery, and interpretation. This feature adds no CommandKit dependency or
application-specific concepts to PromptKit.
Smoke diagnostics retain their separate report/evidence model and are not
enrolled in ordinary execution observation by this change. Reasoning-token
capture, additional built-in cost providers, multiple currencies, currency
conversion, pricing estimates, billing reconciliation, persistent history, and
logging infrastructure are outside this scope.
## Work Needed And Completion Criteria
- Add the context helper and connect observer selection to ordinary and prepared
execution, keeping contextual selection separate from private run state.
- Preserve existing explicit selection and coordinator behavior while applying
the composition and lifetime rules above. Preserve existing observer selection
when no contextual observer is selected.
- Add `provider` to the backend configuration model, typed source helpers,
capture, inspection, and execution plumbing. Update the bundled OpenRouter
backend to select it explicitly. Retain the selection through prepared runs.
- Consolidate provider-specific response and authentication-probe behavior in
`internal/llm`; keep coordination and accounting provider-neutral. Cover
provider-default probes, explicit kind and endpoint overrides, `kind: none`,
and existing explicit probes without a provider selection.
- Verify provider selection independently of backend names and namespaces,
including renamed and inherited backends, equivalent omitted/null/blank values,
trimming and case normalization, rejection of unsupported nonempty values,
and retention through endpoint overrides. Confirm provider metadata is not
serialized into the completion request body. Use the generic fallback selected
when the remaining provider discussion is complete.
- Verify that provider diagnostic defaults do not become explicit values in the
loaded configuration or replace source provenance in inspection. Cover the
changed clearing behavior and endpoint-only authentication overrides.
- Carry optional OpenRouter cost through response decoding, internal/public
conversions, successful run results, attempt and terminal events, and existing
group summaries. Keep result cost available without registering an observer.
Preserve existing token fields and accounting.
- Verify that successful-result cost agrees with terminal-event cost and is
unchanged when observation is disabled, including the unreported-retry example
above. Verify group snapshots with fully reported completed runs alongside a
member without a terminal observation.
- Cover ordinary and prepared execution, coordinated continuations, nested calls
using derived contexts, concurrent calls, multiple engines sharing a scope,
and independent scopes on a reused engine.
- Cover callback ordering, nested contextual registration, nil registration,
duplicate group enrollment, prepared-handle scope selection, and existing
preparation/discard/rejected-claim behavior.
- Verify aggregate accounting through retries and repairs, available usage after
failures or cancellation, and known zero versus unknown or incomplete counts.
Use offline fixtures and injected clients; live inference is unnecessary.
- Cover fractional USD values, explicit zero, omitted/null and unusable cost,
generic built-in selection, optional injected-client cost, mixed known
and unknown totals, repair/retry aggregation, and duplicate group registration.
Use tolerant comparisons where floating-point addition requires them; do not
turn telemetry into an exact-decimal guarantee.
- Document the exact helper contract in GoDoc and add a focused invocation-level
aggregation example to the consumer observation guide, including cost
availability, units, and completeness. Document OpenRouter cost decoding in
the [integration contract](../integrations/openai-compatible-chat.md#response-handling),
and update internal observation and model-client documentation for changed flows.
Document `provider`, its smoke-test defaults and override semantics in the
framework format reference and relevant public GoDoc; update inspection and
diagnostic documentation with the implemented behavior. Include the diagnostic
migration in release notes.
## Implementation Planning Guidance
Organize the eventual implementation plan around two workstreams:
1. Contextual observer selection, including ordinary, prepared, coordinated,
and nested execution boundaries and the existing group collector.
2. Backend provider selection and consolidation within `internal/llm`, including
smoke-test defaults and explicit overrides, followed by provider-reported cost
through decoding, accounting, public results, events, and group summaries.
Include the corresponding configuration and API documentation.
The second area is more extensive than the context helper. Keep backend provider
configuration, diagnostic consolidation, and cost accounting in separately
reviewable implementation units rather than one large implementation prompt.
Complete the remaining provider discussion before preparing that plan; avoid
coupling delivery of contextual observation to provider cost support.
Today, successful results accumulate generation responses in the runner, while
optional observation recorders account for dispatched attempts. Adding cost to
response objects alone does not preserve completeness across unreported retries.
Reuse a small accounting component for result and observation paths so they
apply the same rules, including when no observer is selected. Preserve existing
token accounting rather than expanding this work into a redesign of its public
contract.
Keep tolerant optional-cost decoding local to the model-client boundary. Adding
a plain `*float64` JSON field to the typed envelope would make a nonnumeric or
overflowing value fail decoding of the entire response. Decode the optional
field separately so an unusable cost becomes unknown without changing existing
framing or content validation. This needs no general numeric-conversion layer.
Use the completion criteria above to select focused offline checks for each
unit. This roadmap owns target behavior; a separate implementation plan owns
the detailed work sequence.
## Topics For Further Discussion
Before finalizing the roadmap, settle:
1. A default, lowest-common-denominator OpenAI API-compatible provider used when
the backend does not specify a provider, including whether it has an explicit
selectable identifier and which common conventions it owns.
2. A `vllm` provider with vLLM-specific conventions, identifying the response and
diagnostic behavior to support from reviewed upstream contracts and fixtures.
The normalization, unsupported-value handling, override precedence, and
configuration-inspection boundaries above remain agreed decisions. These topics
do not yet add further provider behavior or an implementation commitment.