Core concepts

Harness

A harness is the execution strategy FlightPath uses to talk to an AI assistant. The term covers both CLI-backed integrations and the Copilot Chat window integration.

FlightPath currently supports:

• copilot-cli
• claude-cli
• codex-cli
• opencode-cli
• qwen-cli
• gemini-cli
• copilot-chat

Workflow

A workflow is a .flightpath.yaml, .flightpath.json, or .prompt.md file that describes work to run. YAML and JSON support multi-step automation. Markdown prompt files are the simplest one-step format.

Step

A workflow steps array can contain two kinds of step:

Type	Purpose
Prompt step	Sends a prompt to a harness
Script step	Runs a shell command without any AI interaction

Prompt steps default to type prompt, so the type field is optional unless you want to be explicit.

Final step

finalStep runs after the queue completes. It is useful for review passes, post-processing, or dynamic queue extension loops.

If the final step has mcpServers: ["flightpath"] and appends more prompts, FlightPath runs the new queue items and then executes the final step again.

Session

A session is the underlying conversation or thread maintained by a harness. FlightPath can:

• start a new session
• resume the immediately previous session with resumeSession: true
• resume a specific earlier step with sessionId: 1
• resume an exact harness session ID string

Session reuse is provider-aware. FlightPath does not try to resume a Claude session in Copilot or the other way around.

Context references

Prompts can include structured references that the prompt editor understands:

Syntax	Purpose
@path/to/file.ts	Attach a full file
@path/to/dir/	Attach a directory tree
#selection:path/to/file.ts:10-25	Attach a line range
#sym:path/to/file.ts:SymbolName:42	Attach a symbol definition
~diff, ~staged, ~stash:0, ~<commit>	Attach git change context
$previous, $all, $step:1	Inject prior FlightPath output

End conditions and pre-conditions

These are script-based gates:

• Pre-condition runs before a prompt and can continue, skip, or stop
• End condition runs after a prompt and can continue, retry, or stop

Use them when a workflow should react to actual project state instead of trusting the model's self-report.